Compare commits

..

12 Commits

Author SHA1 Message Date
nityanandagohain
9604438723 Merge remote-tracking branch 'origin/main' into issue_5267 2026-06-25 17:23:58 +05:30
nityanandagohain
e0a66b7a10 fix: more cleanup 2026-06-25 17:20:48 +05:30
Nityananda Gohain
8040f222ad fix: enable opamp for llmpricing/spanmmapper and remove unit from config (#11285)
* fix: enable opamp for llmpricing

* fix: test files

* chore: cleanups

* fix: don't deploy to opamp if ff is disabled

* fix: enable spanmapper behild feature flag
2026-06-25 11:38:53 +00:00
Nikhil Mantri
a45212cb79 feat(infra-monitoring): remove requiredMetricsCheck from v2 APIs + integration tests for new querier warnings behaviour. (#11792)
* chore: metric_name required checks removed

* refactor(inframonitoring): drop required-metrics test, add test hosts_warnings

* chore: updated integration tests for pods

* chore: updated integration tests for volumes

* chore: updated integration tests for nodes

* chore: updated integration tests for clusters and deployments

* chore: updated statefulsets integration tests

* chore: updated integration tests for jobs and daemonsets

* chore: removed unwanted provisional comments

* test(inframonitoring): dedupe metric-availability warning fixtures, reuse existing datasets

* test(inframonitoring): isolate hosts metric-key-pair warning fixture

Scenario-2 shared host acc-h1 + the accuracy fixture with
test_hosts_value_accuracy, causing a deterministic CI failure (empty
warnings). Restore the dedicated kp-h1 fixture + deployment.environment
groupBy so the warning assertion never depends on data shared with
another test.

* chore: removed unimportant tests for same thing

* test(inframonitoring): drop obsolete metric-key-pair warning scenario

PR #11835 removed the "key X not found on metric" warning from the metric

statement builder (lexer-derived check can't tell a key from a value, so

$variables got false-flagged). The metric_key_pair_not_seen scenario asserted

that now-removed warning, so it fails deterministically after merging main.

Remove the scenario and its orphaned fixture; never-seen-metric coverage

("never been received", still emitted) stays.
2026-06-25 10:26:50 +00:00
nityanandagohain
b01be1f31c fix: update openapi 2026-06-25 11:19:08 +05:30
nityanandagohain
c8a007cd8d fix: cleanup go.mod 2026-06-25 10:55:54 +05:30
nityanandagohain
205b23b830 fix: lint 2026-06-25 10:52:27 +05:30
nityanandagohain
68b166f75e fix: more cleanup and integration test 2026-06-25 10:50:52 +05:30
nityanandagohain
20d8ca6d7d Merge remote-tracking branch 'origin/main' into issue_5267 2026-06-25 10:06:52 +05:30
Abir Roy
a609a4044c fix(ui): resolve monaco find widget clipping and flickering (#11826)
Some checks failed
build-staging / prepare (push) Has been cancelled
build-staging / js-build (push) Has been cancelled
build-staging / go-build (push) Has been cancelled
build-staging / staging (push) Has been cancelled
Release Drafter / update_release_draft (push) Has been cancelled
2026-06-24 20:11:11 +00:00
nityanandagohain
1e1be670f1 feat: integrate with collector 2026-06-23 12:07:16 +05:30
nityanandagohain
d1682f2ab6 feat: span mapper test endpoint 2026-06-19 18:31:31 +05:30
86 changed files with 1748 additions and 4752 deletions

View File

@@ -38,6 +38,7 @@ jobs:
fail-fast: false
matrix:
suite:
- spanmapper
- alerts
- basepath
- callbackauthn

View File

@@ -29,8 +29,6 @@ import (
"github.com/SigNoz/signoz/pkg/modules/cloudintegration/implcloudintegration"
"github.com/SigNoz/signoz/pkg/modules/dashboard"
"github.com/SigNoz/signoz/pkg/modules/dashboard/impldashboard"
"github.com/SigNoz/signoz/pkg/modules/metricreductionrule"
"github.com/SigNoz/signoz/pkg/modules/metricreductionrule/implmetricreductionrule"
"github.com/SigNoz/signoz/pkg/modules/organization"
"github.com/SigNoz/signoz/pkg/modules/retention"
"github.com/SigNoz/signoz/pkg/modules/rulestatehistory"
@@ -121,9 +119,6 @@ func runServer(ctx context.Context, config signoz.Config, logger *slog.Logger) e
func(_ sqlstore.SQLStore, _ dashboard.Module, _ global.Global, _ zeus.Zeus, _ gateway.Gateway, _ licensing.Licensing, _ serviceaccount.Module, _ cloudintegration.Config) (cloudintegration.Module, error) {
return implcloudintegration.NewModule(), nil
},
func(_ sqlstore.SQLStore, _ telemetrystore.TelemetryStore, _ dashboard.Module, _ queryparser.QueryParser, _ licensing.Licensing, _ flagger.Flagger, _ telemetrytypes.MetadataStore, _ factory.ProviderSettings, _ int) metricreductionrule.Module {
return implmetricreductionrule.NewModule()
},
func(c cache.Cache, am alertmanager.Alertmanager, ss sqlstore.SQLStore, ts telemetrystore.TelemetryStore, ms telemetrytypes.MetadataStore, p prometheus.Prometheus, og organization.Getter, rsh rulestatehistory.Module, q querier.Querier, qp queryparser.QueryParser) factory.NamedMap[factory.ProviderFactory[ruler.Ruler, ruler.Config]] {
return factory.MustNewNamedMap(signozruler.NewFactory(c, am, ss, ts, ms, p, og, rsh, q, qp, nil, nil))
},

View File

@@ -24,7 +24,6 @@ import (
"github.com/SigNoz/signoz/ee/modules/cloudintegration/implcloudintegration"
"github.com/SigNoz/signoz/ee/modules/cloudintegration/implcloudintegration/implcloudprovider"
"github.com/SigNoz/signoz/ee/modules/dashboard/impldashboard"
eeimplmetricreductionrule "github.com/SigNoz/signoz/ee/modules/metricreductionrule/implmetricreductionrule"
eequerier "github.com/SigNoz/signoz/ee/querier"
enterpriseapp "github.com/SigNoz/signoz/ee/query-service/app"
eerules "github.com/SigNoz/signoz/ee/query-service/rules"
@@ -47,7 +46,6 @@ import (
pkgcloudintegration "github.com/SigNoz/signoz/pkg/modules/cloudintegration/implcloudintegration"
"github.com/SigNoz/signoz/pkg/modules/dashboard"
pkgimpldashboard "github.com/SigNoz/signoz/pkg/modules/dashboard/impldashboard"
"github.com/SigNoz/signoz/pkg/modules/metricreductionrule"
"github.com/SigNoz/signoz/pkg/modules/organization"
"github.com/SigNoz/signoz/pkg/modules/retention"
"github.com/SigNoz/signoz/pkg/modules/rulestatehistory"
@@ -184,9 +182,6 @@ func runServer(ctx context.Context, config signoz.Config, logger *slog.Logger) e
return implcloudintegration.NewModule(pkgcloudintegration.NewStore(sqlStore), dashboardModule, global, zeus, gateway, licensing, serviceAccount, cloudProvidersMap, config)
},
func(sqlStore sqlstore.SQLStore, ts telemetrystore.TelemetryStore, dashboardModule dashboard.Module, queryParser queryparser.QueryParser, lic licensing.Licensing, flgr pkgflagger.Flagger, ms telemetrytypes.MetadataStore, ps factory.ProviderSettings, threads int) metricreductionrule.Module {
return eeimplmetricreductionrule.NewModule(sqlStore, ts, dashboardModule, queryParser, lic, flgr, ms, ps, threads)
},
func(c cache.Cache, am alertmanager.Alertmanager, ss sqlstore.SQLStore, ts telemetrystore.TelemetryStore, ms telemetrytypes.MetadataStore, p prometheus.Prometheus, og organization.Getter, rsh rulestatehistory.Module, q querier.Querier, qp queryparser.QueryParser) factory.NamedMap[factory.ProviderFactory[ruler.Ruler, ruler.Config]] {
return factory.MustNewNamedMap(signozruler.NewFactory(c, am, ss, ts, ms, p, og, rsh, q, qp, eerules.PrepareTaskFunc, eerules.TestNotification))
},

File diff suppressed because it is too large Load Diff

View File

@@ -1,543 +0,0 @@
package implmetricreductionrule
import (
"context"
"slices"
"time"
sqlbuilder "github.com/huandu/go-sqlbuilder"
"github.com/SigNoz/signoz/pkg/errors"
"github.com/SigNoz/signoz/pkg/telemetrymetrics"
"github.com/SigNoz/signoz/pkg/telemetrystore"
"github.com/SigNoz/signoz/pkg/types/ctxtypes"
"github.com/SigNoz/signoz/pkg/types/metricreductionruletypes"
)
var (
reductionRulesTable = telemetrymetrics.DBName + "." + telemetrymetrics.ReductionRulesTableName
metadataTable = telemetrymetrics.DBName + "." + telemetrymetrics.AttributesMetadataTableName
bufferSeriesTable = telemetrymetrics.DBName + "." + telemetrymetrics.TimeseriesV4BufferTableName
)
const (
timeSeriesBucketMilli = int64(time.Hour / time.Millisecond)
sampleBucketMilli = int64(60 * time.Second / time.Millisecond)
)
type volumeRow struct {
MetricName string
Ingested uint64
Reduced uint64
}
type volumePoint struct {
TimestampMs int64
Ingested uint64
Reduced uint64
}
type clickhouse struct {
telemetryStore telemetrystore.TelemetryStore
threads int
}
func newClickhouse(telemetryStore telemetrystore.TelemetryStore, threads int) *clickhouse {
return &clickhouse{telemetryStore: telemetryStore, threads: threads}
}
func (c *clickhouse) withThreads(ctx context.Context) context.Context {
return ctxtypes.SetClickhouseMaxThreads(ctx, c.threads)
}
func floorToTimeSeriesBucket(ms int64) int64 {
return ms - (ms % timeSeriesBucketMilli)
}
func strictEffectiveFrom(sb *sqlbuilder.SelectBuilder, metricNames []string, effectiveFrom map[string]int64) string {
names := make([]any, 0, len(metricNames))
froms := make([]any, 0, len(metricNames))
for _, name := range metricNames {
names = append(names, name)
froms = append(froms, effectiveFrom[name])
}
return "unix_milli >= transform(metric_name, " + sb.Var(names) + ", " + sb.Var(froms) + ", 0)"
}
func (c *clickhouse) Sync(ctx context.Context, metricName string, labels []string, matchType string, effectiveFromMs int64, deleted bool, updatedAt time.Time) error {
ctx = c.withThreads(ctx)
ib := sqlbuilder.NewInsertBuilder()
ib.InsertInto(reductionRulesTable)
ib.Cols("metric_name", "labels", "match_type", "effective_from_unix_milli", "deleted", "updated_at")
ib.Values(metricName, labels, matchType, effectiveFromMs, deleted, updatedAt)
query, args := ib.BuildWithFlavor(sqlbuilder.ClickHouse)
if err := c.telemetryStore.ClickhouseDB().Exec(ctx, query, args...); err != nil {
return errors.WrapInternalf(err, errors.CodeInternal, "failed to sync reduction rule to clickhouse")
}
return nil
}
func (c *clickhouse) AttributeKeys(ctx context.Context, metricName string, startMs, endMs int64) ([]string, error) {
ctx = c.withThreads(ctx)
sb := sqlbuilder.NewSelectBuilder()
sb.Select("attr_name")
sb.Distinct()
sb.From(metadataTable)
sb.Where(
sb.E("metric_name", metricName),
"NOT startsWith(attr_name, '__')",
sb.GE("last_reported_unix_milli", startMs),
sb.LE("first_reported_unix_milli", endMs),
)
query, args := sb.BuildWithFlavor(sqlbuilder.ClickHouse)
rows, err := c.telemetryStore.ClickhouseDB().Query(ctx, query, args...)
if err != nil {
return nil, errors.WrapInternalf(err, errors.CodeInternal, "failed to fetch metric attribute keys")
}
defer rows.Close()
keys := make([]string, 0)
for rows.Next() {
var key string
if err := rows.Scan(&key); err != nil {
return nil, errors.WrapInternalf(err, errors.CodeInternal, "failed to scan attribute key")
}
keys = append(keys, key)
}
return keys, rows.Err()
}
func (c *clickhouse) EstimateCardinality(ctx context.Context, metricName string, keptLabels []string, startMs, endMs int64) (uint64, uint64, error) {
ctx = c.withThreads(ctx)
startMs = floorToTimeSeriesBucket(startMs)
sb := sqlbuilder.NewSelectBuilder()
reducedExpr := "1"
if len(keptLabels) > 0 {
reducedExpr = "uniq(("
for i, label := range keptLabels {
if i > 0 {
reducedExpr += ", "
}
reducedExpr += "JSONExtractString(labels, " + sb.Var(label) + ")"
}
reducedExpr += "))"
}
sb.Select("uniq(fingerprint)", reducedExpr)
sb.From(bufferSeriesTable)
conds := []string{
sb.E("metric_name", metricName),
sb.GE("unix_milli", startMs),
sb.LT("unix_milli", endMs),
sb.E("is_reduced", false),
}
sb.Where(conds...)
query, args := sb.BuildWithFlavor(sqlbuilder.ClickHouse)
var current, reduced uint64
if err := c.telemetryStore.ClickhouseDB().QueryRow(ctx, query, args...).Scan(&current, &reduced); err != nil {
return 0, 0, errors.WrapInternalf(err, errors.CodeInternal, "failed to estimate reduction impact")
}
if len(keptLabels) == 0 && current == 0 {
reduced = 0
}
if reduced > current {
reduced = current
}
return current, reduced, nil
}
// VolumeByMetric returns ingested vs reduced series counts per metric.
func (c *clickhouse) VolumeByMetric(ctx context.Context, metricNames []string, effectiveFrom map[string]int64, startMs, endMs int64) (map[string]volumeRow, error) {
if len(metricNames) == 0 {
return map[string]volumeRow{}, nil
}
ctx = c.withThreads(ctx)
ingested, err := c.ingestedSeriesCount(ctx, metricNames, effectiveFrom, startMs, endMs)
if err != nil {
return nil, err
}
reduced, err := c.reducedSeriesCount(ctx, metricNames, effectiveFrom, startMs, endMs)
if err != nil {
return nil, err
}
out := make(map[string]volumeRow, len(metricNames))
for metricName, count := range ingested {
out[metricName] = volumeRow{MetricName: metricName, Ingested: count, Reduced: out[metricName].Reduced}
}
for metricName, count := range reduced {
row := out[metricName]
row.MetricName = metricName
row.Reduced = count
out[metricName] = row
}
return out, nil
}
// ingestedSeriesCount counts distinct raw fingerprints per metric from the samples buffer over the
// window.
func (c *clickhouse) ingestedSeriesCount(ctx context.Context, metricNames []string, effectiveFrom map[string]int64, startMs, endMs int64) (map[string]uint64, error) {
names := make([]any, len(metricNames))
for i, name := range metricNames {
names[i] = name
}
sb := sqlbuilder.NewSelectBuilder()
sb.Select("metric_name", "uniq(fingerprint)")
sb.From(telemetrymetrics.DBName + "." + telemetrymetrics.SamplesV4BufferTableName)
conds := []string{
sb.In("metric_name", names...),
sb.GE("unix_milli", startMs),
sb.LT("unix_milli", endMs),
}
if len(effectiveFrom) > 0 {
conds = append(conds, strictEffectiveFrom(sb, metricNames, effectiveFrom))
}
sb.Where(conds...)
sb.GroupBy("metric_name")
query, args := sb.BuildWithFlavor(sqlbuilder.ClickHouse)
rows, err := c.telemetryStore.ClickhouseDB().Query(ctx, query, args...)
if err != nil {
return nil, errors.WrapInternalf(err, errors.CodeInternal, "failed to count ingested series")
}
defer rows.Close()
out := make(map[string]uint64, len(metricNames))
for rows.Next() {
var (
metricName string
count uint64
)
if err := rows.Scan(&metricName, &count); err != nil {
return nil, errors.WrapInternalf(err, errors.CodeInternal, "failed to scan series count")
}
out[metricName] = count
}
return out, rows.Err()
}
// reducedSeriesCount counts distinct reduced_fingerprints per metric, summed across the two 60s
// reduced sample tables.
func (c *clickhouse) reducedSeriesCount(ctx context.Context, metricNames []string, effectiveFrom map[string]int64, startMs, endMs int64) (map[string]uint64, error) {
out := make(map[string]uint64, len(metricNames))
for _, table := range []string{telemetrymetrics.SamplesV4ReducedLastTableName, telemetrymetrics.SamplesV4ReducedSumTableName} {
counts, err := c.reducedSeriesCountForTable(ctx, telemetrymetrics.DBName+"."+table, metricNames, effectiveFrom, startMs, endMs)
if err != nil {
return nil, err
}
for metricName, count := range counts {
out[metricName] += count
}
}
return out, nil
}
func (c *clickhouse) reducedSeriesCountForTable(ctx context.Context, table string, metricNames []string, effectiveFrom map[string]int64, startMs, endMs int64) (map[string]uint64, error) {
names := make([]any, len(metricNames))
for i, name := range metricNames {
names[i] = name
}
sb := sqlbuilder.NewSelectBuilder()
sb.Select("metric_name", "uniq(reduced_fingerprint)")
sb.From(table)
conds := []string{
sb.In("metric_name", names...),
sb.GE("unix_milli", startMs),
sb.LT("unix_milli", endMs),
}
if len(effectiveFrom) > 0 {
conds = append(conds, strictEffectiveFrom(sb, metricNames, effectiveFrom))
}
sb.Where(conds...)
sb.GroupBy("metric_name")
query, args := sb.BuildWithFlavor(sqlbuilder.ClickHouse)
rows, err := c.telemetryStore.ClickhouseDB().Query(ctx, query, args...)
if err != nil {
return nil, errors.WrapInternalf(err, errors.CodeInternal, "failed to count reduced series")
}
defer rows.Close()
out := make(map[string]uint64, len(metricNames))
for rows.Next() {
var (
metricName string
count uint64
)
if err := rows.Scan(&metricName, &count); err != nil {
return nil, errors.WrapInternalf(err, errors.CodeInternal, "failed to scan series count")
}
out[metricName] = count
}
return out, rows.Err()
}
// RankByVolume ranks metrics by ingested/reduced series volume. Like VolumeByMetric, the counts read
// the samples tables with a strict effective_from gate; the reduced count sums distinct
// reduced_fingerprints across the two 60s reduced sample tables.
func (c *clickhouse) RankByVolume(ctx context.Context, metricNames []string, effectiveFrom map[string]int64, orderBy metricreductionruletypes.ReductionRuleOrderBy, order metricreductionruletypes.Order, startMs, endMs int64, offset, limit int) ([]volumeRow, error) {
if len(metricNames) == 0 {
return []volumeRow{}, nil
}
ctx = c.withThreads(ctx)
orderExpr := "ingested"
switch orderBy {
case metricreductionruletypes.OrderByReducedVolume:
orderExpr = "reduced"
case metricreductionruletypes.OrderByReduction:
orderExpr = "if(ingested = 0, 0, (toFloat64(ingested) - toFloat64(reduced)) / toFloat64(ingested))"
}
direction := "ASC"
if order == metricreductionruletypes.OrderDesc {
direction = "DESC"
}
ingestedTable := telemetrymetrics.DBName + "." + telemetrymetrics.SamplesV4BufferTableName
reducedLast := telemetrymetrics.DBName + "." + telemetrymetrics.SamplesV4ReducedLastTableName
reducedSum := telemetrymetrics.DBName + "." + telemetrymetrics.SamplesV4ReducedSumTableName
sb := sqlbuilder.NewSelectBuilder()
sb.Select("base.metric_name AS metric_name", "ifNull(i.cnt, 0) AS ingested", "ifNull(d.cnt, 0) AS reduced")
sb.From("(SELECT arrayJoin(" + sb.Var(metricNames) + ") AS metric_name) AS base")
sb.JoinWithOption(
sqlbuilder.LeftJoin,
"(SELECT metric_name, uniq(fingerprint) AS cnt FROM "+ingestedTable+" WHERE has("+sb.Var(metricNames)+", metric_name) AND unix_milli >= "+sb.Var(startMs)+" AND unix_milli < "+sb.Var(endMs)+" AND "+strictEffectiveFrom(sb, metricNames, effectiveFrom)+" GROUP BY metric_name) AS i",
"base.metric_name = i.metric_name",
)
// Reduced series are spread across two type-specific tables; union the per-table distinct
// reduced_fingerprints and sum per metric (a metric only lands in the table matching its type).
sb.JoinWithOption(
sqlbuilder.LeftJoin,
"(SELECT metric_name, sum(cnt) AS cnt FROM ("+
"SELECT metric_name, uniq(reduced_fingerprint) AS cnt FROM "+reducedLast+" WHERE has("+sb.Var(metricNames)+", metric_name) AND unix_milli >= "+sb.Var(startMs)+" AND unix_milli < "+sb.Var(endMs)+" AND "+strictEffectiveFrom(sb, metricNames, effectiveFrom)+" GROUP BY metric_name"+
" UNION ALL "+
"SELECT metric_name, uniq(reduced_fingerprint) AS cnt FROM "+reducedSum+" WHERE has("+sb.Var(metricNames)+", metric_name) AND unix_milli >= "+sb.Var(startMs)+" AND unix_milli < "+sb.Var(endMs)+" AND "+strictEffectiveFrom(sb, metricNames, effectiveFrom)+" GROUP BY metric_name"+
") GROUP BY metric_name) AS d",
"base.metric_name = d.metric_name",
)
sb.OrderBy(orderExpr + " " + direction)
if limit > 0 {
sb.Limit(limit).Offset(offset)
}
query, args := sb.BuildWithFlavor(sqlbuilder.ClickHouse)
rows, err := c.telemetryStore.ClickhouseDB().Query(ctx, query, args...)
if err != nil {
return nil, errors.WrapInternalf(err, errors.CodeInternal, "failed to rank reduction rules by volume")
}
defer rows.Close()
out := make([]volumeRow, 0, len(metricNames))
for rows.Next() {
var row volumeRow
if err := rows.Scan(&row.MetricName, &row.Ingested, &row.Reduced); err != nil {
return nil, errors.WrapInternalf(err, errors.CodeInternal, "failed to scan volume row")
}
out = append(out, row)
}
return out, rows.Err()
}
func (c *clickhouse) SampleVolume(ctx context.Context, metricNames []string, effectiveFrom map[string]int64, startMs, endMs int64) (uint64, uint64, error) {
if len(metricNames) == 0 {
return 0, 0, nil
}
ctx = c.withThreads(ctx)
ingested, err := c.countRawSamples(ctx, telemetrymetrics.DBName+"."+telemetrymetrics.SamplesV4BufferTableName, metricNames, effectiveFrom, startMs, endMs)
if err != nil {
return 0, 0, err
}
last, err := c.countReducedSamples(ctx, telemetrymetrics.DBName+"."+telemetrymetrics.SamplesV4ReducedLastTableName, metricNames, effectiveFrom, startMs, endMs)
if err != nil {
return 0, 0, err
}
sum, err := c.countReducedSamples(ctx, telemetrymetrics.DBName+"."+telemetrymetrics.SamplesV4ReducedSumTableName, metricNames, effectiveFrom, startMs, endMs)
if err != nil {
return 0, 0, err
}
return ingested, min(last+sum, ingested), nil
}
func (c *clickhouse) countRawSamples(ctx context.Context, table string, metricNames []string, effectiveFrom map[string]int64, startMs, endMs int64) (uint64, error) {
names := make([]any, len(metricNames))
for i, name := range metricNames {
names[i] = name
}
sb := sqlbuilder.NewSelectBuilder()
sb.Select("count()")
sb.From(table)
conds := []string{sb.In("metric_name", names...), sb.GE("unix_milli", startMs), sb.LT("unix_milli", endMs)}
if len(effectiveFrom) > 0 {
conds = append(conds, strictEffectiveFrom(sb, metricNames, effectiveFrom))
}
sb.Where(conds...)
query, args := sb.BuildWithFlavor(sqlbuilder.ClickHouse)
var count uint64
if err := c.telemetryStore.ClickhouseDB().QueryRow(ctx, query, args...).Scan(&count); err != nil {
return 0, errors.WrapInternalf(err, errors.CodeInternal, "failed to count ingested samples")
}
return count, nil
}
func (c *clickhouse) countReducedSamples(ctx context.Context, table string, metricNames []string, effectiveFrom map[string]int64, startMs, endMs int64) (uint64, error) {
names := make([]any, len(metricNames))
for i, name := range metricNames {
names[i] = name
}
sb := sqlbuilder.NewSelectBuilder()
// Reduced tables key the series on reduced_fingerprint (not fingerprint); dedupe ReplacingMergeTree recomputes.
sb.Select("uniq(reduced_fingerprint, unix_milli)")
sb.From(table)
conds := []string{sb.In("metric_name", names...), sb.GE("unix_milli", startMs), sb.LT("unix_milli", endMs)}
if len(effectiveFrom) > 0 {
conds = append(conds, strictEffectiveFrom(sb, metricNames, effectiveFrom))
}
sb.Where(conds...)
query, args := sb.BuildWithFlavor(sqlbuilder.ClickHouse)
var count uint64
if err := c.telemetryStore.ClickhouseDB().QueryRow(ctx, query, args...).Scan(&count); err != nil {
return 0, errors.WrapInternalf(err, errors.CodeInternal, "failed to count reduced samples")
}
return count, nil
}
// SeriesTimeseries returns ingested vs reduced series per 60s bucket from the samples tables, gated
// to each metric's strict effective_from (see strictEffectiveFrom).
func (c *clickhouse) SeriesTimeseries(ctx context.Context, metricNames []string, effectiveFrom map[string]int64, startMs, endMs int64) ([]volumePoint, error) {
if len(metricNames) == 0 {
return []volumePoint{}, nil
}
ctx = c.withThreads(ctx)
ingested, err := c.ingestedSeriesByBucket(ctx, metricNames, effectiveFrom, startMs, endMs)
if err != nil {
return nil, err
}
reduced, err := c.reducedSeriesByBucket(ctx, metricNames, effectiveFrom, startMs, endMs)
if err != nil {
return nil, err
}
return mergeVolumePoints(ingested, reduced), nil
}
func mergeVolumePoints(ingested, reduced map[int64]uint64) []volumePoint {
buckets := make(map[int64]struct{}, len(ingested))
for ts := range ingested {
buckets[ts] = struct{}{}
}
for ts := range reduced {
buckets[ts] = struct{}{}
}
timestamps := make([]int64, 0, len(buckets))
for ts := range buckets {
timestamps = append(timestamps, ts)
}
slices.Sort(timestamps)
points := make([]volumePoint, 0, len(timestamps))
for _, ts := range timestamps {
points = append(points, volumePoint{
TimestampMs: ts,
Ingested: ingested[ts],
Reduced: reduced[ts],
})
}
return points
}
// ingestedSeriesByBucket counts distinct raw fingerprints per 60s bucket from the samples buffer.
func (c *clickhouse) ingestedSeriesByBucket(ctx context.Context, metricNames []string, effectiveFrom map[string]int64, startMs, endMs int64) (map[int64]uint64, error) {
names := make([]any, len(metricNames))
for i, name := range metricNames {
names[i] = name
}
sb := sqlbuilder.NewSelectBuilder()
bucketExpr := "intDiv(unix_milli, " + sb.Var(sampleBucketMilli) + ") * " + sb.Var(sampleBucketMilli) + " AS bucket"
sb.Select(bucketExpr, "uniq(fingerprint)")
sb.From(telemetrymetrics.DBName + "." + telemetrymetrics.SamplesV4BufferTableName)
conds := []string{sb.In("metric_name", names...), sb.GE("unix_milli", startMs), sb.LT("unix_milli", endMs)}
if len(effectiveFrom) > 0 {
conds = append(conds, strictEffectiveFrom(sb, metricNames, effectiveFrom))
}
sb.Where(conds...)
sb.GroupBy("bucket")
return c.scanBuckets(ctx, sb)
}
// reducedSeriesByBucket counts distinct reduced_fingerprints per 60s bucket, summed across the two
// reduced sample tables (a metric only lands in the table matching its type, so per-bucket sums are
// exact).
func (c *clickhouse) reducedSeriesByBucket(ctx context.Context, metricNames []string, effectiveFrom map[string]int64, startMs, endMs int64) (map[int64]uint64, error) {
out := make(map[int64]uint64)
for _, table := range []string{telemetrymetrics.SamplesV4ReducedLastTableName, telemetrymetrics.SamplesV4ReducedSumTableName} {
names := make([]any, len(metricNames))
for i, name := range metricNames {
names[i] = name
}
sb := sqlbuilder.NewSelectBuilder()
bucketExpr := "intDiv(unix_milli, " + sb.Var(sampleBucketMilli) + ") * " + sb.Var(sampleBucketMilli) + " AS bucket"
sb.Select(bucketExpr, "uniq(reduced_fingerprint)")
sb.From(telemetrymetrics.DBName + "." + table)
conds := []string{sb.In("metric_name", names...), sb.GE("unix_milli", startMs), sb.LT("unix_milli", endMs)}
if len(effectiveFrom) > 0 {
conds = append(conds, strictEffectiveFrom(sb, metricNames, effectiveFrom))
}
sb.Where(conds...)
sb.GroupBy("bucket")
counts, err := c.scanBuckets(ctx, sb)
if err != nil {
return nil, err
}
for ts, count := range counts {
out[ts] += count
}
}
return out, nil
}
func (c *clickhouse) scanBuckets(ctx context.Context, sb *sqlbuilder.SelectBuilder) (map[int64]uint64, error) {
query, args := sb.BuildWithFlavor(sqlbuilder.ClickHouse)
rows, err := c.telemetryStore.ClickhouseDB().Query(ctx, query, args...)
if err != nil {
return nil, errors.WrapInternalf(err, errors.CodeInternal, "failed to bucket series by time")
}
defer rows.Close()
out := make(map[int64]uint64)
for rows.Next() {
var (
ts int64
count uint64
)
if err := rows.Scan(&ts, &count); err != nil {
return nil, errors.WrapInternalf(err, errors.CodeInternal, "failed to scan series bucket")
}
out[ts] = count
}
return out, rows.Err()
}

View File

@@ -1,544 +0,0 @@
package implmetricreductionrule
import (
"context"
"log/slog"
"sort"
"strings"
"time"
"github.com/SigNoz/signoz/pkg/errors"
"github.com/SigNoz/signoz/pkg/factory"
"github.com/SigNoz/signoz/pkg/flagger"
"github.com/SigNoz/signoz/pkg/licensing"
"github.com/SigNoz/signoz/pkg/modules/dashboard"
"github.com/SigNoz/signoz/pkg/modules/metricreductionrule"
"github.com/SigNoz/signoz/pkg/queryparser"
"github.com/SigNoz/signoz/pkg/ruler/rulestore/sqlrulestore"
"github.com/SigNoz/signoz/pkg/sqlstore"
"github.com/SigNoz/signoz/pkg/telemetrystore"
"github.com/SigNoz/signoz/pkg/types/featuretypes"
"github.com/SigNoz/signoz/pkg/types/metricreductionruletypes"
"github.com/SigNoz/signoz/pkg/types/metrictypes"
"github.com/SigNoz/signoz/pkg/types/querybuildertypes/querybuildertypesv5"
"github.com/SigNoz/signoz/pkg/types/ruletypes"
"github.com/SigNoz/signoz/pkg/types/telemetrytypes"
"github.com/SigNoz/signoz/pkg/valuer"
)
const (
// effectiveFromMargin delays effective_from so the collector picks up the synced rule before it
// goes live; it must be >= the collector's rule-refresh interval (see signoz-otel-collector#839).
effectiveFromMargin = 5 * time.Minute
defaultPreviewLookback = 24 * time.Hour
pricePerMillionSamplesUSD = 0.1
monthDuration = 30 * 24 * time.Hour
)
type module struct {
store metricreductionruletypes.Store
ch *clickhouse
dashboard dashboard.Module
ruleStore ruletypes.RuleStore
licensing licensing.Licensing
flagger flagger.Flagger
metadataStore telemetrytypes.MetadataStore
logger *slog.Logger
}
func NewModule(sqlStore sqlstore.SQLStore, telemetryStore telemetrystore.TelemetryStore, dashboardModule dashboard.Module, queryParser queryparser.QueryParser, licensing licensing.Licensing, flagger flagger.Flagger, metadataStore telemetrytypes.MetadataStore, providerSettings factory.ProviderSettings, threads int) metricreductionrule.Module {
scoped := factory.NewScopedProviderSettings(providerSettings, "github.com/SigNoz/signoz/ee/modules/metricreductionrule/implmetricreductionrule")
return &module{
store: NewStore(sqlStore),
ch: newClickhouse(telemetryStore, threads),
dashboard: dashboardModule,
ruleStore: sqlrulestore.NewRuleStore(sqlStore, queryParser, providerSettings),
licensing: licensing,
flagger: flagger,
metadataStore: metadataStore,
logger: scoped.Logger(),
}
}
func (m *module) checkAccess(ctx context.Context, orgID valuer.UUID) error {
if !m.flagger.BooleanOrEmpty(ctx, flagger.FeatureEnableMetricsReduction, featuretypes.NewFlaggerEvaluationContext(orgID)) {
return errors.Newf(errors.TypeUnsupported, metricreductionruletypes.ErrCodeMetricReductionRuleUnsupported, "metric volume control is not enabled")
}
if _, err := m.licensing.GetActive(ctx, orgID); err != nil {
return errors.New(errors.TypeLicenseUnavailable, errors.CodeLicenseUnavailable, "metric volume control requires a valid license").WithAdditional(err.Error())
}
return nil
}
func (m *module) List(ctx context.Context, orgID valuer.UUID, params *metricreductionruletypes.ListReductionRulesParams) (*metricreductionruletypes.GettableReductionRules, error) {
if err := m.checkAccess(ctx, orgID); err != nil {
return nil, err
}
if err := params.Validate(); err != nil {
return nil, err
}
now := time.Now()
startMs := now.Add(-defaultPreviewLookback).UnixMilli()
endMs := now.UnixMilli()
switch params.OrderBy {
case metricreductionruletypes.OrderByMetricName, metricreductionruletypes.OrderByLastUpdated:
return m.listSortedByColumn(ctx, orgID, params, startMs, endMs)
default:
return m.listSortedByVolume(ctx, orgID, params, startMs, endMs)
}
}
func (m *module) listSortedByColumn(ctx context.Context, orgID valuer.UUID, params *metricreductionruletypes.ListReductionRulesParams, startMs, endMs int64) (*metricreductionruletypes.GettableReductionRules, error) {
domainRules, total, err := m.store.List(ctx, orgID, params)
if err != nil {
return nil, err
}
metricNames := make([]string, len(domainRules))
effectiveFrom := make(map[string]int64, len(domainRules))
for i, rule := range domainRules {
metricNames[i] = rule.MetricName
effectiveFrom[rule.MetricName] = rule.EffectiveFrom.UnixMilli()
}
volumes, err := m.ch.VolumeByMetric(ctx, metricNames, effectiveFrom, startMs, endMs)
if err != nil {
return nil, err
}
rules := make([]metricreductionruletypes.GettableReductionRule, 0, len(domainRules))
for _, rule := range domainRules {
rules = append(rules, withVolume(toGettableReductionRule(rule), volumes[rule.MetricName]))
}
return &metricreductionruletypes.GettableReductionRules{Rules: rules, Total: total}, nil
}
func (m *module) listSortedByVolume(ctx context.Context, orgID valuer.UUID, params *metricreductionruletypes.ListReductionRulesParams, startMs, endMs int64) (*metricreductionruletypes.GettableReductionRules, error) {
allRules, total, err := m.store.List(ctx, orgID, &metricreductionruletypes.ListReductionRulesParams{Search: params.Search, MetricName: params.MetricName})
if err != nil {
return nil, err
}
if total == 0 {
return &metricreductionruletypes.GettableReductionRules{Rules: []metricreductionruletypes.GettableReductionRule{}, Total: 0}, nil
}
metricNames := make([]string, len(allRules))
effectiveFrom := make(map[string]int64, len(allRules))
ruleByMetric := make(map[string]*metricreductionruletypes.ReductionRule, len(allRules))
for i, rule := range allRules {
metricNames[i] = rule.MetricName
effectiveFrom[rule.MetricName] = rule.EffectiveFrom.UnixMilli()
ruleByMetric[rule.MetricName] = rule
}
ranked, err := m.ch.RankByVolume(ctx, metricNames, effectiveFrom, params.OrderBy, params.Order, startMs, endMs, params.Offset, params.Limit)
if err != nil {
return nil, err
}
rules := make([]metricreductionruletypes.GettableReductionRule, 0, len(ranked))
for _, row := range ranked {
rule, ok := ruleByMetric[row.MetricName]
if !ok {
continue
}
rules = append(rules, withVolume(toGettableReductionRule(rule), row))
}
return &metricreductionruletypes.GettableReductionRules{Rules: rules, Total: total}, nil
}
func (m *module) Create(ctx context.Context, orgID valuer.UUID, userEmail string, req *metricreductionruletypes.PostableReductionRule) (*metricreductionruletypes.GettableReductionRule, error) {
if err := m.checkAccess(ctx, orgID); err != nil {
return nil, err
}
if err := req.Validate(); err != nil {
return nil, err
}
if err := m.validateMetricForReduction(ctx, orgID, req.MetricName); err != nil {
return nil, err
}
now := time.Now()
rule := metricreductionruletypes.NewReductionRule(orgID, req.MetricName, req.MatchType, req.Labels, now.Add(effectiveFromMargin), userEmail)
if err := m.store.RunInTx(ctx, func(ctx context.Context) error {
if err := m.store.Create(ctx, rule); err != nil {
return err
}
return m.ch.Sync(ctx, rule.MetricName, rule.Labels, rule.MatchType.StringValue(), rule.EffectiveFrom.UnixMilli(), false, rule.UpdatedAt)
}); err != nil {
return nil, err
}
gettable := toGettableReductionRule(rule)
return &gettable, nil
}
func (m *module) GetByID(ctx context.Context, orgID valuer.UUID, id valuer.UUID) (*metricreductionruletypes.GettableReductionRule, error) {
if err := m.checkAccess(ctx, orgID); err != nil {
return nil, err
}
rule, err := m.store.GetByID(ctx, orgID, id)
if err != nil {
return nil, err
}
gettable := toGettableReductionRule(rule)
return &gettable, nil
}
func (m *module) UpdateByID(ctx context.Context, orgID valuer.UUID, userEmail string, id valuer.UUID, req *metricreductionruletypes.UpdatableReductionRule) (*metricreductionruletypes.GettableReductionRule, error) {
if err := m.checkAccess(ctx, orgID); err != nil {
return nil, err
}
existing, err := m.store.GetByID(ctx, orgID, id)
if err != nil {
return nil, err
}
if err := req.Validate(); err != nil {
return nil, err
}
now := time.Now()
existing.MatchType = req.MatchType
existing.Labels = metricreductionruletypes.LabelList(req.Labels)
existing.EffectiveFrom = now.Add(effectiveFromMargin)
existing.UpdatedAt = now
existing.UpdatedBy = userEmail
if err := m.store.RunInTx(ctx, func(ctx context.Context) error {
if err := m.store.Upsert(ctx, existing); err != nil {
return err
}
return m.ch.Sync(ctx, existing.MetricName, existing.Labels, existing.MatchType.StringValue(), existing.EffectiveFrom.UnixMilli(), false, existing.UpdatedAt)
}); err != nil {
return nil, err
}
gettable := toGettableReductionRule(existing)
return &gettable, nil
}
func (m *module) DeleteByID(ctx context.Context, orgID valuer.UUID, id valuer.UUID) error {
if err := m.checkAccess(ctx, orgID); err != nil {
return err
}
rule, err := m.store.GetByID(ctx, orgID, id)
if err != nil {
return err
}
now := time.Now()
effectiveFromMs := now.Add(effectiveFromMargin).UnixMilli()
return m.store.RunInTx(ctx, func(ctx context.Context) error {
if err := m.store.DeleteByID(ctx, orgID, id); err != nil {
return err
}
return m.ch.Sync(ctx, rule.MetricName, []string{}, metricreductionruletypes.MatchTypeDrop.StringValue(), effectiveFromMs, true, now)
})
}
func (m *module) Preview(ctx context.Context, orgID valuer.UUID, req *metricreductionruletypes.PostableReductionRulePreview) (*metricreductionruletypes.GettableReductionRulePreview, error) {
if err := m.checkAccess(ctx, orgID); err != nil {
return nil, err
}
if err := req.Validate(); err != nil {
return nil, err
}
if err := m.validateMetricForReduction(ctx, orgID, req.MetricName); err != nil {
return nil, err
}
lookback := time.Duration(req.LookbackMs) * time.Millisecond
if lookback <= 0 {
lookback = defaultPreviewLookback
}
now := time.Now()
startMs := now.Add(-lookback).UnixMilli()
endMs := now.UnixMilli()
current, reduced, reductionPercent, dropped, err := m.estimateVolume(ctx, req.MetricName, req.MatchType, req.Labels, startMs, endMs)
if err != nil {
return nil, err
}
// Baseline is what the metric keeps today (its current rule, or raw if none) so the preview reads
// as current -> proposed.
currentReduced := current
if existing, gerr := m.store.Get(ctx, orgID, req.MetricName); gerr == nil {
if _, existingReduced, _, _, eerr := m.estimateVolume(ctx, req.MetricName, existing.MatchType, existing.Labels, startMs, endMs); eerr == nil {
currentReduced = existingReduced
}
}
return &metricreductionruletypes.GettableReductionRulePreview{
IngestedSeries: current,
CurrentRetainedSeries: currentReduced,
RetainedSeries: reduced,
ReductionPercent: reductionPercent,
DroppedLabels: dropped,
AffectedAssets: m.relatedAssetImpact(ctx, orgID, req.MetricName, dropped),
EffectiveFrom: now.Add(effectiveFromMargin),
}, nil
}
func (m *module) Stats(ctx context.Context, orgID valuer.UUID) (*metricreductionruletypes.GettableReductionRuleStats, error) {
if err := m.checkAccess(ctx, orgID); err != nil {
return nil, err
}
now := time.Now()
startMs := now.Add(-defaultPreviewLookback).UnixMilli()
endMs := now.UnixMilli()
allRules, total, err := m.store.List(ctx, orgID, &metricreductionruletypes.ListReductionRulesParams{})
if err != nil {
return nil, err
}
if total == 0 {
return &metricreductionruletypes.GettableReductionRuleStats{}, nil
}
metricNames := make([]string, len(allRules))
effectiveFrom := make(map[string]int64, len(allRules))
for i, rule := range allRules {
metricNames[i] = rule.MetricName
effectiveFrom[rule.MetricName] = rule.EffectiveFrom.UnixMilli()
}
volumes, err := m.ch.VolumeByMetric(ctx, metricNames, effectiveFrom, startMs, endMs)
if err != nil {
return nil, err
}
var ingestedSeries, reducedSeries uint64
for _, volume := range volumes {
ingestedSeries += volume.Ingested
reducedSeries += volume.Reduced
}
ingestedSamples, reducedSamples, err := m.ch.SampleVolume(ctx, metricNames, effectiveFrom, startMs, endMs)
if err != nil {
return nil, err
}
return &metricreductionruletypes.GettableReductionRuleStats{
IngestedSeries: ingestedSeries,
RetainedSeries: reducedSeries,
EstimatedMonthlySavingsUsd: monthlySavingsUSD(ingestedSamples, reducedSamples, startMs, endMs),
}, nil
}
// monthlySavingsUSD extrapolates the windowed sample reduction to a monthly figure at the per-sample
// list price. Ingested is gated to effective_from upstream, so pre-activation hours don't inflate it.
func monthlySavingsUSD(ingestedSamples, reducedSamples uint64, startMs, endMs int64) float64 {
if reducedSamples >= ingestedSamples || endMs <= startMs {
return 0
}
savedSamples := float64(ingestedSamples - reducedSamples)
monthlySamples := savedSamples * float64(monthDuration.Milliseconds()) / float64(endMs-startMs)
return monthlySamples / 1_000_000 * pricePerMillionSamplesUSD
}
func (m *module) Timeseries(ctx context.Context, orgID valuer.UUID) (*querybuildertypesv5.QueryRangeResponse, error) {
if err := m.checkAccess(ctx, orgID); err != nil {
return nil, err
}
now := time.Now()
startMs := now.Add(-defaultPreviewLookback).UnixMilli()
endMs := now.UnixMilli()
allRules, _, err := m.store.List(ctx, orgID, &metricreductionruletypes.ListReductionRulesParams{})
if err != nil {
return nil, err
}
metricNames := make([]string, len(allRules))
effectiveFrom := make(map[string]int64, len(allRules))
for i, rule := range allRules {
metricNames[i] = rule.MetricName
effectiveFrom[rule.MetricName] = rule.EffectiveFrom.UnixMilli()
}
points, err := m.ch.SeriesTimeseries(ctx, metricNames, effectiveFrom, startMs, endMs)
if err != nil {
return nil, err
}
return buildVolumeTimeseries(points), nil
}
func buildVolumeTimeseries(points []volumePoint) *querybuildertypesv5.QueryRangeResponse {
ingested := make([]*querybuildertypesv5.TimeSeriesValue, 0, len(points))
reduced := make([]*querybuildertypesv5.TimeSeriesValue, 0, len(points))
for _, point := range points {
ingested = append(ingested, &querybuildertypesv5.TimeSeriesValue{Timestamp: point.TimestampMs, Value: float64(point.Ingested)})
reduced = append(reduced, &querybuildertypesv5.TimeSeriesValue{Timestamp: point.TimestampMs, Value: float64(point.Reduced)})
}
return &querybuildertypesv5.QueryRangeResponse{
Type: querybuildertypesv5.RequestTypeTimeSeries,
Data: querybuildertypesv5.QueryData{
Results: []any{
&querybuildertypesv5.TimeSeriesData{
QueryName: "reduction_volume",
Aggregations: []*querybuildertypesv5.AggregationBucket{
{
Series: []*querybuildertypesv5.TimeSeries{
{Labels: []*querybuildertypesv5.Label{{Key: telemetrytypes.TelemetryFieldKey{Name: "series"}, Value: "ingested"}}, Values: ingested},
{Labels: []*querybuildertypesv5.Label{{Key: telemetrytypes.TelemetryFieldKey{Name: "series"}, Value: "retained"}}, Values: reduced},
},
},
},
},
},
},
}
}
func (m *module) validateMetricForReduction(ctx context.Context, orgID valuer.UUID, metricName string) error {
now := time.Now()
startTs := uint64(now.Add(-defaultPreviewLookback).UnixMilli())
endTs := uint64(now.UnixMilli())
_, types, _, err := m.metadataStore.FetchTemporalityAndTypeMulti(ctx, orgID, startTs, endTs, metricName)
if err != nil {
return err
}
metricType, ok := types[metricName]
if !ok || metricType == metrictypes.UnspecifiedType {
return errors.NewNotFoundf(errors.CodeNotFound, "metric not found: %q", metricName)
}
if metricType == metrictypes.ExpHistogramType {
return errors.Newf(errors.TypeInvalidInput, metricreductionruletypes.ErrCodeMetricReductionRuleUnsupportedMetricType,
"exponential histogram metrics cannot be reduced in v1")
}
return nil
}
func (m *module) relatedAssetImpact(ctx context.Context, orgID valuer.UUID, metricName string, dropped []string) []metricreductionruletypes.AffectedAsset {
affected := make([]metricreductionruletypes.AffectedAsset, 0)
droppedSet := make(map[string]struct{}, len(dropped))
for _, label := range dropped {
droppedSet[label] = struct{}{}
}
if dashboards, err := m.dashboard.GetByMetricNames(ctx, orgID, []string{metricName}); err != nil {
m.logger.WarnContext(ctx, "failed to fetch related dashboards for reduction preview", slog.String("metric_name", metricName), errors.Attr(err))
} else {
for _, item := range dashboards[metricName] {
usedLabels := append(splitCSV(item["group_by"]), splitCSV(item["filter_by"])...)
affected = append(affected, metricreductionruletypes.AffectedAsset{
Type: metricreductionruletypes.AssetTypeDashboard,
ID: item["dashboard_id"],
Name: item["dashboard_name"],
Widget: &metricreductionruletypes.AffectedWidget{ID: item["widget_id"], Name: item["widget_name"]},
ImpactedLabels: intersectLabels(usedLabels, droppedSet),
})
}
}
if alerts, err := m.ruleStore.GetStoredRulesByMetricName(ctx, orgID.String(), metricName); err != nil {
m.logger.WarnContext(ctx, "failed to fetch related alerts for reduction preview", slog.String("metric_name", metricName), errors.Attr(err))
} else {
for _, a := range alerts {
affected = append(affected, metricreductionruletypes.AffectedAsset{
Type: metricreductionruletypes.AssetTypeAlert,
ID: a.AlertID,
Name: a.AlertName,
})
}
}
return affected
}
func toGettableReductionRule(rule *metricreductionruletypes.ReductionRule) metricreductionruletypes.GettableReductionRule {
return metricreductionruletypes.GettableReductionRule{
Identifiable: rule.Identifiable,
TimeAuditable: rule.TimeAuditable,
UserAuditable: rule.UserAuditable,
MetricName: rule.MetricName,
MatchType: rule.MatchType,
Labels: rule.Labels,
EffectiveFrom: rule.EffectiveFrom,
Active: !rule.EffectiveFrom.After(time.Now()),
}
}
func withVolume(rule metricreductionruletypes.GettableReductionRule, volume volumeRow) metricreductionruletypes.GettableReductionRule {
rule.IngestedSeries = volume.Ingested
rule.RetainedSeries = volume.Reduced
if volume.Ingested > 0 && volume.Reduced <= volume.Ingested {
rule.ReductionPercent = (1 - float64(volume.Reduced)/float64(volume.Ingested)) * 100
}
return rule
}
func intersectLabels(keys []string, droppedSet map[string]struct{}) []string {
seen := make(map[string]struct{})
var out []string
for _, key := range keys {
if _, ok := droppedSet[key]; !ok {
continue
}
if _, dup := seen[key]; dup {
continue
}
seen[key] = struct{}{}
out = append(out, key)
}
return out
}
func splitCSV(s string) []string {
if s == "" {
return nil
}
return strings.Split(s, ",")
}
func resolveDroppedKept(matchType metricreductionruletypes.MatchType, ruleLabels, keys []string) (dropped, kept []string) {
ruleSet := make(map[string]struct{}, len(ruleLabels))
for _, l := range ruleLabels {
ruleSet[l] = struct{}{}
}
for _, k := range keys {
if metricreductionruletypes.IsProtectedLabel(k) {
kept = append(kept, k)
continue
}
_, listed := ruleSet[k]
drop := listed
if matchType == metricreductionruletypes.MatchTypeKeep {
drop = !listed
}
if drop {
dropped = append(dropped, k)
} else {
kept = append(kept, k)
}
}
sort.Strings(dropped)
sort.Strings(kept)
return dropped, kept
}
func (m *module) estimateVolume(ctx context.Context, metricName string, matchType metricreductionruletypes.MatchType, labels []string, startMs, endMs int64) (current uint64, reduced uint64, reductionPercent float64, dropped []string, err error) {
keys, err := m.ch.AttributeKeys(ctx, metricName, startMs, endMs)
if err != nil {
return 0, 0, 0, nil, err
}
dropped, kept := resolveDroppedKept(matchType, labels, keys)
current, reduced, err = m.ch.EstimateCardinality(ctx, metricName, kept, startMs, endMs)
if err != nil {
return 0, 0, 0, nil, err
}
if current > 0 && reduced <= current {
reductionPercent = (1 - float64(reduced)/float64(current)) * 100
}
return current, reduced, reductionPercent, dropped, nil
}

View File

@@ -1,145 +0,0 @@
package implmetricreductionrule
import (
"context"
"github.com/SigNoz/signoz/pkg/errors"
"github.com/SigNoz/signoz/pkg/sqlstore"
"github.com/SigNoz/signoz/pkg/types/metricreductionruletypes"
"github.com/SigNoz/signoz/pkg/valuer"
)
type store struct {
sqlstore sqlstore.SQLStore
}
func NewStore(sqlstore sqlstore.SQLStore) metricreductionruletypes.Store {
return &store{sqlstore: sqlstore}
}
func (s *store) List(ctx context.Context, orgID valuer.UUID, params *metricreductionruletypes.ListReductionRulesParams) ([]*metricreductionruletypes.ReductionRule, int, error) {
column := "metric_name"
if params.OrderBy == metricreductionruletypes.OrderByLastUpdated {
column = "updated_at"
}
direction := "ASC"
if params.Order == metricreductionruletypes.OrderDesc {
direction = "DESC"
}
rules := make([]*metricreductionruletypes.ReductionRule, 0)
query := s.sqlstore.
BunDBCtx(ctx).
NewSelect().
Model(&rules).
Where("org_id = ?", orgID).
Order(column + " " + direction)
if params.Search != "" {
query = query.Where("metric_name LIKE ?", "%"+params.Search+"%")
}
if params.MetricName != "" {
query = query.Where("metric_name = ?", params.MetricName)
}
if params.Limit > 0 {
query = query.Limit(params.Limit).Offset(params.Offset)
}
total, err := query.ScanAndCount(ctx)
if err != nil {
return nil, 0, err
}
return rules, total, nil
}
func (s *store) Get(ctx context.Context, orgID valuer.UUID, metricName string) (*metricreductionruletypes.ReductionRule, error) {
rule := new(metricreductionruletypes.ReductionRule)
err := s.sqlstore.
BunDBCtx(ctx).
NewSelect().
Model(rule).
Where("org_id = ?", orgID).
Where("metric_name = ?", metricName).
Scan(ctx)
if err != nil {
return nil, s.sqlstore.WrapNotFoundErrf(err, metricreductionruletypes.ErrCodeMetricReductionRuleNotFound, "no reduction rule found for metric %q", metricName)
}
return rule, nil
}
func (s *store) GetByID(ctx context.Context, orgID valuer.UUID, id valuer.UUID) (*metricreductionruletypes.ReductionRule, error) {
rule := new(metricreductionruletypes.ReductionRule)
err := s.sqlstore.
BunDBCtx(ctx).
NewSelect().
Model(rule).
Where("org_id = ?", orgID).
Where("id = ?", id).
Scan(ctx)
if err != nil {
return nil, s.sqlstore.WrapNotFoundErrf(err, metricreductionruletypes.ErrCodeMetricReductionRuleNotFound, "no reduction rule found with id %q", id.String())
}
return rule, nil
}
func (s *store) Create(ctx context.Context, rule *metricreductionruletypes.ReductionRule) error {
res, err := s.sqlstore.
BunDBCtx(ctx).
NewInsert().
Model(rule).
On("CONFLICT (org_id, metric_name) DO NOTHING").
Exec(ctx)
if err != nil {
return err
}
rowsAffected, err := res.RowsAffected()
if err != nil {
return err
}
if rowsAffected == 0 {
return errors.Newf(errors.TypeAlreadyExists, metricreductionruletypes.ErrCodeMetricReductionRuleAlreadyExists,
"a reduction rule for metric %q already exists", rule.MetricName)
}
return nil
}
func (s *store) Upsert(ctx context.Context, rule *metricreductionruletypes.ReductionRule) error {
_, err := s.sqlstore.
BunDBCtx(ctx).
NewInsert().
Model(rule).
On("CONFLICT (org_id, metric_name) DO UPDATE").
Set("match_type = EXCLUDED.match_type").
Set("labels = EXCLUDED.labels").
Set("effective_from = EXCLUDED.effective_from").
Set("updated_at = EXCLUDED.updated_at").
Set("updated_by = EXCLUDED.updated_by").
Exec(ctx)
return err
}
func (s *store) DeleteByID(ctx context.Context, orgID valuer.UUID, id valuer.UUID) error {
res, err := s.sqlstore.
BunDBCtx(ctx).
NewDelete().
Model((*metricreductionruletypes.ReductionRule)(nil)).
Where("org_id = ?", orgID).
Where("id = ?", id).
Exec(ctx)
if err != nil {
return err
}
rowsAffected, err := res.RowsAffected()
if err != nil {
return err
}
if rowsAffected == 0 {
return errors.Newf(errors.TypeNotFound, metricreductionruletypes.ErrCodeMetricReductionRuleNotFound, "no reduction rule found with id %q", id.String())
}
return nil
}
func (s *store) RunInTx(ctx context.Context, cb func(ctx context.Context) error) error {
return s.sqlstore.RunInTxCtx(ctx, nil, cb)
}

View File

@@ -107,15 +107,6 @@ func (ah *APIHandler) getFeatureFlags(w http.ResponseWriter, r *http.Request) {
Route: "",
})
metricsReduction := ah.Signoz.Flagger.BooleanOrEmpty(ctx, flagger.FeatureEnableMetricsReduction, evalCtx)
featureSet = append(featureSet, &licensetypes.Feature{
Name: valuer.NewString(flagger.FeatureEnableMetricsReduction.String()),
Active: metricsReduction,
Usage: 0,
UsageLimit: -1,
Route: "",
})
if constants.IsDotMetricsEnabled {
for idx, feature := range featureSet {
if feature.Name == licensetypes.DotMetricsEnabled {

View File

@@ -90,8 +90,12 @@ func NewServer(config signoz.Config, signoz *signoz.SigNoz) (*Server, error) {
// initiate agent config handler
agentConfMgr, err := agentConf.Initiate(&agentConf.ManagerOptions{
Store: signoz.SQLStore,
AgentFeatures: []agentConf.AgentFeature{logParsingPipelineController},
Store: signoz.SQLStore,
AgentFeatures: []agentConf.AgentFeature{
logParsingPipelineController,
signoz.Modules.SpanMapper,
signoz.Modules.LLMPricingRule,
},
})
if err != nil {
return nil, err

View File

@@ -39,7 +39,7 @@ import { GeneratedAPIInstance } from '../../../generatedAPIInstance';
import type { ErrorType, BodyType } from '../../../generatedAPIInstance';
/**
* Returns a paginated list of Kubernetes clusters with key aggregated metrics derived by summing per-node values within the group: CPU usage, CPU allocatable, memory working set, memory allocatable. Each row also reports per-group nodeCountsByReadiness ({ ready, notReady } from each node's latest k8s.node.condition_ready value) and per-group podCountsByPhase ({ pending, running, succeeded, failed, unknown } from each pod's latest k8s.pod.phase value). Each cluster includes metadata attributes (k8s.cluster.name). The response type is 'list' for the default k8s.cluster.name grouping or 'grouped_list' for custom groupBy keys; in both modes every row aggregates nodes and pods in the group. Supports filtering via a filter expression, custom groupBy, ordering by cpu / cpu_allocatable / memory / memory_allocatable, and pagination via offset/limit. Also reports missing required metrics and whether the requested time range falls before the data retention boundary. Numeric metric fields (clusterCPU, clusterCPUAllocatable, clusterMemory, clusterMemoryAllocatable) return -1 as a sentinel when no data is available for that field.
* Returns a paginated list of Kubernetes clusters with key aggregated metrics derived by summing per-node values within the group: CPU usage, CPU allocatable, memory working set, memory allocatable. Each row also reports per-group nodeCountsByReadiness ({ ready, notReady } from each node's latest k8s.node.condition_ready value) and per-group podCountsByPhase ({ pending, running, succeeded, failed, unknown } from each pod's latest k8s.pod.phase value). Each cluster includes metadata attributes (k8s.cluster.name). The response type is 'list' for the default k8s.cluster.name grouping or 'grouped_list' for custom groupBy keys; in both modes every row aggregates nodes and pods in the group. Supports filtering via a filter expression, custom groupBy, ordering by cpu / cpu_allocatable / memory / memory_allocatable, and pagination via offset/limit. Also reports whether the requested time range falls before the data retention boundary. Numeric metric fields (clusterCPU, clusterCPUAllocatable, clusterMemory, clusterMemoryAllocatable) return -1 as a sentinel when no data is available for that field.
* @summary List Clusters for Infra Monitoring
*/
export const listClusters = (
@@ -122,7 +122,7 @@ export const useListClusters = <
return useMutation(getListClustersMutationOptions(options));
};
/**
* Returns a paginated list of Kubernetes DaemonSets with key aggregated pod metrics: CPU usage and memory working set summed across pods owned by the daemonset, plus average CPU/memory request and limit utilization (daemonSetCPURequest, daemonSetCPULimit, daemonSetMemoryRequest, daemonSetMemoryLimit). Each row also reports the latest known node-level counters from kube-state-metrics: desiredNodes (k8s.daemonset.desired_scheduled_nodes, the number of nodes the daemonset wants to run on) and currentNodes (k8s.daemonset.current_scheduled_nodes, the number of nodes the daemonset currently runs on) — note these are node counts, not pod counts. It also reports per-group podCountsByPhase ({ pending, running, succeeded, failed, unknown } from each pod's latest k8s.pod.phase value). Each daemonset includes metadata attributes (k8s.daemonset.name, k8s.namespace.name, k8s.cluster.name). The response type is 'list' for the default k8s.daemonset.name grouping or 'grouped_list' for custom groupBy keys; in both modes every row aggregates pods owned by daemonsets in the group. Supports filtering via a filter expression, custom groupBy, ordering by cpu / cpu_request / cpu_limit / memory / memory_request / memory_limit / desired_nodes / current_nodes, and pagination via offset/limit. Also reports missing required metrics and whether the requested time range falls before the data retention boundary. Numeric metric fields (daemonSetCPU, daemonSetCPURequest, daemonSetCPULimit, daemonSetMemory, daemonSetMemoryRequest, daemonSetMemoryLimit, desiredNodes, currentNodes) return -1 as a sentinel when no data is available for that field.
* Returns a paginated list of Kubernetes DaemonSets with key aggregated pod metrics: CPU usage and memory working set summed across pods owned by the daemonset, plus average CPU/memory request and limit utilization (daemonSetCPURequest, daemonSetCPULimit, daemonSetMemoryRequest, daemonSetMemoryLimit). Each row also reports the latest known node-level counters from kube-state-metrics: desiredNodes (k8s.daemonset.desired_scheduled_nodes, the number of nodes the daemonset wants to run on) and currentNodes (k8s.daemonset.current_scheduled_nodes, the number of nodes the daemonset currently runs on) — note these are node counts, not pod counts. It also reports per-group podCountsByPhase ({ pending, running, succeeded, failed, unknown } from each pod's latest k8s.pod.phase value). Each daemonset includes metadata attributes (k8s.daemonset.name, k8s.namespace.name, k8s.cluster.name). The response type is 'list' for the default k8s.daemonset.name grouping or 'grouped_list' for custom groupBy keys; in both modes every row aggregates pods owned by daemonsets in the group. Supports filtering via a filter expression, custom groupBy, ordering by cpu / cpu_request / cpu_limit / memory / memory_request / memory_limit / desired_nodes / current_nodes, and pagination via offset/limit. Also reports whether the requested time range falls before the data retention boundary. Numeric metric fields (daemonSetCPU, daemonSetCPURequest, daemonSetCPULimit, daemonSetMemory, daemonSetMemoryRequest, daemonSetMemoryLimit, desiredNodes, currentNodes) return -1 as a sentinel when no data is available for that field.
* @summary List DaemonSets for Infra Monitoring
*/
export const listDaemonSets = (
@@ -205,7 +205,7 @@ export const useListDaemonSets = <
return useMutation(getListDaemonSetsMutationOptions(options));
};
/**
* Returns a paginated list of Kubernetes Deployments with key aggregated pod metrics: CPU usage and memory working set summed across pods owned by the deployment, plus average CPU/memory request and limit utilization (deploymentCPURequest, deploymentCPULimit, deploymentMemoryRequest, deploymentMemoryLimit). Each row also reports the latest known desiredPods (k8s.deployment.desired) and availablePods (k8s.deployment.available) replica counts and per-group podCountsByPhase ({ pending, running, succeeded, failed, unknown } from each pod's latest k8s.pod.phase value). Each deployment includes metadata attributes (k8s.deployment.name, k8s.namespace.name, k8s.cluster.name). The response type is 'list' for the default k8s.deployment.name grouping or 'grouped_list' for custom groupBy keys; in both modes every row aggregates pods owned by deployments in the group. Supports filtering via a filter expression, custom groupBy, ordering by cpu / cpu_request / cpu_limit / memory / memory_request / memory_limit / desired_pods / available_pods, and pagination via offset/limit. Also reports missing required metrics and whether the requested time range falls before the data retention boundary. Numeric metric fields (deploymentCPU, deploymentCPURequest, deploymentCPULimit, deploymentMemory, deploymentMemoryRequest, deploymentMemoryLimit, desiredPods, availablePods) return -1 as a sentinel when no data is available for that field.
* Returns a paginated list of Kubernetes Deployments with key aggregated pod metrics: CPU usage and memory working set summed across pods owned by the deployment, plus average CPU/memory request and limit utilization (deploymentCPURequest, deploymentCPULimit, deploymentMemoryRequest, deploymentMemoryLimit). Each row also reports the latest known desiredPods (k8s.deployment.desired) and availablePods (k8s.deployment.available) replica counts and per-group podCountsByPhase ({ pending, running, succeeded, failed, unknown } from each pod's latest k8s.pod.phase value). Each deployment includes metadata attributes (k8s.deployment.name, k8s.namespace.name, k8s.cluster.name). The response type is 'list' for the default k8s.deployment.name grouping or 'grouped_list' for custom groupBy keys; in both modes every row aggregates pods owned by deployments in the group. Supports filtering via a filter expression, custom groupBy, ordering by cpu / cpu_request / cpu_limit / memory / memory_request / memory_limit / desired_pods / available_pods, and pagination via offset/limit. Also reports whether the requested time range falls before the data retention boundary. Numeric metric fields (deploymentCPU, deploymentCPURequest, deploymentCPULimit, deploymentMemory, deploymentMemoryRequest, deploymentMemoryLimit, desiredPods, availablePods) return -1 as a sentinel when no data is available for that field.
* @summary List Deployments for Infra Monitoring
*/
export const listDeployments = (
@@ -288,7 +288,7 @@ export const useListDeployments = <
return useMutation(getListDeploymentsMutationOptions(options));
};
/**
* Returns a paginated list of hosts with key infrastructure metrics: CPU usage (%), memory usage (%), I/O wait (%), disk usage (%), and 15-minute load average. Each host includes its current status (active/inactive based on metrics reported in the last 10 minutes) and metadata attributes (e.g., os.type). Supports filtering via a filter expression, filtering by host status, custom groupBy to aggregate hosts by any attribute, ordering by any of the five metrics, and pagination via offset/limit. The response type is 'list' for the default host.name grouping or 'grouped_list' for custom groupBy keys. Also reports missing required metrics and whether the requested time range falls before the data retention boundary. Numeric metric fields (cpu, memory, wait, load15, diskUsage) return -1 as a sentinel when no data is available for that field.
* Returns a paginated list of hosts with key infrastructure metrics: CPU usage (%), memory usage (%), I/O wait (%), disk usage (%), and 15-minute load average. Each host includes its current status (active/inactive based on metrics reported in the last 10 minutes) and metadata attributes (e.g., os.type). Supports filtering via a filter expression, filtering by host status, custom groupBy to aggregate hosts by any attribute, ordering by any of the five metrics, and pagination via offset/limit. The response type is 'list' for the default host.name grouping or 'grouped_list' for custom groupBy keys. Also reports whether the requested time range falls before the data retention boundary. Numeric metric fields (cpu, memory, wait, load15, diskUsage) return -1 as a sentinel when no data is available for that field.
* @summary List Hosts for Infra Monitoring
*/
export const listHosts = (
@@ -371,7 +371,7 @@ export const useListHosts = <
return useMutation(getListHostsMutationOptions(options));
};
/**
* Returns a paginated list of Kubernetes Jobs with key aggregated pod metrics: CPU usage and memory working set summed across pods owned by the job, plus average CPU/memory request and limit utilization (jobCPURequest, jobCPULimit, jobMemoryRequest, jobMemoryLimit). Each row also reports the latest known job-level counters from kube-state-metrics: desiredSuccessfulPods (k8s.job.desired_successful_pods, the target completion count), activePods (k8s.job.active_pods), failedPods (k8s.job.failed_pods, cumulative across the lifetime of the job), and successfulPods (k8s.job.successful_pods, cumulative). It also reports per-group podCountsByPhase ({ pending, running, succeeded, failed, unknown } from each pod's latest k8s.pod.phase value); note podCountsByPhase.failed (current pod-phase) is distinct from failedPods (cumulative job kube-state-metric). Each job includes metadata attributes (k8s.job.name, k8s.namespace.name, k8s.cluster.name). The response type is 'list' for the default k8s.job.name grouping or 'grouped_list' for custom groupBy keys; in both modes every row aggregates pods owned by jobs in the group. Supports filtering via a filter expression, custom groupBy, ordering by cpu / cpu_request / cpu_limit / memory / memory_request / memory_limit / desired_successful_pods / active_pods / failed_pods / successful_pods, and pagination via offset/limit. Also reports missing required metrics and whether the requested time range falls before the data retention boundary. Numeric metric fields (jobCPU, jobCPURequest, jobCPULimit, jobMemory, jobMemoryRequest, jobMemoryLimit, desiredSuccessfulPods, activePods, failedPods, successfulPods) return -1 as a sentinel when no data is available for that field.
* Returns a paginated list of Kubernetes Jobs with key aggregated pod metrics: CPU usage and memory working set summed across pods owned by the job, plus average CPU/memory request and limit utilization (jobCPURequest, jobCPULimit, jobMemoryRequest, jobMemoryLimit). Each row also reports the latest known job-level counters from kube-state-metrics: desiredSuccessfulPods (k8s.job.desired_successful_pods, the target completion count), activePods (k8s.job.active_pods), failedPods (k8s.job.failed_pods, cumulative across the lifetime of the job), and successfulPods (k8s.job.successful_pods, cumulative). It also reports per-group podCountsByPhase ({ pending, running, succeeded, failed, unknown } from each pod's latest k8s.pod.phase value); note podCountsByPhase.failed (current pod-phase) is distinct from failedPods (cumulative job kube-state-metric). Each job includes metadata attributes (k8s.job.name, k8s.namespace.name, k8s.cluster.name). The response type is 'list' for the default k8s.job.name grouping or 'grouped_list' for custom groupBy keys; in both modes every row aggregates pods owned by jobs in the group. Supports filtering via a filter expression, custom groupBy, ordering by cpu / cpu_request / cpu_limit / memory / memory_request / memory_limit / desired_successful_pods / active_pods / failed_pods / successful_pods, and pagination via offset/limit. Also reports whether the requested time range falls before the data retention boundary. Numeric metric fields (jobCPU, jobCPURequest, jobCPULimit, jobMemory, jobMemoryRequest, jobMemoryLimit, desiredSuccessfulPods, activePods, failedPods, successfulPods) return -1 as a sentinel when no data is available for that field.
* @summary List Jobs for Infra Monitoring
*/
export const listJobs = (
@@ -454,7 +454,7 @@ export const useListJobs = <
return useMutation(getListJobsMutationOptions(options));
};
/**
* Returns a paginated list of Kubernetes namespaces with key aggregated pod metrics: CPU usage and memory working set (summed across pods in the group), plus per-group podCountsByPhase ({ pending, running, succeeded, failed, unknown } from each pod's latest k8s.pod.phase value in the window). Each namespace includes metadata attributes (k8s.namespace.name, k8s.cluster.name). The response type is 'list' for the default k8s.namespace.name grouping or 'grouped_list' for custom groupBy keys; in both modes every row aggregates pods in the group. Supports filtering via a filter expression, custom groupBy, ordering by cpu / memory, and pagination via offset/limit. Also reports missing required metrics and whether the requested time range falls before the data retention boundary. Numeric metric fields (namespaceCPU, namespaceMemory) return -1 as a sentinel when no data is available for that field.
* Returns a paginated list of Kubernetes namespaces with key aggregated pod metrics: CPU usage and memory working set (summed across pods in the group), plus per-group podCountsByPhase ({ pending, running, succeeded, failed, unknown } from each pod's latest k8s.pod.phase value in the window). Each namespace includes metadata attributes (k8s.namespace.name, k8s.cluster.name). The response type is 'list' for the default k8s.namespace.name grouping or 'grouped_list' for custom groupBy keys; in both modes every row aggregates pods in the group. Supports filtering via a filter expression, custom groupBy, ordering by cpu / memory, and pagination via offset/limit. Also reports whether the requested time range falls before the data retention boundary. Numeric metric fields (namespaceCPU, namespaceMemory) return -1 as a sentinel when no data is available for that field.
* @summary List Namespaces for Infra Monitoring
*/
export const listNamespaces = (
@@ -537,7 +537,7 @@ export const useListNamespaces = <
return useMutation(getListNamespacesMutationOptions(options));
};
/**
* Returns a paginated list of Kubernetes nodes with key metrics: CPU usage, CPU allocatable, memory working set, memory allocatable, per-group nodeCountsByReadiness ({ ready, notReady } from each node's latest k8s.node.condition_ready in the window) and per-group podCountsByPhase ({ pending, running, succeeded, failed, unknown } for pods scheduled on the listed nodes). Each node includes metadata attributes (k8s.node.uid, k8s.cluster.name). The response type is 'list' for the default k8s.node.name grouping (each row is one node with its current condition string: ready / not_ready / no_data) or 'grouped_list' for custom groupBy keys (each row aggregates nodes in the group; condition stays no_data). Supports filtering via a filter expression, custom groupBy, ordering by cpu / cpu_allocatable / memory / memory_allocatable, and pagination via offset/limit. Also reports missing required metrics and whether the requested time range falls before the data retention boundary. Numeric metric fields (nodeCPU, nodeCPUAllocatable, nodeMemory, nodeMemoryAllocatable) return -1 as a sentinel when no data is available for that field.
* Returns a paginated list of Kubernetes nodes with key metrics: CPU usage, CPU allocatable, memory working set, memory allocatable, per-group nodeCountsByReadiness ({ ready, notReady } from each node's latest k8s.node.condition_ready in the window) and per-group podCountsByPhase ({ pending, running, succeeded, failed, unknown } for pods scheduled on the listed nodes). Each node includes metadata attributes (k8s.node.uid, k8s.cluster.name). The response type is 'list' for the default k8s.node.name grouping (each row is one node with its current condition string: ready / not_ready / no_data) or 'grouped_list' for custom groupBy keys (each row aggregates nodes in the group; condition stays no_data). Supports filtering via a filter expression, custom groupBy, ordering by cpu / cpu_allocatable / memory / memory_allocatable, and pagination via offset/limit. Also reports whether the requested time range falls before the data retention boundary. Numeric metric fields (nodeCPU, nodeCPUAllocatable, nodeMemory, nodeMemoryAllocatable) return -1 as a sentinel when no data is available for that field.
* @summary List Nodes for Infra Monitoring
*/
export const listNodes = (
@@ -620,7 +620,7 @@ export const useListNodes = <
return useMutation(getListNodesMutationOptions(options));
};
/**
* Returns a paginated list of Kubernetes pods with key metrics: CPU usage, CPU request/limit utilization, memory working set, memory request/limit utilization, current pod phase (pending/running/succeeded/failed/unknown/no_data), and pod age (ms since start time). Each pod includes metadata attributes (namespace, node, workload owner such as deployment/statefulset/daemonset/job/cronjob, cluster). Supports filtering via a filter expression, custom groupBy to aggregate pods by any attribute, ordering by any of the six metrics (cpu, cpu_request, cpu_limit, memory, memory_request, memory_limit), and pagination via offset/limit. The response type is 'list' for the default k8s.pod.uid grouping (each row is one pod with its current phase) or 'grouped_list' for custom groupBy keys (each row aggregates pods in the group with per-phase counts under podCountsByPhase: { pending, running, succeeded, failed, unknown } derived from each pod's latest phase in the window). Also reports missing required metrics and whether the requested time range falls before the data retention boundary. Numeric metric fields (podCPU, podCPURequest, podCPULimit, podMemory, podMemoryRequest, podMemoryLimit, podAge) return -1 as a sentinel when no data is available for that field.
* Returns a paginated list of Kubernetes pods with key metrics: CPU usage, CPU request/limit utilization, memory working set, memory request/limit utilization, current pod phase (pending/running/succeeded/failed/unknown/no_data), and pod age (ms since start time). Each pod includes metadata attributes (namespace, node, workload owner such as deployment/statefulset/daemonset/job/cronjob, cluster). Supports filtering via a filter expression, custom groupBy to aggregate pods by any attribute, ordering by any of the six metrics (cpu, cpu_request, cpu_limit, memory, memory_request, memory_limit), and pagination via offset/limit. The response type is 'list' for the default k8s.pod.uid grouping (each row is one pod with its current phase) or 'grouped_list' for custom groupBy keys (each row aggregates pods in the group with per-phase counts under podCountsByPhase: { pending, running, succeeded, failed, unknown } derived from each pod's latest phase in the window). Also reports whether the requested time range falls before the data retention boundary. Numeric metric fields (podCPU, podCPURequest, podCPULimit, podMemory, podMemoryRequest, podMemoryLimit, podAge) return -1 as a sentinel when no data is available for that field.
* @summary List Pods for Infra Monitoring
*/
export const listPods = (
@@ -703,7 +703,7 @@ export const useListPods = <
return useMutation(getListPodsMutationOptions(options));
};
/**
* Returns a paginated list of Kubernetes persistent volume claims (PVCs) with key volume metrics: available bytes, capacity bytes, usage (capacity - available), inodes, free inodes, and used inodes. Each row also includes metadata attributes (k8s.persistentvolumeclaim.name, k8s.pod.uid, k8s.pod.name, k8s.namespace.name, k8s.node.name, k8s.statefulset.name, k8s.cluster.name). Supports filtering via a filter expression, custom groupBy to aggregate volumes by any attribute, ordering by any of the six metrics (available, capacity, usage, inodes, inodes_free, inodes_used), and pagination via offset/limit. The response type is 'list' for the default k8s.persistentvolumeclaim.name grouping or 'grouped_list' for custom groupBy keys; in both modes every row aggregates volumes in the group. Also reports missing required metrics and whether the requested time range falls before the data retention boundary. Numeric metric fields (volumeAvailable, volumeCapacity, volumeUsage, volumeInodes, volumeInodesFree, volumeInodesUsed) return -1 as a sentinel when no data is available for that field.
* Returns a paginated list of Kubernetes persistent volume claims (PVCs) with key volume metrics: available bytes, capacity bytes, usage (capacity - available), inodes, free inodes, and used inodes. Each row also includes metadata attributes (k8s.persistentvolumeclaim.name, k8s.pod.uid, k8s.pod.name, k8s.namespace.name, k8s.node.name, k8s.statefulset.name, k8s.cluster.name). Supports filtering via a filter expression, custom groupBy to aggregate volumes by any attribute, ordering by any of the six metrics (available, capacity, usage, inodes, inodes_free, inodes_used), and pagination via offset/limit. The response type is 'list' for the default k8s.persistentvolumeclaim.name grouping or 'grouped_list' for custom groupBy keys; in both modes every row aggregates volumes in the group. Also reports whether the requested time range falls before the data retention boundary. Numeric metric fields (volumeAvailable, volumeCapacity, volumeUsage, volumeInodes, volumeInodesFree, volumeInodesUsed) return -1 as a sentinel when no data is available for that field.
* @summary List Volumes for Infra Monitoring
*/
export const listVolumes = (
@@ -786,7 +786,7 @@ export const useListVolumes = <
return useMutation(getListVolumesMutationOptions(options));
};
/**
* Returns a paginated list of Kubernetes StatefulSets with key aggregated pod metrics: CPU usage and memory working set summed across pods owned by the statefulset, plus average CPU/memory request and limit utilization (statefulSetCPURequest, statefulSetCPULimit, statefulSetMemoryRequest, statefulSetMemoryLimit). Each row also reports the latest known desiredPods (k8s.statefulset.desired_pods) and currentPods (k8s.statefulset.current_pods) replica counts and per-group podCountsByPhase ({ pending, running, succeeded, failed, unknown } from each pod's latest k8s.pod.phase value). Each statefulset includes metadata attributes (k8s.statefulset.name, k8s.namespace.name, k8s.cluster.name). The response type is 'list' for the default k8s.statefulset.name grouping or 'grouped_list' for custom groupBy keys; in both modes every row aggregates pods owned by statefulsets in the group. Supports filtering via a filter expression, custom groupBy, ordering by cpu / cpu_request / cpu_limit / memory / memory_request / memory_limit / desired_pods / current_pods, and pagination via offset/limit. Also reports missing required metrics and whether the requested time range falls before the data retention boundary. Numeric metric fields (statefulSetCPU, statefulSetCPURequest, statefulSetCPULimit, statefulSetMemory, statefulSetMemoryRequest, statefulSetMemoryLimit, desiredPods, currentPods) return -1 as a sentinel when no data is available for that field.
* Returns a paginated list of Kubernetes StatefulSets with key aggregated pod metrics: CPU usage and memory working set summed across pods owned by the statefulset, plus average CPU/memory request and limit utilization (statefulSetCPURequest, statefulSetCPULimit, statefulSetMemoryRequest, statefulSetMemoryLimit). Each row also reports the latest known desiredPods (k8s.statefulset.desired_pods) and currentPods (k8s.statefulset.current_pods) replica counts and per-group podCountsByPhase ({ pending, running, succeeded, failed, unknown } from each pod's latest k8s.pod.phase value). Each statefulset includes metadata attributes (k8s.statefulset.name, k8s.namespace.name, k8s.cluster.name). The response type is 'list' for the default k8s.statefulset.name grouping or 'grouped_list' for custom groupBy keys; in both modes every row aggregates pods owned by statefulsets in the group. Supports filtering via a filter expression, custom groupBy, ordering by cpu / cpu_request / cpu_limit / memory / memory_request / memory_limit / desired_pods / current_pods, and pagination via offset/limit. Also reports whether the requested time range falls before the data retention boundary. Numeric metric fields (statefulSetCPU, statefulSetCPURequest, statefulSetCPULimit, statefulSetMemory, statefulSetMemoryRequest, statefulSetMemoryLimit, desiredPods, currentPods) return -1 as a sentinel when no data is available for that field.
* @summary List StatefulSets for Infra Monitoring
*/
export const listStatefulSets = (

View File

@@ -18,8 +18,6 @@ import type {
} from 'react-query';
import type {
CreateMetricReductionRule201,
DeleteMetricReductionRuleByIDPathParameters,
GetMetricAlerts200,
GetMetricAlertsParams,
GetMetricAttributes200,
@@ -30,762 +28,22 @@ import type {
GetMetricHighlightsParams,
GetMetricMetadata200,
GetMetricMetadataParams,
GetMetricReductionRuleByID200,
GetMetricReductionRuleByIDPathParameters,
GetMetricReductionRuleStats200,
GetMetricReductionRuleTimeseries200,
GetMetricsOnboardingStatus200,
GetMetricsStats200,
GetMetricsTreemap200,
InspectMetrics200,
ListMetricReductionRules200,
ListMetricReductionRulesParams,
ListMetrics200,
ListMetricsParams,
MetricreductionruletypesPostableReductionRuleDTO,
MetricreductionruletypesPostableReductionRulePreviewDTO,
MetricreductionruletypesUpdatableReductionRuleDTO,
MetricsexplorertypesInspectMetricsRequestDTO,
MetricsexplorertypesStatsRequestDTO,
MetricsexplorertypesTreemapRequestDTO,
MetricsexplorertypesUpdateMetricMetadataRequestDTO,
PreviewMetricReductionRule200,
RenderErrorResponseDTO,
UpdateMetricReductionRuleByID200,
UpdateMetricReductionRuleByIDPathParameters,
} from '../sigNoz.schemas';
import { GeneratedAPIInstance } from '../../../generatedAPIInstance';
import type { ErrorType, BodyType } from '../../../generatedAPIInstance';
/**
* Returns active metric volume-control (label reduction) rules.
* @summary List metric reduction rules
*/
export const listMetricReductionRules = (
params?: ListMetricReductionRulesParams,
signal?: AbortSignal,
) => {
return GeneratedAPIInstance<ListMetricReductionRules200>({
url: `/api/v2/metric_reduction_rules`,
method: 'GET',
params,
signal,
});
};
export const getListMetricReductionRulesQueryKey = (
params?: ListMetricReductionRulesParams,
) => {
return [
`/api/v2/metric_reduction_rules`,
...(params ? [params] : []),
] as const;
};
export const getListMetricReductionRulesQueryOptions = <
TData = Awaited<ReturnType<typeof listMetricReductionRules>>,
TError = ErrorType<RenderErrorResponseDTO>,
>(
params?: ListMetricReductionRulesParams,
options?: {
query?: UseQueryOptions<
Awaited<ReturnType<typeof listMetricReductionRules>>,
TError,
TData
>;
},
) => {
const { query: queryOptions } = options ?? {};
const queryKey =
queryOptions?.queryKey ?? getListMetricReductionRulesQueryKey(params);
const queryFn: QueryFunction<
Awaited<ReturnType<typeof listMetricReductionRules>>
> = ({ signal }) => listMetricReductionRules(params, signal);
return { queryKey, queryFn, ...queryOptions } as UseQueryOptions<
Awaited<ReturnType<typeof listMetricReductionRules>>,
TError,
TData
> & { queryKey: QueryKey };
};
export type ListMetricReductionRulesQueryResult = NonNullable<
Awaited<ReturnType<typeof listMetricReductionRules>>
>;
export type ListMetricReductionRulesQueryError =
ErrorType<RenderErrorResponseDTO>;
/**
* @summary List metric reduction rules
*/
export function useListMetricReductionRules<
TData = Awaited<ReturnType<typeof listMetricReductionRules>>,
TError = ErrorType<RenderErrorResponseDTO>,
>(
params?: ListMetricReductionRulesParams,
options?: {
query?: UseQueryOptions<
Awaited<ReturnType<typeof listMetricReductionRules>>,
TError,
TData
>;
},
): UseQueryResult<TData, TError> & { queryKey: QueryKey } {
const queryOptions = getListMetricReductionRulesQueryOptions(params, options);
const query = useQuery(queryOptions) as UseQueryResult<TData, TError> & {
queryKey: QueryKey;
};
return { ...query, queryKey: queryOptions.queryKey };
}
/**
* @summary List metric reduction rules
*/
export const invalidateListMetricReductionRules = async (
queryClient: QueryClient,
params?: ListMetricReductionRulesParams,
options?: InvalidateOptions,
): Promise<QueryClient> => {
await queryClient.invalidateQueries(
{ queryKey: getListMetricReductionRulesQueryKey(params) },
options,
);
return queryClient;
};
/**
* Creates a volume-control rule for a metric and returns it with its id; fails if the metric already has a rule.
* @summary Create a metric reduction rule
*/
export const createMetricReductionRule = (
metricreductionruletypesPostableReductionRuleDTO?: BodyType<MetricreductionruletypesPostableReductionRuleDTO>,
signal?: AbortSignal,
) => {
return GeneratedAPIInstance<CreateMetricReductionRule201>({
url: `/api/v2/metric_reduction_rules`,
method: 'POST',
headers: { 'Content-Type': 'application/json' },
data: metricreductionruletypesPostableReductionRuleDTO,
signal,
});
};
export const getCreateMetricReductionRuleMutationOptions = <
TError = ErrorType<RenderErrorResponseDTO>,
TContext = unknown,
>(options?: {
mutation?: UseMutationOptions<
Awaited<ReturnType<typeof createMetricReductionRule>>,
TError,
{ data?: BodyType<MetricreductionruletypesPostableReductionRuleDTO> },
TContext
>;
}): UseMutationOptions<
Awaited<ReturnType<typeof createMetricReductionRule>>,
TError,
{ data?: BodyType<MetricreductionruletypesPostableReductionRuleDTO> },
TContext
> => {
const mutationKey = ['createMetricReductionRule'];
const { mutation: mutationOptions } = options
? options.mutation &&
'mutationKey' in options.mutation &&
options.mutation.mutationKey
? options
: { ...options, mutation: { ...options.mutation, mutationKey } }
: { mutation: { mutationKey } };
const mutationFn: MutationFunction<
Awaited<ReturnType<typeof createMetricReductionRule>>,
{ data?: BodyType<MetricreductionruletypesPostableReductionRuleDTO> }
> = (props) => {
const { data } = props ?? {};
return createMetricReductionRule(data);
};
return { mutationFn, ...mutationOptions };
};
export type CreateMetricReductionRuleMutationResult = NonNullable<
Awaited<ReturnType<typeof createMetricReductionRule>>
>;
export type CreateMetricReductionRuleMutationBody =
| BodyType<MetricreductionruletypesPostableReductionRuleDTO>
| undefined;
export type CreateMetricReductionRuleMutationError =
ErrorType<RenderErrorResponseDTO>;
/**
* @summary Create a metric reduction rule
*/
export const useCreateMetricReductionRule = <
TError = ErrorType<RenderErrorResponseDTO>,
TContext = unknown,
>(options?: {
mutation?: UseMutationOptions<
Awaited<ReturnType<typeof createMetricReductionRule>>,
TError,
{ data?: BodyType<MetricreductionruletypesPostableReductionRuleDTO> },
TContext
>;
}): UseMutationResult<
Awaited<ReturnType<typeof createMetricReductionRule>>,
TError,
{ data?: BodyType<MetricreductionruletypesPostableReductionRuleDTO> },
TContext
> => {
return useMutation(getCreateMetricReductionRuleMutationOptions(options));
};
/**
* Deletes a volume-control rule by its id.
* @summary Delete a metric reduction rule by id
*/
export const deleteMetricReductionRuleByID = (
{ id }: DeleteMetricReductionRuleByIDPathParameters,
signal?: AbortSignal,
) => {
return GeneratedAPIInstance<void>({
url: `/api/v2/metric_reduction_rules/${id}`,
method: 'DELETE',
signal,
});
};
export const getDeleteMetricReductionRuleByIDMutationOptions = <
TError = ErrorType<RenderErrorResponseDTO>,
TContext = unknown,
>(options?: {
mutation?: UseMutationOptions<
Awaited<ReturnType<typeof deleteMetricReductionRuleByID>>,
TError,
{ pathParams: DeleteMetricReductionRuleByIDPathParameters },
TContext
>;
}): UseMutationOptions<
Awaited<ReturnType<typeof deleteMetricReductionRuleByID>>,
TError,
{ pathParams: DeleteMetricReductionRuleByIDPathParameters },
TContext
> => {
const mutationKey = ['deleteMetricReductionRuleByID'];
const { mutation: mutationOptions } = options
? options.mutation &&
'mutationKey' in options.mutation &&
options.mutation.mutationKey
? options
: { ...options, mutation: { ...options.mutation, mutationKey } }
: { mutation: { mutationKey } };
const mutationFn: MutationFunction<
Awaited<ReturnType<typeof deleteMetricReductionRuleByID>>,
{ pathParams: DeleteMetricReductionRuleByIDPathParameters }
> = (props) => {
const { pathParams } = props ?? {};
return deleteMetricReductionRuleByID(pathParams);
};
return { mutationFn, ...mutationOptions };
};
export type DeleteMetricReductionRuleByIDMutationResult = NonNullable<
Awaited<ReturnType<typeof deleteMetricReductionRuleByID>>
>;
export type DeleteMetricReductionRuleByIDMutationError =
ErrorType<RenderErrorResponseDTO>;
/**
* @summary Delete a metric reduction rule by id
*/
export const useDeleteMetricReductionRuleByID = <
TError = ErrorType<RenderErrorResponseDTO>,
TContext = unknown,
>(options?: {
mutation?: UseMutationOptions<
Awaited<ReturnType<typeof deleteMetricReductionRuleByID>>,
TError,
{ pathParams: DeleteMetricReductionRuleByIDPathParameters },
TContext
>;
}): UseMutationResult<
Awaited<ReturnType<typeof deleteMetricReductionRuleByID>>,
TError,
{ pathParams: DeleteMetricReductionRuleByIDPathParameters },
TContext
> => {
return useMutation(getDeleteMetricReductionRuleByIDMutationOptions(options));
};
/**
* Returns a single volume-control rule by its id.
* @summary Get a metric reduction rule by id
*/
export const getMetricReductionRuleByID = (
{ id }: GetMetricReductionRuleByIDPathParameters,
signal?: AbortSignal,
) => {
return GeneratedAPIInstance<GetMetricReductionRuleByID200>({
url: `/api/v2/metric_reduction_rules/${id}`,
method: 'GET',
signal,
});
};
export const getGetMetricReductionRuleByIDQueryKey = ({
id,
}: GetMetricReductionRuleByIDPathParameters) => {
return [`/api/v2/metric_reduction_rules/${id}`] as const;
};
export const getGetMetricReductionRuleByIDQueryOptions = <
TData = Awaited<ReturnType<typeof getMetricReductionRuleByID>>,
TError = ErrorType<RenderErrorResponseDTO>,
>(
{ id }: GetMetricReductionRuleByIDPathParameters,
options?: {
query?: UseQueryOptions<
Awaited<ReturnType<typeof getMetricReductionRuleByID>>,
TError,
TData
>;
},
) => {
const { query: queryOptions } = options ?? {};
const queryKey =
queryOptions?.queryKey ?? getGetMetricReductionRuleByIDQueryKey({ id });
const queryFn: QueryFunction<
Awaited<ReturnType<typeof getMetricReductionRuleByID>>
> = ({ signal }) => getMetricReductionRuleByID({ id }, signal);
return {
queryKey,
queryFn,
enabled: !!id,
...queryOptions,
} as UseQueryOptions<
Awaited<ReturnType<typeof getMetricReductionRuleByID>>,
TError,
TData
> & { queryKey: QueryKey };
};
export type GetMetricReductionRuleByIDQueryResult = NonNullable<
Awaited<ReturnType<typeof getMetricReductionRuleByID>>
>;
export type GetMetricReductionRuleByIDQueryError =
ErrorType<RenderErrorResponseDTO>;
/**
* @summary Get a metric reduction rule by id
*/
export function useGetMetricReductionRuleByID<
TData = Awaited<ReturnType<typeof getMetricReductionRuleByID>>,
TError = ErrorType<RenderErrorResponseDTO>,
>(
{ id }: GetMetricReductionRuleByIDPathParameters,
options?: {
query?: UseQueryOptions<
Awaited<ReturnType<typeof getMetricReductionRuleByID>>,
TError,
TData
>;
},
): UseQueryResult<TData, TError> & { queryKey: QueryKey } {
const queryOptions = getGetMetricReductionRuleByIDQueryOptions(
{ id },
options,
);
const query = useQuery(queryOptions) as UseQueryResult<TData, TError> & {
queryKey: QueryKey;
};
return { ...query, queryKey: queryOptions.queryKey };
}
/**
* @summary Get a metric reduction rule by id
*/
export const invalidateGetMetricReductionRuleByID = async (
queryClient: QueryClient,
{ id }: GetMetricReductionRuleByIDPathParameters,
options?: InvalidateOptions,
): Promise<QueryClient> => {
await queryClient.invalidateQueries(
{ queryKey: getGetMetricReductionRuleByIDQueryKey({ id }) },
options,
);
return queryClient;
};
/**
* Updates the match type and labels of a volume-control rule by its id; the metric name is immutable.
* @summary Update a metric reduction rule by id
*/
export const updateMetricReductionRuleByID = (
{ id }: UpdateMetricReductionRuleByIDPathParameters,
metricreductionruletypesUpdatableReductionRuleDTO?: BodyType<MetricreductionruletypesUpdatableReductionRuleDTO>,
signal?: AbortSignal,
) => {
return GeneratedAPIInstance<UpdateMetricReductionRuleByID200>({
url: `/api/v2/metric_reduction_rules/${id}`,
method: 'PUT',
headers: { 'Content-Type': 'application/json' },
data: metricreductionruletypesUpdatableReductionRuleDTO,
signal,
});
};
export const getUpdateMetricReductionRuleByIDMutationOptions = <
TError = ErrorType<RenderErrorResponseDTO>,
TContext = unknown,
>(options?: {
mutation?: UseMutationOptions<
Awaited<ReturnType<typeof updateMetricReductionRuleByID>>,
TError,
{
pathParams: UpdateMetricReductionRuleByIDPathParameters;
data?: BodyType<MetricreductionruletypesUpdatableReductionRuleDTO>;
},
TContext
>;
}): UseMutationOptions<
Awaited<ReturnType<typeof updateMetricReductionRuleByID>>,
TError,
{
pathParams: UpdateMetricReductionRuleByIDPathParameters;
data?: BodyType<MetricreductionruletypesUpdatableReductionRuleDTO>;
},
TContext
> => {
const mutationKey = ['updateMetricReductionRuleByID'];
const { mutation: mutationOptions } = options
? options.mutation &&
'mutationKey' in options.mutation &&
options.mutation.mutationKey
? options
: { ...options, mutation: { ...options.mutation, mutationKey } }
: { mutation: { mutationKey } };
const mutationFn: MutationFunction<
Awaited<ReturnType<typeof updateMetricReductionRuleByID>>,
{
pathParams: UpdateMetricReductionRuleByIDPathParameters;
data?: BodyType<MetricreductionruletypesUpdatableReductionRuleDTO>;
}
> = (props) => {
const { pathParams, data } = props ?? {};
return updateMetricReductionRuleByID(pathParams, data);
};
return { mutationFn, ...mutationOptions };
};
export type UpdateMetricReductionRuleByIDMutationResult = NonNullable<
Awaited<ReturnType<typeof updateMetricReductionRuleByID>>
>;
export type UpdateMetricReductionRuleByIDMutationBody =
| BodyType<MetricreductionruletypesUpdatableReductionRuleDTO>
| undefined;
export type UpdateMetricReductionRuleByIDMutationError =
ErrorType<RenderErrorResponseDTO>;
/**
* @summary Update a metric reduction rule by id
*/
export const useUpdateMetricReductionRuleByID = <
TError = ErrorType<RenderErrorResponseDTO>,
TContext = unknown,
>(options?: {
mutation?: UseMutationOptions<
Awaited<ReturnType<typeof updateMetricReductionRuleByID>>,
TError,
{
pathParams: UpdateMetricReductionRuleByIDPathParameters;
data?: BodyType<MetricreductionruletypesUpdatableReductionRuleDTO>;
},
TContext
>;
}): UseMutationResult<
Awaited<ReturnType<typeof updateMetricReductionRuleByID>>,
TError,
{
pathParams: UpdateMetricReductionRuleByIDPathParameters;
data?: BodyType<MetricreductionruletypesUpdatableReductionRuleDTO>;
},
TContext
> => {
return useMutation(getUpdateMetricReductionRuleByIDMutationOptions(options));
};
/**
* Estimates the series reduction and related-asset impact of a candidate volume-control rule without persisting it.
* @summary Preview a metric reduction rule
*/
export const previewMetricReductionRule = (
metricreductionruletypesPostableReductionRulePreviewDTO?: BodyType<MetricreductionruletypesPostableReductionRulePreviewDTO>,
signal?: AbortSignal,
) => {
return GeneratedAPIInstance<PreviewMetricReductionRule200>({
url: `/api/v2/metric_reduction_rules/preview`,
method: 'POST',
headers: { 'Content-Type': 'application/json' },
data: metricreductionruletypesPostableReductionRulePreviewDTO,
signal,
});
};
export const getPreviewMetricReductionRuleMutationOptions = <
TError = ErrorType<RenderErrorResponseDTO>,
TContext = unknown,
>(options?: {
mutation?: UseMutationOptions<
Awaited<ReturnType<typeof previewMetricReductionRule>>,
TError,
{ data?: BodyType<MetricreductionruletypesPostableReductionRulePreviewDTO> },
TContext
>;
}): UseMutationOptions<
Awaited<ReturnType<typeof previewMetricReductionRule>>,
TError,
{ data?: BodyType<MetricreductionruletypesPostableReductionRulePreviewDTO> },
TContext
> => {
const mutationKey = ['previewMetricReductionRule'];
const { mutation: mutationOptions } = options
? options.mutation &&
'mutationKey' in options.mutation &&
options.mutation.mutationKey
? options
: { ...options, mutation: { ...options.mutation, mutationKey } }
: { mutation: { mutationKey } };
const mutationFn: MutationFunction<
Awaited<ReturnType<typeof previewMetricReductionRule>>,
{ data?: BodyType<MetricreductionruletypesPostableReductionRulePreviewDTO> }
> = (props) => {
const { data } = props ?? {};
return previewMetricReductionRule(data);
};
return { mutationFn, ...mutationOptions };
};
export type PreviewMetricReductionRuleMutationResult = NonNullable<
Awaited<ReturnType<typeof previewMetricReductionRule>>
>;
export type PreviewMetricReductionRuleMutationBody =
| BodyType<MetricreductionruletypesPostableReductionRulePreviewDTO>
| undefined;
export type PreviewMetricReductionRuleMutationError =
ErrorType<RenderErrorResponseDTO>;
/**
* @summary Preview a metric reduction rule
*/
export const usePreviewMetricReductionRule = <
TError = ErrorType<RenderErrorResponseDTO>,
TContext = unknown,
>(options?: {
mutation?: UseMutationOptions<
Awaited<ReturnType<typeof previewMetricReductionRule>>,
TError,
{ data?: BodyType<MetricreductionruletypesPostableReductionRulePreviewDTO> },
TContext
>;
}): UseMutationResult<
Awaited<ReturnType<typeof previewMetricReductionRule>>,
TError,
{ data?: BodyType<MetricreductionruletypesPostableReductionRulePreviewDTO> },
TContext
> => {
return useMutation(getPreviewMetricReductionRuleMutationOptions(options));
};
/**
* Returns total ingested vs retained series and the estimated monthly savings across all volume-control rules.
* @summary Metric reduction stats
*/
export const getMetricReductionRuleStats = (signal?: AbortSignal) => {
return GeneratedAPIInstance<GetMetricReductionRuleStats200>({
url: `/api/v2/metric_reduction_rules/stats`,
method: 'GET',
signal,
});
};
export const getGetMetricReductionRuleStatsQueryKey = () => {
return [`/api/v2/metric_reduction_rules/stats`] as const;
};
export const getGetMetricReductionRuleStatsQueryOptions = <
TData = Awaited<ReturnType<typeof getMetricReductionRuleStats>>,
TError = ErrorType<RenderErrorResponseDTO>,
>(options?: {
query?: UseQueryOptions<
Awaited<ReturnType<typeof getMetricReductionRuleStats>>,
TError,
TData
>;
}) => {
const { query: queryOptions } = options ?? {};
const queryKey =
queryOptions?.queryKey ?? getGetMetricReductionRuleStatsQueryKey();
const queryFn: QueryFunction<
Awaited<ReturnType<typeof getMetricReductionRuleStats>>
> = ({ signal }) => getMetricReductionRuleStats(signal);
return { queryKey, queryFn, ...queryOptions } as UseQueryOptions<
Awaited<ReturnType<typeof getMetricReductionRuleStats>>,
TError,
TData
> & { queryKey: QueryKey };
};
export type GetMetricReductionRuleStatsQueryResult = NonNullable<
Awaited<ReturnType<typeof getMetricReductionRuleStats>>
>;
export type GetMetricReductionRuleStatsQueryError =
ErrorType<RenderErrorResponseDTO>;
/**
* @summary Metric reduction stats
*/
export function useGetMetricReductionRuleStats<
TData = Awaited<ReturnType<typeof getMetricReductionRuleStats>>,
TError = ErrorType<RenderErrorResponseDTO>,
>(options?: {
query?: UseQueryOptions<
Awaited<ReturnType<typeof getMetricReductionRuleStats>>,
TError,
TData
>;
}): UseQueryResult<TData, TError> & { queryKey: QueryKey } {
const queryOptions = getGetMetricReductionRuleStatsQueryOptions(options);
const query = useQuery(queryOptions) as UseQueryResult<TData, TError> & {
queryKey: QueryKey;
};
return { ...query, queryKey: queryOptions.queryKey };
}
/**
* @summary Metric reduction stats
*/
export const invalidateGetMetricReductionRuleStats = async (
queryClient: QueryClient,
options?: InvalidateOptions,
): Promise<QueryClient> => {
await queryClient.invalidateQueries(
{ queryKey: getGetMetricReductionRuleStatsQueryKey() },
options,
);
return queryClient;
};
/**
* Returns ingested vs retained series over time across all volume-control rules (hourly buckets), in the query-range time-series response shape.
* @summary Metric reduction volume over time
*/
export const getMetricReductionRuleTimeseries = (signal?: AbortSignal) => {
return GeneratedAPIInstance<GetMetricReductionRuleTimeseries200>({
url: `/api/v2/metric_reduction_rules/timeseries`,
method: 'GET',
signal,
});
};
export const getGetMetricReductionRuleTimeseriesQueryKey = () => {
return [`/api/v2/metric_reduction_rules/timeseries`] as const;
};
export const getGetMetricReductionRuleTimeseriesQueryOptions = <
TData = Awaited<ReturnType<typeof getMetricReductionRuleTimeseries>>,
TError = ErrorType<RenderErrorResponseDTO>,
>(options?: {
query?: UseQueryOptions<
Awaited<ReturnType<typeof getMetricReductionRuleTimeseries>>,
TError,
TData
>;
}) => {
const { query: queryOptions } = options ?? {};
const queryKey =
queryOptions?.queryKey ?? getGetMetricReductionRuleTimeseriesQueryKey();
const queryFn: QueryFunction<
Awaited<ReturnType<typeof getMetricReductionRuleTimeseries>>
> = ({ signal }) => getMetricReductionRuleTimeseries(signal);
return { queryKey, queryFn, ...queryOptions } as UseQueryOptions<
Awaited<ReturnType<typeof getMetricReductionRuleTimeseries>>,
TError,
TData
> & { queryKey: QueryKey };
};
export type GetMetricReductionRuleTimeseriesQueryResult = NonNullable<
Awaited<ReturnType<typeof getMetricReductionRuleTimeseries>>
>;
export type GetMetricReductionRuleTimeseriesQueryError =
ErrorType<RenderErrorResponseDTO>;
/**
* @summary Metric reduction volume over time
*/
export function useGetMetricReductionRuleTimeseries<
TData = Awaited<ReturnType<typeof getMetricReductionRuleTimeseries>>,
TError = ErrorType<RenderErrorResponseDTO>,
>(options?: {
query?: UseQueryOptions<
Awaited<ReturnType<typeof getMetricReductionRuleTimeseries>>,
TError,
TData
>;
}): UseQueryResult<TData, TError> & { queryKey: QueryKey } {
const queryOptions = getGetMetricReductionRuleTimeseriesQueryOptions(options);
const query = useQuery(queryOptions) as UseQueryResult<TData, TError> & {
queryKey: QueryKey;
};
return { ...query, queryKey: queryOptions.queryKey };
}
/**
* @summary Metric reduction volume over time
*/
export const invalidateGetMetricReductionRuleTimeseries = async (
queryClient: QueryClient,
options?: InvalidateOptions,
): Promise<QueryClient> => {
await queryClient.invalidateQueries(
{ queryKey: getGetMetricReductionRuleTimeseriesQueryKey() },
options,
);
return queryClient;
};
/**
* This endpoint returns a list of distinct metric names within the specified time range
* @summary List metric names

View File

@@ -5535,13 +5535,6 @@ export interface InframonitoringtypesClusterRecordDTO {
podCountsByPhase: InframonitoringtypesPodCountsByPhaseDTO;
}
export interface InframonitoringtypesRequiredMetricsCheckDTO {
/**
* @type array,null
*/
missingMetrics: string[] | null;
}
export enum InframonitoringtypesResponseTypeDTO {
list = 'list',
grouped_list = 'grouped_list',
@@ -5577,7 +5570,6 @@ export interface InframonitoringtypesClustersDTO {
* @type array
*/
records: InframonitoringtypesClusterRecordDTO[];
requiredMetricsCheck: InframonitoringtypesRequiredMetricsCheckDTO;
/**
* @type integer
*/
@@ -5655,7 +5647,6 @@ export interface InframonitoringtypesDaemonSetsDTO {
* @type array
*/
records: InframonitoringtypesDaemonSetRecordDTO[];
requiredMetricsCheck: InframonitoringtypesRequiredMetricsCheckDTO;
/**
* @type integer
*/
@@ -5733,7 +5724,6 @@ export interface InframonitoringtypesDeploymentsDTO {
* @type array
*/
records: InframonitoringtypesDeploymentRecordDTO[];
requiredMetricsCheck: InframonitoringtypesRequiredMetricsCheckDTO;
/**
* @type integer
*/
@@ -5819,7 +5809,6 @@ export interface InframonitoringtypesHostsDTO {
* @type array
*/
records: InframonitoringtypesHostRecordDTO[];
requiredMetricsCheck: InframonitoringtypesRequiredMetricsCheckDTO;
/**
* @type integer
*/
@@ -5905,7 +5894,6 @@ export interface InframonitoringtypesJobsDTO {
* @type array
*/
records: InframonitoringtypesJobRecordDTO[];
requiredMetricsCheck: InframonitoringtypesRequiredMetricsCheckDTO;
/**
* @type integer
*/
@@ -5955,7 +5943,6 @@ export interface InframonitoringtypesNamespacesDTO {
* @type array
*/
records: InframonitoringtypesNamespaceRecordDTO[];
requiredMetricsCheck: InframonitoringtypesRequiredMetricsCheckDTO;
/**
* @type integer
*/
@@ -6022,7 +6009,6 @@ export interface InframonitoringtypesNodesDTO {
* @type array
*/
records: InframonitoringtypesNodeRecordDTO[];
requiredMetricsCheck: InframonitoringtypesRequiredMetricsCheckDTO;
/**
* @type integer
*/
@@ -6106,7 +6092,6 @@ export interface InframonitoringtypesPodsDTO {
* @type array
*/
records: InframonitoringtypesPodRecordDTO[];
requiredMetricsCheck: InframonitoringtypesRequiredMetricsCheckDTO;
/**
* @type integer
*/
@@ -6454,7 +6439,6 @@ export interface InframonitoringtypesStatefulSetsDTO {
* @type array
*/
records: InframonitoringtypesStatefulSetRecordDTO[];
requiredMetricsCheck: InframonitoringtypesRequiredMetricsCheckDTO;
/**
* @type integer
*/
@@ -6523,7 +6507,6 @@ export interface InframonitoringtypesVolumesDTO {
* @type array
*/
records: InframonitoringtypesVolumeRecordDTO[];
requiredMetricsCheck: InframonitoringtypesRequiredMetricsCheckDTO;
/**
* @type integer
*/
@@ -6689,213 +6672,6 @@ export interface LlmpricingruletypesUpdatableLLMPricingRulesDTO {
rules: LlmpricingruletypesUpdatableLLMPricingRuleDTO[] | null;
}
export enum MetricreductionruletypesAssetTypeDTO {
dashboard = 'dashboard',
alert_rule = 'alert_rule',
}
export interface MetricreductionruletypesAffectedWidgetDTO {
/**
* @type string
*/
id: string;
/**
* @type string
*/
name: string;
}
export interface MetricreductionruletypesAffectedAssetDTO {
/**
* @type string
*/
id: string;
/**
* @type array,null
*/
impactedLabels: string[] | null;
/**
* @type string
*/
name: string;
type: MetricreductionruletypesAssetTypeDTO;
widget?: MetricreductionruletypesAffectedWidgetDTO;
}
export enum MetricreductionruletypesMatchTypeDTO {
drop = 'drop',
keep = 'keep',
}
export interface MetricreductionruletypesGettableReductionRuleDTO {
/**
* @type boolean
*/
active: boolean;
/**
* @type string
* @format date-time
*/
createdAt?: string;
/**
* @type string
*/
createdBy?: string;
/**
* @type string
* @format date-time
*/
effectiveFrom: string;
/**
* @type string
*/
id: string;
/**
* @type integer
* @minimum 0
*/
ingestedSeries: number;
/**
* @type array,null
*/
labels: string[] | null;
matchType: MetricreductionruletypesMatchTypeDTO;
/**
* @type string
*/
metricName: string;
/**
* @type number
* @format double
*/
reductionPercent: number;
/**
* @type integer
* @minimum 0
*/
retainedSeries: number;
/**
* @type string
* @format date-time
*/
updatedAt?: string;
/**
* @type string
*/
updatedBy?: string;
}
export interface MetricreductionruletypesGettableReductionRulePreviewDTO {
/**
* @type array,null
*/
affectedAssets: MetricreductionruletypesAffectedAssetDTO[] | null;
/**
* @type integer
* @minimum 0
*/
currentRetainedSeries: number;
/**
* @type array,null
*/
droppedLabels: string[] | null;
/**
* @type string
* @format date-time
*/
effectiveFrom: string;
/**
* @type integer
* @minimum 0
*/
ingestedSeries: number;
/**
* @type number
* @format double
*/
reductionPercent: number;
/**
* @type integer
* @minimum 0
*/
retainedSeries: number;
}
export interface MetricreductionruletypesGettableReductionRuleStatsDTO {
/**
* @type number
* @format double
*/
estimatedMonthlySavingsUsd: number;
/**
* @type integer
* @minimum 0
*/
ingestedSeries: number;
/**
* @type integer
* @minimum 0
*/
retainedSeries: number;
}
export interface MetricreductionruletypesGettableReductionRulesDTO {
/**
* @type array,null
*/
rules: MetricreductionruletypesGettableReductionRuleDTO[] | null;
/**
* @type integer
*/
total: number;
}
export enum MetricreductionruletypesOrderDTO {
asc = 'asc',
desc = 'desc',
}
export interface MetricreductionruletypesPostableReductionRuleDTO {
/**
* @type array,null
*/
labels: string[] | null;
matchType: MetricreductionruletypesMatchTypeDTO;
/**
* @type string
*/
metricName: string;
}
export interface MetricreductionruletypesPostableReductionRulePreviewDTO {
/**
* @type array,null
*/
labels: string[] | null;
/**
* @type integer
* @format int64
*/
lookbackMs?: number;
matchType: MetricreductionruletypesMatchTypeDTO;
/**
* @type string
*/
metricName: string;
}
export enum MetricreductionruletypesReductionRuleOrderByDTO {
metric = 'metric',
ingested_volume = 'ingested_volume',
reduced_volume = 'reduced_volume',
reduction = 'reduction',
last_updated = 'last_updated',
}
export interface MetricreductionruletypesUpdatableReductionRuleDTO {
/**
* @type array,null
*/
labels: string[] | null;
matchType: MetricreductionruletypesMatchTypeDTO;
}
export interface MetricsexplorertypesInspectMetricsRequestDTO {
/**
* @type integer
@@ -8454,6 +8230,48 @@ export interface SpantypesGettableSpanMapperGroupsDTO {
items: SpantypesSpanMapperGroupDTO[];
}
export type SpantypesSpanMapperTestSpanDTOAttributesAnyOf = {
[key: string]: unknown;
};
/**
* @nullable
*/
export type SpantypesSpanMapperTestSpanDTOAttributes =
SpantypesSpanMapperTestSpanDTOAttributesAnyOf | null;
export type SpantypesSpanMapperTestSpanDTOResourceAnyOf = {
[key: string]: unknown;
};
/**
* @nullable
*/
export type SpantypesSpanMapperTestSpanDTOResource =
SpantypesSpanMapperTestSpanDTOResourceAnyOf | null;
export interface SpantypesSpanMapperTestSpanDTO {
/**
* @type object,null
*/
attributes?: SpantypesSpanMapperTestSpanDTOAttributes;
/**
* @type object,null
*/
resource?: SpantypesSpanMapperTestSpanDTOResource;
}
export interface SpantypesGettableSpanMapperTestDTO {
/**
* @type array,null
*/
collectorLogs?: string[] | null;
/**
* @type array,null
*/
spans?: SpantypesSpanMapperTestSpanDTO[] | null;
}
export enum SpantypesSpanAggregationTypeDTO {
span_count = 'span_count',
execution_time_percentage = 'execution_time_percentage',
@@ -8749,6 +8567,33 @@ export interface SpantypesPostableSpanMapperGroupDTO {
name: string;
}
export interface SpantypesPostableSpanMapperTestGroupDTO {
condition: SpantypesSpanMapperGroupConditionDTO | null;
/**
* @type boolean
*/
enabled?: boolean;
/**
* @type array,null
*/
mappers?: SpantypesPostableSpanMapperDTO[] | null;
/**
* @type string
*/
name: string;
}
export interface SpantypesPostableSpanMapperTestDTO {
/**
* @type array,null
*/
groups: SpantypesPostableSpanMapperTestGroupDTO[] | null;
/**
* @type array,null
*/
spans: SpantypesSpanMapperTestSpanDTO[] | null;
}
export interface SpantypesSpanAggregationDTO {
aggregation: SpantypesSpanAggregationTypeDTO;
field: TelemetrytypesTelemetryFieldKeyDTO;
@@ -10130,6 +9975,14 @@ export type UpdateSpanMapperPathParameters = {
groupId: string;
mapperId: string;
};
export type TestSpanMappers200 = {
data: SpantypesGettableSpanMapperTestDTO;
/**
* @type string
*/
status: string;
};
export type GetStats200Data = { [key: string]: unknown };
export type GetStats200 = {
@@ -10541,102 +10394,6 @@ export type Livez200 = {
status: string;
};
export type ListMetricReductionRulesParams = {
/**
* @description undefined
*/
orderBy?: MetricreductionruletypesReductionRuleOrderByDTO;
/**
* @description undefined
*/
order?: MetricreductionruletypesOrderDTO;
/**
* @type string
* @description undefined
*/
search?: string;
/**
* @type string
* @description undefined
*/
metricName?: string;
/**
* @type integer
* @description undefined
*/
offset?: number;
/**
* @type integer
* @description undefined
*/
limit?: number;
};
export type ListMetricReductionRules200 = {
data: MetricreductionruletypesGettableReductionRulesDTO;
/**
* @type string
*/
status: string;
};
export type CreateMetricReductionRule201 = {
data: MetricreductionruletypesGettableReductionRuleDTO;
/**
* @type string
*/
status: string;
};
export type DeleteMetricReductionRuleByIDPathParameters = {
id: string;
};
export type GetMetricReductionRuleByIDPathParameters = {
id: string;
};
export type GetMetricReductionRuleByID200 = {
data: MetricreductionruletypesGettableReductionRuleDTO;
/**
* @type string
*/
status: string;
};
export type UpdateMetricReductionRuleByIDPathParameters = {
id: string;
};
export type UpdateMetricReductionRuleByID200 = {
data: MetricreductionruletypesGettableReductionRuleDTO;
/**
* @type string
*/
status: string;
};
export type PreviewMetricReductionRule200 = {
data: MetricreductionruletypesGettableReductionRulePreviewDTO;
/**
* @type string
*/
status: string;
};
export type GetMetricReductionRuleStats200 = {
data: MetricreductionruletypesGettableReductionRuleStatsDTO;
/**
* @type string
*/
status: string;
};
export type GetMetricReductionRuleTimeseries200 = {
data: Querybuildertypesv5QueryRangeResponseDTO;
/**
* @type string
*/
status: string;
};
export type ListMetricsParams = {
/**
* @type integer,null

View File

@@ -30,8 +30,10 @@ import type {
RenderErrorResponseDTO,
SpantypesPostableSpanMapperDTO,
SpantypesPostableSpanMapperGroupDTO,
SpantypesPostableSpanMapperTestDTO,
SpantypesUpdatableSpanMapperDTO,
SpantypesUpdatableSpanMapperGroupDTO,
TestSpanMappers200,
UpdateSpanMapperGroupPathParameters,
UpdateSpanMapperPathParameters,
} from '../sigNoz.schemas';
@@ -780,3 +782,86 @@ export const useUpdateSpanMapper = <
> => {
return useMutation(getUpdateSpanMapperMutationOptions(options));
};
/**
* Tests how span mappers would transform sample spans
* @summary Test span mappers against sample spans
*/
export const testSpanMappers = (
spantypesPostableSpanMapperTestDTO?: BodyType<SpantypesPostableSpanMapperTestDTO>,
signal?: AbortSignal,
) => {
return GeneratedAPIInstance<TestSpanMappers200>({
url: `/api/v1/span_mapper_groups/test`,
method: 'POST',
headers: { 'Content-Type': 'application/json' },
data: spantypesPostableSpanMapperTestDTO,
signal,
});
};
export const getTestSpanMappersMutationOptions = <
TError = ErrorType<RenderErrorResponseDTO>,
TContext = unknown,
>(options?: {
mutation?: UseMutationOptions<
Awaited<ReturnType<typeof testSpanMappers>>,
TError,
{ data?: BodyType<SpantypesPostableSpanMapperTestDTO> },
TContext
>;
}): UseMutationOptions<
Awaited<ReturnType<typeof testSpanMappers>>,
TError,
{ data?: BodyType<SpantypesPostableSpanMapperTestDTO> },
TContext
> => {
const mutationKey = ['testSpanMappers'];
const { mutation: mutationOptions } = options
? options.mutation &&
'mutationKey' in options.mutation &&
options.mutation.mutationKey
? options
: { ...options, mutation: { ...options.mutation, mutationKey } }
: { mutation: { mutationKey } };
const mutationFn: MutationFunction<
Awaited<ReturnType<typeof testSpanMappers>>,
{ data?: BodyType<SpantypesPostableSpanMapperTestDTO> }
> = (props) => {
const { data } = props ?? {};
return testSpanMappers(data);
};
return { mutationFn, ...mutationOptions };
};
export type TestSpanMappersMutationResult = NonNullable<
Awaited<ReturnType<typeof testSpanMappers>>
>;
export type TestSpanMappersMutationBody =
| BodyType<SpantypesPostableSpanMapperTestDTO>
| undefined;
export type TestSpanMappersMutationError = ErrorType<RenderErrorResponseDTO>;
/**
* @summary Test span mappers against sample spans
*/
export const useTestSpanMappers = <
TError = ErrorType<RenderErrorResponseDTO>,
TContext = unknown,
>(options?: {
mutation?: UseMutationOptions<
Awaited<ReturnType<typeof testSpanMappers>>,
TError,
{ data?: BodyType<SpantypesPostableSpanMapperTestDTO> },
TContext
>;
}): UseMutationResult<
Awaited<ReturnType<typeof testSpanMappers>>,
TError,
{ data?: BodyType<SpantypesPostableSpanMapperTestDTO> },
TContext
> => {
return useMutation(getTestSpanMappersMutationOptions(options));
};

View File

@@ -794,6 +794,13 @@ notifications - 2050
background: color-mix(in srgb, var(--l3-background) 20%, transparent);
}
// =================================================================
// Monaco Editor style overrides
.monaco-editor .find-widget.visible {
top: 30px !important;
right: 45px !important;
}
body.ai-assistant-panel-open {
.PylonChat-bubbleFrameContainer,
.PylonChat-chatWindowFrameContainer {

6
go.mod
View File

@@ -9,7 +9,7 @@ require (
github.com/DATA-DOG/go-sqlmock v1.5.2
github.com/SigNoz/clickhouse-go-mock v0.14.0
github.com/SigNoz/govaluate v0.0.0-20240203125216-988004ccc7fd
github.com/SigNoz/signoz-otel-collector v0.144.3
github.com/SigNoz/signoz-otel-collector v0.144.6-rc.1.0.20260625043036-fb3dbb450bbd
github.com/antlr4-go/antlr/v4 v4.13.1
github.com/antonmedv/expr v1.15.3
github.com/bytedance/sonic v1.14.1
@@ -150,10 +150,6 @@ require (
github.com/ugorji/go/codec v1.3.0 // indirect
github.com/uptrace/opentelemetry-go-extra/otelsql v0.3.2 // indirect
github.com/x448/float16 v0.8.4 // indirect
go.opentelemetry.io/collector/client v1.54.0 // indirect
go.opentelemetry.io/collector/config/configoptional v1.50.0 // indirect
go.opentelemetry.io/collector/config/configretry v1.50.0 // indirect
go.opentelemetry.io/collector/exporter/exporterhelper v0.144.0 // indirect
go.opentelemetry.io/collector/internal/componentalias v0.148.0 // indirect
go.opentelemetry.io/collector/pdata/xpdata v0.148.0 // indirect
go.uber.org/goleak v1.3.0 // indirect

25
go.sum
View File

@@ -110,11 +110,13 @@ github.com/SigNoz/expr v1.17.7-beta h1:FyZkleM5dTQ0O6muQfwGpoH5A2ohmN/XTasRCO72g
github.com/SigNoz/expr v1.17.7-beta/go.mod h1:8/vRC7+7HBzESEqt5kKpYXxrxkr31SaO8r40VO/1IT4=
github.com/SigNoz/govaluate v0.0.0-20240203125216-988004ccc7fd h1:Bk43AsDYe0fhkbj57eGXx8H3ZJ4zhmQXBnrW523ktj8=
github.com/SigNoz/govaluate v0.0.0-20240203125216-988004ccc7fd/go.mod h1:nxRcH/OEdM8QxzH37xkGzomr1O0JpYBRS6pwjsWW6Pc=
github.com/SigNoz/signoz-otel-collector v0.144.3 h1:/7PPIqIpPsaWtrgnfHam2XVYP41ZlgEKLHzQO8oVxcA=
github.com/SigNoz/signoz-otel-collector v0.144.3/go.mod h1:9pLVpcIQvUT88ZiNnZN/MI+XLruvwC+Xm2UzPmGjNfA=
github.com/SigNoz/signoz-otel-collector v0.144.6-rc.1.0.20260625043036-fb3dbb450bbd h1:MGQATRMNEsBrdHzHb7uj2JIzLXXgQNcNxZHfmAAIIs8=
github.com/SigNoz/signoz-otel-collector v0.144.6-rc.1.0.20260625043036-fb3dbb450bbd/go.mod h1:Jw1Y3s/ZOSz6RmLjZtj2A7wK6bse0T4pxs+oggBQnSs=
github.com/Yiling-J/theine-go v0.6.2 h1:1GeoXeQ0O0AUkiwj2S9Jc0Mzx+hpqzmqsJ4kIC4M9AY=
github.com/Yiling-J/theine-go v0.6.2/go.mod h1:08QpMa5JZ2pKN+UJCRrCasWYO1IKCdl54Xa836rpmDU=
github.com/afex/hystrix-go v0.0.0-20180502004556-fa1af6a1f4f5/go.mod h1:SkGFH1ia65gfNATL8TAiHDNxPzPdmEL5uirI2Uyuz6c=
github.com/alecthomas/participle/v2 v2.1.4 h1:W/H79S8Sat/krZ3el6sQMvMaahJ+XcM9WSI2naI7w2U=
github.com/alecthomas/participle/v2 v2.1.4/go.mod h1:8tqVbpTX20Ru4NfYQgZf4mP18eXPTBViyMWiArNEgGI=
github.com/alecthomas/template v0.0.0-20160405071501-a0175ee3bccc/go.mod h1:LOuyumcjzFXgccqObfd/Ljyb9UuFJ6TxHnclSeseNhc=
github.com/alecthomas/template v0.0.0-20190718012654-fb15b899a751/go.mod h1:LOuyumcjzFXgccqObfd/Ljyb9UuFJ6TxHnclSeseNhc=
github.com/alecthomas/units v0.0.0-20151022065526-2efee857e7cf/go.mod h1:ybxpYRFXyAe+OPACYpWeL0wqObRcbAqCMya13uyzqw0=
@@ -124,6 +126,10 @@ github.com/alecthomas/units v0.0.0-20240927000941-0f3dac36c52b h1:mimo19zliBX/vS
github.com/alecthomas/units v0.0.0-20240927000941-0f3dac36c52b/go.mod h1:fvzegU4vN3H1qMT+8wDmzjAcDONcgo2/SZ/TyfdUOFs=
github.com/andybalholm/brotli v1.2.0 h1:ukwgCxwYrmACq68yiUqwIWnGY0cTPox/M94sVwToPjQ=
github.com/andybalholm/brotli v1.2.0/go.mod h1:rzTDkvFWvIrjDXZHkuS16NPggd91W3kUSvPlQ1pLaKY=
github.com/antchfx/xmlquery v1.5.0 h1:uAi+mO40ZWfyU6mlUBxRVvL6uBNZ6LMU4M3+mQIBV4c=
github.com/antchfx/xmlquery v1.5.0/go.mod h1:lJfWRXzYMK1ss32zm1GQV3gMIW/HFey3xDZmkP1SuNc=
github.com/antchfx/xpath v1.3.6 h1:s0y+ElRRtTQdfHP609qFu0+c6bglDv20pqOViQjjdPI=
github.com/antchfx/xpath v1.3.6/go.mod h1:i54GszH55fYfBmoZXapTHN8T8tkcHfRgLyVwwqzXNcs=
github.com/antihax/optional v1.0.0/go.mod h1:uupD/76wgC+ih3iEmQUL+0Ugr19nfwCT1kdvxnR2qWY=
github.com/antlr4-go/antlr/v4 v4.13.1 h1:SqQKkuVZ+zWkMMNkjy5FZe5mr5WURWnlpmOuzYWrPrQ=
github.com/antlr4-go/antlr/v4 v4.13.1/go.mod h1:GKmUxMtwp6ZgGwZSva4eWPC5mS6vUAmOABFgjdkM7Nw=
@@ -286,6 +292,8 @@ github.com/ebitengine/purego v0.9.1 h1:a/k2f2HQU3Pi399RPW1MOaZyhKJL9w/xFpKAg4q1s
github.com/ebitengine/purego v0.9.1/go.mod h1:iIjxzd6CiRiOG0UyXP+V1+jWqUXVjPKLAI0mRfJZTmQ=
github.com/edsrzf/mmap-go v1.2.0 h1:hXLYlkbaPzt1SaQk+anYwKSRNhufIDCchSPkUD6dD84=
github.com/edsrzf/mmap-go v1.2.0/go.mod h1:19H/e8pUPLicwkyNgOykDXkJ9F0MHE+Z52B8EIth78Q=
github.com/elastic/go-grok v0.3.1 h1:WEhUxe2KrwycMnlvMimJXvzRa7DoByJB4PVUIE1ZD/U=
github.com/elastic/go-grok v0.3.1/go.mod h1:n38ls8ZgOboZRgKcjMY8eFeZFMmcL9n2lP0iHhIDk64=
github.com/elastic/lunes v0.2.0 h1:WI3bsdOTuaYXVe2DS1KbqA7u7FOHN4o8qJw80ZyZoQs=
github.com/elastic/lunes v0.2.0/go.mod h1:u3W/BdONWTrh0JjNZ21C907dDc+cUZttZrGa625nf2k=
github.com/emersion/go-sasl v0.0.0-20241020182733-b788ff22d5a6 h1:oP4q0fw+fOSWn3DfFi4EXdT+B+gTtzx8GC9xsc26Znk=
@@ -461,6 +469,7 @@ github.com/golang/glog v0.0.0-20160126235308-23def4e6c14b/go.mod h1:SBH7ygxi8pfU
github.com/golang/groupcache v0.0.0-20190702054246-869f871628b6/go.mod h1:cIg4eruTrX1D+g88fzRXU5OdNfaM+9IcxsU14FzY7Hc=
github.com/golang/groupcache v0.0.0-20191227052852-215e87163ea7/go.mod h1:cIg4eruTrX1D+g88fzRXU5OdNfaM+9IcxsU14FzY7Hc=
github.com/golang/groupcache v0.0.0-20200121045136-8c9f03a8e57e/go.mod h1:cIg4eruTrX1D+g88fzRXU5OdNfaM+9IcxsU14FzY7Hc=
github.com/golang/groupcache v0.0.0-20210331224755-41bb18bfe9da h1:oI5xCqsCo564l8iNU+DwB5epxmsaqB+rhGL0m5jtYqE=
github.com/golang/groupcache v0.0.0-20210331224755-41bb18bfe9da/go.mod h1:cIg4eruTrX1D+g88fzRXU5OdNfaM+9IcxsU14FzY7Hc=
github.com/golang/mock v1.1.1/go.mod h1:oTYuIxOrZwtPieC+H1uAHpcLFnEyAGVDL/k47Jfbm0A=
github.com/golang/mock v1.2.0/go.mod h1:oTYuIxOrZwtPieC+H1uAHpcLFnEyAGVDL/k47Jfbm0A=
@@ -674,6 +683,8 @@ github.com/huandu/xstrings v1.5.0 h1:2ag3IFq9ZDANvthTwTiqSSZLjDc+BedvHPAp5tJy2TI
github.com/huandu/xstrings v1.5.0/go.mod h1:y5/lhBue+AyNmUVz9RLU9xbLR0o4KIIExikq4ovT0aE=
github.com/iancoleman/orderedmap v0.3.0 h1:5cbR2grmZR/DiVt+VJopEhtVs9YGInGIxAoMJn+Ichc=
github.com/iancoleman/orderedmap v0.3.0/go.mod h1:XuLcCUkdL5owUCQeF2Ue9uuw1EptkJDkXXS7VoV7XGE=
github.com/iancoleman/strcase v0.3.0 h1:nTXanmYxhfFAMjZL34Ov6gkzEsSJZ5DbhxWjvSASxEI=
github.com/iancoleman/strcase v0.3.0/go.mod h1:iwCmte+B7n89clKwxIoIXy/HfoL7AsD47ZCWhYzw7ho=
github.com/ianlancetaylor/demangle v0.0.0-20181102032728-5e5cf60278f6/go.mod h1:aSSvb/t6k1mPoxDqO4vJh6VOCGPwU4O0C2/Eqndh1Sc=
github.com/ianlancetaylor/demangle v0.0.0-20200824232613-28f6c0f3b639/go.mod h1:aSSvb/t6k1mPoxDqO4vJh6VOCGPwU4O0C2/Eqndh1Sc=
github.com/inconshreveable/mousetrap v1.1.0 h1:wN+x4NVGpMsO7ErUn/mUI3vEoE6Jt13X2s0bqwp9tc8=
@@ -866,12 +877,18 @@ github.com/open-telemetry/opentelemetry-collector-contrib/internal/coreinternal
github.com/open-telemetry/opentelemetry-collector-contrib/internal/coreinternal v0.144.0/go.mod h1:O2rZKRXk1WeYhzfJBVXES/g7+PlIds/TzPZW/4NfTNA=
github.com/open-telemetry/opentelemetry-collector-contrib/internal/exp/metrics v0.148.0 h1:CiTjQE/Hh5xK2t56ogrDK4nl0+tJPNmASCs4zEYZ/xU=
github.com/open-telemetry/opentelemetry-collector-contrib/internal/exp/metrics v0.148.0/go.mod h1:WUFkzTiOpt7EYyL67gv1GOf3RD8qKWGtin3lY9LYzW4=
github.com/open-telemetry/opentelemetry-collector-contrib/internal/filter v0.144.0 h1:Ywu5mU4K5TMJigiXdyZloCRs/cq3/2OnoK3WjxNHWJo=
github.com/open-telemetry/opentelemetry-collector-contrib/internal/filter v0.144.0/go.mod h1:iebqlu6UvpiV1hO37r1sXA9fXaCaA8sQXilG0///xss=
github.com/open-telemetry/opentelemetry-collector-contrib/pkg/ottl v0.144.0 h1:TMRTvQSAeeLtkKwSrqcbectxDRPiqB6yYM3IvjC75es=
github.com/open-telemetry/opentelemetry-collector-contrib/pkg/ottl v0.144.0/go.mod h1:1HU0qJ4hFrphDebuBs3I4DPQ6zyBFGinQ5/bXEUM7pw=
github.com/open-telemetry/opentelemetry-collector-contrib/pkg/pdatatest v0.148.0 h1:i12duJOl5VCb9mbb8FfZCaP2CjeXbNsbg82JjSe7sy8=
github.com/open-telemetry/opentelemetry-collector-contrib/pkg/pdatatest v0.148.0/go.mod h1:jyw+QvkmCrF/oYy31O2ndb5KZZK4l+iR89msnV3LN/k=
github.com/open-telemetry/opentelemetry-collector-contrib/pkg/pdatautil v0.148.0 h1:1TLg6YrS3Au6F7xw3ws2Njbwj13IMqPplvGFi+18fWs=
github.com/open-telemetry/opentelemetry-collector-contrib/pkg/pdatautil v0.148.0/go.mod h1:P8hZEDIQk4REgUWyLhSVRHwTxK6KkifKfg36BmmQ/DI=
github.com/open-telemetry/opentelemetry-collector-contrib/pkg/stanza v0.144.0 h1:EIAygME70IOdEwaSr6bA3Wcdp7hXEqRsGsVfrI5v8OA=
github.com/open-telemetry/opentelemetry-collector-contrib/pkg/stanza v0.144.0/go.mod h1:3Y6ctEEwRg19B0jqsrQH6Hiquqte+zC0ZxpXLLSa5sA=
github.com/open-telemetry/opentelemetry-collector-contrib/processor/attributesprocessor v0.144.0 h1:gRk73SsIJv3q/HI0kxMRN5TiIiJj+MRxrz0GEYx3jZw=
github.com/open-telemetry/opentelemetry-collector-contrib/processor/attributesprocessor v0.144.0/go.mod h1:7b8ZcPdN6JSm6+LUq3rienoqHHiX60kyoOHDPCMM+L8=
github.com/open-telemetry/opentelemetry-collector-contrib/processor/deltatocumulativeprocessor v0.148.0 h1:xgD/kNGp/wWY+bwY599Pc01OamYN17phRiTP934bM5Y=
github.com/open-telemetry/opentelemetry-collector-contrib/processor/deltatocumulativeprocessor v0.148.0/go.mod h1:ZK7wvaefla9lB3bAW0rNKt7IzRPcTRQoOFqr4sZy/XM=
github.com/open-telemetry/opentelemetry-collector-contrib/processor/logstransformprocessor v0.144.0 h1:HbmpzTixpQG/xGhQuQoiJTXQPrixe+yivAsF6tl2o4g=
@@ -1119,6 +1136,10 @@ github.com/tmthrgd/go-hex v0.0.0-20190904060850-447a3041c3bc/go.mod h1:bciPuU6GH
github.com/tv42/httpunix v0.0.0-20150427012821-b75d8614f926/go.mod h1:9ESjWnEqriFuLhtthL60Sar/7RFoluCcXsuvEwTV5KM=
github.com/twitchyliquid64/golang-asm v0.15.1 h1:SU5vSMR7hnwNxj24w34ZyCi/FmDZTkS4MhqMhdFk5YI=
github.com/twitchyliquid64/golang-asm v0.15.1/go.mod h1:a1lVb/DtPvCB8fslRZhAngC2+aY1QWCk3Cedj/Gdt08=
github.com/twmb/murmur3 v1.1.8 h1:8Yt9taO/WN3l08xErzjeschgZU2QSrwm1kclYq+0aRg=
github.com/twmb/murmur3 v1.1.8/go.mod h1:Qq/R7NUyOfr65zD+6Q5IHKsJLwP7exErjN6lyyq3OSQ=
github.com/ua-parser/uap-go v0.0.0-20240611065828-3a4781585db6 h1:SIKIoA4e/5Y9ZOl0DCe3eVMLPOQzJxgZpfdHHeauNTM=
github.com/ua-parser/uap-go v0.0.0-20240611065828-3a4781585db6/go.mod h1:BUbeWZiieNxAuuADTBNb3/aeje6on3DhU3rpWsQSB1E=
github.com/ugorji/go/codec v1.3.0 h1:Qd2W2sQawAfG8XSvzwhBeoGq71zXOC/Q1E9y/wUcsUA=
github.com/ugorji/go/codec v1.3.0/go.mod h1:pRBVtBSKl77K30Bv8R2P+cLSGaTtex6fsA2Wjqmfxj4=
github.com/uptrace/bun v1.2.9 h1:OOt2DlIcRUMSZPr6iXDFg/LaQd59kOxbAjpIVHddKRs=

View File

@@ -16,7 +16,7 @@ func (provider *provider) addInfraMonitoringRoutes(router *mux.Router) error {
ID: "ListHosts",
Tags: []string{"inframonitoring"},
Summary: "List Hosts for Infra Monitoring",
Description: "Returns a paginated list of hosts with key infrastructure metrics: CPU usage (%), memory usage (%), I/O wait (%), disk usage (%), and 15-minute load average. Each host includes its current status (active/inactive based on metrics reported in the last 10 minutes) and metadata attributes (e.g., os.type). Supports filtering via a filter expression, filtering by host status, custom groupBy to aggregate hosts by any attribute, ordering by any of the five metrics, and pagination via offset/limit. The response type is 'list' for the default host.name grouping or 'grouped_list' for custom groupBy keys. Also reports missing required metrics and whether the requested time range falls before the data retention boundary. Numeric metric fields (cpu, memory, wait, load15, diskUsage) return -1 as a sentinel when no data is available for that field.",
Description: "Returns a paginated list of hosts with key infrastructure metrics: CPU usage (%), memory usage (%), I/O wait (%), disk usage (%), and 15-minute load average. Each host includes its current status (active/inactive based on metrics reported in the last 10 minutes) and metadata attributes (e.g., os.type). Supports filtering via a filter expression, filtering by host status, custom groupBy to aggregate hosts by any attribute, ordering by any of the five metrics, and pagination via offset/limit. The response type is 'list' for the default host.name grouping or 'grouped_list' for custom groupBy keys. Also reports whether the requested time range falls before the data retention boundary. Numeric metric fields (cpu, memory, wait, load15, diskUsage) return -1 as a sentinel when no data is available for that field.",
Request: new(inframonitoringtypes.PostableHosts),
RequestContentType: "application/json",
Response: new(inframonitoringtypes.Hosts),
@@ -35,7 +35,7 @@ func (provider *provider) addInfraMonitoringRoutes(router *mux.Router) error {
ID: "ListPods",
Tags: []string{"inframonitoring"},
Summary: "List Pods for Infra Monitoring",
Description: "Returns a paginated list of Kubernetes pods with key metrics: CPU usage, CPU request/limit utilization, memory working set, memory request/limit utilization, current pod phase (pending/running/succeeded/failed/unknown/no_data), and pod age (ms since start time). Each pod includes metadata attributes (namespace, node, workload owner such as deployment/statefulset/daemonset/job/cronjob, cluster). Supports filtering via a filter expression, custom groupBy to aggregate pods by any attribute, ordering by any of the six metrics (cpu, cpu_request, cpu_limit, memory, memory_request, memory_limit), and pagination via offset/limit. The response type is 'list' for the default k8s.pod.uid grouping (each row is one pod with its current phase) or 'grouped_list' for custom groupBy keys (each row aggregates pods in the group with per-phase counts under podCountsByPhase: { pending, running, succeeded, failed, unknown } derived from each pod's latest phase in the window). Also reports missing required metrics and whether the requested time range falls before the data retention boundary. Numeric metric fields (podCPU, podCPURequest, podCPULimit, podMemory, podMemoryRequest, podMemoryLimit, podAge) return -1 as a sentinel when no data is available for that field.",
Description: "Returns a paginated list of Kubernetes pods with key metrics: CPU usage, CPU request/limit utilization, memory working set, memory request/limit utilization, current pod phase (pending/running/succeeded/failed/unknown/no_data), and pod age (ms since start time). Each pod includes metadata attributes (namespace, node, workload owner such as deployment/statefulset/daemonset/job/cronjob, cluster). Supports filtering via a filter expression, custom groupBy to aggregate pods by any attribute, ordering by any of the six metrics (cpu, cpu_request, cpu_limit, memory, memory_request, memory_limit), and pagination via offset/limit. The response type is 'list' for the default k8s.pod.uid grouping (each row is one pod with its current phase) or 'grouped_list' for custom groupBy keys (each row aggregates pods in the group with per-phase counts under podCountsByPhase: { pending, running, succeeded, failed, unknown } derived from each pod's latest phase in the window). Also reports whether the requested time range falls before the data retention boundary. Numeric metric fields (podCPU, podCPURequest, podCPULimit, podMemory, podMemoryRequest, podMemoryLimit, podAge) return -1 as a sentinel when no data is available for that field.",
Request: new(inframonitoringtypes.PostablePods),
RequestContentType: "application/json",
Response: new(inframonitoringtypes.Pods),
@@ -54,7 +54,7 @@ func (provider *provider) addInfraMonitoringRoutes(router *mux.Router) error {
ID: "ListNodes",
Tags: []string{"inframonitoring"},
Summary: "List Nodes for Infra Monitoring",
Description: "Returns a paginated list of Kubernetes nodes with key metrics: CPU usage, CPU allocatable, memory working set, memory allocatable, per-group nodeCountsByReadiness ({ ready, notReady } from each node's latest k8s.node.condition_ready in the window) and per-group podCountsByPhase ({ pending, running, succeeded, failed, unknown } for pods scheduled on the listed nodes). Each node includes metadata attributes (k8s.node.uid, k8s.cluster.name). The response type is 'list' for the default k8s.node.name grouping (each row is one node with its current condition string: ready / not_ready / no_data) or 'grouped_list' for custom groupBy keys (each row aggregates nodes in the group; condition stays no_data). Supports filtering via a filter expression, custom groupBy, ordering by cpu / cpu_allocatable / memory / memory_allocatable, and pagination via offset/limit. Also reports missing required metrics and whether the requested time range falls before the data retention boundary. Numeric metric fields (nodeCPU, nodeCPUAllocatable, nodeMemory, nodeMemoryAllocatable) return -1 as a sentinel when no data is available for that field.",
Description: "Returns a paginated list of Kubernetes nodes with key metrics: CPU usage, CPU allocatable, memory working set, memory allocatable, per-group nodeCountsByReadiness ({ ready, notReady } from each node's latest k8s.node.condition_ready in the window) and per-group podCountsByPhase ({ pending, running, succeeded, failed, unknown } for pods scheduled on the listed nodes). Each node includes metadata attributes (k8s.node.uid, k8s.cluster.name). The response type is 'list' for the default k8s.node.name grouping (each row is one node with its current condition string: ready / not_ready / no_data) or 'grouped_list' for custom groupBy keys (each row aggregates nodes in the group; condition stays no_data). Supports filtering via a filter expression, custom groupBy, ordering by cpu / cpu_allocatable / memory / memory_allocatable, and pagination via offset/limit. Also reports whether the requested time range falls before the data retention boundary. Numeric metric fields (nodeCPU, nodeCPUAllocatable, nodeMemory, nodeMemoryAllocatable) return -1 as a sentinel when no data is available for that field.",
Request: new(inframonitoringtypes.PostableNodes),
RequestContentType: "application/json",
Response: new(inframonitoringtypes.Nodes),
@@ -73,7 +73,7 @@ func (provider *provider) addInfraMonitoringRoutes(router *mux.Router) error {
ID: "ListNamespaces",
Tags: []string{"inframonitoring"},
Summary: "List Namespaces for Infra Monitoring",
Description: "Returns a paginated list of Kubernetes namespaces with key aggregated pod metrics: CPU usage and memory working set (summed across pods in the group), plus per-group podCountsByPhase ({ pending, running, succeeded, failed, unknown } from each pod's latest k8s.pod.phase value in the window). Each namespace includes metadata attributes (k8s.namespace.name, k8s.cluster.name). The response type is 'list' for the default k8s.namespace.name grouping or 'grouped_list' for custom groupBy keys; in both modes every row aggregates pods in the group. Supports filtering via a filter expression, custom groupBy, ordering by cpu / memory, and pagination via offset/limit. Also reports missing required metrics and whether the requested time range falls before the data retention boundary. Numeric metric fields (namespaceCPU, namespaceMemory) return -1 as a sentinel when no data is available for that field.",
Description: "Returns a paginated list of Kubernetes namespaces with key aggregated pod metrics: CPU usage and memory working set (summed across pods in the group), plus per-group podCountsByPhase ({ pending, running, succeeded, failed, unknown } from each pod's latest k8s.pod.phase value in the window). Each namespace includes metadata attributes (k8s.namespace.name, k8s.cluster.name). The response type is 'list' for the default k8s.namespace.name grouping or 'grouped_list' for custom groupBy keys; in both modes every row aggregates pods in the group. Supports filtering via a filter expression, custom groupBy, ordering by cpu / memory, and pagination via offset/limit. Also reports whether the requested time range falls before the data retention boundary. Numeric metric fields (namespaceCPU, namespaceMemory) return -1 as a sentinel when no data is available for that field.",
Request: new(inframonitoringtypes.PostableNamespaces),
RequestContentType: "application/json",
Response: new(inframonitoringtypes.Namespaces),
@@ -92,7 +92,7 @@ func (provider *provider) addInfraMonitoringRoutes(router *mux.Router) error {
ID: "ListClusters",
Tags: []string{"inframonitoring"},
Summary: "List Clusters for Infra Monitoring",
Description: "Returns a paginated list of Kubernetes clusters with key aggregated metrics derived by summing per-node values within the group: CPU usage, CPU allocatable, memory working set, memory allocatable. Each row also reports per-group nodeCountsByReadiness ({ ready, notReady } from each node's latest k8s.node.condition_ready value) and per-group podCountsByPhase ({ pending, running, succeeded, failed, unknown } from each pod's latest k8s.pod.phase value). Each cluster includes metadata attributes (k8s.cluster.name). The response type is 'list' for the default k8s.cluster.name grouping or 'grouped_list' for custom groupBy keys; in both modes every row aggregates nodes and pods in the group. Supports filtering via a filter expression, custom groupBy, ordering by cpu / cpu_allocatable / memory / memory_allocatable, and pagination via offset/limit. Also reports missing required metrics and whether the requested time range falls before the data retention boundary. Numeric metric fields (clusterCPU, clusterCPUAllocatable, clusterMemory, clusterMemoryAllocatable) return -1 as a sentinel when no data is available for that field.",
Description: "Returns a paginated list of Kubernetes clusters with key aggregated metrics derived by summing per-node values within the group: CPU usage, CPU allocatable, memory working set, memory allocatable. Each row also reports per-group nodeCountsByReadiness ({ ready, notReady } from each node's latest k8s.node.condition_ready value) and per-group podCountsByPhase ({ pending, running, succeeded, failed, unknown } from each pod's latest k8s.pod.phase value). Each cluster includes metadata attributes (k8s.cluster.name). The response type is 'list' for the default k8s.cluster.name grouping or 'grouped_list' for custom groupBy keys; in both modes every row aggregates nodes and pods in the group. Supports filtering via a filter expression, custom groupBy, ordering by cpu / cpu_allocatable / memory / memory_allocatable, and pagination via offset/limit. Also reports whether the requested time range falls before the data retention boundary. Numeric metric fields (clusterCPU, clusterCPUAllocatable, clusterMemory, clusterMemoryAllocatable) return -1 as a sentinel when no data is available for that field.",
Request: new(inframonitoringtypes.PostableClusters),
RequestContentType: "application/json",
Response: new(inframonitoringtypes.Clusters),
@@ -111,7 +111,7 @@ func (provider *provider) addInfraMonitoringRoutes(router *mux.Router) error {
ID: "ListVolumes",
Tags: []string{"inframonitoring"},
Summary: "List Volumes for Infra Monitoring",
Description: "Returns a paginated list of Kubernetes persistent volume claims (PVCs) with key volume metrics: available bytes, capacity bytes, usage (capacity - available), inodes, free inodes, and used inodes. Each row also includes metadata attributes (k8s.persistentvolumeclaim.name, k8s.pod.uid, k8s.pod.name, k8s.namespace.name, k8s.node.name, k8s.statefulset.name, k8s.cluster.name). Supports filtering via a filter expression, custom groupBy to aggregate volumes by any attribute, ordering by any of the six metrics (available, capacity, usage, inodes, inodes_free, inodes_used), and pagination via offset/limit. The response type is 'list' for the default k8s.persistentvolumeclaim.name grouping or 'grouped_list' for custom groupBy keys; in both modes every row aggregates volumes in the group. Also reports missing required metrics and whether the requested time range falls before the data retention boundary. Numeric metric fields (volumeAvailable, volumeCapacity, volumeUsage, volumeInodes, volumeInodesFree, volumeInodesUsed) return -1 as a sentinel when no data is available for that field.",
Description: "Returns a paginated list of Kubernetes persistent volume claims (PVCs) with key volume metrics: available bytes, capacity bytes, usage (capacity - available), inodes, free inodes, and used inodes. Each row also includes metadata attributes (k8s.persistentvolumeclaim.name, k8s.pod.uid, k8s.pod.name, k8s.namespace.name, k8s.node.name, k8s.statefulset.name, k8s.cluster.name). Supports filtering via a filter expression, custom groupBy to aggregate volumes by any attribute, ordering by any of the six metrics (available, capacity, usage, inodes, inodes_free, inodes_used), and pagination via offset/limit. The response type is 'list' for the default k8s.persistentvolumeclaim.name grouping or 'grouped_list' for custom groupBy keys; in both modes every row aggregates volumes in the group. Also reports whether the requested time range falls before the data retention boundary. Numeric metric fields (volumeAvailable, volumeCapacity, volumeUsage, volumeInodes, volumeInodesFree, volumeInodesUsed) return -1 as a sentinel when no data is available for that field.",
Request: new(inframonitoringtypes.PostableVolumes),
RequestContentType: "application/json",
Response: new(inframonitoringtypes.Volumes),
@@ -130,7 +130,7 @@ func (provider *provider) addInfraMonitoringRoutes(router *mux.Router) error {
ID: "ListDeployments",
Tags: []string{"inframonitoring"},
Summary: "List Deployments for Infra Monitoring",
Description: "Returns a paginated list of Kubernetes Deployments with key aggregated pod metrics: CPU usage and memory working set summed across pods owned by the deployment, plus average CPU/memory request and limit utilization (deploymentCPURequest, deploymentCPULimit, deploymentMemoryRequest, deploymentMemoryLimit). Each row also reports the latest known desiredPods (k8s.deployment.desired) and availablePods (k8s.deployment.available) replica counts and per-group podCountsByPhase ({ pending, running, succeeded, failed, unknown } from each pod's latest k8s.pod.phase value). Each deployment includes metadata attributes (k8s.deployment.name, k8s.namespace.name, k8s.cluster.name). The response type is 'list' for the default k8s.deployment.name grouping or 'grouped_list' for custom groupBy keys; in both modes every row aggregates pods owned by deployments in the group. Supports filtering via a filter expression, custom groupBy, ordering by cpu / cpu_request / cpu_limit / memory / memory_request / memory_limit / desired_pods / available_pods, and pagination via offset/limit. Also reports missing required metrics and whether the requested time range falls before the data retention boundary. Numeric metric fields (deploymentCPU, deploymentCPURequest, deploymentCPULimit, deploymentMemory, deploymentMemoryRequest, deploymentMemoryLimit, desiredPods, availablePods) return -1 as a sentinel when no data is available for that field.",
Description: "Returns a paginated list of Kubernetes Deployments with key aggregated pod metrics: CPU usage and memory working set summed across pods owned by the deployment, plus average CPU/memory request and limit utilization (deploymentCPURequest, deploymentCPULimit, deploymentMemoryRequest, deploymentMemoryLimit). Each row also reports the latest known desiredPods (k8s.deployment.desired) and availablePods (k8s.deployment.available) replica counts and per-group podCountsByPhase ({ pending, running, succeeded, failed, unknown } from each pod's latest k8s.pod.phase value). Each deployment includes metadata attributes (k8s.deployment.name, k8s.namespace.name, k8s.cluster.name). The response type is 'list' for the default k8s.deployment.name grouping or 'grouped_list' for custom groupBy keys; in both modes every row aggregates pods owned by deployments in the group. Supports filtering via a filter expression, custom groupBy, ordering by cpu / cpu_request / cpu_limit / memory / memory_request / memory_limit / desired_pods / available_pods, and pagination via offset/limit. Also reports whether the requested time range falls before the data retention boundary. Numeric metric fields (deploymentCPU, deploymentCPURequest, deploymentCPULimit, deploymentMemory, deploymentMemoryRequest, deploymentMemoryLimit, desiredPods, availablePods) return -1 as a sentinel when no data is available for that field.",
Request: new(inframonitoringtypes.PostableDeployments),
RequestContentType: "application/json",
Response: new(inframonitoringtypes.Deployments),
@@ -149,7 +149,7 @@ func (provider *provider) addInfraMonitoringRoutes(router *mux.Router) error {
ID: "ListStatefulSets",
Tags: []string{"inframonitoring"},
Summary: "List StatefulSets for Infra Monitoring",
Description: "Returns a paginated list of Kubernetes StatefulSets with key aggregated pod metrics: CPU usage and memory working set summed across pods owned by the statefulset, plus average CPU/memory request and limit utilization (statefulSetCPURequest, statefulSetCPULimit, statefulSetMemoryRequest, statefulSetMemoryLimit). Each row also reports the latest known desiredPods (k8s.statefulset.desired_pods) and currentPods (k8s.statefulset.current_pods) replica counts and per-group podCountsByPhase ({ pending, running, succeeded, failed, unknown } from each pod's latest k8s.pod.phase value). Each statefulset includes metadata attributes (k8s.statefulset.name, k8s.namespace.name, k8s.cluster.name). The response type is 'list' for the default k8s.statefulset.name grouping or 'grouped_list' for custom groupBy keys; in both modes every row aggregates pods owned by statefulsets in the group. Supports filtering via a filter expression, custom groupBy, ordering by cpu / cpu_request / cpu_limit / memory / memory_request / memory_limit / desired_pods / current_pods, and pagination via offset/limit. Also reports missing required metrics and whether the requested time range falls before the data retention boundary. Numeric metric fields (statefulSetCPU, statefulSetCPURequest, statefulSetCPULimit, statefulSetMemory, statefulSetMemoryRequest, statefulSetMemoryLimit, desiredPods, currentPods) return -1 as a sentinel when no data is available for that field.",
Description: "Returns a paginated list of Kubernetes StatefulSets with key aggregated pod metrics: CPU usage and memory working set summed across pods owned by the statefulset, plus average CPU/memory request and limit utilization (statefulSetCPURequest, statefulSetCPULimit, statefulSetMemoryRequest, statefulSetMemoryLimit). Each row also reports the latest known desiredPods (k8s.statefulset.desired_pods) and currentPods (k8s.statefulset.current_pods) replica counts and per-group podCountsByPhase ({ pending, running, succeeded, failed, unknown } from each pod's latest k8s.pod.phase value). Each statefulset includes metadata attributes (k8s.statefulset.name, k8s.namespace.name, k8s.cluster.name). The response type is 'list' for the default k8s.statefulset.name grouping or 'grouped_list' for custom groupBy keys; in both modes every row aggregates pods owned by statefulsets in the group. Supports filtering via a filter expression, custom groupBy, ordering by cpu / cpu_request / cpu_limit / memory / memory_request / memory_limit / desired_pods / current_pods, and pagination via offset/limit. Also reports whether the requested time range falls before the data retention boundary. Numeric metric fields (statefulSetCPU, statefulSetCPURequest, statefulSetCPULimit, statefulSetMemory, statefulSetMemoryRequest, statefulSetMemoryLimit, desiredPods, currentPods) return -1 as a sentinel when no data is available for that field.",
Request: new(inframonitoringtypes.PostableStatefulSets),
RequestContentType: "application/json",
Response: new(inframonitoringtypes.StatefulSets),
@@ -168,7 +168,7 @@ func (provider *provider) addInfraMonitoringRoutes(router *mux.Router) error {
ID: "ListJobs",
Tags: []string{"inframonitoring"},
Summary: "List Jobs for Infra Monitoring",
Description: "Returns a paginated list of Kubernetes Jobs with key aggregated pod metrics: CPU usage and memory working set summed across pods owned by the job, plus average CPU/memory request and limit utilization (jobCPURequest, jobCPULimit, jobMemoryRequest, jobMemoryLimit). Each row also reports the latest known job-level counters from kube-state-metrics: desiredSuccessfulPods (k8s.job.desired_successful_pods, the target completion count), activePods (k8s.job.active_pods), failedPods (k8s.job.failed_pods, cumulative across the lifetime of the job), and successfulPods (k8s.job.successful_pods, cumulative). It also reports per-group podCountsByPhase ({ pending, running, succeeded, failed, unknown } from each pod's latest k8s.pod.phase value); note podCountsByPhase.failed (current pod-phase) is distinct from failedPods (cumulative job kube-state-metric). Each job includes metadata attributes (k8s.job.name, k8s.namespace.name, k8s.cluster.name). The response type is 'list' for the default k8s.job.name grouping or 'grouped_list' for custom groupBy keys; in both modes every row aggregates pods owned by jobs in the group. Supports filtering via a filter expression, custom groupBy, ordering by cpu / cpu_request / cpu_limit / memory / memory_request / memory_limit / desired_successful_pods / active_pods / failed_pods / successful_pods, and pagination via offset/limit. Also reports missing required metrics and whether the requested time range falls before the data retention boundary. Numeric metric fields (jobCPU, jobCPURequest, jobCPULimit, jobMemory, jobMemoryRequest, jobMemoryLimit, desiredSuccessfulPods, activePods, failedPods, successfulPods) return -1 as a sentinel when no data is available for that field.",
Description: "Returns a paginated list of Kubernetes Jobs with key aggregated pod metrics: CPU usage and memory working set summed across pods owned by the job, plus average CPU/memory request and limit utilization (jobCPURequest, jobCPULimit, jobMemoryRequest, jobMemoryLimit). Each row also reports the latest known job-level counters from kube-state-metrics: desiredSuccessfulPods (k8s.job.desired_successful_pods, the target completion count), activePods (k8s.job.active_pods), failedPods (k8s.job.failed_pods, cumulative across the lifetime of the job), and successfulPods (k8s.job.successful_pods, cumulative). It also reports per-group podCountsByPhase ({ pending, running, succeeded, failed, unknown } from each pod's latest k8s.pod.phase value); note podCountsByPhase.failed (current pod-phase) is distinct from failedPods (cumulative job kube-state-metric). Each job includes metadata attributes (k8s.job.name, k8s.namespace.name, k8s.cluster.name). The response type is 'list' for the default k8s.job.name grouping or 'grouped_list' for custom groupBy keys; in both modes every row aggregates pods owned by jobs in the group. Supports filtering via a filter expression, custom groupBy, ordering by cpu / cpu_request / cpu_limit / memory / memory_request / memory_limit / desired_successful_pods / active_pods / failed_pods / successful_pods, and pagination via offset/limit. Also reports whether the requested time range falls before the data retention boundary. Numeric metric fields (jobCPU, jobCPURequest, jobCPULimit, jobMemory, jobMemoryRequest, jobMemoryLimit, desiredSuccessfulPods, activePods, failedPods, successfulPods) return -1 as a sentinel when no data is available for that field.",
Request: new(inframonitoringtypes.PostableJobs),
RequestContentType: "application/json",
Response: new(inframonitoringtypes.Jobs),
@@ -187,7 +187,7 @@ func (provider *provider) addInfraMonitoringRoutes(router *mux.Router) error {
ID: "ListDaemonSets",
Tags: []string{"inframonitoring"},
Summary: "List DaemonSets for Infra Monitoring",
Description: "Returns a paginated list of Kubernetes DaemonSets with key aggregated pod metrics: CPU usage and memory working set summed across pods owned by the daemonset, plus average CPU/memory request and limit utilization (daemonSetCPURequest, daemonSetCPULimit, daemonSetMemoryRequest, daemonSetMemoryLimit). Each row also reports the latest known node-level counters from kube-state-metrics: desiredNodes (k8s.daemonset.desired_scheduled_nodes, the number of nodes the daemonset wants to run on) and currentNodes (k8s.daemonset.current_scheduled_nodes, the number of nodes the daemonset currently runs on) — note these are node counts, not pod counts. It also reports per-group podCountsByPhase ({ pending, running, succeeded, failed, unknown } from each pod's latest k8s.pod.phase value). Each daemonset includes metadata attributes (k8s.daemonset.name, k8s.namespace.name, k8s.cluster.name). The response type is 'list' for the default k8s.daemonset.name grouping or 'grouped_list' for custom groupBy keys; in both modes every row aggregates pods owned by daemonsets in the group. Supports filtering via a filter expression, custom groupBy, ordering by cpu / cpu_request / cpu_limit / memory / memory_request / memory_limit / desired_nodes / current_nodes, and pagination via offset/limit. Also reports missing required metrics and whether the requested time range falls before the data retention boundary. Numeric metric fields (daemonSetCPU, daemonSetCPURequest, daemonSetCPULimit, daemonSetMemory, daemonSetMemoryRequest, daemonSetMemoryLimit, desiredNodes, currentNodes) return -1 as a sentinel when no data is available for that field.",
Description: "Returns a paginated list of Kubernetes DaemonSets with key aggregated pod metrics: CPU usage and memory working set summed across pods owned by the daemonset, plus average CPU/memory request and limit utilization (daemonSetCPURequest, daemonSetCPULimit, daemonSetMemoryRequest, daemonSetMemoryLimit). Each row also reports the latest known node-level counters from kube-state-metrics: desiredNodes (k8s.daemonset.desired_scheduled_nodes, the number of nodes the daemonset wants to run on) and currentNodes (k8s.daemonset.current_scheduled_nodes, the number of nodes the daemonset currently runs on) — note these are node counts, not pod counts. It also reports per-group podCountsByPhase ({ pending, running, succeeded, failed, unknown } from each pod's latest k8s.pod.phase value). Each daemonset includes metadata attributes (k8s.daemonset.name, k8s.namespace.name, k8s.cluster.name). The response type is 'list' for the default k8s.daemonset.name grouping or 'grouped_list' for custom groupBy keys; in both modes every row aggregates pods owned by daemonsets in the group. Supports filtering via a filter expression, custom groupBy, ordering by cpu / cpu_request / cpu_limit / memory / memory_request / memory_limit / desired_nodes / current_nodes, and pagination via offset/limit. Also reports whether the requested time range falls before the data retention boundary. Numeric metric fields (daemonSetCPU, daemonSetCPURequest, daemonSetCPULimit, daemonSetMemory, daemonSetMemoryRequest, daemonSetMemoryLimit, desiredNodes, currentNodes) return -1 as a sentinel when no data is available for that field.",
Request: new(inframonitoringtypes.PostableDaemonSets),
RequestContentType: "application/json",
Response: new(inframonitoringtypes.DaemonSets),

View File

@@ -1,156 +0,0 @@
package signozapiserver
import (
"net/http"
"github.com/SigNoz/signoz/pkg/http/handler"
"github.com/SigNoz/signoz/pkg/types"
"github.com/SigNoz/signoz/pkg/types/metricreductionruletypes"
"github.com/SigNoz/signoz/pkg/types/querybuildertypes/querybuildertypesv5"
"github.com/gorilla/mux"
)
func (provider *provider) addMetricReductionRuleRoutes(router *mux.Router) error {
if err := router.Handle("/api/v2/metric_reduction_rules", handler.New(
provider.authzMiddleware.ViewAccess(provider.metricReductionRuleHandler.List),
handler.OpenAPIDef{
ID: "ListMetricReductionRules",
Tags: []string{"metrics"},
Summary: "List metric reduction rules",
Description: "Returns active metric volume-control (label reduction) rules.",
RequestQuery: new(metricreductionruletypes.ListReductionRulesParams),
Response: new(metricreductionruletypes.GettableReductionRules),
ResponseContentType: "application/json",
SuccessStatusCode: http.StatusOK,
ErrorStatusCodes: []int{http.StatusUnauthorized, http.StatusNotImplemented, http.StatusUnavailableForLegalReasons, http.StatusInternalServerError},
SecuritySchemes: newSecuritySchemes(types.RoleViewer),
},
)).Methods(http.MethodGet).GetError(); err != nil {
return err
}
if err := router.Handle("/api/v2/metric_reduction_rules", handler.New(
provider.authzMiddleware.AdminAccess(provider.metricReductionRuleHandler.Create),
handler.OpenAPIDef{
ID: "CreateMetricReductionRule",
Tags: []string{"metrics"},
Summary: "Create a metric reduction rule",
Description: "Creates a volume-control rule for a metric and returns it with its id; fails if the metric already has a rule.",
Request: new(metricreductionruletypes.PostableReductionRule),
RequestContentType: "application/json",
Response: new(metricreductionruletypes.GettableReductionRule),
ResponseContentType: "application/json",
SuccessStatusCode: http.StatusCreated,
ErrorStatusCodes: []int{http.StatusBadRequest, http.StatusUnauthorized, http.StatusForbidden, http.StatusConflict, http.StatusNotImplemented, http.StatusUnavailableForLegalReasons, http.StatusInternalServerError},
SecuritySchemes: newSecuritySchemes(types.RoleAdmin),
},
)).Methods(http.MethodPost).GetError(); err != nil {
return err
}
if err := router.Handle("/api/v2/metric_reduction_rules/stats", handler.New(
provider.authzMiddleware.ViewAccess(provider.metricReductionRuleHandler.Stats),
handler.OpenAPIDef{
ID: "GetMetricReductionRuleStats",
Tags: []string{"metrics"},
Summary: "Metric reduction stats",
Description: "Returns total ingested vs retained series and the estimated monthly savings across all volume-control rules.",
Response: new(metricreductionruletypes.GettableReductionRuleStats),
ResponseContentType: "application/json",
SuccessStatusCode: http.StatusOK,
ErrorStatusCodes: []int{http.StatusUnauthorized, http.StatusNotImplemented, http.StatusUnavailableForLegalReasons, http.StatusInternalServerError},
SecuritySchemes: newSecuritySchemes(types.RoleViewer),
},
)).Methods(http.MethodGet).GetError(); err != nil {
return err
}
if err := router.Handle("/api/v2/metric_reduction_rules/timeseries", handler.New(
provider.authzMiddleware.ViewAccess(provider.metricReductionRuleHandler.Timeseries),
handler.OpenAPIDef{
ID: "GetMetricReductionRuleTimeseries",
Tags: []string{"metrics"},
Summary: "Metric reduction volume over time",
Description: "Returns ingested vs retained series over time across all volume-control rules (hourly buckets), in the query-range time-series response shape.",
Response: new(querybuildertypesv5.QueryRangeResponse),
ResponseContentType: "application/json",
SuccessStatusCode: http.StatusOK,
ErrorStatusCodes: []int{http.StatusUnauthorized, http.StatusNotImplemented, http.StatusUnavailableForLegalReasons, http.StatusInternalServerError},
SecuritySchemes: newSecuritySchemes(types.RoleViewer),
},
)).Methods(http.MethodGet).GetError(); err != nil {
return err
}
if err := router.Handle("/api/v2/metric_reduction_rules/preview", handler.New(
provider.authzMiddleware.AdminAccess(provider.metricReductionRuleHandler.Preview),
handler.OpenAPIDef{
ID: "PreviewMetricReductionRule",
Tags: []string{"metrics"},
Summary: "Preview a metric reduction rule",
Description: "Estimates the series reduction and related-asset impact of a candidate volume-control rule without persisting it.",
Request: new(metricreductionruletypes.PostableReductionRulePreview),
RequestContentType: "application/json",
Response: new(metricreductionruletypes.GettableReductionRulePreview),
ResponseContentType: "application/json",
SuccessStatusCode: http.StatusOK,
ErrorStatusCodes: []int{http.StatusBadRequest, http.StatusUnauthorized, http.StatusForbidden, http.StatusNotFound, http.StatusNotImplemented, http.StatusUnavailableForLegalReasons, http.StatusInternalServerError},
SecuritySchemes: newSecuritySchemes(types.RoleAdmin),
},
)).Methods(http.MethodPost).GetError(); err != nil {
return err
}
if err := router.Handle("/api/v2/metric_reduction_rules/{id}", handler.New(
provider.authzMiddleware.ViewAccess(provider.metricReductionRuleHandler.GetByID),
handler.OpenAPIDef{
ID: "GetMetricReductionRuleByID",
Tags: []string{"metrics"},
Summary: "Get a metric reduction rule by id",
Description: "Returns a single volume-control rule by its id.",
Response: new(metricreductionruletypes.GettableReductionRule),
ResponseContentType: "application/json",
SuccessStatusCode: http.StatusOK,
ErrorStatusCodes: []int{http.StatusUnauthorized, http.StatusNotFound, http.StatusNotImplemented, http.StatusUnavailableForLegalReasons, http.StatusInternalServerError},
SecuritySchemes: newSecuritySchemes(types.RoleViewer),
},
)).Methods(http.MethodGet).GetError(); err != nil {
return err
}
if err := router.Handle("/api/v2/metric_reduction_rules/{id}", handler.New(
provider.authzMiddleware.AdminAccess(provider.metricReductionRuleHandler.UpdateByID),
handler.OpenAPIDef{
ID: "UpdateMetricReductionRuleByID",
Tags: []string{"metrics"},
Summary: "Update a metric reduction rule by id",
Description: "Updates the match type and labels of a volume-control rule by its id; the metric name is immutable.",
Request: new(metricreductionruletypes.UpdatableReductionRule),
RequestContentType: "application/json",
Response: new(metricreductionruletypes.GettableReductionRule),
ResponseContentType: "application/json",
SuccessStatusCode: http.StatusOK,
ErrorStatusCodes: []int{http.StatusBadRequest, http.StatusUnauthorized, http.StatusForbidden, http.StatusNotFound, http.StatusNotImplemented, http.StatusUnavailableForLegalReasons, http.StatusInternalServerError},
SecuritySchemes: newSecuritySchemes(types.RoleAdmin),
},
)).Methods(http.MethodPut).GetError(); err != nil {
return err
}
if err := router.Handle("/api/v2/metric_reduction_rules/{id}", handler.New(
provider.authzMiddleware.AdminAccess(provider.metricReductionRuleHandler.DeleteByID),
handler.OpenAPIDef{
ID: "DeleteMetricReductionRuleByID",
Tags: []string{"metrics"},
Summary: "Delete a metric reduction rule by id",
Description: "Deletes a volume-control rule by its id.",
SuccessStatusCode: http.StatusNoContent,
ErrorStatusCodes: []int{http.StatusUnauthorized, http.StatusForbidden, http.StatusNotFound, http.StatusNotImplemented, http.StatusUnavailableForLegalReasons, http.StatusInternalServerError},
SecuritySchemes: newSecuritySchemes(types.RoleAdmin),
},
)).Methods(http.MethodDelete).GetError(); err != nil {
return err
}
return nil
}

View File

@@ -18,7 +18,6 @@ import (
"github.com/SigNoz/signoz/pkg/modules/fields"
"github.com/SigNoz/signoz/pkg/modules/inframonitoring"
"github.com/SigNoz/signoz/pkg/modules/llmpricingrule"
"github.com/SigNoz/signoz/pkg/modules/metricreductionrule"
"github.com/SigNoz/signoz/pkg/modules/metricsexplorer"
"github.com/SigNoz/signoz/pkg/modules/organization"
"github.com/SigNoz/signoz/pkg/modules/preference"
@@ -40,40 +39,39 @@ import (
)
type provider struct {
config apiserver.Config
settings factory.ScopedProviderSettings
router *mux.Router
authzMiddleware *middleware.AuthZ
authzService authz.AuthZ
orgHandler organization.Handler
userHandler user.Handler
sessionHandler session.Handler
authDomainHandler authdomain.Handler
preferenceHandler preference.Handler
globalHandler global.Handler
promoteHandler promote.Handler
flaggerHandler flagger.Handler
dashboardModule dashboard.Module
dashboardHandler dashboard.Handler
metricsExplorerHandler metricsexplorer.Handler
metricReductionRuleHandler metricreductionrule.Handler
infraMonitoringHandler inframonitoring.Handler
gatewayHandler gateway.Handler
fieldsHandler fields.Handler
authzHandler authz.Handler
rawDataExportHandler rawdataexport.Handler
zeusHandler zeus.Handler
querierHandler querier.Handler
serviceAccountHandler serviceaccount.Handler
factoryHandler factory.Handler
cloudIntegrationHandler cloudintegration.Handler
ruleStateHistoryHandler rulestatehistory.Handler
spanMapperHandler spanmapper.Handler
alertmanagerHandler alertmanager.Handler
traceDetailHandler tracedetail.Handler
rulerHandler ruler.Handler
llmPricingRuleHandler llmpricingrule.Handler
statsHandler statsreporter.Handler
config apiserver.Config
settings factory.ScopedProviderSettings
router *mux.Router
authzMiddleware *middleware.AuthZ
authzService authz.AuthZ
orgHandler organization.Handler
userHandler user.Handler
sessionHandler session.Handler
authDomainHandler authdomain.Handler
preferenceHandler preference.Handler
globalHandler global.Handler
promoteHandler promote.Handler
flaggerHandler flagger.Handler
dashboardModule dashboard.Module
dashboardHandler dashboard.Handler
metricsExplorerHandler metricsexplorer.Handler
infraMonitoringHandler inframonitoring.Handler
gatewayHandler gateway.Handler
fieldsHandler fields.Handler
authzHandler authz.Handler
rawDataExportHandler rawdataexport.Handler
zeusHandler zeus.Handler
querierHandler querier.Handler
serviceAccountHandler serviceaccount.Handler
factoryHandler factory.Handler
cloudIntegrationHandler cloudintegration.Handler
ruleStateHistoryHandler rulestatehistory.Handler
spanMapperHandler spanmapper.Handler
alertmanagerHandler alertmanager.Handler
traceDetailHandler tracedetail.Handler
rulerHandler ruler.Handler
llmPricingRuleHandler llmpricingrule.Handler
statsHandler statsreporter.Handler
}
func NewFactory(
@@ -90,7 +88,6 @@ func NewFactory(
dashboardModule dashboard.Module,
dashboardHandler dashboard.Handler,
metricsExplorerHandler metricsexplorer.Handler,
metricReductionRuleHandler metricreductionrule.Handler,
infraMonitoringHandler inframonitoring.Handler,
gatewayHandler gateway.Handler,
fieldsHandler fields.Handler,
@@ -127,7 +124,6 @@ func NewFactory(
dashboardModule,
dashboardHandler,
metricsExplorerHandler,
metricReductionRuleHandler,
infraMonitoringHandler,
gatewayHandler,
fieldsHandler,
@@ -166,7 +162,6 @@ func newProvider(
dashboardModule dashboard.Module,
dashboardHandler dashboard.Handler,
metricsExplorerHandler metricsexplorer.Handler,
metricReductionRuleHandler metricreductionrule.Handler,
infraMonitoringHandler inframonitoring.Handler,
gatewayHandler gateway.Handler,
fieldsHandler fields.Handler,
@@ -189,39 +184,38 @@ func newProvider(
router := mux.NewRouter().UseEncodedPath()
provider := &provider{
config: config,
settings: settings,
router: router,
orgHandler: orgHandler,
userHandler: userHandler,
authzService: authzService,
sessionHandler: sessionHandler,
authDomainHandler: authDomainHandler,
preferenceHandler: preferenceHandler,
globalHandler: globalHandler,
promoteHandler: promoteHandler,
flaggerHandler: flaggerHandler,
dashboardModule: dashboardModule,
dashboardHandler: dashboardHandler,
metricsExplorerHandler: metricsExplorerHandler,
metricReductionRuleHandler: metricReductionRuleHandler,
infraMonitoringHandler: infraMonitoringHandler,
gatewayHandler: gatewayHandler,
fieldsHandler: fieldsHandler,
authzHandler: authzHandler,
rawDataExportHandler: rawDataExportHandler,
zeusHandler: zeusHandler,
querierHandler: querierHandler,
serviceAccountHandler: serviceAccountHandler,
factoryHandler: factoryHandler,
cloudIntegrationHandler: cloudIntegrationHandler,
ruleStateHistoryHandler: ruleStateHistoryHandler,
spanMapperHandler: spanMapperHandler,
alertmanagerHandler: alertmanagerHandler,
traceDetailHandler: traceDetailHandler,
rulerHandler: rulerHandler,
llmPricingRuleHandler: llmPricingRuleHandler,
statsHandler: statsHandler,
config: config,
settings: settings,
router: router,
orgHandler: orgHandler,
userHandler: userHandler,
authzService: authzService,
sessionHandler: sessionHandler,
authDomainHandler: authDomainHandler,
preferenceHandler: preferenceHandler,
globalHandler: globalHandler,
promoteHandler: promoteHandler,
flaggerHandler: flaggerHandler,
dashboardModule: dashboardModule,
dashboardHandler: dashboardHandler,
metricsExplorerHandler: metricsExplorerHandler,
infraMonitoringHandler: infraMonitoringHandler,
gatewayHandler: gatewayHandler,
fieldsHandler: fieldsHandler,
authzHandler: authzHandler,
rawDataExportHandler: rawDataExportHandler,
zeusHandler: zeusHandler,
querierHandler: querierHandler,
serviceAccountHandler: serviceAccountHandler,
factoryHandler: factoryHandler,
cloudIntegrationHandler: cloudIntegrationHandler,
ruleStateHistoryHandler: ruleStateHistoryHandler,
spanMapperHandler: spanMapperHandler,
alertmanagerHandler: alertmanagerHandler,
traceDetailHandler: traceDetailHandler,
rulerHandler: rulerHandler,
llmPricingRuleHandler: llmPricingRuleHandler,
statsHandler: statsHandler,
}
provider.authzMiddleware = middleware.NewAuthZ(settings.Logger(), orgGetter, authzService)
@@ -278,10 +272,6 @@ func (provider *provider) AddToRouter(router *mux.Router) error {
return err
}
if err := provider.addMetricReductionRuleRoutes(router); err != nil {
return err
}
if err := provider.addInfraMonitoringRoutes(router); err != nil {
return err
}

View File

@@ -51,6 +51,26 @@ func (provider *provider) addSpanMapperRoutes(router *mux.Router) error {
return err
}
if err := router.Handle("/api/v1/span_mapper_groups/test", handler.New(
provider.authzMiddleware.ViewAccess(provider.spanMapperHandler.TestMappers),
handler.OpenAPIDef{
ID: "TestSpanMappers",
Tags: []string{"spanmapper"},
Summary: "Test span mappers against sample spans",
Description: "Tests how span mappers would transform sample spans",
Request: new(spantypes.PostableSpanMapperTest),
RequestContentType: "application/json",
Response: new(spantypes.GettableSpanMapperTest),
ResponseContentType: "application/json",
SuccessStatusCode: http.StatusOK,
ErrorStatusCodes: []int{http.StatusBadRequest, http.StatusNotFound},
Deprecated: false,
SecuritySchemes: newSecuritySchemes(types.RoleViewer),
},
)).Methods(http.MethodPost).GetError(); err != nil {
return err
}
if err := router.Handle("/api/v1/span_mapper_groups/{groupId}", handler.New(
provider.authzMiddleware.AdminAccess(provider.spanMapperHandler.UpdateGroup),
handler.OpenAPIDef{

View File

@@ -413,64 +413,27 @@ func (m *module) buildFilterClause(ctx context.Context, filter *qbtypes.Filter,
// NOTE: this method is not specific to infra monitoring — it queries attributes_metadata generically.
// Consider moving to telemetryMetaStore when a second use case emerges.
//
// getMetricsExistenceAndEarliestTime checks which of the given metric names have been
// reported. It returns a list of missing metrics (those not found or with zero count)
// and the earliest first-reported timestamp across all present metrics.
// When all metrics are missing, minFirstReportedUnixMilli is 0.
// TODO(nikhilmantri0902, srikanthccv): This method was designed this way because querier errors if any of the metrics
// in the querier list was never sent, the QueryRange call throws not found error. Modify this method, if QueryRange
// behaviour changes towards this.
func (m *module) getMetricsExistenceAndEarliestTime(ctx context.Context, metricNames []string) ([]string, uint64, error) {
// getEarliestMetricTime returns the earliest first_reported_unix_milli across the
// given metric names. It is used solely for the end-time-before-retention check.
// When none of the metrics have ever been reported, it returns 0.
func (m *module) getEarliestMetricTime(ctx context.Context, metricNames []string) (uint64, error) {
if len(metricNames) == 0 {
return nil, 0, nil
return 0, nil
}
sb := sqlbuilder.NewSelectBuilder()
sb.Select("metric_name", "count(*) AS cnt", "min(first_reported_unix_milli) AS min_first_reported")
sb.Select("min(first_reported_unix_milli) AS min_first_reported")
sb.From(fmt.Sprintf("%s.%s", telemetrymetrics.DBName, telemetrymetrics.AttributesMetadataTableName))
sb.Where(sb.In("metric_name", sqlbuilder.List(metricNames)))
sb.GroupBy("metric_name")
query, args := sb.BuildWithFlavor(sqlbuilder.ClickHouse)
rows, err := m.telemetryStore.ClickhouseDB().Query(ctx, query, args...)
if err != nil {
return nil, 0, err
}
defer rows.Close()
type metricInfo struct {
count uint64
minFirstReported uint64
}
found := make(map[string]metricInfo, len(metricNames))
for rows.Next() {
var name string
var cnt, minFR uint64
if err := rows.Scan(&name, &cnt, &minFR); err != nil {
return nil, 0, err
}
found[name] = metricInfo{count: cnt, minFirstReported: minFR}
}
if err := rows.Err(); err != nil {
return nil, 0, err
var minFirstReported uint64
if err := m.telemetryStore.ClickhouseDB().QueryRow(ctx, query, args...).Scan(&minFirstReported); err != nil {
return 0, err
}
var missingMetrics []string
var globalMinFirstReported uint64
for _, name := range metricNames {
info, ok := found[name]
if !ok || info.count == 0 {
missingMetrics = append(missingMetrics, name)
continue
}
if globalMinFirstReported == 0 || info.minFirstReported < globalMinFirstReported {
globalMinFirstReported = info.minFirstReported
}
}
return missingMetrics, globalMinFirstReported, nil
return minFirstReported, nil
}
// getMetadata fetches the latest values of additionalCols for each unique combination of groupBy keys,

View File

@@ -78,26 +78,18 @@ func (m *module) ListHosts(ctx context.Context, orgID valuer.UUID, req *inframon
resp.Type = inframonitoringtypes.ResponseTypeGroupedList
}
// 1. Check which required metrics exist and get earliest retention time.
// If any required metric is missing, return early with the list of missing metrics.
// 2. If metrics exist but req.End is before the earliest reported time, return early with endTimeBeforeRetention=true.
missingMetrics, minFirstReportedUnixMilli, err := m.getMetricsExistenceAndEarliestTime(ctx, hostsTableMetricNamesList)
// If req.End is before the earliest reported time for these metrics, return early
// with endTimeBeforeRetention=true.
minFirstReportedUnixMilli, err := m.getEarliestMetricTime(ctx, hostsTableMetricNamesList)
if err != nil {
return nil, err
}
if len(missingMetrics) > 0 {
resp.RequiredMetricsCheck = inframonitoringtypes.RequiredMetricsCheck{MissingMetrics: missingMetrics}
resp.Records = []inframonitoringtypes.HostRecord{}
resp.Total = 0
return resp, nil
}
if req.End < int64(minFirstReportedUnixMilli) {
resp.EndTimeBeforeRetention = true
resp.Records = []inframonitoringtypes.HostRecord{}
resp.Total = 0
return resp, nil
}
resp.RequiredMetricsCheck = inframonitoringtypes.RequiredMetricsCheck{MissingMetrics: []string{}}
// TOD(nikhilmantri0902): replace this separate ClickHouse query with a sub-query inside the main query builder query
// once QB supports sub-queries.
@@ -191,23 +183,16 @@ func (m *module) ListPods(ctx context.Context, orgID valuer.UUID, req *inframoni
resp.Type = inframonitoringtypes.ResponseTypeGroupedList
}
missingMetrics, minFirstReportedUnixMilli, err := m.getMetricsExistenceAndEarliestTime(ctx, podsTableMetricNamesList)
minFirstReportedUnixMilli, err := m.getEarliestMetricTime(ctx, podsTableMetricNamesList)
if err != nil {
return nil, err
}
if len(missingMetrics) > 0 {
resp.RequiredMetricsCheck = inframonitoringtypes.RequiredMetricsCheck{MissingMetrics: missingMetrics}
resp.Records = []inframonitoringtypes.PodRecord{}
resp.Total = 0
return resp, nil
}
if req.End < int64(minFirstReportedUnixMilli) {
resp.EndTimeBeforeRetention = true
resp.Records = []inframonitoringtypes.PodRecord{}
resp.Total = 0
return resp, nil
}
resp.RequiredMetricsCheck = inframonitoringtypes.RequiredMetricsCheck{MissingMetrics: []string{}}
metadataMap, err := m.getPodsTableMetadata(ctx, req)
if err != nil {
@@ -276,23 +261,16 @@ func (m *module) ListNodes(ctx context.Context, orgID valuer.UUID, req *inframon
resp.Type = inframonitoringtypes.ResponseTypeGroupedList
}
missingMetrics, minFirstReportedUnixMilli, err := m.getMetricsExistenceAndEarliestTime(ctx, nodesTableMetricNamesList)
minFirstReportedUnixMilli, err := m.getEarliestMetricTime(ctx, nodesTableMetricNamesList)
if err != nil {
return nil, err
}
if len(missingMetrics) > 0 {
resp.RequiredMetricsCheck = inframonitoringtypes.RequiredMetricsCheck{MissingMetrics: missingMetrics}
resp.Records = []inframonitoringtypes.NodeRecord{}
resp.Total = 0
return resp, nil
}
if req.End < int64(minFirstReportedUnixMilli) {
resp.EndTimeBeforeRetention = true
resp.Records = []inframonitoringtypes.NodeRecord{}
resp.Total = 0
return resp, nil
}
resp.RequiredMetricsCheck = inframonitoringtypes.RequiredMetricsCheck{MissingMetrics: []string{}}
metadataMap, err := m.getNodesTableMetadata(ctx, req)
if err != nil {
@@ -366,23 +344,16 @@ func (m *module) ListNamespaces(ctx context.Context, orgID valuer.UUID, req *inf
resp.Type = inframonitoringtypes.ResponseTypeGroupedList
}
missingMetrics, minFirstReportedUnixMilli, err := m.getMetricsExistenceAndEarliestTime(ctx, namespacesTableMetricNamesList)
minFirstReportedUnixMilli, err := m.getEarliestMetricTime(ctx, namespacesTableMetricNamesList)
if err != nil {
return nil, err
}
if len(missingMetrics) > 0 {
resp.RequiredMetricsCheck = inframonitoringtypes.RequiredMetricsCheck{MissingMetrics: missingMetrics}
resp.Records = []inframonitoringtypes.NamespaceRecord{}
resp.Total = 0
return resp, nil
}
if req.End < int64(minFirstReportedUnixMilli) {
resp.EndTimeBeforeRetention = true
resp.Records = []inframonitoringtypes.NamespaceRecord{}
resp.Total = 0
return resp, nil
}
resp.RequiredMetricsCheck = inframonitoringtypes.RequiredMetricsCheck{MissingMetrics: []string{}}
metadataMap, err := m.getNamespacesTableMetadata(ctx, req)
if err != nil {
@@ -450,23 +421,16 @@ func (m *module) ListClusters(ctx context.Context, orgID valuer.UUID, req *infra
resp.Type = inframonitoringtypes.ResponseTypeGroupedList
}
missingMetrics, minFirstReportedUnixMilli, err := m.getMetricsExistenceAndEarliestTime(ctx, clustersTableMetricNamesList)
minFirstReportedUnixMilli, err := m.getEarliestMetricTime(ctx, clustersTableMetricNamesList)
if err != nil {
return nil, err
}
if len(missingMetrics) > 0 {
resp.RequiredMetricsCheck = inframonitoringtypes.RequiredMetricsCheck{MissingMetrics: missingMetrics}
resp.Records = []inframonitoringtypes.ClusterRecord{}
resp.Total = 0
return resp, nil
}
if req.End < int64(minFirstReportedUnixMilli) {
resp.EndTimeBeforeRetention = true
resp.Records = []inframonitoringtypes.ClusterRecord{}
resp.Total = 0
return resp, nil
}
resp.RequiredMetricsCheck = inframonitoringtypes.RequiredMetricsCheck{MissingMetrics: []string{}}
metadataMap, err := m.getClustersTableMetadata(ctx, req)
if err != nil {
@@ -547,23 +511,16 @@ func (m *module) ListVolumes(ctx context.Context, orgID valuer.UUID, req *infram
}
req.Filter.Expression = mergeFilterExpressions(volumesBaseFilterExpr, req.Filter.Expression)
missingMetrics, minFirstReportedUnixMilli, err := m.getMetricsExistenceAndEarliestTime(ctx, volumesTableMetricNamesList)
minFirstReportedUnixMilli, err := m.getEarliestMetricTime(ctx, volumesTableMetricNamesList)
if err != nil {
return nil, err
}
if len(missingMetrics) > 0 {
resp.RequiredMetricsCheck = inframonitoringtypes.RequiredMetricsCheck{MissingMetrics: missingMetrics}
resp.Records = []inframonitoringtypes.VolumeRecord{}
resp.Total = 0
return resp, nil
}
if req.End < int64(minFirstReportedUnixMilli) {
resp.EndTimeBeforeRetention = true
resp.Records = []inframonitoringtypes.VolumeRecord{}
resp.Total = 0
return resp, nil
}
resp.RequiredMetricsCheck = inframonitoringtypes.RequiredMetricsCheck{MissingMetrics: []string{}}
metadataMap, err := m.getVolumesTableMetadata(ctx, req)
if err != nil {
@@ -632,23 +589,16 @@ func (m *module) ListDeployments(ctx context.Context, orgID valuer.UUID, req *in
}
req.Filter.Expression = mergeFilterExpressions(deploymentsBaseFilterExpr, req.Filter.Expression)
missingMetrics, minFirstReportedUnixMilli, err := m.getMetricsExistenceAndEarliestTime(ctx, deploymentsTableMetricNamesList)
minFirstReportedUnixMilli, err := m.getEarliestMetricTime(ctx, deploymentsTableMetricNamesList)
if err != nil {
return nil, err
}
if len(missingMetrics) > 0 {
resp.RequiredMetricsCheck = inframonitoringtypes.RequiredMetricsCheck{MissingMetrics: missingMetrics}
resp.Records = []inframonitoringtypes.DeploymentRecord{}
resp.Total = 0
return resp, nil
}
if req.End < int64(minFirstReportedUnixMilli) {
resp.EndTimeBeforeRetention = true
resp.Records = []inframonitoringtypes.DeploymentRecord{}
resp.Total = 0
return resp, nil
}
resp.RequiredMetricsCheck = inframonitoringtypes.RequiredMetricsCheck{MissingMetrics: []string{}}
metadataMap, err := m.getDeploymentsTableMetadata(ctx, req)
if err != nil {
@@ -722,23 +672,16 @@ func (m *module) ListStatefulSets(ctx context.Context, orgID valuer.UUID, req *i
}
req.Filter.Expression = mergeFilterExpressions(statefulSetsBaseFilterExpr, req.Filter.Expression)
missingMetrics, minFirstReportedUnixMilli, err := m.getMetricsExistenceAndEarliestTime(ctx, statefulSetsTableMetricNamesList)
minFirstReportedUnixMilli, err := m.getEarliestMetricTime(ctx, statefulSetsTableMetricNamesList)
if err != nil {
return nil, err
}
if len(missingMetrics) > 0 {
resp.RequiredMetricsCheck = inframonitoringtypes.RequiredMetricsCheck{MissingMetrics: missingMetrics}
resp.Records = []inframonitoringtypes.StatefulSetRecord{}
resp.Total = 0
return resp, nil
}
if req.End < int64(minFirstReportedUnixMilli) {
resp.EndTimeBeforeRetention = true
resp.Records = []inframonitoringtypes.StatefulSetRecord{}
resp.Total = 0
return resp, nil
}
resp.RequiredMetricsCheck = inframonitoringtypes.RequiredMetricsCheck{MissingMetrics: []string{}}
metadataMap, err := m.getStatefulSetsTableMetadata(ctx, req)
if err != nil {
@@ -814,23 +757,16 @@ func (m *module) ListJobs(ctx context.Context, orgID valuer.UUID, req *inframoni
}
req.Filter.Expression = mergeFilterExpressions(jobsBaseFilterExpr, req.Filter.Expression)
missingMetrics, minFirstReportedUnixMilli, err := m.getMetricsExistenceAndEarliestTime(ctx, jobsTableMetricNamesList)
minFirstReportedUnixMilli, err := m.getEarliestMetricTime(ctx, jobsTableMetricNamesList)
if err != nil {
return nil, err
}
if len(missingMetrics) > 0 {
resp.RequiredMetricsCheck = inframonitoringtypes.RequiredMetricsCheck{MissingMetrics: missingMetrics}
resp.Records = []inframonitoringtypes.JobRecord{}
resp.Total = 0
return resp, nil
}
if req.End < int64(minFirstReportedUnixMilli) {
resp.EndTimeBeforeRetention = true
resp.Records = []inframonitoringtypes.JobRecord{}
resp.Total = 0
return resp, nil
}
resp.RequiredMetricsCheck = inframonitoringtypes.RequiredMetricsCheck{MissingMetrics: []string{}}
metadataMap, err := m.getJobsTableMetadata(ctx, req)
if err != nil {
@@ -906,23 +842,16 @@ func (m *module) ListDaemonSets(ctx context.Context, orgID valuer.UUID, req *inf
}
req.Filter.Expression = mergeFilterExpressions(daemonSetsBaseFilterExpr, req.Filter.Expression)
missingMetrics, minFirstReportedUnixMilli, err := m.getMetricsExistenceAndEarliestTime(ctx, daemonSetsTableMetricNamesList)
minFirstReportedUnixMilli, err := m.getEarliestMetricTime(ctx, daemonSetsTableMetricNamesList)
if err != nil {
return nil, err
}
if len(missingMetrics) > 0 {
resp.RequiredMetricsCheck = inframonitoringtypes.RequiredMetricsCheck{MissingMetrics: missingMetrics}
resp.Records = []inframonitoringtypes.DaemonSetRecord{}
resp.Total = 0
return resp, nil
}
if req.End < int64(minFirstReportedUnixMilli) {
resp.EndTimeBeforeRetention = true
resp.Records = []inframonitoringtypes.DaemonSetRecord{}
resp.Total = 0
return resp, nil
}
resp.RequiredMetricsCheck = inframonitoringtypes.RequiredMetricsCheck{MissingMetrics: []string{}}
metadataMap, err := m.getDaemonSetsTableMetadata(ctx, req)
if err != nil {

View File

@@ -6,19 +6,22 @@ import (
"time"
"github.com/SigNoz/signoz/pkg/errors"
"github.com/SigNoz/signoz/pkg/flagger"
"github.com/SigNoz/signoz/pkg/modules/llmpricingrule"
"github.com/SigNoz/signoz/pkg/query-service/agentConf"
"github.com/SigNoz/signoz/pkg/types/featuretypes"
"github.com/SigNoz/signoz/pkg/types/llmpricingruletypes"
"github.com/SigNoz/signoz/pkg/types/opamptypes"
"github.com/SigNoz/signoz/pkg/valuer"
)
type module struct {
store llmpricingruletypes.Store
store llmpricingruletypes.Store
flagger flagger.Flagger
}
func NewModule(store llmpricingruletypes.Store) llmpricingrule.Module {
return &module{store: store}
func NewModule(store llmpricingruletypes.Store, flagger flagger.Flagger) llmpricingrule.Module {
return &module{store: store, flagger: flagger}
}
func (module *module) List(ctx context.Context, orgID valuer.UUID, offset, limit int, search string, isOverride *bool) ([]*llmpricingruletypes.LLMPricingRule, int, error) {
@@ -89,6 +92,16 @@ func (module *module) AgentFeatureType() agentConf.AgentFeatureType {
func (module *module) RecommendAgentConfig(orgID valuer.UUID, currentConfYaml []byte, configVersion *opamptypes.AgentConfigVersion) ([]byte, string, error) {
ctx := context.Background()
// Skip the llm pricing processor unless AI observability is enabled for the org.
evalCtx := featuretypes.NewFlaggerEvaluationContext(orgID)
enabled, err := module.flagger.Boolean(ctx, flagger.FeatureEnableAIObservability, evalCtx)
if err != nil {
return nil, "", err
}
if !enabled {
return currentConfYaml, "", nil
}
rules, err := module.getEnabledRules(ctx, orgID)
if err != nil {
return nil, "", err

View File

@@ -1,198 +0,0 @@
package implmetricreductionrule
import (
"net/http"
"github.com/SigNoz/signoz/pkg/errors"
"github.com/SigNoz/signoz/pkg/http/binding"
"github.com/SigNoz/signoz/pkg/http/render"
"github.com/SigNoz/signoz/pkg/modules/metricreductionrule"
"github.com/SigNoz/signoz/pkg/types/authtypes"
"github.com/SigNoz/signoz/pkg/types/metricreductionruletypes"
"github.com/SigNoz/signoz/pkg/valuer"
"github.com/gorilla/mux"
)
type handler struct {
module metricreductionrule.Module
}
func NewHandler(module metricreductionrule.Module) metricreductionrule.Handler {
return &handler{module: module}
}
func idFromPath(r *http.Request) (valuer.UUID, error) {
id, err := valuer.NewUUID(mux.Vars(r)["id"])
if err != nil {
return valuer.UUID{}, errors.NewInvalidInputf(errors.CodeInvalidInput, "id must be a valid uuid")
}
return id, nil
}
func (h *handler) List(rw http.ResponseWriter, r *http.Request) {
claims, err := authtypes.ClaimsFromContext(r.Context())
if err != nil {
render.Error(rw, err)
return
}
var params metricreductionruletypes.ListReductionRulesParams
if err := binding.Query.BindQuery(r.URL.Query(), &params); err != nil {
render.Error(rw, err)
return
}
out, err := h.module.List(r.Context(), valuer.MustNewUUID(claims.OrgID), &params)
if err != nil {
render.Error(rw, err)
return
}
render.Success(rw, http.StatusOK, out)
}
func (h *handler) Preview(rw http.ResponseWriter, r *http.Request) {
claims, err := authtypes.ClaimsFromContext(r.Context())
if err != nil {
render.Error(rw, err)
return
}
var in metricreductionruletypes.PostableReductionRulePreview
if err := binding.JSON.BindBody(r.Body, &in); err != nil {
render.Error(rw, err)
return
}
out, err := h.module.Preview(r.Context(), valuer.MustNewUUID(claims.OrgID), &in)
if err != nil {
render.Error(rw, err)
return
}
render.Success(rw, http.StatusOK, out)
}
func (h *handler) Stats(rw http.ResponseWriter, r *http.Request) {
claims, err := authtypes.ClaimsFromContext(r.Context())
if err != nil {
render.Error(rw, err)
return
}
out, err := h.module.Stats(r.Context(), valuer.MustNewUUID(claims.OrgID))
if err != nil {
render.Error(rw, err)
return
}
render.Success(rw, http.StatusOK, out)
}
func (h *handler) Timeseries(rw http.ResponseWriter, r *http.Request) {
claims, err := authtypes.ClaimsFromContext(r.Context())
if err != nil {
render.Error(rw, err)
return
}
out, err := h.module.Timeseries(r.Context(), valuer.MustNewUUID(claims.OrgID))
if err != nil {
render.Error(rw, err)
return
}
render.Success(rw, http.StatusOK, out)
}
func (h *handler) Create(rw http.ResponseWriter, r *http.Request) {
claims, err := authtypes.ClaimsFromContext(r.Context())
if err != nil {
render.Error(rw, err)
return
}
var in metricreductionruletypes.PostableReductionRule
if err := binding.JSON.BindBody(r.Body, &in); err != nil {
render.Error(rw, err)
return
}
out, err := h.module.Create(r.Context(), valuer.MustNewUUID(claims.OrgID), claims.Email, &in)
if err != nil {
render.Error(rw, err)
return
}
render.Success(rw, http.StatusCreated, out)
}
func (h *handler) GetByID(rw http.ResponseWriter, r *http.Request) {
claims, err := authtypes.ClaimsFromContext(r.Context())
if err != nil {
render.Error(rw, err)
return
}
id, err := idFromPath(r)
if err != nil {
render.Error(rw, err)
return
}
out, err := h.module.GetByID(r.Context(), valuer.MustNewUUID(claims.OrgID), id)
if err != nil {
render.Error(rw, err)
return
}
render.Success(rw, http.StatusOK, out)
}
func (h *handler) UpdateByID(rw http.ResponseWriter, r *http.Request) {
claims, err := authtypes.ClaimsFromContext(r.Context())
if err != nil {
render.Error(rw, err)
return
}
id, err := idFromPath(r)
if err != nil {
render.Error(rw, err)
return
}
var in metricreductionruletypes.UpdatableReductionRule
if err := binding.JSON.BindBody(r.Body, &in); err != nil {
render.Error(rw, err)
return
}
out, err := h.module.UpdateByID(r.Context(), valuer.MustNewUUID(claims.OrgID), claims.Email, id, &in)
if err != nil {
render.Error(rw, err)
return
}
render.Success(rw, http.StatusOK, out)
}
func (h *handler) DeleteByID(rw http.ResponseWriter, r *http.Request) {
claims, err := authtypes.ClaimsFromContext(r.Context())
if err != nil {
render.Error(rw, err)
return
}
id, err := idFromPath(r)
if err != nil {
render.Error(rw, err)
return
}
if err := h.module.DeleteByID(r.Context(), valuer.MustNewUUID(claims.OrgID), id); err != nil {
render.Error(rw, err)
return
}
render.Success(rw, http.StatusNoContent, nil)
}

View File

@@ -1,52 +0,0 @@
package implmetricreductionrule
import (
"context"
"github.com/SigNoz/signoz/pkg/errors"
"github.com/SigNoz/signoz/pkg/modules/metricreductionrule"
"github.com/SigNoz/signoz/pkg/types/metricreductionruletypes"
"github.com/SigNoz/signoz/pkg/types/querybuildertypes/querybuildertypesv5"
"github.com/SigNoz/signoz/pkg/valuer"
)
type module struct{}
func NewModule() metricreductionrule.Module {
return &module{}
}
var errUnsupported = errors.New(errors.TypeUnsupported, metricreductionruletypes.ErrCodeMetricReductionRuleUnsupported,
"metric volume control is an enterprise feature")
func (m *module) List(_ context.Context, _ valuer.UUID, _ *metricreductionruletypes.ListReductionRulesParams) (*metricreductionruletypes.GettableReductionRules, error) {
return nil, errUnsupported
}
func (m *module) Create(_ context.Context, _ valuer.UUID, _ string, _ *metricreductionruletypes.PostableReductionRule) (*metricreductionruletypes.GettableReductionRule, error) {
return nil, errUnsupported
}
func (m *module) GetByID(_ context.Context, _ valuer.UUID, _ valuer.UUID) (*metricreductionruletypes.GettableReductionRule, error) {
return nil, errUnsupported
}
func (m *module) UpdateByID(_ context.Context, _ valuer.UUID, _ string, _ valuer.UUID, _ *metricreductionruletypes.UpdatableReductionRule) (*metricreductionruletypes.GettableReductionRule, error) {
return nil, errUnsupported
}
func (m *module) DeleteByID(_ context.Context, _ valuer.UUID, _ valuer.UUID) error {
return errUnsupported
}
func (m *module) Preview(_ context.Context, _ valuer.UUID, _ *metricreductionruletypes.PostableReductionRulePreview) (*metricreductionruletypes.GettableReductionRulePreview, error) {
return nil, errUnsupported
}
func (m *module) Stats(_ context.Context, _ valuer.UUID) (*metricreductionruletypes.GettableReductionRuleStats, error) {
return nil, errUnsupported
}
func (m *module) Timeseries(_ context.Context, _ valuer.UUID) (*querybuildertypesv5.QueryRangeResponse, error) {
return nil, errUnsupported
}

View File

@@ -1,32 +0,0 @@
package metricreductionrule
import (
"context"
"net/http"
"github.com/SigNoz/signoz/pkg/types/metricreductionruletypes"
"github.com/SigNoz/signoz/pkg/types/querybuildertypes/querybuildertypesv5"
"github.com/SigNoz/signoz/pkg/valuer"
)
type Module interface {
List(ctx context.Context, orgID valuer.UUID, params *metricreductionruletypes.ListReductionRulesParams) (*metricreductionruletypes.GettableReductionRules, error)
Create(ctx context.Context, orgID valuer.UUID, userEmail string, req *metricreductionruletypes.PostableReductionRule) (*metricreductionruletypes.GettableReductionRule, error)
GetByID(ctx context.Context, orgID valuer.UUID, id valuer.UUID) (*metricreductionruletypes.GettableReductionRule, error)
UpdateByID(ctx context.Context, orgID valuer.UUID, userEmail string, id valuer.UUID, req *metricreductionruletypes.UpdatableReductionRule) (*metricreductionruletypes.GettableReductionRule, error)
DeleteByID(ctx context.Context, orgID valuer.UUID, id valuer.UUID) error
Preview(ctx context.Context, orgID valuer.UUID, req *metricreductionruletypes.PostableReductionRulePreview) (*metricreductionruletypes.GettableReductionRulePreview, error)
Stats(ctx context.Context, orgID valuer.UUID) (*metricreductionruletypes.GettableReductionRuleStats, error)
Timeseries(ctx context.Context, orgID valuer.UUID) (*querybuildertypesv5.QueryRangeResponse, error)
}
type Handler interface {
List(rw http.ResponseWriter, r *http.Request)
Create(rw http.ResponseWriter, r *http.Request)
GetByID(rw http.ResponseWriter, r *http.Request)
UpdateByID(rw http.ResponseWriter, r *http.Request)
DeleteByID(rw http.ResponseWriter, r *http.Request)
Preview(rw http.ResponseWriter, r *http.Request)
Stats(rw http.ResponseWriter, r *http.Request)
Timeseries(rw http.ResponseWriter, r *http.Request)
}

View File

@@ -273,6 +273,35 @@ func (h *handler) DeleteMapper(rw http.ResponseWriter, r *http.Request) {
render.Success(rw, http.StatusNoContent, nil)
}
// TestMappers handles POST /api/v1/span_mapper_groups/test.
func (h *handler) TestMappers(rw http.ResponseWriter, r *http.Request) {
ctx, cancel := context.WithTimeout(r.Context(), 10*time.Second)
defer cancel()
claims, err := authtypes.ClaimsFromContext(ctx)
if err != nil {
render.Error(rw, err)
return
}
orgID := valuer.MustNewUUID(claims.OrgID)
req := new(spantypes.PostableSpanMapperTest)
if err := binding.JSON.BindBody(r.Body, req); err != nil {
render.Error(rw, err)
return
}
groups := spantypes.NewSpanMapperGroupsWithMappersFromPostable(orgID, req.Groups)
out, collectorLogs, err := h.module.TestMappers(ctx, orgID, req.Spans, groups)
if err != nil {
render.Error(rw, err)
return
}
render.Success(rw, http.StatusOK, &spantypes.GettableSpanMapperTest{Spans: out, CollectorLogs: collectorLogs})
}
// groupIDFromPath extracts and validates the {id} or {groupId} path variable.
func groupIDFromPath(r *http.Request) (valuer.UUID, error) {
vars := mux.Vars(r)

View File

@@ -4,19 +4,23 @@ import (
"context"
"encoding/json"
"github.com/SigNoz/signoz/pkg/errors"
"github.com/SigNoz/signoz/pkg/flagger"
"github.com/SigNoz/signoz/pkg/modules/spanmapper"
"github.com/SigNoz/signoz/pkg/query-service/agentConf"
"github.com/SigNoz/signoz/pkg/types/featuretypes"
"github.com/SigNoz/signoz/pkg/types/opamptypes"
"github.com/SigNoz/signoz/pkg/types/spantypes"
"github.com/SigNoz/signoz/pkg/valuer"
)
type module struct {
store spantypes.SpanMapperStore
store spantypes.SpanMapperStore
flagger flagger.Flagger
}
func NewModule(store spantypes.SpanMapperStore) spanmapper.Module {
return &module{store: store}
func NewModule(store spantypes.SpanMapperStore, flagger flagger.Flagger) spanmapper.Module {
return &module{store: store, flagger: flagger}
}
func (module *module) ListGroups(ctx context.Context, orgID valuer.UUID, q *spantypes.ListSpanMapperGroupsQuery) ([]*spantypes.SpanMapperGroup, error) {
@@ -102,6 +106,52 @@ func (module *module) DeleteMapper(ctx context.Context, orgID, groupID, id value
return nil
}
func (module *module) TestMappers(ctx context.Context, orgID valuer.UUID, spans []spantypes.SpanMapperTestSpan, groups []*spantypes.SpanMapperGroupWithMappers) ([]spantypes.SpanMapperTestSpan, []string, error) {
if len(spans) == 0 {
return nil, nil, errors.New(errors.TypeInvalidInput, spantypes.ErrCodeMappingInvalidInput, "'spans' must contain at least one span")
}
resolved, err := module.backfillMappers(ctx, orgID, groups)
if err != nil {
return nil, nil, err
}
out, collectorLogs, err := spantypes.SimulateSpanMappersProcessing(ctx, resolved, spans)
if err != nil {
return nil, nil, err
}
return out, collectorLogs, nil
}
// backfillMappers loads saved mappers for any group whose Mappers is nil.
func (module *module) backfillMappers(ctx context.Context, orgID valuer.UUID, groups []*spantypes.SpanMapperGroupWithMappers) ([]*spantypes.SpanMapperGroupWithMappers, error) {
savedGroups, err := module.store.ListGroups(ctx, orgID, nil)
if err != nil {
return nil, err
}
savedByName := make(map[string]*spantypes.SpanMapperGroup, len(savedGroups))
for _, g := range savedGroups {
savedByName[g.Name] = g
}
// For each group in the request, if Mappers is nil, load the saved mappers for that group name.
for _, g := range groups {
if g.Mappers != nil {
continue
}
saved, ok := savedByName[g.Group.Name]
if !ok {
return nil, errors.Newf(errors.TypeInvalidInput, spantypes.ErrCodeMappingGroupNotFound, "no saved group named %q to load mappers from; send 'mappers' for new or edited groups", g.Group.Name)
}
loaded, err := module.store.ListMappers(ctx, orgID, saved.ID)
if err != nil {
return nil, err
}
g.Mappers = loaded
}
return groups, nil
}
func (module *module) AgentFeatureType() agentConf.AgentFeatureType {
return spantypes.SpanAttrMappingFeatureType
}
@@ -109,12 +159,22 @@ func (module *module) AgentFeatureType() agentConf.AgentFeatureType {
func (module *module) RecommendAgentConfig(orgID valuer.UUID, currentConfYaml []byte, configVersion *opamptypes.AgentConfigVersion) ([]byte, string, error) {
ctx := context.Background()
enabled, err := module.listEnabledGroupsWithMappers(ctx, orgID)
// Skip the llm pricing processor unless AI observability is enabled for the org.
evalCtx := featuretypes.NewFlaggerEvaluationContext(orgID)
enabled, err := module.flagger.Boolean(ctx, flagger.FeatureEnableAIObservability, evalCtx)
if err != nil {
return nil, "", err
}
if !enabled {
return currentConfYaml, "", nil
}
enabledMappers, err := module.listEnabledGroupsWithMappers(ctx, orgID)
if err != nil {
return nil, "", err
}
updatedConf, err := spantypes.GenerateCollectorConfigWithSpanMapperProcessor(currentConfYaml, enabled)
updatedConf, err := spantypes.GenerateCollectorConfigWithSpanMapperProcessor(currentConfYaml, enabledMappers)
if err != nil {
return nil, "", err
}

View File

@@ -27,6 +27,7 @@ type Module interface {
CreateMapper(ctx context.Context, orgID, groupID valuer.UUID, mapper *spantypes.SpanMapper) error
UpdateMapper(ctx context.Context, orgID, groupID, id valuer.UUID, fieldContext spantypes.FieldContext, config *spantypes.SpanMapperConfig, enabled *bool, updatedBy string) error
DeleteMapper(ctx context.Context, orgID, groupID, id valuer.UUID) error
TestMappers(ctx context.Context, orgID valuer.UUID, spans []spantypes.SpanMapperTestSpan, groups []*spantypes.SpanMapperGroupWithMappers) ([]spantypes.SpanMapperTestSpan, []string, error)
}
// Handler defines the HTTP handler interface for mapping group and mapper endpoints.
@@ -42,4 +43,5 @@ type Handler interface {
CreateMapper(rw http.ResponseWriter, r *http.Request)
UpdateMapper(rw http.ResponseWriter, r *http.Request)
DeleteMapper(rw http.ResponseWriter, r *http.Request)
TestMappers(rw http.ResponseWriter, r *http.Request)
}

View File

@@ -113,6 +113,8 @@ func NewServer(config signoz.Config, signoz *signoz.SigNoz) (*Server, error) {
Store: signoz.SQLStore,
AgentFeatures: []agentConf.AgentFeature{
logParsingPipelineController,
signoz.Modules.SpanMapper,
signoz.Modules.LLMPricingRule,
},
},
)

View File

@@ -24,8 +24,6 @@ import (
"github.com/SigNoz/signoz/pkg/modules/inframonitoring/implinframonitoring"
"github.com/SigNoz/signoz/pkg/modules/llmpricingrule"
"github.com/SigNoz/signoz/pkg/modules/llmpricingrule/impllmpricingrule"
"github.com/SigNoz/signoz/pkg/modules/metricreductionrule"
"github.com/SigNoz/signoz/pkg/modules/metricreductionrule/implmetricreductionrule"
"github.com/SigNoz/signoz/pkg/modules/metricsexplorer"
"github.com/SigNoz/signoz/pkg/modules/metricsexplorer/implmetricsexplorer"
"github.com/SigNoz/signoz/pkg/modules/quickfilter"
@@ -66,7 +64,6 @@ type Handlers struct {
SpanPercentile spanpercentile.Handler
Services services.Handler
MetricsExplorer metricsexplorer.Handler
MetricReductionRule metricreductionrule.Handler
InfraMonitoring inframonitoring.Handler
Global global.Handler
FlaggerHandler flagger.Handler
@@ -113,7 +110,6 @@ func NewHandlers(
RawDataExport: implrawdataexport.NewHandler(modules.RawDataExport),
Services: implservices.NewHandler(modules.Services),
MetricsExplorer: implmetricsexplorer.NewHandler(modules.MetricsExplorer),
MetricReductionRule: implmetricreductionrule.NewHandler(modules.MetricReductionRule),
InfraMonitoring: implinframonitoring.NewHandler(modules.InfraMonitoring),
SpanPercentile: implspanpercentile.NewHandler(modules.SpanPercentile),
Global: signozglobal.NewHandler(global),

View File

@@ -59,7 +59,7 @@ func TestNewHandlers(t *testing.T) {
userGetter := impluser.NewGetter(impluser.NewStore(sqlstore, providerSettings), userRoleStore, flagger)
retentionGetter := implretention.NewGetter(implretention.NewStore(sqlstore))
modules := NewModules(sqlstore, tokenizer, emailing, providerSettings, orgGetter, alertmanager, nil, nil, nil, nil, nil, nil, nil, queryParser, Config{}, dashboardModule, userGetter, userRoleStore, nil, nil, retentionGetter, flagger, tagModule, nil)
modules := NewModules(sqlstore, tokenizer, emailing, providerSettings, orgGetter, alertmanager, nil, nil, nil, nil, nil, nil, nil, queryParser, Config{}, dashboardModule, userGetter, userRoleStore, nil, nil, retentionGetter, flagger, tagModule)
querierHandler := querier.NewHandler(providerSettings, nil, nil)
registryHandler := factory.NewHandler(nil)

View File

@@ -21,7 +21,6 @@ import (
"github.com/SigNoz/signoz/pkg/modules/llmpricingrule/impllmpricingrule"
"github.com/SigNoz/signoz/pkg/modules/logspipeline"
"github.com/SigNoz/signoz/pkg/modules/logspipeline/impllogspipeline"
"github.com/SigNoz/signoz/pkg/modules/metricreductionrule"
"github.com/SigNoz/signoz/pkg/modules/metricsexplorer"
"github.com/SigNoz/signoz/pkg/modules/metricsexplorer/implmetricsexplorer"
"github.com/SigNoz/signoz/pkg/modules/organization"
@@ -67,34 +66,33 @@ import (
)
type Modules struct {
OrgGetter organization.Getter
OrgSetter organization.Setter
Preference preference.Module
UserSetter user.Setter
UserGetter user.Getter
RetentionGetter retention.Getter
SavedView savedview.Module
Apdex apdex.Module
Dashboard dashboard.Module
QuickFilter quickfilter.Module
TraceFunnel tracefunnel.Module
RawDataExport rawdataexport.Module
AuthDomain authdomain.Module
Session session.Module
Services services.Module
SpanPercentile spanpercentile.Module
MetricsExplorer metricsexplorer.Module
MetricReductionRule metricreductionrule.Module
InfraMonitoring inframonitoring.Module
Promote promote.Module
ServiceAccount serviceaccount.Module
CloudIntegration cloudintegration.Module
LogsPipeline logspipeline.Module
RuleStateHistory rulestatehistory.Module
TraceDetail tracedetail.Module
SpanMapper spanmapper.Module
LLMPricingRule llmpricingrule.Module
Tag tag.Module
OrgGetter organization.Getter
OrgSetter organization.Setter
Preference preference.Module
UserSetter user.Setter
UserGetter user.Getter
RetentionGetter retention.Getter
SavedView savedview.Module
Apdex apdex.Module
Dashboard dashboard.Module
QuickFilter quickfilter.Module
TraceFunnel tracefunnel.Module
RawDataExport rawdataexport.Module
AuthDomain authdomain.Module
Session session.Module
Services services.Module
SpanPercentile spanpercentile.Module
MetricsExplorer metricsexplorer.Module
InfraMonitoring inframonitoring.Module
Promote promote.Module
ServiceAccount serviceaccount.Module
CloudIntegration cloudintegration.Module
LogsPipeline logspipeline.Module
RuleStateHistory rulestatehistory.Module
TraceDetail tracedetail.Module
SpanMapper spanmapper.Module
LLMPricingRule llmpricingrule.Module
Tag tag.Module
}
func NewModules(
@@ -121,7 +119,6 @@ func NewModules(
retentionGetter retention.Getter,
fl flagger.Flagger,
tagModule tag.Module,
metricReductionRule metricreductionrule.Module,
) Modules {
quickfilter := implquickfilter.NewModule(implquickfilter.NewStore(sqlstore))
orgSetter := implorganization.NewSetter(implorganization.NewStore(sqlstore), alertmanager, quickfilter)
@@ -133,33 +130,32 @@ func NewModules(
ruleStore := sqlrulestore.NewRuleStore(sqlstore, queryParser, providerSettings)
return Modules{
OrgGetter: orgGetter,
OrgSetter: orgSetter,
Preference: implpreference.NewModule(implpreference.NewStore(sqlstore), preferencetypes.NewAvailablePreference()),
SavedView: implsavedview.NewModule(sqlstore),
Apdex: implapdex.NewModule(sqlstore),
Dashboard: dashboard,
UserSetter: userSetter,
UserGetter: userGetter,
RetentionGetter: retentionGetter,
QuickFilter: quickfilter,
TraceFunnel: impltracefunnel.NewModule(impltracefunnel.NewStore(sqlstore)),
RawDataExport: implrawdataexport.NewModule(querier),
AuthDomain: implauthdomain.NewModule(implauthdomain.NewStore(sqlstore), authNs),
Session: implsession.NewModule(providerSettings, authNs, userSetter, userGetter, implauthdomain.NewModule(implauthdomain.NewStore(sqlstore), authNs), tokenizer, orgGetter),
SpanPercentile: implspanpercentile.NewModule(querier, providerSettings),
Services: implservices.NewModule(querier, telemetryStore),
MetricsExplorer: implmetricsexplorer.NewModule(telemetryStore, telemetryMetadataStore, cache, ruleStore, dashboard, providerSettings, config.MetricsExplorer),
MetricReductionRule: metricReductionRule,
InfraMonitoring: implinframonitoring.NewModule(telemetryStore, telemetryMetadataStore, querier, providerSettings, config.InfraMonitoring),
Promote: implpromote.NewModule(telemetryMetadataStore, telemetryStore),
ServiceAccount: serviceAccount,
LogsPipeline: impllogspipeline.NewModule(sqlstore),
RuleStateHistory: implrulestatehistory.NewModule(implrulestatehistory.NewStore(telemetryStore, telemetryMetadataStore, providerSettings.Logger)),
CloudIntegration: cloudIntegrationModule,
TraceDetail: impltracedetail.NewModule(impltracedetail.NewTraceStore(telemetryStore), providerSettings, config.TraceDetail),
SpanMapper: implspanmapper.NewModule(implspanmapper.NewStore(sqlstore)),
LLMPricingRule: impllmpricingrule.NewModule(impllmpricingrule.NewStore(sqlstore)),
Tag: tagModule,
OrgGetter: orgGetter,
OrgSetter: orgSetter,
Preference: implpreference.NewModule(implpreference.NewStore(sqlstore), preferencetypes.NewAvailablePreference()),
SavedView: implsavedview.NewModule(sqlstore),
Apdex: implapdex.NewModule(sqlstore),
Dashboard: dashboard,
UserSetter: userSetter,
UserGetter: userGetter,
RetentionGetter: retentionGetter,
QuickFilter: quickfilter,
TraceFunnel: impltracefunnel.NewModule(impltracefunnel.NewStore(sqlstore)),
RawDataExport: implrawdataexport.NewModule(querier),
AuthDomain: implauthdomain.NewModule(implauthdomain.NewStore(sqlstore), authNs),
Session: implsession.NewModule(providerSettings, authNs, userSetter, userGetter, implauthdomain.NewModule(implauthdomain.NewStore(sqlstore), authNs), tokenizer, orgGetter),
SpanPercentile: implspanpercentile.NewModule(querier, providerSettings),
Services: implservices.NewModule(querier, telemetryStore),
MetricsExplorer: implmetricsexplorer.NewModule(telemetryStore, telemetryMetadataStore, cache, ruleStore, dashboard, providerSettings, config.MetricsExplorer),
InfraMonitoring: implinframonitoring.NewModule(telemetryStore, telemetryMetadataStore, querier, providerSettings, config.InfraMonitoring),
Promote: implpromote.NewModule(telemetryMetadataStore, telemetryStore),
ServiceAccount: serviceAccount,
LogsPipeline: impllogspipeline.NewModule(sqlstore),
RuleStateHistory: implrulestatehistory.NewModule(implrulestatehistory.NewStore(telemetryStore, telemetryMetadataStore, providerSettings.Logger)),
CloudIntegration: cloudIntegrationModule,
TraceDetail: impltracedetail.NewModule(impltracedetail.NewTraceStore(telemetryStore), providerSettings, config.TraceDetail),
SpanMapper: implspanmapper.NewModule(implspanmapper.NewStore(sqlstore), fl),
LLMPricingRule: impllmpricingrule.NewModule(impllmpricingrule.NewStore(sqlstore), fl),
Tag: tagModule,
}
}

View File

@@ -16,7 +16,6 @@ import (
"github.com/SigNoz/signoz/pkg/instrumentation/instrumentationtest"
"github.com/SigNoz/signoz/pkg/modules/cloudintegration/implcloudintegration"
"github.com/SigNoz/signoz/pkg/modules/dashboard/impldashboard"
"github.com/SigNoz/signoz/pkg/modules/metricreductionrule/implmetricreductionrule"
"github.com/SigNoz/signoz/pkg/modules/organization/implorganization"
"github.com/SigNoz/signoz/pkg/modules/retention/implretention"
"github.com/SigNoz/signoz/pkg/modules/serviceaccount"
@@ -64,7 +63,7 @@ func TestNewModules(t *testing.T) {
retentionGetter := implretention.NewGetter(implretention.NewStore(sqlstore))
modules := NewModules(sqlstore, tokenizer, emailing, providerSettings, orgGetter, alertmanager, nil, nil, nil, nil, nil, nil, nil, queryParser, Config{}, dashboardModule, userGetter, userRoleStore, serviceAccount, implcloudintegration.NewModule(), retentionGetter, flagger, tagModule, implmetricreductionrule.NewModule())
modules := NewModules(sqlstore, tokenizer, emailing, providerSettings, orgGetter, alertmanager, nil, nil, nil, nil, nil, nil, nil, queryParser, Config{}, dashboardModule, userGetter, userRoleStore, serviceAccount, implcloudintegration.NewModule(), retentionGetter, flagger, tagModule)
reflectVal := reflect.ValueOf(modules)
for i := 0; i < reflectVal.NumField(); i++ {

View File

@@ -23,7 +23,6 @@ import (
"github.com/SigNoz/signoz/pkg/modules/fields"
"github.com/SigNoz/signoz/pkg/modules/inframonitoring"
"github.com/SigNoz/signoz/pkg/modules/llmpricingrule"
"github.com/SigNoz/signoz/pkg/modules/metricreductionrule"
"github.com/SigNoz/signoz/pkg/modules/metricsexplorer"
"github.com/SigNoz/signoz/pkg/modules/organization"
"github.com/SigNoz/signoz/pkg/modules/preference"
@@ -69,7 +68,6 @@ func NewOpenAPI(ctx context.Context, instrumentation instrumentation.Instrumenta
struct{ dashboard.Module }{},
struct{ dashboard.Handler }{},
struct{ metricsexplorer.Handler }{},
struct{ metricreductionrule.Handler }{},
struct{ inframonitoring.Handler }{},
struct{ gateway.Handler }{},
struct{ fields.Handler }{},

View File

@@ -215,7 +215,6 @@ func NewSQLMigrationProviderFactories(
sqlmigration.NewRecreateUserDashboardPreferenceFactory(sqlstore, sqlschema),
sqlmigration.NewMigrateRecurrenceBoundsFactory(sqlstore),
sqlmigration.NewAddDashboardViewFactory(sqlstore, sqlschema),
sqlmigration.NewAddMetricReductionRulesFactory(sqlstore, sqlschema),
)
}
@@ -296,7 +295,6 @@ func NewAPIServerProviderFactories(orgGetter organization.Getter, authz authz.Au
modules.Dashboard,
handlers.Dashboard,
handlers.MetricsExplorer,
handlers.MetricReductionRule,
handlers.InfraMonitoring,
handlers.GatewayHandler,
handlers.Fields,

View File

@@ -26,7 +26,6 @@ import (
"github.com/SigNoz/signoz/pkg/meterreporter"
"github.com/SigNoz/signoz/pkg/modules/cloudintegration"
"github.com/SigNoz/signoz/pkg/modules/dashboard"
"github.com/SigNoz/signoz/pkg/modules/metricreductionrule"
"github.com/SigNoz/signoz/pkg/modules/organization"
"github.com/SigNoz/signoz/pkg/modules/organization/implorganization"
"github.com/SigNoz/signoz/pkg/modules/retention"
@@ -115,7 +114,6 @@ func New(
meterReporterProviderFactories func(context.Context, factory.ProviderSettings, flagger.Flagger, licensing.Licensing, telemetrystore.TelemetryStore, retention.Getter, organization.Getter, zeus.Zeus) (factory.NamedMap[factory.ProviderFactory[meterreporter.Reporter, meterreporter.Config]], string),
querierHandlerCallback func(factory.ProviderSettings, querier.Querier, analytics.Analytics) querier.Handler,
cloudIntegrationCallback func(sqlstore.SQLStore, dashboard.Module, global.Global, zeus.Zeus, gateway.Gateway, licensing.Licensing, serviceaccount.Module, cloudintegration.Config) (cloudintegration.Module, error),
metricReductionRuleModuleCallback func(sqlstore.SQLStore, telemetrystore.TelemetryStore, dashboard.Module, queryparser.QueryParser, licensing.Licensing, flagger.Flagger, telemetrytypes.MetadataStore, factory.ProviderSettings, int) metricreductionrule.Module,
rulerProviderFactories func(cache.Cache, alertmanager.Alertmanager, sqlstore.SQLStore, telemetrystore.TelemetryStore, telemetrytypes.MetadataStore, prometheus.Prometheus, organization.Getter, rulestatehistory.Module, querier.Querier, queryparser.QueryParser) factory.NamedMap[factory.ProviderFactory[ruler.Ruler, ruler.Config]],
) (*SigNoz, error) {
// Initialize instrumentation
@@ -466,10 +464,8 @@ func New(
return nil, err
}
metricReductionRuleModule := metricReductionRuleModuleCallback(sqlstore, telemetrystore, dashboard, queryParser, licensing, flagger, telemetryMetadataStore, providerSettings, config.MetricsExplorer.TelemetryStore.Threads)
// Initialize all modules
modules := NewModules(sqlstore, tokenizer, emailing, providerSettings, orgGetter, alertmanager, analytics, querier, telemetrystore, telemetryMetadataStore, authNs, authz, cache, queryParser, config, dashboard, userGetter, userRoleStore, serviceAccount, cloudIntegrationModule, retentionGetter, flagger, tagModule, metricReductionRuleModule)
modules := NewModules(sqlstore, tokenizer, emailing, providerSettings, orgGetter, alertmanager, analytics, querier, telemetrystore, telemetryMetadataStore, authNs, authz, cache, queryParser, config, dashboard, userGetter, userRoleStore, serviceAccount, cloudIntegrationModule, retentionGetter, flagger, tagModule)
// Initialize ruler from the variant-specific provider factories
rulerInstance, err := factory.NewProviderFromNamedMap(ctx, providerSettings, config.Ruler, rulerProviderFactories(cache, alertmanager, sqlstore, telemetrystore, telemetryMetadataStore, prometheus, orgGetter, modules.RuleStateHistory, querier, queryParser), "signoz")

View File

@@ -1,90 +0,0 @@
package sqlmigration
import (
"context"
"github.com/SigNoz/signoz/pkg/factory"
"github.com/SigNoz/signoz/pkg/sqlschema"
"github.com/SigNoz/signoz/pkg/sqlstore"
"github.com/uptrace/bun"
"github.com/uptrace/bun/migrate"
)
type addMetricReductionRules struct {
sqlschema sqlschema.SQLSchema
sqlstore sqlstore.SQLStore
}
func NewAddMetricReductionRulesFactory(sqlstore sqlstore.SQLStore, sqlschema sqlschema.SQLSchema) factory.ProviderFactory[SQLMigration, Config] {
return factory.NewProviderFactory(factory.MustNewName("add_metric_reduction_rule"), func(_ context.Context, _ factory.ProviderSettings, _ Config) (SQLMigration, error) {
return &addMetricReductionRules{
sqlschema: sqlschema,
sqlstore: sqlstore,
}, nil
})
}
func (migration *addMetricReductionRules) Register(migrations *migrate.Migrations) error {
if err := migrations.Register(migration.Up, migration.Down); err != nil {
return err
}
return nil
}
func (migration *addMetricReductionRules) Up(ctx context.Context, db *bun.DB) error {
tx, err := db.BeginTx(ctx, nil)
if err != nil {
return err
}
defer func() {
_ = tx.Rollback()
}()
sqls := [][]byte{}
tableSQLs := migration.sqlschema.Operator().CreateTable(&sqlschema.Table{
Name: "metric_reduction_rule",
Columns: []*sqlschema.Column{
{Name: "id", DataType: sqlschema.DataTypeText, Nullable: false},
{Name: "org_id", DataType: sqlschema.DataTypeText, Nullable: false},
{Name: "metric_name", DataType: sqlschema.DataTypeText, Nullable: false},
{Name: "match_type", DataType: sqlschema.DataTypeText, Nullable: false},
{Name: "labels", DataType: sqlschema.DataTypeText, Nullable: false, Default: "'[]'"},
{Name: "effective_from", DataType: sqlschema.DataTypeTimestamp, Nullable: false},
{Name: "created_at", DataType: sqlschema.DataTypeTimestamp, Nullable: false},
{Name: "updated_at", DataType: sqlschema.DataTypeTimestamp, Nullable: false},
{Name: "created_by", DataType: sqlschema.DataTypeText, Nullable: false},
{Name: "updated_by", DataType: sqlschema.DataTypeText, Nullable: false},
},
PrimaryKeyConstraint: &sqlschema.PrimaryKeyConstraint{
ColumnNames: []sqlschema.ColumnName{"id"},
},
ForeignKeyConstraints: []*sqlschema.ForeignKeyConstraint{
{
ReferencingColumnName: sqlschema.ColumnName("org_id"),
ReferencedTableName: sqlschema.TableName("organizations"),
ReferencedColumnName: sqlschema.ColumnName("id"),
},
},
})
sqls = append(sqls, tableSQLs...)
indexSQLs := migration.sqlschema.Operator().CreateIndex(&sqlschema.UniqueIndex{
TableName: "metric_reduction_rule",
ColumnNames: []sqlschema.ColumnName{"org_id", "metric_name"},
})
sqls = append(sqls, indexSQLs...)
for _, sql := range sqls {
if _, err := tx.ExecContext(ctx, string(sql)); err != nil {
return err
}
}
return tx.Commit()
}
func (migration *addMetricReductionRules) Down(context.Context, *bun.DB) error {
return nil
}

View File

@@ -41,8 +41,6 @@ const (
SamplesV4ReducedSumTableName = "distributed_samples_v4_reduced_sum_60s"
TimeseriesV4ReducedTableName = "distributed_time_series_v4_reduced"
TimeseriesV4ReducedLocalTableName = "time_series_v4_reduced"
ReductionRulesTableName = "distributed_metric_reduction_rules"
)
var (

View File

@@ -12,7 +12,6 @@ type Clusters struct {
Type ResponseType `json:"type" required:"true"`
Records []ClusterRecord `json:"records" required:"true" nullable:"false"`
Total int `json:"total" required:"true"`
RequiredMetricsCheck RequiredMetricsCheck `json:"requiredMetricsCheck" required:"true"`
EndTimeBeforeRetention bool `json:"endTimeBeforeRetention" required:"true"`
Warning *qbtypes.QueryWarnData `json:"warning,omitempty"`
}

View File

@@ -12,7 +12,6 @@ type DaemonSets struct {
Type ResponseType `json:"type" required:"true"`
Records []DaemonSetRecord `json:"records" required:"true" nullable:"false"`
Total int `json:"total" required:"true"`
RequiredMetricsCheck RequiredMetricsCheck `json:"requiredMetricsCheck" required:"true"`
EndTimeBeforeRetention bool `json:"endTimeBeforeRetention" required:"true"`
Warning *qbtypes.QueryWarnData `json:"warning,omitempty"`
}

View File

@@ -12,7 +12,6 @@ type Deployments struct {
Type ResponseType `json:"type" required:"true"`
Records []DeploymentRecord `json:"records" required:"true" nullable:"false"`
Total int `json:"total" required:"true"`
RequiredMetricsCheck RequiredMetricsCheck `json:"requiredMetricsCheck" required:"true"`
EndTimeBeforeRetention bool `json:"endTimeBeforeRetention" required:"true"`
Warning *qbtypes.QueryWarnData `json:"warning,omitempty"`
}

View File

@@ -12,7 +12,6 @@ type Hosts struct {
Type ResponseType `json:"type" required:"true"`
Records []HostRecord `json:"records" required:"true" nullable:"false"`
Total int `json:"total" required:"true"`
RequiredMetricsCheck RequiredMetricsCheck `json:"requiredMetricsCheck" required:"true"`
EndTimeBeforeRetention bool `json:"endTimeBeforeRetention" required:"true"`
Warning *qbtypes.QueryWarnData `json:"warning,omitempty"`
}
@@ -30,10 +29,6 @@ type HostRecord struct {
Meta map[string]string `json:"meta" required:"true"`
}
type RequiredMetricsCheck struct {
MissingMetrics []string `json:"missingMetrics" required:"true"`
}
type PostableHosts struct {
Start int64 `json:"start" required:"true"`
End int64 `json:"end" required:"true"`

View File

@@ -12,7 +12,6 @@ type Jobs struct {
Type ResponseType `json:"type" required:"true"`
Records []JobRecord `json:"records" required:"true" nullable:"false"`
Total int `json:"total" required:"true"`
RequiredMetricsCheck RequiredMetricsCheck `json:"requiredMetricsCheck" required:"true"`
EndTimeBeforeRetention bool `json:"endTimeBeforeRetention" required:"true"`
Warning *qbtypes.QueryWarnData `json:"warning,omitempty"`
}

View File

@@ -12,7 +12,6 @@ type Namespaces struct {
Type ResponseType `json:"type" required:"true"`
Records []NamespaceRecord `json:"records" required:"true" nullable:"false"`
Total int `json:"total" required:"true"`
RequiredMetricsCheck RequiredMetricsCheck `json:"requiredMetricsCheck" required:"true"`
EndTimeBeforeRetention bool `json:"endTimeBeforeRetention" required:"true"`
Warning *qbtypes.QueryWarnData `json:"warning,omitempty"`
}

View File

@@ -12,7 +12,6 @@ type Nodes struct {
Type ResponseType `json:"type" required:"true"`
Records []NodeRecord `json:"records" required:"true" nullable:"false"`
Total int `json:"total" required:"true"`
RequiredMetricsCheck RequiredMetricsCheck `json:"requiredMetricsCheck" required:"true"`
EndTimeBeforeRetention bool `json:"endTimeBeforeRetention" required:"true"`
Warning *qbtypes.QueryWarnData `json:"warning,omitempty"`
}

View File

@@ -12,7 +12,6 @@ type Pods struct {
Type ResponseType `json:"type" required:"true"`
Records []PodRecord `json:"records" required:"true" nullable:"false"`
Total int `json:"total" required:"true"`
RequiredMetricsCheck RequiredMetricsCheck `json:"requiredMetricsCheck" required:"true"`
EndTimeBeforeRetention bool `json:"endTimeBeforeRetention" required:"true"`
Warning *qbtypes.QueryWarnData `json:"warning,omitempty"`
}

View File

@@ -12,7 +12,6 @@ type StatefulSets struct {
Type ResponseType `json:"type" required:"true"`
Records []StatefulSetRecord `json:"records" required:"true" nullable:"false"`
Total int `json:"total" required:"true"`
RequiredMetricsCheck RequiredMetricsCheck `json:"requiredMetricsCheck" required:"true"`
EndTimeBeforeRetention bool `json:"endTimeBeforeRetention" required:"true"`
Warning *qbtypes.QueryWarnData `json:"warning,omitempty"`
}

View File

@@ -12,7 +12,6 @@ type Volumes struct {
Type ResponseType `json:"type" required:"true"`
Records []VolumeRecord `json:"records" required:"true" nullable:"false"`
Total int `json:"total" required:"true"`
RequiredMetricsCheck RequiredMetricsCheck `json:"requiredMetricsCheck" required:"true"`
EndTimeBeforeRetention bool `json:"endTimeBeforeRetention" required:"true"`
Warning *qbtypes.QueryWarnData `json:"warning,omitempty"`
}

View File

@@ -53,7 +53,8 @@ var (
LLMPricingRuleCacheModeSubtract = LLMPricingRuleCacheMode{valuer.NewString("subtract")}
// LLMPricingRuleCacheModeAdditive: cached tokens are reported separately (Anthropic-style).
LLMPricingRuleCacheModeAdditive = LLMPricingRuleCacheMode{valuer.NewString("additive")}
// LLMPricingRuleCacheModeUnknown: provider behaviour is unknown; falls back to subtract.
// LLMPricingRuleCacheModeUnknown: provider behaviour is unknown. buildProcessorConfig
// normalizes this to an empty mode in the collector config.
LLMPricingRuleCacheModeUnknown = LLMPricingRuleCacheMode{valuer.NewString("unknown")}
)

View File

@@ -26,24 +26,23 @@ type LLMPricingRuleProcessorAttrs struct {
CacheWrite string `yaml:"cache_write" json:"cache_write"`
}
// LLMPricingRuleProcessorDefaultPricing holds the pricing unit and the list of model-specific rules.
// LLMPricingRuleProcessorDefaultPricing holds the list of model-specific rules.
type LLMPricingRuleProcessorDefaultPricing struct {
Unit string `yaml:"unit" json:"unit"`
Rules []LLMPricingRuleProcessor `yaml:"rules" json:"rules"`
}
// LLMPricingRuleProcessor is a single pricing rule inside the processor config.
type LLMPricingRuleProcessor struct {
Name string `yaml:"name" json:"name"`
Pattern []string `yaml:"pattern" json:"pattern"`
Cache LLMPricingRuleProcessorCache `yaml:"cache" json:"cache"`
In float64 `yaml:"in" json:"in"`
Out float64 `yaml:"out" json:"out"`
Name string `yaml:"name" json:"name"`
Pattern []string `yaml:"pattern" json:"pattern"`
Cache *LLMPricingRuleProcessorCache `yaml:"cache,omitempty" json:"cache,omitempty"`
In float64 `yaml:"in" json:"in"`
Out float64 `yaml:"out" json:"out"`
}
// LLMPricingRuleProcessorCache describes how cached tokens are accounted for.
type LLMPricingRuleProcessorCache struct {
Mode string `yaml:"mode" json:"mode"`
Mode string `yaml:"mode,omitempty" json:"mode,omitempty"`
Read float64 `yaml:"read" json:"read"`
Write float64 `yaml:"write" json:"write"`
}
@@ -61,10 +60,14 @@ type LLMPricingRuleProcessorOutputAttrs struct {
func buildProcessorConfig(rules []*LLMPricingRule) *LLMPricingRuleProcessorConfig {
pricingRules := make([]LLMPricingRuleProcessor, 0, len(rules))
for _, r := range rules {
var cache LLMPricingRuleProcessorCache
var cache *LLMPricingRuleProcessorCache
if r.Pricing.Cache != nil {
cache = LLMPricingRuleProcessorCache{
Mode: r.Pricing.Cache.Mode.StringValue(),
mode := r.Pricing.Cache.Mode.StringValue()
if mode != LLMPricingRuleCacheModeSubtract.StringValue() && mode != LLMPricingRuleCacheModeAdditive.StringValue() {
mode = ""
}
cache = &LLMPricingRuleProcessorCache{
Mode: mode,
Read: r.Pricing.Cache.Read,
Write: r.Pricing.Cache.Write,
}
@@ -87,7 +90,6 @@ func buildProcessorConfig(rules []*LLMPricingRule) *LLMPricingRuleProcessorConfi
CacheWrite: GenAIUsageCacheCreationInputTokens,
},
DefaultPricing: LLMPricingRuleProcessorDefaultPricing{
Unit: UnitPerMillionTokens.StringValue(),
Rules: pricingRules,
},
OutputAttrs: LLMPricingRuleProcessorOutputAttrs{

View File

@@ -41,6 +41,16 @@ func makePricingRule(model string, patterns []string, cacheMode LLMPricingRuleCa
}
}
func makePricingRuleNoCache(model string, patterns []string, costIn, costOut float64) *LLMPricingRule {
return &LLMPricingRule{
Model: model,
ModelPattern: StringSlice(patterns),
Unit: UnitPerMillionTokens,
Pricing: LLMRulePricing{Input: costIn, Output: costOut},
Enabled: true,
}
}
func TestGenerateCollectorConfigWithLLMPricingProcessor(t *testing.T) {
tests := []struct {
name string
@@ -62,6 +72,24 @@ func TestGenerateCollectorConfigWithLLMPricingProcessor(t *testing.T) {
rules: nil,
expectedFile: "collector_no_rules.yaml",
},
// A rule without cache pricing omits the cache block entirely so the
// collector does not apply any cache cost.
{
name: "rule_without_cache",
rules: []*LLMPricingRule{
makePricingRuleNoCache("gpt-4o", []string{"gpt-4o*"}, 5.0, 15.0),
},
expectedFile: "collector_rule_without_cache.yaml",
},
// An unknown cache mode still emits the cache block (with prices) but omits
// the mode field; the collector handles a missing mode in its default branch.
{
name: "rule_cache_mode_unknown",
rules: []*LLMPricingRule{
makePricingRule("gpt-4o", []string{"gpt-4o*"}, LLMPricingRuleCacheModeUnknown, 5.0, 15.0, 2.5, 0),
},
expectedFile: "collector_rule_cache_mode_unknown.yaml",
},
}
input, err := os.ReadFile(filepath.Join("testdata", "collector_baseline.yaml"))

View File

@@ -11,7 +11,6 @@ processors:
cache_read: gen_ai.usage.cache_read.input_tokens
cache_write: gen_ai.usage.cache_creation.input_tokens
default_pricing:
unit: per_million_tokens
rules: []
output_attrs:
in: _signoz.gen_ai.cost_input

View File

@@ -11,7 +11,6 @@ processors:
cache_read: gen_ai.usage.cache_read.input_tokens
cache_write: gen_ai.usage.cache_creation.input_tokens
default_pricing:
unit: per_million_tokens
rules: []
output_attrs:
in: _signoz.gen_ai.cost_input

View File

@@ -0,0 +1,42 @@
exporters:
otlp:
endpoint: localhost:4317
processors:
batch: {}
signozllmpricing:
attrs:
model: gen_ai.request.model
in: gen_ai.usage.input_tokens
out: gen_ai.usage.output_tokens
cache_read: gen_ai.usage.cache_read.input_tokens
cache_write: gen_ai.usage.cache_creation.input_tokens
default_pricing:
rules:
- name: gpt-4o
pattern:
- gpt-4o*
cache:
read: 2.5
write: 0
in: 5
out: 15
output_attrs:
in: _signoz.gen_ai.cost_input
out: _signoz.gen_ai.cost_output
cache_read: _signoz.gen_ai.cost_cache_read
cache_write: _signoz.gen_ai.cost_cache_write
total: _signoz.gen_ai.total_cost
receivers:
otlp:
protocols:
grpc: null
service:
pipelines:
traces:
exporters:
- otlp
processors:
- batch
- signozllmpricing
receivers:
- otlp

View File

@@ -0,0 +1,39 @@
exporters:
otlp:
endpoint: localhost:4317
processors:
batch: {}
signozllmpricing:
attrs:
model: gen_ai.request.model
in: gen_ai.usage.input_tokens
out: gen_ai.usage.output_tokens
cache_read: gen_ai.usage.cache_read.input_tokens
cache_write: gen_ai.usage.cache_creation.input_tokens
default_pricing:
rules:
- name: gpt-4o
pattern:
- gpt-4o*
in: 5
out: 15
output_attrs:
in: _signoz.gen_ai.cost_input
out: _signoz.gen_ai.cost_output
cache_read: _signoz.gen_ai.cost_cache_read
cache_write: _signoz.gen_ai.cost_cache_write
total: _signoz.gen_ai.total_cost
receivers:
otlp:
protocols:
grpc: null
service:
pipelines:
traces:
exporters:
- otlp
processors:
- batch
- signozllmpricing
receivers:
- otlp

View File

@@ -11,7 +11,6 @@ processors:
cache_read: gen_ai.usage.cache_read.input_tokens
cache_write: gen_ai.usage.cache_creation.input_tokens
default_pricing:
unit: per_million_tokens
rules:
- name: gpt-4o
pattern:

View File

@@ -1,59 +0,0 @@
package metricreductionruletypes
import (
"github.com/SigNoz/signoz/pkg/errors"
"github.com/SigNoz/signoz/pkg/valuer"
)
type Order struct {
valuer.String
}
var (
OrderAsc = Order{valuer.NewString("asc")}
OrderDesc = Order{valuer.NewString("desc")}
)
func (Order) Enum() []any {
return []any{OrderAsc, OrderDesc}
}
type ReductionRuleOrderBy struct {
valuer.String
}
var (
OrderByMetricName = ReductionRuleOrderBy{valuer.NewString("metric")}
OrderByIngestedVolume = ReductionRuleOrderBy{valuer.NewString("ingested_volume")}
OrderByReducedVolume = ReductionRuleOrderBy{valuer.NewString("reduced_volume")}
OrderByReduction = ReductionRuleOrderBy{valuer.NewString("reduction")}
OrderByLastUpdated = ReductionRuleOrderBy{valuer.NewString("last_updated")}
)
func (ReductionRuleOrderBy) Enum() []any {
return []any{OrderByMetricName, OrderByIngestedVolume, OrderByReducedVolume, OrderByReduction, OrderByLastUpdated}
}
type ListReductionRulesParams struct {
OrderBy ReductionRuleOrderBy `query:"orderBy,default=reduction" json:"orderBy"`
Order Order `query:"order,default=desc" json:"order"`
Search string `query:"search" json:"search"`
MetricName string `query:"metricName" json:"metricName,omitempty"`
Offset int `query:"offset" json:"offset"`
Limit int `query:"limit,default=10" json:"limit"`
}
const maxReductionRulesPageSize = 1000
func (p *ListReductionRulesParams) Validate() error {
if p.Limit <= 0 {
return errors.NewInvalidInputf(errors.CodeInvalidInput, "limit must be greater than 0")
}
if p.Limit > maxReductionRulesPageSize {
return errors.NewInvalidInputf(errors.CodeInvalidInput, "limit must not exceed %d", maxReductionRulesPageSize)
}
if p.Offset < 0 {
return errors.NewInvalidInputf(errors.CodeInvalidInput, "offset must not be negative")
}
return nil
}

View File

@@ -1,24 +0,0 @@
package metricreductionruletypes_test
import (
"testing"
"github.com/SigNoz/signoz/pkg/http/binding"
"github.com/SigNoz/signoz/pkg/types/metricreductionruletypes"
"github.com/stretchr/testify/assert"
"github.com/stretchr/testify/require"
)
func TestListReductionRulesParamsSortDefaults(t *testing.T) {
var params metricreductionruletypes.ListReductionRulesParams
require.NoError(t, binding.Query.BindQuery(map[string][]string{"limit": {"10"}}, &params))
assert.Equal(t, metricreductionruletypes.OrderByReduction, params.OrderBy, "orderBy defaults to reduction")
assert.Equal(t, metricreductionruletypes.OrderDesc, params.Order, "order defaults to desc")
}
func TestListReductionRulesParamsValidate(t *testing.T) {
require.Error(t, (&metricreductionruletypes.ListReductionRulesParams{Limit: 0}).Validate(), "limit must be set")
require.Error(t, (&metricreductionruletypes.ListReductionRulesParams{Limit: 10, Offset: -1}).Validate(), "offset must not be negative")
require.NoError(t, (&metricreductionruletypes.ListReductionRulesParams{Limit: 10}).Validate())
}

View File

@@ -1,68 +0,0 @@
package metricreductionruletypes
import (
"time"
"github.com/SigNoz/signoz/pkg/errors"
"github.com/SigNoz/signoz/pkg/valuer"
)
type AssetType struct {
valuer.String
}
var (
AssetTypeDashboard = AssetType{valuer.NewString("dashboard")}
AssetTypeAlert = AssetType{valuer.NewString("alert_rule")}
)
func (AssetType) Enum() []any {
return []any{AssetTypeDashboard, AssetTypeAlert}
}
type PostableReductionRulePreview struct {
MetricName string `json:"metricName" required:"true"`
MatchType MatchType `json:"matchType" required:"true"`
Labels []string `json:"labels" required:"true" nullable:"true"`
LookbackMs int64 `json:"lookbackMs,omitempty"`
}
func (req *PostableReductionRulePreview) Validate() error {
if req == nil {
return errors.NewInvalidInputf(errors.CodeInvalidInput, "request is nil")
}
if req.MetricName == "" {
return errors.NewInvalidInputf(errors.CodeInvalidInput, "metricName is required")
}
if req.MatchType != MatchTypeDrop && req.MatchType != MatchTypeKeep {
return errors.NewInvalidInputf(errors.CodeInvalidInput,
"matchType must be one of %q or %q", MatchTypeDrop.StringValue(), MatchTypeKeep.StringValue())
}
if len(req.Labels) == 0 {
return errors.NewInvalidInputf(errors.CodeInvalidInput, "labels must not be empty")
}
return nil
}
type AffectedWidget struct {
ID string `json:"id" required:"true"`
Name string `json:"name" required:"true"`
}
type AffectedAsset struct {
Type AssetType `json:"type" required:"true"`
ID string `json:"id" required:"true"`
Name string `json:"name" required:"true"`
Widget *AffectedWidget `json:"widget,omitempty"`
ImpactedLabels []string `json:"impactedLabels" required:"true" nullable:"true"`
}
type GettableReductionRulePreview struct {
IngestedSeries uint64 `json:"ingestedSeries" required:"true"`
CurrentRetainedSeries uint64 `json:"currentRetainedSeries" required:"true"`
RetainedSeries uint64 `json:"retainedSeries" required:"true"`
ReductionPercent float64 `json:"reductionPercent" required:"true"`
DroppedLabels []string `json:"droppedLabels" required:"true" nullable:"true"`
AffectedAssets []AffectedAsset `json:"affectedAssets" required:"true" nullable:"true"`
EffectiveFrom time.Time `json:"effectiveFrom" required:"true"`
}

View File

@@ -1,168 +0,0 @@
package metricreductionruletypes
import (
"database/sql/driver"
"encoding/json"
"time"
"github.com/SigNoz/signoz/pkg/errors"
"github.com/SigNoz/signoz/pkg/types"
"github.com/SigNoz/signoz/pkg/valuer"
"github.com/uptrace/bun"
)
var (
ErrCodeMetricReductionRuleUnsupported = errors.MustNewCode("metric_reduction_rule_unsupported")
ErrCodeMetricReductionRuleNotFound = errors.MustNewCode("metric_reduction_rule_not_found")
ErrCodeMetricReductionRuleAlreadyExists = errors.MustNewCode("metric_reduction_rule_already_exists")
ErrCodeMetricReductionRuleProtectedLabel = errors.MustNewCode("metric_reduction_rule_protected_label")
ErrCodeMetricReductionRuleUnsupportedMetricType = errors.MustNewCode("metric_reduction_rule_unsupported_metric_type")
)
type MatchType struct {
valuer.String
}
var (
MatchTypeDrop = MatchType{valuer.NewString("drop")}
MatchTypeKeep = MatchType{valuer.NewString("keep")}
)
func (MatchType) Enum() []any {
return []any{MatchTypeDrop, MatchTypeKeep}
}
// LabelList is a []string persisted as a single JSON text column.
type LabelList []string
func (l LabelList) Value() (driver.Value, error) {
if l == nil {
return "[]", nil
}
b, err := json.Marshal(l)
if err != nil {
return nil, err
}
return string(b), nil
}
func (l *LabelList) Scan(src any) error {
var raw []byte
switch v := src.(type) {
case string:
raw = []byte(v)
case []byte:
raw = v
case nil:
*l = nil
return nil
default:
return errors.NewInternalf(errors.CodeInternal, "metricreductionruletypes: cannot scan %T into LabelList", src)
}
return json.Unmarshal(raw, l)
}
type ReductionRule struct {
bun.BaseModel `bun:"table:metric_reduction_rule" json:"-"`
types.Identifiable
types.TimeAuditable
types.UserAuditable
OrgID valuer.UUID `bun:"org_id,type:text,notnull"`
MetricName string `bun:"metric_name,type:text,notnull"`
MatchType MatchType `bun:"match_type,type:text,notnull"`
Labels LabelList `bun:"labels,type:text,notnull,default:'[]'"`
EffectiveFrom time.Time `bun:"effective_from,notnull"`
}
func NewReductionRule(orgID valuer.UUID, metricName string, matchType MatchType, labels []string, effectiveFrom time.Time, by string) *ReductionRule {
now := time.Now()
return &ReductionRule{
Identifiable: types.Identifiable{ID: valuer.GenerateUUID()},
TimeAuditable: types.TimeAuditable{CreatedAt: now, UpdatedAt: now},
UserAuditable: types.UserAuditable{CreatedBy: by, UpdatedBy: by},
OrgID: orgID,
MetricName: metricName,
MatchType: matchType,
Labels: LabelList(labels),
EffectiveFrom: effectiveFrom,
}
}
type GettableReductionRule struct {
types.Identifiable
types.TimeAuditable
types.UserAuditable
MetricName string `json:"metricName" required:"true"`
MatchType MatchType `json:"matchType" required:"true"`
Labels []string `json:"labels" required:"true" nullable:"true"`
EffectiveFrom time.Time `json:"effectiveFrom" required:"true"`
Active bool `json:"active" required:"true"`
IngestedSeries uint64 `json:"ingestedSeries" required:"true"`
RetainedSeries uint64 `json:"retainedSeries" required:"true"`
ReductionPercent float64 `json:"reductionPercent" required:"true"`
}
type GettableReductionRules struct {
Rules []GettableReductionRule `json:"rules" required:"true" nullable:"true"`
Total int `json:"total" required:"true"`
}
type UpdatableReductionRule struct {
MatchType MatchType `json:"matchType" required:"true"`
Labels []string `json:"labels" required:"true" nullable:"true"`
}
type PostableReductionRule struct {
MetricName string `json:"metricName" required:"true"`
UpdatableReductionRule
}
var protectedLabels = map[string]struct{}{
"le": {},
"quantile": {},
"__name__": {},
"__temporality__": {},
"deployment.environment": {},
}
// IsProtectedLabel reports whether a label is always retained regardless of a reduction rule.
func IsProtectedLabel(label string) bool {
_, ok := protectedLabels[label]
return ok
}
func (req *UpdatableReductionRule) Validate() error {
if req == nil {
return errors.NewInvalidInputf(errors.CodeInvalidInput, "request is nil")
}
if req.MatchType != MatchTypeDrop && req.MatchType != MatchTypeKeep {
return errors.NewInvalidInputf(errors.CodeInvalidInput,
"matchType must be one of %q or %q", MatchTypeDrop.StringValue(), MatchTypeKeep.StringValue())
}
if len(req.Labels) == 0 {
return errors.NewInvalidInputf(errors.CodeInvalidInput,
"labels must not be empty; to allow all attributes, delete the rule instead")
}
if req.MatchType == MatchTypeDrop {
for _, label := range req.Labels {
if IsProtectedLabel(label) {
return errors.Newf(errors.TypeInvalidInput, ErrCodeMetricReductionRuleProtectedLabel,
"label %q is protected and cannot be dropped", label)
}
}
}
return nil
}
func (req *PostableReductionRule) Validate() error {
if req == nil {
return errors.NewInvalidInputf(errors.CodeInvalidInput, "request is nil")
}
if req.MetricName == "" {
return errors.NewInvalidInputf(errors.CodeInvalidInput, "metricName is required")
}
return req.UpdatableReductionRule.Validate()
}

View File

@@ -1,40 +0,0 @@
package metricreductionruletypes_test
import (
"testing"
"github.com/SigNoz/signoz/pkg/types/metricreductionruletypes"
"github.com/stretchr/testify/require"
)
func TestUpdatableReductionRuleValidate(t *testing.T) {
cases := []struct {
name string
req *metricreductionruletypes.UpdatableReductionRule
wantErr bool
}{
{"nil", nil, true},
{"invalid match type", &metricreductionruletypes.UpdatableReductionRule{Labels: []string{"host"}}, true},
{"empty labels", &metricreductionruletypes.UpdatableReductionRule{MatchType: metricreductionruletypes.MatchTypeDrop}, true},
{"drop protected label", &metricreductionruletypes.UpdatableReductionRule{MatchType: metricreductionruletypes.MatchTypeDrop, Labels: []string{"host", "le"}}, true},
{"keep protected label is allowed", &metricreductionruletypes.UpdatableReductionRule{MatchType: metricreductionruletypes.MatchTypeKeep, Labels: []string{"le"}}, false},
{"valid drop", &metricreductionruletypes.UpdatableReductionRule{MatchType: metricreductionruletypes.MatchTypeDrop, Labels: []string{"host"}}, false},
}
for _, tc := range cases {
t.Run(tc.name, func(t *testing.T) {
if tc.wantErr {
require.Error(t, tc.req.Validate())
return
}
require.NoError(t, tc.req.Validate())
})
}
}
func TestPostableReductionRuleValidate(t *testing.T) {
valid := metricreductionruletypes.UpdatableReductionRule{MatchType: metricreductionruletypes.MatchTypeKeep, Labels: []string{"host"}}
require.Error(t, (*metricreductionruletypes.PostableReductionRule)(nil).Validate(), "nil request")
require.Error(t, (&metricreductionruletypes.PostableReductionRule{UpdatableReductionRule: valid}).Validate(), "metricName required")
require.NoError(t, (&metricreductionruletypes.PostableReductionRule{MetricName: "m", UpdatableReductionRule: valid}).Validate())
}

View File

@@ -1,8 +0,0 @@
package metricreductionruletypes
// GettableReductionRuleStats is the aggregate volume-control summary across all of an org's rules.
type GettableReductionRuleStats struct {
IngestedSeries uint64 `json:"ingestedSeries" required:"true"`
RetainedSeries uint64 `json:"retainedSeries" required:"true"`
EstimatedMonthlySavingsUsd float64 `json:"estimatedMonthlySavingsUsd" required:"true"`
}

View File

@@ -1,17 +0,0 @@
package metricreductionruletypes
import (
"context"
"github.com/SigNoz/signoz/pkg/valuer"
)
type Store interface {
List(ctx context.Context, orgID valuer.UUID, params *ListReductionRulesParams) ([]*ReductionRule, int, error)
Get(ctx context.Context, orgID valuer.UUID, metricName string) (*ReductionRule, error)
GetByID(ctx context.Context, orgID valuer.UUID, id valuer.UUID) (*ReductionRule, error)
Create(ctx context.Context, rule *ReductionRule) error
Upsert(ctx context.Context, rule *ReductionRule) error
DeleteByID(ctx context.Context, orgID valuer.UUID, id valuer.UUID) error
RunInTx(ctx context.Context, cb func(ctx context.Context) error) error
}

View File

@@ -0,0 +1,186 @@
package spantypes
import (
"context"
"sort"
"strings"
"time"
"github.com/SigNoz/signoz-otel-collector/pkg/collectorsimulator"
"github.com/SigNoz/signoz-otel-collector/processor/signozspanmapperprocessor"
"github.com/SigNoz/signoz/pkg/errors"
"go.opentelemetry.io/collector/otelcol"
"go.opentelemetry.io/collector/pdata/ptrace"
"gopkg.in/yaml.v3"
)
var (
ErrCodeProcessorFactoryMapFailed = errors.MustNewCode("processor_factory_map_failed")
ErrCodeSpanMapperSimulationFailed = errors.MustNewCode("span_mapper_simulation_failed")
)
const spanInputOrderAttr = "__signoz_input_idx__"
func SimulateSpanMappersProcessing(ctx context.Context, groups []*SpanMapperGroupWithMappers, spans []SpanMapperTestSpan) ([]SpanMapperTestSpan, []string, error) {
enabled := filterEnabledGroupsWithMappers(groups)
if len(enabled) < 1 {
return spans, nil, nil
}
// this is done to preserve the order in which the request was sent
for i := range spans {
if spans[i].Attributes == nil {
spans[i].Attributes = map[string]any{}
}
spans[i].Attributes[spanInputOrderAttr] = int64(i)
}
simulatorInput := SpansToPTraces(spans)
processorFactories, err := otelcol.MakeFactoryMap(signozspanmapperprocessor.NewFactory())
if err != nil {
return nil, nil, errors.WrapInternalf(err, ErrCodeProcessorFactoryMapFailed, "could not construct processor factory map")
}
configGenerator := func(baseConf []byte) ([]byte, error) {
withProcessor, err := GenerateCollectorConfigWithSpanMapperProcessor(baseConf, enabled)
if err != nil {
return nil, err
}
return wireSpanMapperIntoTracesPipeline(withProcessor)
}
// signozspanmapperprocessor does no batching; spans flow through immediately.
timeout := 200 * time.Millisecond
outputTraces, collectorErrs, simErr := collectorsimulator.SimulateTracesProcessing(
ctx,
processorFactories,
configGenerator,
simulatorInput,
timeout,
)
if simErr != nil {
if errors.Is(simErr, collectorsimulator.ErrInvalidConfig) {
return nil, nil, errors.WrapInvalidInputf(simErr, errors.CodeInvalidInput, "invalid config")
}
return nil, nil, errors.WrapInternalf(simErr, ErrCodeSpanMapperSimulationFailed, "could not simulate span mapper processing")
}
outputSpans := PTracesToSpans(outputTraces)
sort.Slice(outputSpans, func(i, j int) bool {
iIdx, _ := outputSpans[i].Attributes[spanInputOrderAttr].(int64)
jIdx, _ := outputSpans[j].Attributes[spanInputOrderAttr].(int64)
return iIdx < jIdx
})
for _, s := range outputSpans {
delete(s.Attributes, spanInputOrderAttr)
}
collectorWarnAndErrorLogs := []string{}
for _, log := range collectorErrs {
if log == "" || strings.Contains(log, "featuregate.go") {
continue
}
collectorWarnAndErrorLogs = append(collectorWarnAndErrorLogs, log)
}
return outputSpans, collectorWarnAndErrorLogs, nil
}
func SpansToPTraces(spans []SpanMapperTestSpan) []ptrace.Traces {
result := make([]ptrace.Traces, 0, len(spans))
for _, s := range spans {
td := ptrace.NewTraces()
rs := td.ResourceSpans().AppendEmpty()
if s.Resource != nil {
_ = rs.Resource().Attributes().FromRaw(s.Resource)
}
sl := rs.ScopeSpans().AppendEmpty()
span := sl.Spans().AppendEmpty()
if s.Attributes != nil {
_ = span.Attributes().FromRaw(s.Attributes)
}
result = append(result, td)
}
return result
}
func PTracesToSpans(traces []ptrace.Traces) []SpanMapperTestSpan {
result := []SpanMapperTestSpan{}
for _, td := range traces {
rss := td.ResourceSpans()
for i := 0; i < rss.Len(); i++ {
rs := rss.At(i)
resourceAttrs := rs.Resource().Attributes().AsRaw()
ilss := rs.ScopeSpans()
for j := 0; j < ilss.Len(); j++ {
spans := ilss.At(j).Spans()
for k := 0; k < spans.Len(); k++ {
result = append(result, SpanMapperTestSpan{
Attributes: spans.At(k).Attributes().AsRaw(),
Resource: resourceAttrs,
})
}
}
}
}
return result
}
// wireSpanMapperIntoTracesPipeline appends "signozspanmapper" to
// service.pipelines.traces.processors so the processor defined by
// GenerateCollectorConfigWithSpanMapperProcessor actually runs against the
// traces flowing through the simulator. Idempotent: skips appending if the
// processor name is already present.
func wireSpanMapperIntoTracesPipeline(confYaml []byte) ([]byte, error) {
var conf map[string]any
if err := yaml.Unmarshal(confYaml, &conf); err != nil {
return nil, errors.Wrapf(err, errors.TypeInvalidInput, ErrCodeInvalidCollectorConfig, "failed to unmarshal collector config for pipeline wiring")
}
service, _ := conf["service"].(map[string]any)
if service == nil {
return confYaml, nil
}
pipelines, _ := service["pipelines"].(map[string]any)
if pipelines == nil {
return confYaml, nil
}
traces, _ := pipelines["traces"].(map[string]any)
if traces == nil {
return confYaml, nil
}
procs, _ := traces["processors"].([]any)
for _, p := range procs {
if name, ok := p.(string); ok && name == ProcessorName {
return confYaml, nil
}
}
traces["processors"] = append(procs, ProcessorName)
out, err := yaml.Marshal(conf)
if err != nil {
return nil, errors.Wrapf(err, errors.TypeInternal, ErrCodeBuildMappingProcessorConfig, "failed to marshal collector config after pipeline wiring")
}
return out, nil
}
func filterEnabledGroupsWithMappers(groups []*SpanMapperGroupWithMappers) []*SpanMapperGroupWithMappers {
out := make([]*SpanMapperGroupWithMappers, 0, len(groups))
for _, gm := range groups {
if gm == nil || gm.Group == nil || !gm.Group.Enabled {
continue
}
enabled := make([]*SpanMapper, 0, len(gm.Mappers))
for _, m := range gm.Mappers {
if m != nil && m.Enabled {
enabled = append(enabled, m)
}
}
if len(enabled) > 0 {
out = append(out, &SpanMapperGroupWithMappers{Group: gm.Group, Mappers: enabled})
}
}
return out
}

View File

@@ -0,0 +1,43 @@
package spantypes
import (
"context"
"testing"
"github.com/stretchr/testify/assert"
"github.com/stretchr/testify/require"
)
// TestSimulateSpanMappersProcessing_EndToEnd is an integration test: it spins
// up an actual in-memory otel-collector pipeline with signozspanmapperprocessor
// and verifies the produced span has the expected target attribute.
func TestSimulateSpanMappersProcessing_EndToEnd(t *testing.T) {
groups := []*SpanMapperGroupWithMappers{{
Group: &SpanMapperGroup{
Name: "llm",
Condition: SpanMapperGroupCondition{Attributes: []string{"model"}},
Enabled: true,
},
Mappers: []*SpanMapper{{
Name: "gen_ai.request.model",
FieldContext: FieldContextSpanAttribute,
Config: SpanMapperConfig{Sources: []SpanMapperSource{
{Key: "llm.model", Context: FieldContextSpanAttribute, Operation: SpanMapperOperationCopy, Priority: 1},
}},
Enabled: true,
}},
}}
spans := []SpanMapperTestSpan{{Attributes: map[string]any{"llm.model": "gpt-4"}}}
out, _, err := SimulateSpanMappersProcessing(context.Background(), groups, spans)
require.NoError(t, err)
require.Len(t, out, 1)
assert.Equal(t, "gpt-4", out[0].Attributes["gen_ai.request.model"], "target attribute must be populated by the spanmapper processor")
// Source attribute is preserved (copy, not move).
assert.Equal(t, "gpt-4", out[0].Attributes["llm.model"])
// Order-tracking attribute is stripped from the output.
_, hasOrderAttr := out[0].Attributes[spanInputOrderAttr]
assert.False(t, hasOrderAttr, "internal ordering attribute must be removed from the response")
}

View File

@@ -0,0 +1,54 @@
package spantypes
import (
"github.com/SigNoz/signoz/pkg/valuer"
)
type SpanMapperTestSpan struct {
Attributes map[string]any `json:"attributes"`
Resource map[string]any `json:"resource"`
}
// Mappers is optional because the module can backfill from the store by Group.Name.
type PostableSpanMapperTestGroup struct {
PostableSpanMapperGroup
Mappers []PostableSpanMapper `json:"mappers"`
}
type PostableSpanMapperTest struct {
Spans []SpanMapperTestSpan `json:"spans" required:"true"`
Groups []PostableSpanMapperTestGroup `json:"groups" required:"true"`
}
type GettableSpanMapperTest struct {
Spans []SpanMapperTestSpan `json:"spans"`
CollectorLogs []string `json:"collectorLogs"`
}
func NewSpanMapperGroupsWithMappersFromPostable(orgID valuer.UUID, in []PostableSpanMapperTestGroup) []*SpanMapperGroupWithMappers {
out := make([]*SpanMapperGroupWithMappers, 0, len(in))
for _, pg := range in {
var mappers []*SpanMapper
if pg.Mappers != nil {
mappers = make([]*SpanMapper, 0, len(pg.Mappers))
for _, pm := range pg.Mappers {
mappers = append(mappers, &SpanMapper{
Name: pm.Name,
FieldContext: pm.FieldContext,
Config: pm.Config,
Enabled: pm.Enabled,
})
}
}
out = append(out, &SpanMapperGroupWithMappers{
Group: &SpanMapperGroup{
OrgID: orgID,
Name: pg.Name,
Condition: pg.Condition,
Enabled: pg.Enabled,
},
Mappers: mappers,
})
}
return out
}

View File

@@ -4,7 +4,6 @@ import (
"fmt"
"strings"
"github.com/SigNoz/signoz-otel-collector/exporter/jsontypeexporter"
"github.com/SigNoz/signoz/pkg/valuer"
)
@@ -22,7 +21,7 @@ const (
// BodyJSONStringSearchPrefix is the prefix used for body JSON search queries.
// e.g., "body.status" where "body." is the prefix.
BodyJSONStringSearchPrefix = "body."
ArraySep = jsontypeexporter.ArraySeparator
ArraySep = "[]."
ArraySepSuffix = "[]"
// TODO(Piyush): Remove once we've migrated to the new array syntax.
ArrayAnyIndex = "[*]."

View File

@@ -6,7 +6,6 @@ import (
"slices"
"strings"
"github.com/SigNoz/signoz-otel-collector/exporter/jsontypeexporter"
"github.com/SigNoz/signoz/pkg/errors"
"github.com/SigNoz/signoz/pkg/valuer"
)
@@ -76,7 +75,7 @@ func (n *JSONAccessNode) Alias() string {
parentAlias := strings.TrimLeft(n.Parent.Alias(), "`")
parentAlias = strings.TrimRight(parentAlias, "`")
sep := jsontypeexporter.ArraySeparator
sep := "[]."
if n.Parent.isRoot {
sep = "."
}

View File

@@ -1,3 +0,0 @@
{"metric_name":"k8s.pod.cpu.usage","labels":{"k8s.pod.uid":"miss-p1-uid","k8s.pod.name":"miss-p1","k8s.daemonset.name":"miss-ds","k8s.node.name":"node-x","k8s.namespace.name":"ns-miss","k8s.cluster.name":"cluster-x"},"timestamp":"2025-01-10T10:00:00+00:00","value":0.5,"temporality":"Unspecified","type_":"Gauge","is_monotonic":false}
{"metric_name":"k8s.pod.cpu.usage","labels":{"k8s.pod.uid":"miss-p1-uid","k8s.pod.name":"miss-p1","k8s.daemonset.name":"miss-ds","k8s.node.name":"node-x","k8s.namespace.name":"ns-miss","k8s.cluster.name":"cluster-x"},"timestamp":"2025-01-10T10:02:00+00:00","value":0.5,"temporality":"Unspecified","type_":"Gauge","is_monotonic":false}
{"metric_name":"k8s.pod.cpu.usage","labels":{"k8s.pod.uid":"miss-p1-uid","k8s.pod.name":"miss-p1","k8s.daemonset.name":"miss-ds","k8s.node.name":"node-x","k8s.namespace.name":"ns-miss","k8s.cluster.name":"cluster-x"},"timestamp":"2025-01-10T10:04:00+00:00","value":0.5,"temporality":"Unspecified","type_":"Gauge","is_monotonic":false}

View File

@@ -1,3 +0,0 @@
{"metric_name":"k8s.pod.cpu.usage","labels":{"k8s.pod.uid":"miss-p1-uid","k8s.pod.name":"miss-p1","k8s.statefulset.name":"miss-ss","k8s.namespace.name":"ns-miss","k8s.cluster.name":"cluster-x"},"timestamp":"2025-01-10T10:00:00+00:00","value":0.5,"temporality":"Unspecified","type_":"Gauge","is_monotonic":false}
{"metric_name":"k8s.pod.cpu.usage","labels":{"k8s.pod.uid":"miss-p1-uid","k8s.pod.name":"miss-p1","k8s.statefulset.name":"miss-ss","k8s.namespace.name":"ns-miss","k8s.cluster.name":"cluster-x"},"timestamp":"2025-01-10T10:02:00+00:00","value":0.5,"temporality":"Unspecified","type_":"Gauge","is_monotonic":false}
{"metric_name":"k8s.pod.cpu.usage","labels":{"k8s.pod.uid":"miss-p1-uid","k8s.pod.name":"miss-p1","k8s.statefulset.name":"miss-ss","k8s.namespace.name":"ns-miss","k8s.cluster.name":"cluster-x"},"timestamp":"2025-01-10T10:04:00+00:00","value":0.5,"temporality":"Unspecified","type_":"Gauge","is_monotonic":false}

View File

@@ -0,0 +1,12 @@
{"metric_name": "k8s.volume.capacity", "labels": {"k8s.persistentvolumeclaim.name": "fop-pvc", "k8s.pod.uid": "fop-pvc-uid", "k8s.pod.name": "pod-fop-pvc", "k8s.namespace.name": "ns-acc", "k8s.node.name": "node-x", "k8s.cluster.name": "cluster-x", "k8s.statefulset.name": "ss-x"}, "timestamp": "2025-01-10T10:00:00+00:00", "value": 100000000000.0, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}
{"metric_name": "k8s.volume.capacity", "labels": {"k8s.persistentvolumeclaim.name": "fop-pvc", "k8s.pod.uid": "fop-pvc-uid", "k8s.pod.name": "pod-fop-pvc", "k8s.namespace.name": "ns-acc", "k8s.node.name": "node-x", "k8s.cluster.name": "cluster-x", "k8s.statefulset.name": "ss-x"}, "timestamp": "2025-01-10T10:02:00+00:00", "value": 100000000000.0, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}
{"metric_name": "k8s.volume.capacity", "labels": {"k8s.persistentvolumeclaim.name": "fop-pvc", "k8s.pod.uid": "fop-pvc-uid", "k8s.pod.name": "pod-fop-pvc", "k8s.namespace.name": "ns-acc", "k8s.node.name": "node-x", "k8s.cluster.name": "cluster-x", "k8s.statefulset.name": "ss-x"}, "timestamp": "2025-01-10T10:04:00+00:00", "value": 100000000000.0, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}
{"metric_name": "k8s.volume.inodes", "labels": {"k8s.persistentvolumeclaim.name": "fop-pvc", "k8s.pod.uid": "fop-pvc-uid", "k8s.pod.name": "pod-fop-pvc", "k8s.namespace.name": "ns-acc", "k8s.node.name": "node-x", "k8s.cluster.name": "cluster-x", "k8s.statefulset.name": "ss-x"}, "timestamp": "2025-01-10T10:00:00+00:00", "value": 1000000.0, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}
{"metric_name": "k8s.volume.inodes", "labels": {"k8s.persistentvolumeclaim.name": "fop-pvc", "k8s.pod.uid": "fop-pvc-uid", "k8s.pod.name": "pod-fop-pvc", "k8s.namespace.name": "ns-acc", "k8s.node.name": "node-x", "k8s.cluster.name": "cluster-x", "k8s.statefulset.name": "ss-x"}, "timestamp": "2025-01-10T10:02:00+00:00", "value": 1000000.0, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}
{"metric_name": "k8s.volume.inodes", "labels": {"k8s.persistentvolumeclaim.name": "fop-pvc", "k8s.pod.uid": "fop-pvc-uid", "k8s.pod.name": "pod-fop-pvc", "k8s.namespace.name": "ns-acc", "k8s.node.name": "node-x", "k8s.cluster.name": "cluster-x", "k8s.statefulset.name": "ss-x"}, "timestamp": "2025-01-10T10:04:00+00:00", "value": 1000000.0, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}
{"metric_name": "k8s.volume.inodes.free", "labels": {"k8s.persistentvolumeclaim.name": "fop-pvc", "k8s.pod.uid": "fop-pvc-uid", "k8s.pod.name": "pod-fop-pvc", "k8s.namespace.name": "ns-acc", "k8s.node.name": "node-x", "k8s.cluster.name": "cluster-x", "k8s.statefulset.name": "ss-x"}, "timestamp": "2025-01-10T10:00:00+00:00", "value": 800000.0, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}
{"metric_name": "k8s.volume.inodes.free", "labels": {"k8s.persistentvolumeclaim.name": "fop-pvc", "k8s.pod.uid": "fop-pvc-uid", "k8s.pod.name": "pod-fop-pvc", "k8s.namespace.name": "ns-acc", "k8s.node.name": "node-x", "k8s.cluster.name": "cluster-x", "k8s.statefulset.name": "ss-x"}, "timestamp": "2025-01-10T10:02:00+00:00", "value": 800000.0, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}
{"metric_name": "k8s.volume.inodes.free", "labels": {"k8s.persistentvolumeclaim.name": "fop-pvc", "k8s.pod.uid": "fop-pvc-uid", "k8s.pod.name": "pod-fop-pvc", "k8s.namespace.name": "ns-acc", "k8s.node.name": "node-x", "k8s.cluster.name": "cluster-x", "k8s.statefulset.name": "ss-x"}, "timestamp": "2025-01-10T10:04:00+00:00", "value": 800000.0, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}
{"metric_name": "k8s.volume.inodes.used", "labels": {"k8s.persistentvolumeclaim.name": "fop-pvc", "k8s.pod.uid": "fop-pvc-uid", "k8s.pod.name": "pod-fop-pvc", "k8s.namespace.name": "ns-acc", "k8s.node.name": "node-x", "k8s.cluster.name": "cluster-x", "k8s.statefulset.name": "ss-x"}, "timestamp": "2025-01-10T10:00:00+00:00", "value": 200000.0, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}
{"metric_name": "k8s.volume.inodes.used", "labels": {"k8s.persistentvolumeclaim.name": "fop-pvc", "k8s.pod.uid": "fop-pvc-uid", "k8s.pod.name": "pod-fop-pvc", "k8s.namespace.name": "ns-acc", "k8s.node.name": "node-x", "k8s.cluster.name": "cluster-x", "k8s.statefulset.name": "ss-x"}, "timestamp": "2025-01-10T10:02:00+00:00", "value": 200000.0, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}
{"metric_name": "k8s.volume.inodes.used", "labels": {"k8s.persistentvolumeclaim.name": "fop-pvc", "k8s.pod.uid": "fop-pvc-uid", "k8s.pod.name": "pod-fop-pvc", "k8s.namespace.name": "ns-acc", "k8s.node.name": "node-x", "k8s.cluster.name": "cluster-x", "k8s.statefulset.name": "ss-x"}, "timestamp": "2025-01-10T10:04:00+00:00", "value": 200000.0, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}

View File

@@ -1,3 +0,0 @@
{"metric_name":"k8s.volume.available","labels":{"k8s.persistentvolumeclaim.name":"miss-pvc","k8s.pod.uid":"pod-x-uid","k8s.pod.name":"pod-x","k8s.namespace.name":"ns-x","k8s.node.name":"node-x","k8s.cluster.name":"cluster-x","k8s.statefulset.name":"ss-x"},"timestamp":"2025-01-10T10:00:00+00:00","value":1000000000.0,"temporality":"Unspecified","type_":"Gauge","is_monotonic":false}
{"metric_name":"k8s.volume.available","labels":{"k8s.persistentvolumeclaim.name":"miss-pvc","k8s.pod.uid":"pod-x-uid","k8s.pod.name":"pod-x","k8s.namespace.name":"ns-x","k8s.node.name":"node-x","k8s.cluster.name":"cluster-x","k8s.statefulset.name":"ss-x"},"timestamp":"2025-01-10T10:02:00+00:00","value":1000000000.0,"temporality":"Unspecified","type_":"Gauge","is_monotonic":false}
{"metric_name":"k8s.volume.available","labels":{"k8s.persistentvolumeclaim.name":"miss-pvc","k8s.pod.uid":"pod-x-uid","k8s.pod.name":"pod-x","k8s.namespace.name":"ns-x","k8s.node.name":"node-x","k8s.cluster.name":"cluster-x","k8s.statefulset.name":"ss-x"},"timestamp":"2025-01-10T10:04:00+00:00","value":1000000000.0,"temporality":"Unspecified","type_":"Gauge","is_monotonic":false}

View File

@@ -11,7 +11,7 @@ from fixtures import types
from fixtures.auth import USER_ADMIN_EMAIL, USER_ADMIN_PASSWORD
from fixtures.fs import get_testdata_file_path
from fixtures.metrics import Metrics
from fixtures.querier import compare_values
from fixtures.querier import compare_values, get_all_warnings
ENDPOINT = "/api/v2/infra_monitoring/hosts"
@@ -56,7 +56,8 @@ def test_hosts_accuracy(
# Shape/contract.
assert data["total"] == len(expected["records"])
assert len(data["records"]) == len(expected["records"])
assert data["requiredMetricsCheck"]["missingMetrics"] == []
# Full data present -> no warnings surfaced.
assert get_all_warnings(response.json()) == []
assert data["endTimeBeforeRetention"] is False
assert {r["hostName"] for r in data["records"]} == set(exp_by_host.keys())
@@ -79,45 +80,81 @@ def test_hosts_accuracy(
assert compare_values(record[field], exp[field], 1e-9), f"{record['hostName']}.{field}: got {record[field]}, expected {exp[field]}"
def test_hosts_missing_metrics(
@pytest.mark.parametrize(
"case",
[
# Scenario 1: a required host metric was never ingested. Post-#11754 the
# querier drops it instead of hard-erroring, so the endpoint returns 200
# with the hosts that DO have data; the never-seen metric's column is the
# -1 sentinel and a "has never been received" warning is surfaced.
pytest.param(
{
"dataset": "hosts_missing_metrics.jsonl", # seeds only system.cpu.time
"body": {"filter": {"expression": "host.name = 'miss-h1'"}},
# singular form is "has", plural (>1 missing) is "have" -> match the common stem
"warn_substrings": ["never been received"],
"warn_names": [
"system.memory.usage",
"system.cpu.load_average.15m",
"system.filesystem.usage",
],
# cpu/wait derive from the present system.cpu.time; the rest come
# from never-seen metrics -> -1 sentinel.
"data_fields": ["cpu", "wait"],
"no_data_fields": ["memory", "load15", "diskUsage"],
},
id="metric_never_seen",
),
],
)
def test_hosts_warnings(
signoz: types.SigNoz,
create_user_admin: None, # pylint: disable=unused-argument
get_token,
insert_metrics,
case: dict,
) -> None:
"""Seed only system.cpu.time; assert other 3 required metrics flagged missing."""
"""Data-availability gaps surface as non-blocking warnings (200 + data),
not hard errors. Covers never-seen metrics surfacing a "never been
received" warning while present metrics still return data."""
now = datetime.now(tz=UTC).replace(microsecond=0)
insert_metrics(
Metrics.load_from_file(
get_testdata_file_path("inframonitoring/hosts_missing_metrics.jsonl"),
get_testdata_file_path(f"inframonitoring/{case['dataset']}"),
base_time=now - timedelta(minutes=4),
)
)
token = get_token(USER_ADMIN_EMAIL, USER_ADMIN_PASSWORD)
body: dict = {
"start": int((now - timedelta(minutes=5)).timestamp() * 1000),
"end": int(now.timestamp() * 1000),
"limit": 50,
}
body.update(case["body"])
response = requests.post(
signoz.self.host_configs["8080"].get(ENDPOINT),
headers={"authorization": f"Bearer {token}"},
json={
"start": int((now - timedelta(minutes=5)).timestamp() * 1000),
"end": int(now.timestamp() * 1000),
"limit": 50,
},
json=body,
timeout=5,
)
assert response.status_code == HTTPStatus.OK
assert response.status_code == HTTPStatus.OK, response.text
data = response.json()["data"]
warnings = get_all_warnings(response.json())
assert set(data["requiredMetricsCheck"]["missingMetrics"]) == {
"system.memory.usage",
"system.cpu.load_average.15m",
"system.filesystem.usage",
}
# Endpoint short-circuits when any required metric is missing:
# records is empty and total=0 regardless of which hosts have partial data.
# See pkg/modules/inframonitoring/implinframonitoring/module.go:84-89.
assert data["records"] == []
assert data["total"] == 0
for substr in case["warn_substrings"]:
assert any(substr in w["message"] for w in warnings), f"{substr!r} not surfaced: {warnings!r}"
for name in case["warn_names"]:
assert any(name in w["message"] for w in warnings), f"{name!r} not surfaced: {warnings!r}"
assert len(data["records"]) >= 1, f"expected at least one record: {data!r}"
if case["data_fields"] or case["no_data_fields"]:
record = data["records"][0]
for field in case["data_fields"]:
assert record[field] != -1, f"expected {field} populated, got {record[field]}"
for field in case["no_data_fields"]:
assert record[field] == -1, f"expected {field} == -1 sentinel, got {record[field]}"
@pytest.mark.parametrize(

View File

@@ -11,26 +11,11 @@ from fixtures import types
from fixtures.auth import USER_ADMIN_EMAIL, USER_ADMIN_PASSWORD
from fixtures.fs import get_testdata_file_path
from fixtures.metrics import Metrics
from fixtures.querier import compare_values
from fixtures.querier import compare_values, get_all_warnings
from fixtures.time import parse_timestamp
ENDPOINT = "/api/v2/infra_monitoring/pods"
# Required metrics for the v2 pods endpoint
# (pkg/modules/inframonitoring/implinframonitoring/pods_constants.go:24-32).
REQUIRED_METRICS = {
"k8s.pod.cpu.usage",
"k8s.pod.cpu_request_utilization",
"k8s.pod.cpu_limit_utilization",
"k8s.pod.memory.working_set",
"k8s.pod.memory_request_utilization",
"k8s.pod.memory_limit_utilization",
"k8s.pod.phase",
}
# Numeric values emitted by the k8s.pod.phase metric (OTel kubeletstatsreceiver).
PHASE_NUM = {"pending": 1, "running": 2, "succeeded": 3, "failed": 4, "unknown": 5}
# Placeholder in JSONL labels that gets substituted with a runtime ISO string.
START_TIME_PLACEHOLDER = "__START_TIME__"
@@ -116,7 +101,8 @@ def test_pods_accuracy(
# Shape/contract.
assert data["total"] == len(expected["records"])
assert len(data["records"]) == len(expected["records"])
assert data["requiredMetricsCheck"]["missingMetrics"] == []
# Full data present -> no warnings surfaced.
assert get_all_warnings(response.json()) == []
assert data["endTimeBeforeRetention"] is False
assert {r["meta"]["k8s.pod.name"] for r in data["records"]} == set(exp_by_name.keys())
@@ -162,42 +148,91 @@ def test_pods_accuracy(
assert record["podAge"] == expected_age_ms, f"{pod_name}.podAge: got {record['podAge']}, expected {expected_age_ms}"
def test_pods_missing_metrics(
@pytest.mark.parametrize(
"case",
[
# Scenario 1: required metrics were never ingested. Post-#11754 the querier
# drops them (no hard error), so the endpoint returns 200 with the pod that
# DOES have data; never-seen columns are the -1 sentinel and a
# "have never been received" warning is surfaced. Pods has no formulas, so
# each missing metric maps straight to one -1 column.
pytest.param(
{
"dataset": "pods_missing_metrics.jsonl", # seeds only k8s.pod.cpu.usage
"body": {"filter": {"expression": "k8s.pod.name = 'miss-p1'"}},
"warn_substrings": ["never been received"],
"warn_names": [
"k8s.pod.cpu_request_utilization",
"k8s.pod.cpu_limit_utilization",
"k8s.pod.memory.working_set",
"k8s.pod.memory_request_utilization",
"k8s.pod.memory_limit_utilization",
],
# podCPU derives from the present k8s.pod.cpu.usage; the rest from
# never-seen metrics -> -1 sentinel.
"data_fields": ["podCPU"],
"no_data_fields": [
"podCPURequest",
"podCPULimit",
"podMemory",
"podMemoryRequest",
"podMemoryLimit",
],
},
id="metric_never_seen",
),
],
)
def test_pods_warnings(
signoz: types.SigNoz,
create_user_admin: None, # pylint: disable=unused-argument
get_token,
insert_metrics,
case: dict,
) -> None:
"""Seed only k8s.pod.cpu.usage; assert other 6 required metrics flagged missing.
The endpoint short-circuits and returns empty records + total=0 when any
required metric is missing (module.go:192-197).
"""
"""A never-ingested metric surfaces a non-blocking warning (200 + data), not a
hard error: the endpoint returns the entity that DOES have data and the
never-seen columns carry the -1 sentinel. (The generic never-seen
(metric, key)-pair-via-groupBy warning is entity-agnostic and is exercised
once, for hosts, in 01_hosts.py.)"""
now = datetime.now(tz=UTC).replace(microsecond=0)
insert_metrics(
_load_pods_metrics(
"inframonitoring/pods_missing_metrics.jsonl",
f"inframonitoring/{case['dataset']}",
base_time=now - timedelta(minutes=4),
)
)
token = get_token(USER_ADMIN_EMAIL, USER_ADMIN_PASSWORD)
body: dict = {
"start": int((now - timedelta(minutes=5)).timestamp() * 1000),
"end": int(now.timestamp() * 1000),
"limit": 50,
}
body.update(case["body"])
response = requests.post(
signoz.self.host_configs["8080"].get(ENDPOINT),
headers={"authorization": f"Bearer {token}"},
json={
"start": int((now - timedelta(minutes=5)).timestamp() * 1000),
"end": int(now.timestamp() * 1000),
"limit": 50,
},
json=body,
timeout=5,
)
assert response.status_code == HTTPStatus.OK, response.text
data = response.json()["data"]
warnings = get_all_warnings(response.json())
assert set(data["requiredMetricsCheck"]["missingMetrics"]) == (REQUIRED_METRICS - {"k8s.pod.cpu.usage"})
assert data["records"] == []
assert data["total"] == 0
for substr in case["warn_substrings"]:
assert any(substr in w["message"] for w in warnings), f"{substr!r} not surfaced: {warnings!r}"
for name in case["warn_names"]:
assert any(name in w["message"] for w in warnings), f"{name!r} not surfaced: {warnings!r}"
assert len(data["records"]) >= 1, f"expected at least one record: {data!r}"
if case["data_fields"] or case["no_data_fields"]:
record = data["records"][0]
for field in case["data_fields"]:
assert record[field] != -1, f"expected {field} populated, got {record[field]}"
for field in case["no_data_fields"]:
assert record[field] == -1, f"expected {field} == -1 sentinel, got {record[field]}"
@pytest.mark.parametrize(

View File

@@ -11,24 +11,10 @@ from fixtures import types
from fixtures.auth import USER_ADMIN_EMAIL, USER_ADMIN_PASSWORD
from fixtures.fs import get_testdata_file_path
from fixtures.metrics import Metrics
from fixtures.querier import compare_values
from fixtures.querier import compare_values, get_all_warnings
ENDPOINT = "/api/v2/infra_monitoring/nodes"
# Required metrics for the v2 nodes endpoint
# (pkg/modules/inframonitoring/implinframonitoring/nodes_constants.go:22-29).
REQUIRED_METRICS = {
"k8s.node.cpu.usage",
"k8s.node.allocatable_cpu",
"k8s.node.memory.working_set",
"k8s.node.allocatable_memory",
"k8s.node.condition_ready",
"k8s.pod.phase",
}
# Numeric values emitted by k8s.node.condition_ready.
COND_NUM = {"ready": 1, "not_ready": 0}
def test_nodes_accuracy(
signoz: types.SigNoz,
@@ -71,7 +57,8 @@ def test_nodes_accuracy(
# Shape/contract.
assert data["total"] == len(expected["records"])
assert len(data["records"]) == len(expected["records"])
assert data["requiredMetricsCheck"]["missingMetrics"] == []
# Full data present -> no warnings surfaced.
assert get_all_warnings(response.json()) == []
assert data["endTimeBeforeRetention"] is False
assert {r["nodeName"] for r in data["records"]} == set(exp_by_name.keys())
@@ -107,38 +94,83 @@ def test_nodes_accuracy(
assert record["podCountsByPhase"] == exp["podCountsByPhase"]
def test_nodes_missing_metrics(
@pytest.mark.parametrize(
"case",
[
# Scenario 1: required metrics were never ingested. Post-#11754 the querier
# drops them (no hard error), so the endpoint returns 200 with the node that
# DOES have data; never-seen columns are the -1 sentinel + a
# "have never been received" warning. Nodes has no formulas, so each missing
# metric maps straight to one -1 column.
pytest.param(
{
"dataset": "nodes_missing_metrics.jsonl", # seeds only k8s.node.cpu.usage
"body": {"filter": {"expression": "k8s.node.name = 'miss-n1'"}},
"warn_substrings": ["never been received"],
"warn_names": [
"k8s.node.allocatable_cpu",
"k8s.node.memory.working_set",
"k8s.node.allocatable_memory",
],
# nodeCPU derives from the present k8s.node.cpu.usage; the rest from
# never-seen metrics -> -1 sentinel.
"data_fields": ["nodeCPU"],
"no_data_fields": ["nodeCPUAllocatable", "nodeMemory", "nodeMemoryAllocatable"],
},
id="metric_never_seen",
),
],
)
def test_nodes_warnings(
signoz: types.SigNoz,
create_user_admin: None, # pylint: disable=unused-argument
get_token,
insert_metrics,
case: dict,
) -> None:
"""Seed only k8s.node.cpu.usage; assert other 5 required metrics flagged missing."""
"""A never-ingested metric surfaces a non-blocking warning (200 + data), not a
hard error: the endpoint returns the entity that DOES have data and the
never-seen columns carry the -1 sentinel. (The generic never-seen
(metric, key)-pair-via-groupBy warning is entity-agnostic and is exercised
once, for hosts, in 01_hosts.py.)"""
now = datetime.now(tz=UTC).replace(microsecond=0)
insert_metrics(
Metrics.load_from_file(
get_testdata_file_path("inframonitoring/nodes_missing_metrics.jsonl"),
get_testdata_file_path(f"inframonitoring/{case['dataset']}"),
base_time=now - timedelta(minutes=4),
)
)
token = get_token(USER_ADMIN_EMAIL, USER_ADMIN_PASSWORD)
body: dict = {
"start": int((now - timedelta(minutes=5)).timestamp() * 1000),
"end": int(now.timestamp() * 1000),
"limit": 50,
}
body.update(case["body"])
response = requests.post(
signoz.self.host_configs["8080"].get(ENDPOINT),
headers={"authorization": f"Bearer {token}"},
json={
"start": int((now - timedelta(minutes=5)).timestamp() * 1000),
"end": int(now.timestamp() * 1000),
"limit": 50,
},
json=body,
timeout=5,
)
assert response.status_code == HTTPStatus.OK, response.text
data = response.json()["data"]
warnings = get_all_warnings(response.json())
assert set(data["requiredMetricsCheck"]["missingMetrics"]) == (REQUIRED_METRICS - {"k8s.node.cpu.usage"})
assert data["records"] == []
assert data["total"] == 0
for substr in case["warn_substrings"]:
assert any(substr in w["message"] for w in warnings), f"{substr!r} not surfaced: {warnings!r}"
for name in case["warn_names"]:
assert any(name in w["message"] for w in warnings), f"{name!r} not surfaced: {warnings!r}"
assert len(data["records"]) >= 1, f"expected at least one record: {data!r}"
if case["data_fields"] or case["no_data_fields"]:
record = data["records"][0]
for field in case["data_fields"]:
assert record[field] != -1, f"expected {field} populated, got {record[field]}"
for field in case["no_data_fields"]:
assert record[field] == -1, f"expected {field} == -1 sentinel, got {record[field]}"
@pytest.mark.parametrize(

View File

@@ -11,18 +11,10 @@ from fixtures import types
from fixtures.auth import USER_ADMIN_EMAIL, USER_ADMIN_PASSWORD
from fixtures.fs import get_testdata_file_path
from fixtures.metrics import Metrics
from fixtures.querier import compare_values
from fixtures.querier import compare_values, get_all_warnings
ENDPOINT = "/api/v2/infra_monitoring/namespaces"
# Required metrics for the v2 namespaces endpoint
# (pkg/modules/inframonitoring/implinframonitoring/namespaces_constants.go:22-26).
REQUIRED_METRICS = {
"k8s.pod.cpu.usage",
"k8s.pod.memory.working_set",
"k8s.pod.phase",
}
def test_namespaces_accuracy(
signoz: types.SigNoz,
@@ -71,7 +63,8 @@ def test_namespaces_accuracy(
# Shape/contract.
assert data["total"] == len(expected["records"])
assert len(data["records"]) == len(expected["records"])
assert data["requiredMetricsCheck"]["missingMetrics"] == []
# Full data present -> no warnings surfaced.
assert get_all_warnings(response.json()) == []
assert data["endTimeBeforeRetention"] is False
assert {r["namespaceName"] for r in data["records"]} == set(exp_by_name.keys())
@@ -99,38 +92,79 @@ def test_namespaces_accuracy(
assert record["podCountsByPhase"] == exp["podCountsByPhase"]
def test_namespaces_missing_metrics(
@pytest.mark.parametrize(
"case",
[
# Scenario 1: a required metric was never ingested. Post-#11754 the querier
# drops it (no hard error), so the endpoint returns 200 with the namespace
# that DOES have data; the never-seen column is the -1 sentinel + a
# "have never been received" warning. Namespaces has no formulas (2 columns:
# namespaceCPU=A, namespaceMemory=D). Default groupBy is two keys
# [k8s.namespace.name, k8s.cluster.name]; the seed carries both so the
# page-groups IN-filter parses.
pytest.param(
{
"dataset": "namespaces_missing_metrics.jsonl", # seeds only k8s.pod.cpu.usage
"body": {"filter": {"expression": "k8s.namespace.name = 'miss-ns'"}},
"warn_substrings": ["never been received", "k8s.pod.memory.working_set"],
"warn_names": [],
"data_fields": ["namespaceCPU"],
"no_data_fields": ["namespaceMemory"],
},
id="metric_never_seen",
),
],
)
def test_namespaces_warnings(
signoz: types.SigNoz,
create_user_admin: None, # pylint: disable=unused-argument
get_token,
insert_metrics,
case: dict,
) -> None:
"""Seed only k8s.pod.cpu.usage; assert other 2 required metrics flagged missing."""
"""A never-ingested metric surfaces a non-blocking warning (200 + data), not a
hard error: the endpoint returns the entity that DOES have data and the
never-seen columns carry the -1 sentinel. (The generic never-seen
(metric, key)-pair-via-groupBy warning is entity-agnostic and is exercised
once, for hosts, in 01_hosts.py.)"""
now = datetime.now(tz=UTC).replace(microsecond=0)
insert_metrics(
Metrics.load_from_file(
get_testdata_file_path("inframonitoring/namespaces_missing_metrics.jsonl"),
get_testdata_file_path(f"inframonitoring/{case['dataset']}"),
base_time=now - timedelta(minutes=4),
)
)
token = get_token(USER_ADMIN_EMAIL, USER_ADMIN_PASSWORD)
body: dict = {
"start": int((now - timedelta(minutes=5)).timestamp() * 1000),
"end": int(now.timestamp() * 1000),
"limit": 50,
}
body.update(case["body"])
response = requests.post(
signoz.self.host_configs["8080"].get(ENDPOINT),
headers={"authorization": f"Bearer {token}"},
json={
"start": int((now - timedelta(minutes=5)).timestamp() * 1000),
"end": int(now.timestamp() * 1000),
"limit": 50,
},
json=body,
timeout=5,
)
assert response.status_code == HTTPStatus.OK, response.text
data = response.json()["data"]
warnings = get_all_warnings(response.json())
assert set(data["requiredMetricsCheck"]["missingMetrics"]) == (REQUIRED_METRICS - {"k8s.pod.cpu.usage"})
assert data["records"] == []
assert data["total"] == 0
for substr in case["warn_substrings"]:
assert any(substr in w["message"] for w in warnings), f"{substr!r} not surfaced: {warnings!r}"
for name in case["warn_names"]:
assert any(name in w["message"] for w in warnings), f"{name!r} not surfaced: {warnings!r}"
assert len(data["records"]) >= 1, f"expected at least one record: {data!r}"
if case["data_fields"] or case["no_data_fields"]:
record = data["records"][0]
for field in case["data_fields"]:
assert record[field] != -1, f"expected {field} populated, got {record[field]}"
for field in case["no_data_fields"]:
assert record[field] == -1, f"expected {field} == -1 sentinel, got {record[field]}"
@pytest.mark.parametrize(

View File

@@ -11,21 +11,10 @@ from fixtures import types
from fixtures.auth import USER_ADMIN_EMAIL, USER_ADMIN_PASSWORD
from fixtures.fs import get_testdata_file_path
from fixtures.metrics import Metrics
from fixtures.querier import compare_values
from fixtures.querier import compare_values, get_all_warnings
ENDPOINT = "/api/v2/infra_monitoring/clusters"
# Required metrics for the v2 clusters endpoint
# (pkg/modules/inframonitoring/implinframonitoring/clusters_constants.go:23-30).
REQUIRED_METRICS = {
"k8s.node.cpu.usage",
"k8s.node.allocatable_cpu",
"k8s.node.memory.working_set",
"k8s.node.allocatable_memory",
"k8s.node.condition_ready",
"k8s.pod.phase",
}
def test_clusters_accuracy(
signoz: types.SigNoz,
@@ -74,7 +63,8 @@ def test_clusters_accuracy(
# Shape/contract.
assert data["total"] == len(expected["records"])
assert len(data["records"]) == len(expected["records"])
assert data["requiredMetricsCheck"]["missingMetrics"] == []
# Full data present -> no warnings surfaced.
assert get_all_warnings(response.json()) == []
assert data["endTimeBeforeRetention"] is False
assert {r["clusterName"] for r in data["records"]} == set(exp_by_name.keys())
@@ -113,38 +103,82 @@ def test_clusters_accuracy(
assert record["podCountsByPhase"] == exp["podCountsByPhase"]
def test_clusters_missing_metrics(
@pytest.mark.parametrize(
"case",
[
# Scenario 1: a required metric was never ingested. Post-#11754 the querier
# drops it (no hard error), so the endpoint returns 200 with the cluster
# that DOES have data; never-seen columns are the -1 sentinel + a
# "have never been received" warning. Clusters has no formulas
# (clusterCPU=A, clusterCPUAllocatable=B, clusterMemory=C,
# clusterMemoryAllocatable=D).
pytest.param(
{
"dataset": "clusters_missing_metrics.jsonl", # seeds only k8s.node.cpu.usage
"body": {"filter": {"expression": "k8s.cluster.name = 'miss-cluster'"}},
"warn_substrings": ["never been received"],
"warn_names": [
"k8s.node.allocatable_cpu",
"k8s.node.memory.working_set",
"k8s.node.allocatable_memory",
],
"data_fields": ["clusterCPU"],
"no_data_fields": ["clusterCPUAllocatable", "clusterMemory", "clusterMemoryAllocatable"],
},
id="metric_never_seen",
),
],
)
def test_clusters_warnings(
signoz: types.SigNoz,
create_user_admin: None, # pylint: disable=unused-argument
get_token,
insert_metrics,
case: dict,
) -> None:
"""Seed only k8s.node.cpu.usage; assert other 5 required metrics flagged missing."""
"""A never-ingested metric surfaces a non-blocking warning (200 + data), not a
hard error: the endpoint returns the entity that DOES have data and the
never-seen columns carry the -1 sentinel. (The generic never-seen
(metric, key)-pair-via-groupBy warning is entity-agnostic and is exercised
once, for hosts, in 01_hosts.py.)"""
now = datetime.now(tz=UTC).replace(microsecond=0)
insert_metrics(
Metrics.load_from_file(
get_testdata_file_path("inframonitoring/clusters_missing_metrics.jsonl"),
get_testdata_file_path(f"inframonitoring/{case['dataset']}"),
base_time=now - timedelta(minutes=4),
)
)
token = get_token(USER_ADMIN_EMAIL, USER_ADMIN_PASSWORD)
body: dict = {
"start": int((now - timedelta(minutes=5)).timestamp() * 1000),
"end": int(now.timestamp() * 1000),
"limit": 50,
}
body.update(case["body"])
response = requests.post(
signoz.self.host_configs["8080"].get(ENDPOINT),
headers={"authorization": f"Bearer {token}"},
json={
"start": int((now - timedelta(minutes=5)).timestamp() * 1000),
"end": int(now.timestamp() * 1000),
"limit": 50,
},
json=body,
timeout=5,
)
assert response.status_code == HTTPStatus.OK, response.text
data = response.json()["data"]
warnings = get_all_warnings(response.json())
assert set(data["requiredMetricsCheck"]["missingMetrics"]) == (REQUIRED_METRICS - {"k8s.node.cpu.usage"})
assert data["records"] == []
assert data["total"] == 0
for substr in case["warn_substrings"]:
assert any(substr in w["message"] for w in warnings), f"{substr!r} not surfaced: {warnings!r}"
for name in case["warn_names"]:
assert any(name in w["message"] for w in warnings), f"{name!r} not surfaced: {warnings!r}"
assert len(data["records"]) >= 1, f"expected at least one record: {data!r}"
if case["data_fields"] or case["no_data_fields"]:
record = data["records"][0]
for field in case["data_fields"]:
assert record[field] != -1, f"expected {field} populated, got {record[field]}"
for field in case["no_data_fields"]:
assert record[field] == -1, f"expected {field} == -1 sentinel, got {record[field]}"
@pytest.mark.parametrize(

View File

@@ -11,20 +11,10 @@ from fixtures import types
from fixtures.auth import USER_ADMIN_EMAIL, USER_ADMIN_PASSWORD
from fixtures.fs import get_testdata_file_path
from fixtures.metrics import Metrics
from fixtures.querier import compare_values
from fixtures.querier import compare_values, get_all_warnings
ENDPOINT = "/api/v2/infra_monitoring/pvcs"
# Required metrics for the v2 volumes endpoint
# (pkg/modules/inframonitoring/implinframonitoring/volumes_constants.go:20-27).
REQUIRED_METRICS = {
"k8s.volume.available",
"k8s.volume.capacity",
"k8s.volume.inodes",
"k8s.volume.inodes.free",
"k8s.volume.inodes.used",
}
def test_volumes_accuracy(
signoz: types.SigNoz,
@@ -71,7 +61,8 @@ def test_volumes_accuracy(
# Shape/contract.
assert data["total"] == len(expected["records"])
assert len(data["records"]) == len(expected["records"])
assert data["requiredMetricsCheck"]["missingMetrics"] == []
# Full data present -> no warnings surfaced.
assert get_all_warnings(response.json()) == []
assert data["endTimeBeforeRetention"] is False
assert {r["persistentVolumeClaimName"] for r in data["records"]} == set(exp_by_name.keys())
@@ -117,38 +108,81 @@ def test_volumes_accuracy(
assert compare_values(record[field], exp[field], 1e-6), f"{record['persistentVolumeClaimName']}.{field}: got {record[field]}, expected {exp[field]}"
def test_volumes_missing_metrics(
@pytest.mark.parametrize(
"case",
[
# Scenario 1: a metric was never ingested. Post-#11754 the querier drops it
# (no hard error), so the endpoint returns 200 with whatever flowed; the
# never-seen column is the -1 sentinel + a "have never been received"
# warning. Here we omit the FORMULA OPERAND k8s.volume.available
# (volumeUsage = capacity - available): since A uses TimeAggregationAvg it is
# NOT zero-defaultable, so the formula drops the group -> volumeUsage == -1
# (it does NOT fall back to capacity). capacity + inodes stay real.
pytest.param(
{
"dataset": "volumes_formula_operand_missing.jsonl",
"body": {"filter": {"expression": "k8s.persistentvolumeclaim.name = 'fop-pvc'"}},
"warn_substrings": ["never been received", "k8s.volume.available"],
"warn_names": [],
"data_fields": ["volumeCapacity", "volumeInodes", "volumeInodesFree", "volumeInodesUsed"],
"no_data_fields": ["volumeAvailable", "volumeUsage"],
},
id="metric_never_seen",
),
],
)
def test_volumes_warnings(
signoz: types.SigNoz,
create_user_admin: None, # pylint: disable=unused-argument
get_token,
insert_metrics,
case: dict,
) -> None:
"""Seed only k8s.volume.available; other 4 required metrics flagged missing."""
"""A never-ingested metric surfaces a non-blocking warning (200 + data), not a
hard error. Here the never-seen metric is the FORMULA OPERAND
k8s.volume.available (volumeUsage = capacity - available): since A uses
TimeAggregationAvg it is NOT zero-defaultable, so the formula drops the group
-> volumeUsage == -1 (it does NOT fall back to capacity); capacity + inodes
stay real. (The generic never-seen (metric, key)-pair-via-groupBy warning is
entity-agnostic and is exercised once, for hosts, in 01_hosts.py.)"""
now = datetime.now(tz=UTC).replace(microsecond=0)
insert_metrics(
Metrics.load_from_file(
get_testdata_file_path("inframonitoring/volumes_missing_metrics.jsonl"),
get_testdata_file_path(f"inframonitoring/{case['dataset']}"),
base_time=now - timedelta(minutes=4),
)
)
token = get_token(USER_ADMIN_EMAIL, USER_ADMIN_PASSWORD)
body: dict = {
"start": int((now - timedelta(minutes=5)).timestamp() * 1000),
"end": int(now.timestamp() * 1000),
"limit": 50,
}
body.update(case["body"])
response = requests.post(
signoz.self.host_configs["8080"].get(ENDPOINT),
headers={"authorization": f"Bearer {token}"},
json={
"start": int((now - timedelta(minutes=5)).timestamp() * 1000),
"end": int(now.timestamp() * 1000),
"limit": 50,
},
json=body,
timeout=5,
)
assert response.status_code == HTTPStatus.OK, response.text
data = response.json()["data"]
warnings = get_all_warnings(response.json())
assert set(data["requiredMetricsCheck"]["missingMetrics"]) == (REQUIRED_METRICS - {"k8s.volume.available"})
assert data["records"] == []
assert data["total"] == 0
for substr in case["warn_substrings"]:
assert any(substr in w["message"] for w in warnings), f"{substr!r} not surfaced: {warnings!r}"
for name in case["warn_names"]:
assert any(name in w["message"] for w in warnings), f"{name!r} not surfaced: {warnings!r}"
assert len(data["records"]) >= 1, f"expected at least one record: {data!r}"
if case["data_fields"] or case["no_data_fields"]:
record = data["records"][0]
for field in case["data_fields"]:
assert record[field] != -1, f"expected {field} populated, got {record[field]}"
for field in case["no_data_fields"]:
assert record[field] == -1, f"expected {field} == -1 sentinel, got {record[field]}"
@pytest.mark.parametrize(

View File

@@ -11,24 +11,10 @@ from fixtures import types
from fixtures.auth import USER_ADMIN_EMAIL, USER_ADMIN_PASSWORD
from fixtures.fs import get_testdata_file_path
from fixtures.metrics import Metrics
from fixtures.querier import compare_values
from fixtures.querier import compare_values, get_all_warnings
ENDPOINT = "/api/v2/infra_monitoring/deployments"
# Required metrics for the v2 deployments endpoint
# (pkg/modules/inframonitoring/implinframonitoring/deployments_constants.go:24-34).
REQUIRED_METRICS = {
"k8s.pod.phase",
"k8s.pod.cpu.usage",
"k8s.pod.cpu_request_utilization",
"k8s.pod.cpu_limit_utilization",
"k8s.pod.memory.working_set",
"k8s.pod.memory_request_utilization",
"k8s.pod.memory_limit_utilization",
"k8s.deployment.desired",
"k8s.deployment.available",
}
def test_deployments_accuracy(
signoz: types.SigNoz,
@@ -75,7 +61,8 @@ def test_deployments_accuracy(
# Shape/contract.
assert data["total"] == len(expected["records"])
assert len(data["records"]) == len(expected["records"])
assert data["requiredMetricsCheck"]["missingMetrics"] == []
# Full data present -> no warnings surfaced.
assert get_all_warnings(response.json()) == []
assert data["endTimeBeforeRetention"] is False
assert {r["deploymentName"] for r in data["records"]} == set(exp_by_name.keys())
@@ -123,38 +110,89 @@ def test_deployments_accuracy(
assert record["podCountsByPhase"] == exp["podCountsByPhase"]
def test_deployments_missing_metrics(
@pytest.mark.parametrize(
"case",
[
# Scenario 1: required metrics were never ingested. Post-#11754 the querier
# drops them (no hard error), so the endpoint returns 200 with the deployment
# that DOES have data; never-seen columns are the -1 sentinel + a
# "have never been received" warning. No formulas; pod- and deployment-level
# metrics each map to one column.
pytest.param(
{
"dataset": "deployments_missing_metrics.jsonl", # seeds only k8s.pod.cpu.usage
"body": {"filter": {"expression": "k8s.deployment.name = 'miss-dep'"}},
"warn_substrings": ["never been received"],
"warn_names": [
"k8s.pod.memory.working_set",
"k8s.deployment.desired",
"k8s.deployment.available",
],
"data_fields": ["deploymentCPU"],
"no_data_fields": [
"deploymentCPURequest",
"deploymentCPULimit",
"deploymentMemory",
"deploymentMemoryRequest",
"deploymentMemoryLimit",
"desiredPods",
"availablePods",
],
},
id="metric_never_seen",
),
],
)
def test_deployments_warnings(
signoz: types.SigNoz,
create_user_admin: None, # pylint: disable=unused-argument
get_token,
insert_metrics,
case: dict,
) -> None:
"""Seed only k8s.pod.cpu.usage; assert other 8 required metrics flagged missing."""
"""A never-ingested metric surfaces a non-blocking warning (200 + data), not a
hard error: the endpoint returns the entity that DOES have data and the
never-seen columns carry the -1 sentinel. (The generic never-seen
(metric, key)-pair-via-groupBy warning is entity-agnostic and is exercised
once, for hosts, in 01_hosts.py.)"""
now = datetime.now(tz=UTC).replace(microsecond=0)
insert_metrics(
Metrics.load_from_file(
get_testdata_file_path("inframonitoring/deployments_missing_metrics.jsonl"),
get_testdata_file_path(f"inframonitoring/{case['dataset']}"),
base_time=now - timedelta(minutes=4),
)
)
token = get_token(USER_ADMIN_EMAIL, USER_ADMIN_PASSWORD)
body: dict = {
"start": int((now - timedelta(minutes=5)).timestamp() * 1000),
"end": int(now.timestamp() * 1000),
"limit": 50,
}
body.update(case["body"])
response = requests.post(
signoz.self.host_configs["8080"].get(ENDPOINT),
headers={"authorization": f"Bearer {token}"},
json={
"start": int((now - timedelta(minutes=5)).timestamp() * 1000),
"end": int(now.timestamp() * 1000),
"limit": 50,
},
json=body,
timeout=5,
)
assert response.status_code == HTTPStatus.OK, response.text
data = response.json()["data"]
warnings = get_all_warnings(response.json())
assert set(data["requiredMetricsCheck"]["missingMetrics"]) == (REQUIRED_METRICS - {"k8s.pod.cpu.usage"})
assert data["records"] == []
assert data["total"] == 0
for substr in case["warn_substrings"]:
assert any(substr in w["message"] for w in warnings), f"{substr!r} not surfaced: {warnings!r}"
for name in case["warn_names"]:
assert any(name in w["message"] for w in warnings), f"{name!r} not surfaced: {warnings!r}"
assert len(data["records"]) >= 1, f"expected at least one record: {data!r}"
if case["data_fields"] or case["no_data_fields"]:
record = data["records"][0]
for field in case["data_fields"]:
assert record[field] != -1, f"expected {field} populated, got {record[field]}"
for field in case["no_data_fields"]:
assert record[field] == -1, f"expected {field} == -1 sentinel, got {record[field]}"
@pytest.mark.parametrize(

View File

@@ -11,24 +11,10 @@ from fixtures import types
from fixtures.auth import USER_ADMIN_EMAIL, USER_ADMIN_PASSWORD
from fixtures.fs import get_testdata_file_path
from fixtures.metrics import Metrics
from fixtures.querier import compare_values
from fixtures.querier import compare_values, get_all_warnings
ENDPOINT = "/api/v2/infra_monitoring/statefulsets"
# Required metrics for the v2 statefulsets endpoint
# (pkg/modules/inframonitoring/implinframonitoring/statefulsets_constants.go:24-34).
REQUIRED_METRICS = {
"k8s.pod.phase",
"k8s.pod.cpu.usage",
"k8s.pod.cpu_request_utilization",
"k8s.pod.cpu_limit_utilization",
"k8s.pod.memory.working_set",
"k8s.pod.memory_request_utilization",
"k8s.pod.memory_limit_utilization",
"k8s.statefulset.desired_pods",
"k8s.statefulset.current_pods",
}
def test_statefulsets_accuracy(
signoz: types.SigNoz,
@@ -75,7 +61,8 @@ def test_statefulsets_accuracy(
# Shape/contract.
assert data["total"] == len(expected["records"])
assert len(data["records"]) == len(expected["records"])
assert data["requiredMetricsCheck"]["missingMetrics"] == []
# Full data present -> no warnings surfaced.
assert get_all_warnings(response.json()) == []
assert data["endTimeBeforeRetention"] is False
assert {r["statefulSetName"] for r in data["records"]} == set(exp_by_name.keys())
@@ -123,40 +110,6 @@ def test_statefulsets_accuracy(
assert record["podCountsByPhase"] == exp["podCountsByPhase"]
def test_statefulsets_missing_metrics(
signoz: types.SigNoz,
create_user_admin: None, # pylint: disable=unused-argument
get_token,
insert_metrics,
) -> None:
"""Seed only k8s.pod.cpu.usage; assert other 8 required metrics flagged missing."""
now = datetime.now(tz=UTC).replace(microsecond=0)
insert_metrics(
Metrics.load_from_file(
get_testdata_file_path("inframonitoring/statefulsets_missing_metrics.jsonl"),
base_time=now - timedelta(minutes=4),
)
)
token = get_token(USER_ADMIN_EMAIL, USER_ADMIN_PASSWORD)
response = requests.post(
signoz.self.host_configs["8080"].get(ENDPOINT),
headers={"authorization": f"Bearer {token}"},
json={
"start": int((now - timedelta(minutes=5)).timestamp() * 1000),
"end": int(now.timestamp() * 1000),
"limit": 50,
},
timeout=5,
)
assert response.status_code == HTTPStatus.OK, response.text
data = response.json()["data"]
assert set(data["requiredMetricsCheck"]["missingMetrics"]) == (REQUIRED_METRICS - {"k8s.pod.cpu.usage"})
assert data["records"] == []
assert data["total"] == 0
@pytest.mark.parametrize(
"expression,expected",
[

View File

@@ -11,26 +11,10 @@ from fixtures import types
from fixtures.auth import USER_ADMIN_EMAIL, USER_ADMIN_PASSWORD
from fixtures.fs import get_testdata_file_path
from fixtures.metrics import Metrics
from fixtures.querier import compare_values
from fixtures.querier import compare_values, get_all_warnings
ENDPOINT = "/api/v2/infra_monitoring/jobs"
# Required metrics for the v2 jobs endpoint
# (pkg/modules/inframonitoring/implinframonitoring/jobs_constants.go:24-36).
REQUIRED_METRICS = {
"k8s.pod.phase",
"k8s.pod.cpu.usage",
"k8s.pod.cpu_request_utilization",
"k8s.pod.cpu_limit_utilization",
"k8s.pod.memory.working_set",
"k8s.pod.memory_request_utilization",
"k8s.pod.memory_limit_utilization",
"k8s.job.active_pods",
"k8s.job.failed_pods",
"k8s.job.successful_pods",
"k8s.job.desired_successful_pods",
}
def test_jobs_accuracy(
signoz: types.SigNoz,
@@ -78,7 +62,8 @@ def test_jobs_accuracy(
# Shape/contract.
assert data["total"] == len(expected["records"])
assert len(data["records"]) == len(expected["records"])
assert data["requiredMetricsCheck"]["missingMetrics"] == []
# Full data present -> no warnings surfaced.
assert get_all_warnings(response.json()) == []
assert data["endTimeBeforeRetention"] is False
assert {r["jobName"] for r in data["records"]} == set(exp_by_name.keys())
@@ -128,38 +113,91 @@ def test_jobs_accuracy(
assert record["podCountsByPhase"] == exp["podCountsByPhase"]
def test_jobs_missing_metrics(
@pytest.mark.parametrize(
"case",
[
# Scenario 1: required metrics were never ingested. Post-#11754 the querier
# drops them (no hard error), so the endpoint returns 200 with the job that
# DOES have data; never-seen columns are the -1 sentinel + a
# "have never been received" warning. No formulas; pod- and job-level
# metrics each map to one column.
pytest.param(
{
"dataset": "jobs_missing_metrics.jsonl", # seeds only k8s.pod.cpu.usage
"body": {"filter": {"expression": "k8s.job.name = 'miss-job'"}},
"warn_substrings": ["never been received"],
"warn_names": [
"k8s.pod.memory.working_set",
"k8s.job.desired_successful_pods",
"k8s.job.successful_pods",
],
"data_fields": ["jobCPU"],
"no_data_fields": [
"jobCPURequest",
"jobCPULimit",
"jobMemory",
"jobMemoryRequest",
"jobMemoryLimit",
"desiredSuccessfulPods",
"activePods",
"failedPods",
"successfulPods",
],
},
id="metric_never_seen",
),
],
)
def test_jobs_warnings(
signoz: types.SigNoz,
create_user_admin: None, # pylint: disable=unused-argument
get_token,
insert_metrics,
case: dict,
) -> None:
"""Seed only k8s.pod.cpu.usage; assert other 10 required metrics flagged missing."""
"""A never-ingested metric surfaces a non-blocking warning (200 + data), not a
hard error: the endpoint returns the entity that DOES have data and the
never-seen columns carry the -1 sentinel. (The generic never-seen
(metric, key)-pair-via-groupBy warning is entity-agnostic and is exercised
once, for hosts, in 01_hosts.py.)"""
now = datetime.now(tz=UTC).replace(microsecond=0)
insert_metrics(
Metrics.load_from_file(
get_testdata_file_path("inframonitoring/jobs_missing_metrics.jsonl"),
get_testdata_file_path(f"inframonitoring/{case['dataset']}"),
base_time=now - timedelta(minutes=4),
)
)
token = get_token(USER_ADMIN_EMAIL, USER_ADMIN_PASSWORD)
body: dict = {
"start": int((now - timedelta(minutes=5)).timestamp() * 1000),
"end": int(now.timestamp() * 1000),
"limit": 50,
}
body.update(case["body"])
response = requests.post(
signoz.self.host_configs["8080"].get(ENDPOINT),
headers={"authorization": f"Bearer {token}"},
json={
"start": int((now - timedelta(minutes=5)).timestamp() * 1000),
"end": int(now.timestamp() * 1000),
"limit": 50,
},
json=body,
timeout=5,
)
assert response.status_code == HTTPStatus.OK, response.text
data = response.json()["data"]
warnings = get_all_warnings(response.json())
assert set(data["requiredMetricsCheck"]["missingMetrics"]) == (REQUIRED_METRICS - {"k8s.pod.cpu.usage"})
assert data["records"] == []
assert data["total"] == 0
for substr in case["warn_substrings"]:
assert any(substr in w["message"] for w in warnings), f"{substr!r} not surfaced: {warnings!r}"
for name in case["warn_names"]:
assert any(name in w["message"] for w in warnings), f"{name!r} not surfaced: {warnings!r}"
assert len(data["records"]) >= 1, f"expected at least one record: {data!r}"
if case["data_fields"] or case["no_data_fields"]:
record = data["records"][0]
for field in case["data_fields"]:
assert record[field] != -1, f"expected {field} populated, got {record[field]}"
for field in case["no_data_fields"]:
assert record[field] == -1, f"expected {field} == -1 sentinel, got {record[field]}"
@pytest.mark.parametrize(

View File

@@ -11,24 +11,10 @@ from fixtures import types
from fixtures.auth import USER_ADMIN_EMAIL, USER_ADMIN_PASSWORD
from fixtures.fs import get_testdata_file_path
from fixtures.metrics import Metrics
from fixtures.querier import compare_values
from fixtures.querier import compare_values, get_all_warnings
ENDPOINT = "/api/v2/infra_monitoring/daemonsets"
# Required metrics for the v2 daemonsets endpoint
# (pkg/modules/inframonitoring/implinframonitoring/daemonsets_constants.go:24-34).
REQUIRED_METRICS = {
"k8s.pod.phase",
"k8s.pod.cpu.usage",
"k8s.pod.cpu_request_utilization",
"k8s.pod.cpu_limit_utilization",
"k8s.pod.memory.working_set",
"k8s.pod.memory_request_utilization",
"k8s.pod.memory_limit_utilization",
"k8s.daemonset.desired_scheduled_nodes",
"k8s.daemonset.current_scheduled_nodes",
}
def test_daemonsets_accuracy(
signoz: types.SigNoz,
@@ -75,7 +61,8 @@ def test_daemonsets_accuracy(
# Shape/contract.
assert data["total"] == len(expected["records"])
assert len(data["records"]) == len(expected["records"])
assert data["requiredMetricsCheck"]["missingMetrics"] == []
# Full data present -> no warnings surfaced.
assert get_all_warnings(response.json()) == []
assert data["endTimeBeforeRetention"] is False
assert {r["daemonSetName"] for r in data["records"]} == set(exp_by_name.keys())
@@ -123,40 +110,6 @@ def test_daemonsets_accuracy(
assert record["podCountsByPhase"] == exp["podCountsByPhase"]
def test_daemonsets_missing_metrics(
signoz: types.SigNoz,
create_user_admin: None, # pylint: disable=unused-argument
get_token,
insert_metrics,
) -> None:
"""Seed only k8s.pod.cpu.usage; assert other 8 required metrics flagged missing."""
now = datetime.now(tz=UTC).replace(microsecond=0)
insert_metrics(
Metrics.load_from_file(
get_testdata_file_path("inframonitoring/daemonsets_missing_metrics.jsonl"),
base_time=now - timedelta(minutes=4),
)
)
token = get_token(USER_ADMIN_EMAIL, USER_ADMIN_PASSWORD)
response = requests.post(
signoz.self.host_configs["8080"].get(ENDPOINT),
headers={"authorization": f"Bearer {token}"},
json={
"start": int((now - timedelta(minutes=5)).timestamp() * 1000),
"end": int(now.timestamp() * 1000),
"limit": 50,
},
timeout=5,
)
assert response.status_code == HTTPStatus.OK, response.text
data = response.json()["data"]
assert set(data["requiredMetricsCheck"]["missingMetrics"]) == (REQUIRED_METRICS - {"k8s.pod.cpu.usage"})
assert data["records"] == []
assert data["total"] == 0
@pytest.mark.parametrize(
"expression,expected",
[

View File

@@ -15,7 +15,6 @@ from fixtures.querier import (
build_builder_query,
find_named_result,
get_all_warnings,
get_error_message,
index_series_by_label,
make_query_request,
)

View File

@@ -0,0 +1,174 @@
from collections.abc import Callable
from http import HTTPStatus
import requests
from fixtures import types
from fixtures.auth import USER_ADMIN_EMAIL, USER_ADMIN_PASSWORD
GROUPS_PATH = "/api/v1/span_mapper_groups"
def _auth_headers(token: str) -> dict[str, str]:
return {
"authorization": f"Bearer {token}",
"content-type": "application/json",
}
def test_create_groups_and_simulate_with_backfill(
signoz: types.SigNoz,
create_user_admin: types.Operation, # pylint: disable=unused-argument
get_token: Callable[[str, str], str],
) -> None:
"""
Setup:
Create a mapping group and a mapper through the CRUD API, then hit the
simulate endpoint with two groups: the saved one referenced by name only
(server backfills its mappers from the store) and a second, unsaved group
sent with inline mappers.
Tests:
1. Create a group (POST /span_mapper_groups) and read back its id
2. Create a mapper in that group (POST .../{groupId}/span_mappers)
3. List groups and mappers and verify what we created is persisted
4. Simulate spans against both groups: a matching span gets the saved
group's mappers (backfilled, copy) and the inline group's mappers
(move) applied, while a span matching no condition passes through
5. Delete the group and verify it (and its mappers) are gone
"""
token = get_token(USER_ADMIN_EMAIL, USER_ADMIN_PASSWORD)
create_group = requests.post(
signoz.self.host_configs["8080"].get(GROUPS_PATH),
timeout=10,
headers=_auth_headers(token),
json={
"name": "llm-backfill",
"condition": {"attributes": ["model"], "resource": []},
"enabled": True,
},
)
assert create_group.status_code == HTTPStatus.CREATED
group = create_group.json()["data"]
group_id = group["id"]
assert group["name"] == "llm-backfill"
assert group["enabled"] is True
create_mapper = requests.post(
signoz.self.host_configs["8080"].get(f"{GROUPS_PATH}/{group_id}/span_mappers"),
timeout=10,
headers=_auth_headers(token),
json={
"name": "gen_ai.request.model",
"fieldContext": "attribute",
"config": {
"sources": [
{
"key": "llm.model",
"context": "attribute",
"operation": "copy",
"priority": 1,
}
]
},
"enabled": True,
},
)
assert create_mapper.status_code == HTTPStatus.CREATED
mapper = create_mapper.json()["data"]
assert mapper["name"] == "gen_ai.request.model"
assert mapper["group_id"] == group_id
list_groups = requests.get(
signoz.self.host_configs["8080"].get(GROUPS_PATH),
timeout=10,
headers=_auth_headers(token),
)
assert list_groups.status_code == HTTPStatus.OK
assert group_id in [g["id"] for g in list_groups.json()["data"]["items"]]
list_mappers = requests.get(
signoz.self.host_configs["8080"].get(f"{GROUPS_PATH}/{group_id}/span_mappers"),
timeout=10,
headers=_auth_headers(token),
)
assert list_mappers.status_code == HTTPStatus.OK
assert "gen_ai.request.model" in [m["name"] for m in list_mappers.json()["data"]["items"]]
simulate = requests.post(
signoz.self.host_configs["8080"].get(f"{GROUPS_PATH}/test"),
timeout=10,
headers=_auth_headers(token),
json={
"spans": [
{
"attributes": {"llm.model": "gpt-4", "db.system": "postgres"},
"resource": {},
},
# Matches no group condition, so it must pass through untouched.
{
"attributes": {"http.method": "GET"},
"resource": {},
},
],
"groups": [
# No "mappers" key: the server backfills them from the saved group.
{
"name": "llm-backfill",
"condition": {"attributes": ["model"], "resource": []},
"enabled": True,
},
# Unsaved group; mappers provided inline.
{
"name": "db-inline",
"condition": {"attributes": ["db"], "resource": []},
"enabled": True,
"mappers": [
{
"name": "db.name",
"fieldContext": "attribute",
"config": {
"sources": [
{
"key": "db.system",
"context": "attribute",
"operation": "move",
"priority": 1,
}
]
},
"enabled": True,
}
],
},
],
},
)
assert simulate.status_code == HTTPStatus.OK
out_spans = simulate.json()["data"]["spans"]
assert len(out_spans) == 2
attrs = out_spans[0]["attributes"]
assert attrs["gen_ai.request.model"] == "gpt-4" # backfilled mapper applied
assert attrs["llm.model"] == "gpt-4" # copy preserves source
assert attrs["db.name"] == "postgres" # inline mapper applied
assert "db.system" not in attrs # move removes source
assert out_spans[1]["attributes"] == {"http.method": "GET"} # unchanged
delete_group = requests.delete(
signoz.self.host_configs["8080"].get(f"{GROUPS_PATH}/{group_id}"),
timeout=10,
headers=_auth_headers(token),
)
assert delete_group.status_code == HTTPStatus.NO_CONTENT
list_after_delete = requests.get(
signoz.self.host_configs["8080"].get(GROUPS_PATH),
timeout=10,
headers=_auth_headers(token),
)
assert list_after_delete.status_code == HTTPStatus.OK
assert group_id not in [g["id"] for g in list_after_delete.json()["data"]["items"]]