Compare commits

..

21 Commits

Author SHA1 Message Date
Piyush Singariya
b30bfa6371 fix: better review for test file 2026-04-02 12:53:44 +05:30
Piyush Singariya
e7f4a04b36 Merge branch 'main' into fix/array-json 2026-04-01 15:44:01 +05:30
Piyush Singariya
0687634da3 fix: stringified integer value input 2026-04-01 15:25:35 +05:30
Piyush Singariya
7e7732243e fix: dynamic array tests 2026-04-01 12:54:26 +05:30
Piyush Singariya
2f952e402f feat: change filtering of dynamic arrays 2026-04-01 12:09:32 +05:30
Piyush Singariya
a12febca4a fix: array json element comparison 2026-04-01 10:34:55 +05:30
Piyush Singariya
cb71c9c3f7 Merge branch 'main' into fix/array-json 2026-03-31 15:42:09 +05:30
Piyush Singariya
1cd4ce6509 Merge branch 'main' into fix/array-json 2026-03-31 14:55:36 +05:30
Piyush Singariya
9299c8ab18 fix: indexed unit tests 2026-03-30 15:47:47 +05:30
Piyush Singariya
24749de269 fix: comment 2026-03-30 15:16:28 +05:30
Piyush Singariya
39098ec3f4 fix: unit tests 2026-03-30 15:12:17 +05:30
Piyush Singariya
fe554f5c94 fix: remove not used paths from testdata 2026-03-30 14:24:48 +05:30
Piyush Singariya
8a60a041a6 fix: unit tests 2026-03-30 14:14:49 +05:30
Piyush Singariya
541f19c34a fix: array type filtering from dynamic arrays 2026-03-30 12:59:31 +05:30
Piyush Singariya
010db03d6e fix: indexed tests passing 2026-03-30 12:24:26 +05:30
Piyush Singariya
5408acbd8c fix: primitive conditions working 2026-03-30 12:01:35 +05:30
Piyush Singariya
0de6c85f81 feat: align negative operators to include other logs 2026-03-28 10:30:11 +05:30
Piyush Singariya
69ec24fa05 test: fix unit tests 2026-03-27 15:12:49 +05:30
Piyush Singariya
539d732b65 fix: contextual path index usage 2026-03-27 14:44:51 +05:30
Piyush Singariya
843d5fb199 Merge branch 'main' into feat/json-index 2026-03-27 14:17:52 +05:30
Piyush Singariya
fabdfb8cc1 feat: enable JSON Path index 2026-03-27 14:07:37 +05:30
666 changed files with 7985 additions and 82721 deletions

View File

@@ -55,8 +55,6 @@ jobs:
sqlstore-provider:
- postgres
- sqlite
sqlite-mode:
- wal
clickhouse-version:
- 25.5.6
- 25.12.5
@@ -104,7 +102,6 @@ jobs:
--basetemp=./tmp/ \
src/${{matrix.src}} \
--sqlstore-provider ${{matrix.sqlstore-provider}} \
--sqlite-mode ${{matrix.sqlite-mode}} \
--postgres-version ${{matrix.postgres-version}} \
--clickhouse-version ${{matrix.clickhouse-version}} \
--schema-migrator-version ${{matrix.schema-migrator-version}}

View File

@@ -86,7 +86,7 @@ sqlstore:
# The path to the SQLite database file.
path: /var/lib/signoz/signoz.db
# The journal mode for the sqlite database. Supported values: delete, wal.
mode: wal
mode: delete
# The timeout for the sqlite database to wait for a lock.
busy_timeout: 10s
# The default transaction locking behavior. Supported values: deferred, immediate, exclusive.

View File

@@ -327,6 +327,27 @@ components:
nullable: true
type: array
type: object
AuthtypesStorableRole:
properties:
createdAt:
format: date-time
type: string
description:
type: string
id:
type: string
name:
type: string
orgId:
type: string
type:
type: string
updatedAt:
format: date-time
type: string
required:
- id
type: object
AuthtypesTransaction:
properties:
object:
@@ -350,7 +371,7 @@ components:
id:
type: string
role:
$ref: '#/components/schemas/AuthtypesRole'
$ref: '#/components/schemas/AuthtypesStorableRole'
roleId:
type: string
updatedAt:
@@ -360,11 +381,6 @@ components:
type: string
required:
- id
- userId
- roleId
- createdAt
- updatedAt
- role
type: object
AuthtypesUserWithRoles:
properties:
@@ -2297,6 +2313,15 @@ components:
- status
- error
type: object
RulestatehistorytypesAlertState:
enum:
- inactive
- pending
- recovering
- firing
- nodata
- disabled
type: string
RulestatehistorytypesGettableRuleStateHistory:
properties:
fingerprint:
@@ -2308,15 +2333,15 @@ components:
nullable: true
type: array
overallState:
$ref: '#/components/schemas/RuletypesAlertState'
$ref: '#/components/schemas/RulestatehistorytypesAlertState'
overallStateChanged:
type: boolean
ruleId:
ruleID:
type: string
ruleName:
type: string
state:
$ref: '#/components/schemas/RuletypesAlertState'
$ref: '#/components/schemas/RulestatehistorytypesAlertState'
stateChanged:
type: boolean
unixMilli:
@@ -2326,7 +2351,7 @@ components:
format: double
type: number
required:
- ruleId
- ruleID
- ruleName
- overallState
- overallStateChanged
@@ -2416,21 +2441,12 @@ components:
format: int64
type: integer
state:
$ref: '#/components/schemas/RuletypesAlertState'
$ref: '#/components/schemas/RulestatehistorytypesAlertState'
required:
- state
- start
- end
type: object
RuletypesAlertState:
enum:
- inactive
- pending
- recovering
- firing
- nodata
- disabled
type: string
ServiceaccounttypesGettableFactorAPIKey:
properties:
createdAt:
@@ -8453,7 +8469,7 @@ paths:
- in: query
name: state
schema:
$ref: '#/components/schemas/RuletypesAlertState'
$ref: '#/components/schemas/RulestatehistorytypesAlertState'
- in: query
name: filterExpression
schema:

View File

@@ -193,7 +193,6 @@ uv run pytest --basetemp=./tmp/ -vv --reuse src/passwordauthn/01_register.py::te
Tests can be configured using pytest options:
- `--sqlstore-provider` - Choose database provider (default: postgres)
- `--sqlite-mode` - SQLite journal mode: `delete` or `wal` (default: delete). Only relevant when `--sqlstore-provider=sqlite`.
- `--postgres-version` - PostgreSQL version (default: 15)
- `--clickhouse-version` - ClickHouse version (default: 25.5.6)
- `--zookeeper-version` - Zookeeper version (default: 3.7.1)
@@ -203,6 +202,7 @@ Example:
uv run pytest --basetemp=./tmp/ -vv --reuse --sqlstore-provider=postgres --postgres-version=14 src/auth/
```
## What should I remember?
- **Always use the `--reuse` flag** when setting up the environment to keep containers running
@@ -213,4 +213,3 @@ uv run pytest --basetemp=./tmp/ -vv --reuse --sqlstore-provider=postgres --postg
- **Use descriptive test names** that clearly indicate what is being tested
- **Leverage fixtures** for common setup and authentication
- **Test both success and failure scenarios** to ensure robust functionality
- **`--sqlite-mode=wal` does not work on macOS.** The integration test environment runs SigNoz inside a Linux container with the SQLite database file mounted from the macOS host. WAL mode requires shared memory between connections, and connections crossing the VM boundary (macOS host ↔ Linux container) cannot share the WAL index, resulting in `SQLITE_IOERR_SHORT_READ`. WAL mode is tested in CI on Linux only.

View File

@@ -32,7 +32,7 @@ func (s Seasonality) IsValid() bool {
}
type AnomaliesRequest struct {
Params *qbtypes.QueryRangeRequest
Params qbtypes.QueryRangeRequest
Seasonality Seasonality
}
@@ -81,7 +81,7 @@ type anomalyQueryParams struct {
Past3SeasonQuery qbtypes.QueryRangeRequest
}
func prepareAnomalyQueryParams(req *qbtypes.QueryRangeRequest, seasonality Seasonality) *anomalyQueryParams {
func prepareAnomalyQueryParams(req qbtypes.QueryRangeRequest, seasonality Seasonality) *anomalyQueryParams {
start := req.Start
end := req.End

View File

@@ -76,12 +76,12 @@ func (provider *provider) Start(ctx context.Context) error {
}
func (provider *provider) Audit(ctx context.Context, event audittypes.AuditEvent) {
if event.PrincipalAttributes.PrincipalOrgID.IsZero() {
if event.PrincipalOrgID.IsZero() {
provider.settings.Logger().WarnContext(ctx, "audit event dropped as org_id is zero")
return
}
if _, err := provider.licensing.GetActive(ctx, event.PrincipalAttributes.PrincipalOrgID); err != nil {
if _, err := provider.licensing.GetActive(ctx, event.PrincipalOrgID); err != nil {
return
}

View File

@@ -65,7 +65,7 @@ func (h *handler) QueryRange(rw http.ResponseWriter, req *http.Request) {
}
if anomalyQuery, ok := queryRangeRequest.IsAnomalyRequest(); ok {
anomalies, err := h.handleAnomalyQuery(ctx, orgID, anomalyQuery, &queryRangeRequest)
anomalies, err := h.handleAnomalyQuery(ctx, orgID, anomalyQuery, queryRangeRequest)
if err != nil {
render.Error(rw, errors.NewInternalf(errors.CodeInternal, "failed to get anomalies: %v", err))
return
@@ -149,7 +149,7 @@ func (h *handler) createAnomalyProvider(seasonality anomalyV2.Seasonality) anoma
}
}
func (h *handler) handleAnomalyQuery(ctx context.Context, orgID valuer.UUID, anomalyQuery *qbtypes.QueryBuilderQuery[qbtypes.MetricAggregation], queryRangeRequest *qbtypes.QueryRangeRequest) (*anomalyV2.AnomaliesResponse, error) {
func (h *handler) handleAnomalyQuery(ctx context.Context, orgID valuer.UUID, anomalyQuery *qbtypes.QueryBuilderQuery[qbtypes.MetricAggregation], queryRangeRequest qbtypes.QueryRangeRequest) (*anomalyV2.AnomaliesResponse, error) {
seasonality := extractSeasonality(anomalyQuery)
provider := h.createAnomalyProvider(seasonality)

View File

@@ -49,6 +49,7 @@ import (
opAmpModel "github.com/SigNoz/signoz/pkg/query-service/app/opamp/model"
baseconst "github.com/SigNoz/signoz/pkg/query-service/constants"
"github.com/SigNoz/signoz/pkg/query-service/healthcheck"
baseint "github.com/SigNoz/signoz/pkg/query-service/interfaces"
baserules "github.com/SigNoz/signoz/pkg/query-service/rules"
"github.com/SigNoz/signoz/pkg/query-service/utils"
)
@@ -98,6 +99,7 @@ func NewServer(config signoz.Config, signoz *signoz.SigNoz) (*Server, error) {
)
rm, err := makeRulesManager(
reader,
signoz.Cache,
signoz.Alertmanager,
signoz.SQLStore,
@@ -227,7 +229,7 @@ func (s *Server) createPublicServer(apiHandler *api.APIHandler, web web.Web) (*h
s.config.APIServer.Timeout.Default,
s.config.APIServer.Timeout.Max,
).Wrap)
r.Use(middleware.NewAudit(s.signoz.Instrumentation.Logger(), s.config.APIServer.Logging.ExcludedRoutes, nil).Wrap)
r.Use(middleware.NewLogging(s.signoz.Instrumentation.Logger(), s.config.APIServer.Logging.ExcludedRoutes).Wrap)
r.Use(middleware.NewComment().Wrap)
apiHandler.RegisterRoutes(r, am)
@@ -343,7 +345,7 @@ func (s *Server) Stop(ctx context.Context) error {
return nil
}
func makeRulesManager(cache cache.Cache, alertmanager alertmanager.Alertmanager, sqlstore sqlstore.SQLStore, telemetryStore telemetrystore.TelemetryStore, metadataStore telemetrytypes.MetadataStore, prometheus prometheus.Prometheus, orgGetter organization.Getter, ruleStateHistoryModule rulestatehistory.Module, querier querier.Querier, providerSettings factory.ProviderSettings, queryParser queryparser.QueryParser) (*baserules.Manager, error) {
func makeRulesManager(ch baseint.Reader, cache cache.Cache, alertmanager alertmanager.Alertmanager, sqlstore sqlstore.SQLStore, telemetryStore telemetrystore.TelemetryStore, metadataStore telemetrytypes.MetadataStore, prometheus prometheus.Prometheus, orgGetter organization.Getter, ruleStateHistoryModule rulestatehistory.Module, querier querier.Querier, providerSettings factory.ProviderSettings, queryParser queryparser.QueryParser) (*baserules.Manager, error) {
ruleStore := sqlrulestore.NewRuleStore(sqlstore, queryParser, providerSettings)
maintenanceStore := sqlrulestore.NewMaintenanceStore(sqlstore)
// create manager opts
@@ -352,6 +354,7 @@ func makeRulesManager(cache cache.Cache, alertmanager alertmanager.Alertmanager,
MetadataStore: metadataStore,
Prometheus: prometheus,
Context: context.Background(),
Reader: ch,
Querier: querier,
Logger: providerSettings.Logger,
Cache: cache,
@@ -362,7 +365,7 @@ func makeRulesManager(cache cache.Cache, alertmanager alertmanager.Alertmanager,
OrgGetter: orgGetter,
RuleStore: ruleStore,
MaintenanceStore: maintenanceStore,
SQLStore: sqlstore,
SqlStore: sqlstore,
QueryParser: queryParser,
RuleStateHistoryModule: ruleStateHistoryModule,
}

View File

@@ -5,34 +5,58 @@ import (
"encoding/json"
"fmt"
"log/slog"
"math"
"strings"
"sync"
"time"
"github.com/SigNoz/signoz/ee/query-service/anomaly"
"github.com/SigNoz/signoz/pkg/cache"
"github.com/SigNoz/signoz/pkg/errors"
"github.com/SigNoz/signoz/pkg/querier"
"github.com/SigNoz/signoz/pkg/types/rulestatehistorytypes"
"github.com/SigNoz/signoz/pkg/query-service/common"
"github.com/SigNoz/signoz/pkg/query-service/model"
"github.com/SigNoz/signoz/pkg/transition"
"github.com/SigNoz/signoz/pkg/types/ruletypes"
"github.com/SigNoz/signoz/pkg/valuer"
querierV2 "github.com/SigNoz/signoz/pkg/query-service/app/querier/v2"
"github.com/SigNoz/signoz/pkg/query-service/app/queryBuilder"
"github.com/SigNoz/signoz/pkg/query-service/interfaces"
v3 "github.com/SigNoz/signoz/pkg/query-service/model/v3"
"github.com/SigNoz/signoz/pkg/query-service/utils/labels"
"github.com/SigNoz/signoz/pkg/query-service/utils/times"
"github.com/SigNoz/signoz/pkg/query-service/utils/timestamp"
"github.com/SigNoz/signoz/pkg/units"
baserules "github.com/SigNoz/signoz/pkg/query-service/rules"
"github.com/SigNoz/signoz/ee/anomaly"
querierV5 "github.com/SigNoz/signoz/pkg/querier"
anomalyV2 "github.com/SigNoz/signoz/ee/anomaly"
qbtypes "github.com/SigNoz/signoz/pkg/types/querybuildertypes/querybuildertypesv5"
)
const (
RuleTypeAnomaly = "anomaly_rule"
)
type AnomalyRule struct {
*baserules.BaseRule
mtx sync.Mutex
// querier is used for alerts migrated after the introduction of new query builder
querier querier.Querier
reader interfaces.Reader
provider anomaly.Provider
// querierV2 is used for alerts created after the introduction of new metrics query builder
querierV2 interfaces.Querier
// querierV5 is used for alerts migrated after the introduction of new query builder
querierV5 querierV5.Querier
provider anomaly.Provider
providerV2 anomalyV2.Provider
version string
logger *slog.Logger
@@ -46,16 +70,18 @@ func NewAnomalyRule(
id string,
orgID valuer.UUID,
p *ruletypes.PostableRule,
querier querier.Querier,
reader interfaces.Reader,
querierV5 querierV5.Querier,
logger *slog.Logger,
cache cache.Cache,
opts ...baserules.RuleOption,
) (*AnomalyRule, error) {
logger.Info("creating new AnomalyRule", slog.String("rule.id", id))
logger.Info("creating new AnomalyRule", "rule_id", id)
opts = append(opts, baserules.WithLogger(logger))
baseRule, err := baserules.NewBaseRule(id, orgID, p, opts...)
baseRule, err := baserules.NewBaseRule(id, orgID, p, reader, opts...)
if err != nil {
return nil, err
}
@@ -75,38 +101,93 @@ func NewAnomalyRule(
t.seasonality = anomaly.SeasonalityDaily
}
logger.Info("using seasonality", slog.String("rule.id", id), slog.String("rule.seasonality", t.seasonality.StringValue()))
logger.Info("using seasonality", "seasonality", t.seasonality.String())
querierOptsV2 := querierV2.QuerierOptions{
Reader: reader,
Cache: cache,
KeyGenerator: queryBuilder.NewKeyGenerator(),
}
t.querierV2 = querierV2.NewQuerier(querierOptsV2)
t.reader = reader
if t.seasonality == anomaly.SeasonalityHourly {
t.provider = anomaly.NewHourlyProvider(
anomaly.WithQuerier[*anomaly.HourlyProvider](querier),
anomaly.WithLogger[*anomaly.HourlyProvider](logger),
anomaly.WithCache[*anomaly.HourlyProvider](cache),
anomaly.WithKeyGenerator[*anomaly.HourlyProvider](queryBuilder.NewKeyGenerator()),
anomaly.WithReader[*anomaly.HourlyProvider](reader),
)
} else if t.seasonality == anomaly.SeasonalityDaily {
t.provider = anomaly.NewDailyProvider(
anomaly.WithQuerier[*anomaly.DailyProvider](querier),
anomaly.WithLogger[*anomaly.DailyProvider](logger),
anomaly.WithCache[*anomaly.DailyProvider](cache),
anomaly.WithKeyGenerator[*anomaly.DailyProvider](queryBuilder.NewKeyGenerator()),
anomaly.WithReader[*anomaly.DailyProvider](reader),
)
} else if t.seasonality == anomaly.SeasonalityWeekly {
t.provider = anomaly.NewWeeklyProvider(
anomaly.WithQuerier[*anomaly.WeeklyProvider](querier),
anomaly.WithLogger[*anomaly.WeeklyProvider](logger),
anomaly.WithCache[*anomaly.WeeklyProvider](cache),
anomaly.WithKeyGenerator[*anomaly.WeeklyProvider](queryBuilder.NewKeyGenerator()),
anomaly.WithReader[*anomaly.WeeklyProvider](reader),
)
}
t.querier = querier
if t.seasonality == anomaly.SeasonalityHourly {
t.providerV2 = anomalyV2.NewHourlyProvider(
anomalyV2.WithQuerier[*anomalyV2.HourlyProvider](querierV5),
anomalyV2.WithLogger[*anomalyV2.HourlyProvider](logger),
)
} else if t.seasonality == anomaly.SeasonalityDaily {
t.providerV2 = anomalyV2.NewDailyProvider(
anomalyV2.WithQuerier[*anomalyV2.DailyProvider](querierV5),
anomalyV2.WithLogger[*anomalyV2.DailyProvider](logger),
)
} else if t.seasonality == anomaly.SeasonalityWeekly {
t.providerV2 = anomalyV2.NewWeeklyProvider(
anomalyV2.WithQuerier[*anomalyV2.WeeklyProvider](querierV5),
anomalyV2.WithLogger[*anomalyV2.WeeklyProvider](logger),
)
}
t.querierV5 = querierV5
t.version = p.Version
t.logger = logger
return &t, nil
}
func (r *AnomalyRule) Type() ruletypes.RuleType {
return ruletypes.RuleTypeAnomaly
return RuleTypeAnomaly
}
func (r *AnomalyRule) prepareQueryRange(ctx context.Context, ts time.Time) *qbtypes.QueryRangeRequest {
func (r *AnomalyRule) prepareQueryRange(ctx context.Context, ts time.Time) (*v3.QueryRangeParamsV3, error) {
r.logger.InfoContext(ctx, "prepare query range request", slog.String("rule.id", r.ID()), slog.Int64("ts", ts.UnixMilli()), slog.Int64("eval.window_ms", r.EvalWindow().Milliseconds()), slog.Int64("eval.delay_ms", r.EvalDelay().Milliseconds()))
r.logger.InfoContext(
ctx, "prepare query range request v4", "ts", ts.UnixMilli(), "eval_window", r.EvalWindow().Milliseconds(), "eval_delay", r.EvalDelay().Milliseconds(),
)
st, en := r.Timestamps(ts)
start := st.UnixMilli()
end := en.UnixMilli()
compositeQuery := r.Condition().CompositeQuery
if compositeQuery.PanelType != v3.PanelTypeGraph {
compositeQuery.PanelType = v3.PanelTypeGraph
}
// default mode
return &v3.QueryRangeParamsV3{
Start: start,
End: end,
Step: int64(math.Max(float64(common.MinAllowedStepInterval(start, end)), 60)),
CompositeQuery: compositeQuery,
Variables: make(map[string]interface{}, 0),
NoCache: false,
}, nil
}
func (r *AnomalyRule) prepareQueryRangeV5(ctx context.Context, ts time.Time) (*qbtypes.QueryRangeRequest, error) {
r.logger.InfoContext(ctx, "prepare query range request v5", "ts", ts.UnixMilli(), "eval_window", r.EvalWindow().Milliseconds(), "eval_delay", r.EvalDelay().Milliseconds())
startTs, endTs := r.Timestamps(ts)
start, end := startTs.UnixMilli(), endTs.UnixMilli()
@@ -122,14 +203,25 @@ func (r *AnomalyRule) prepareQueryRange(ctx context.Context, ts time.Time) *qbty
}
req.CompositeQuery.Queries = make([]qbtypes.QueryEnvelope, len(r.Condition().CompositeQuery.Queries))
copy(req.CompositeQuery.Queries, r.Condition().CompositeQuery.Queries)
return req
return req, nil
}
func (r *AnomalyRule) GetSelectedQuery() string {
return r.Condition().GetSelectedQueryName()
}
func (r *AnomalyRule) buildAndRunQuery(ctx context.Context, orgID valuer.UUID, ts time.Time) (ruletypes.Vector, error) {
params := r.prepareQueryRange(ctx, ts)
params, err := r.prepareQueryRange(ctx, ts)
if err != nil {
return nil, err
}
err = r.PopulateTemporality(ctx, orgID, params)
if err != nil {
return nil, fmt.Errorf("internal error while setting temporality")
}
anomalies, err := r.provider.GetAnomalies(ctx, orgID, &anomaly.AnomaliesRequest{
anomalies, err := r.provider.GetAnomalies(ctx, orgID, &anomaly.GetAnomaliesRequest{
Params: params,
Seasonality: r.seasonality,
})
@@ -137,43 +229,87 @@ func (r *AnomalyRule) buildAndRunQuery(ctx context.Context, orgID valuer.UUID, t
return nil, err
}
var queryResult *qbtypes.TimeSeriesData
var queryResult *v3.Result
for _, result := range anomalies.Results {
if result.QueryName == r.SelectedQuery(ctx) {
if result.QueryName == r.GetSelectedQuery() {
queryResult = result
break
}
}
if queryResult == nil {
r.logger.WarnContext(ctx, "nil qb result", slog.String("rule.id", r.ID()), slog.Int64("ts", ts.UnixMilli()))
return ruletypes.Vector{}, nil
}
hasData := len(queryResult.Aggregations) > 0 &&
queryResult.Aggregations[0] != nil &&
len(queryResult.Aggregations[0].AnomalyScores) > 0
hasData := len(queryResult.AnomalyScores) > 0
if missingDataAlert := r.HandleMissingDataAlert(ctx, ts, hasData); missingDataAlert != nil {
return ruletypes.Vector{*missingDataAlert}, nil
} else if !hasData {
r.logger.WarnContext(ctx, "no anomaly result", slog.String("rule.id", r.ID()))
return ruletypes.Vector{}, nil
}
var resultVector ruletypes.Vector
scoresJSON, _ := json.Marshal(queryResult.Aggregations[0].AnomalyScores)
// TODO(srikanthccv): this could be noisy but we do this to answer false alert requests
r.logger.InfoContext(ctx, "anomaly scores", slog.String("rule.id", r.ID()), slog.String("anomaly.scores", string(scoresJSON)))
scoresJSON, _ := json.Marshal(queryResult.AnomalyScores)
r.logger.InfoContext(ctx, "anomaly scores", "scores", string(scoresJSON))
for _, series := range queryResult.AnomalyScores {
if !r.Condition().ShouldEval(series) {
r.logger.InfoContext(ctx, "not enough data points to evaluate series, skipping", "ruleid", r.ID(), "numPoints", len(series.Points), "requiredPoints", r.Condition().RequiredNumPoints)
continue
}
results, err := r.Threshold.Eval(*series, r.Unit(), ruletypes.EvalData{
ActiveAlerts: r.ActiveAlertsLabelFP(),
SendUnmatched: r.ShouldSendUnmatched(),
})
if err != nil {
return nil, err
}
resultVector = append(resultVector, results...)
}
return resultVector, nil
}
func (r *AnomalyRule) buildAndRunQueryV5(ctx context.Context, orgID valuer.UUID, ts time.Time) (ruletypes.Vector, error) {
params, err := r.prepareQueryRangeV5(ctx, ts)
if err != nil {
return nil, err
}
anomalies, err := r.providerV2.GetAnomalies(ctx, orgID, &anomalyV2.AnomaliesRequest{
Params: *params,
Seasonality: anomalyV2.Seasonality{String: valuer.NewString(r.seasonality.String())},
})
if err != nil {
return nil, err
}
var qbResult *qbtypes.TimeSeriesData
for _, result := range anomalies.Results {
if result.QueryName == r.GetSelectedQuery() {
qbResult = result
break
}
}
if qbResult == nil {
r.logger.WarnContext(ctx, "nil qb result", "ts", ts.UnixMilli())
}
queryResult := transition.ConvertV5TimeSeriesDataToV4Result(qbResult)
hasData := len(queryResult.AnomalyScores) > 0
if missingDataAlert := r.HandleMissingDataAlert(ctx, ts, hasData); missingDataAlert != nil {
return ruletypes.Vector{*missingDataAlert}, nil
}
var resultVector ruletypes.Vector
scoresJSON, _ := json.Marshal(queryResult.AnomalyScores)
r.logger.InfoContext(ctx, "anomaly scores", "scores", string(scoresJSON))
// Filter out new series if newGroupEvalDelay is configured
seriesToProcess := queryResult.Aggregations[0].AnomalyScores
seriesToProcess := queryResult.AnomalyScores
if r.ShouldSkipNewGroups() {
filteredSeries, filterErr := r.BaseRule.FilterNewSeries(ctx, ts, seriesToProcess)
// In case of error we log the error and continue with the original series
if filterErr != nil {
r.logger.ErrorContext(ctx, "error filtering new series", slog.String("rule.id", r.ID()), errors.Attr(filterErr))
r.logger.ErrorContext(ctx, "Error filtering new series, ", errors.Attr(filterErr), "rule_name", r.Name())
} else {
seriesToProcess = filteredSeries
}
@@ -181,10 +317,10 @@ func (r *AnomalyRule) buildAndRunQuery(ctx context.Context, orgID valuer.UUID, t
for _, series := range seriesToProcess {
if !r.Condition().ShouldEval(series) {
r.logger.InfoContext(ctx, "not enough data points to evaluate series, skipping", slog.String("rule.id", r.ID()), slog.Int("series.num_points", len(series.Values)), slog.Int("series.required_points", r.Condition().RequiredNumPoints))
r.logger.InfoContext(ctx, "not enough data points to evaluate series, skipping", "ruleid", r.ID(), "numPoints", len(series.Points), "requiredPoints", r.Condition().RequiredNumPoints)
continue
}
results, err := r.Threshold.Eval(series, r.Unit(), ruletypes.EvalData{
results, err := r.Threshold.Eval(*series, r.Unit(), ruletypes.EvalData{
ActiveAlerts: r.ActiveAlertsLabelFP(),
SendUnmatched: r.ShouldSendUnmatched(),
})
@@ -205,9 +341,13 @@ func (r *AnomalyRule) Eval(ctx context.Context, ts time.Time) (int, error) {
var res ruletypes.Vector
var err error
r.logger.InfoContext(ctx, "running query", slog.String("rule.id", r.ID()))
res, err = r.buildAndRunQuery(ctx, r.OrgID(), ts)
if r.version == "v5" {
r.logger.InfoContext(ctx, "running v5 query")
res, err = r.buildAndRunQueryV5(ctx, r.OrgID(), ts)
} else {
r.logger.InfoContext(ctx, "running v4 query")
res, err = r.buildAndRunQuery(ctx, r.OrgID(), ts)
}
if err != nil {
return 0, err
}
@@ -231,7 +371,7 @@ func (r *AnomalyRule) Eval(ctx context.Context, ts time.Time) (int, error) {
}
value := valueFormatter.Format(smpl.V, r.Unit())
threshold := valueFormatter.Format(smpl.Target, smpl.TargetUnit)
r.logger.DebugContext(ctx, "alert template data for rule", slog.String("rule.id", r.ID()), slog.String("formatter.name", valueFormatter.Name()), slog.String("alert.value", value), slog.String("alert.threshold", threshold))
r.logger.DebugContext(ctx, "Alert template data for rule", "rule_name", r.Name(), "formatter", valueFormatter.Name(), "value", value, "threshold", threshold)
tmplData := ruletypes.AlertTemplateData(l, value, threshold)
// Inject some convenience variables that are easier to remember for users
@@ -246,34 +386,35 @@ func (r *AnomalyRule) Eval(ctx context.Context, ts time.Time) (int, error) {
defs+text,
"__alert_"+r.Name(),
tmplData,
times.Time(timestamp.FromTime(ts)),
nil,
)
result, err := tmpl.Expand()
if err != nil {
result = fmt.Sprintf("<error expanding template: %s>", err)
r.logger.ErrorContext(ctx, "expanding alert template failed", slog.String("rule.id", r.ID()), errors.Attr(err), slog.Any("alert.template_data", tmplData))
r.logger.ErrorContext(ctx, "Expanding alert template failed", errors.Attr(err), "data", tmplData, "rule_name", r.Name())
}
return result
}
lb := ruletypes.NewBuilder(smpl.Metric...).Del(ruletypes.MetricNameLabel).Del(ruletypes.TemporalityLabel)
resultLabels := ruletypes.NewBuilder(smpl.Metric...).Del(ruletypes.MetricNameLabel).Del(ruletypes.TemporalityLabel).Labels()
lb := labels.NewBuilder(smpl.Metric).Del(labels.MetricNameLabel).Del(labels.TemporalityLabel)
resultLabels := labels.NewBuilder(smpl.Metric).Del(labels.MetricNameLabel).Del(labels.TemporalityLabel).Labels()
for name, value := range r.Labels().Map() {
lb.Set(name, expand(value))
}
lb.Set(ruletypes.AlertNameLabel, r.Name())
lb.Set(ruletypes.AlertRuleIDLabel, r.ID())
lb.Set(ruletypes.RuleSourceLabel, r.GeneratorURL())
lb.Set(labels.AlertNameLabel, r.Name())
lb.Set(labels.AlertRuleIdLabel, r.ID())
lb.Set(labels.RuleSourceLabel, r.GeneratorURL())
annotations := make(ruletypes.Labels, 0, len(r.Annotations().Map()))
annotations := make(labels.Labels, 0, len(r.Annotations().Map()))
for name, value := range r.Annotations().Map() {
annotations = append(annotations, ruletypes.Label{Name: name, Value: expand(value)})
annotations = append(annotations, labels.Label{Name: name, Value: expand(value)})
}
if smpl.IsMissing {
lb.Set(ruletypes.AlertNameLabel, "[No data] "+r.Name())
lb.Set(ruletypes.NoDataLabel, "true")
lb.Set(labels.AlertNameLabel, "[No data] "+r.Name())
lb.Set(labels.NoDataLabel, "true")
}
lbs := lb.Labels()
@@ -281,17 +422,17 @@ func (r *AnomalyRule) Eval(ctx context.Context, ts time.Time) (int, error) {
resultFPs[h] = struct{}{}
if _, ok := alerts[h]; ok {
r.logger.ErrorContext(ctx, "the alert query returns duplicate records", slog.String("rule.id", r.ID()), slog.Any("alert", alerts[h]))
err = errors.NewInternalf(errors.CodeInternal, "duplicate alert found, vector contains metrics with the same labelset after applying alert labels")
r.logger.ErrorContext(ctx, "the alert query returns duplicate records", "rule_id", r.ID(), "alert", alerts[h])
err = fmt.Errorf("duplicate alert found, vector contains metrics with the same labelset after applying alert labels")
return 0, err
}
alerts[h] = &ruletypes.Alert{
Labels: lbs,
QueryResultLabels: resultLabels,
QueryResultLables: resultLabels,
Annotations: annotations,
ActiveAt: ts,
State: ruletypes.StatePending,
State: model.StatePending,
Value: smpl.V,
GeneratorURL: r.GeneratorURL(),
Receivers: ruleReceiverMap[lbs.Map()[ruletypes.LabelThresholdName]],
@@ -300,12 +441,12 @@ func (r *AnomalyRule) Eval(ctx context.Context, ts time.Time) (int, error) {
}
}
r.logger.InfoContext(ctx, "number of alerts found", slog.String("rule.id", r.ID()), slog.Int("alert.count", len(alerts)))
r.logger.InfoContext(ctx, "number of alerts found", "rule_name", r.Name(), "alerts_count", len(alerts))
// alerts[h] is ready, add or update active list now
for h, a := range alerts {
// Check whether we already have alerting state for the identifying label set.
// Update the last value and annotations if so, create a new alert entry otherwise.
if alert, ok := r.Active[h]; ok && alert.State != ruletypes.StateInactive {
if alert, ok := r.Active[h]; ok && alert.State != model.StateInactive {
alert.Value = a.Value
alert.Annotations = a.Annotations
@@ -321,76 +462,76 @@ func (r *AnomalyRule) Eval(ctx context.Context, ts time.Time) (int, error) {
r.Active[h] = a
}
itemsToAdd := []rulestatehistorytypes.RuleStateHistory{}
itemsToAdd := []model.RuleStateHistory{}
// Check if any pending alerts should be removed or fire now. Write out alert timeseries.
for fp, a := range r.Active {
labelsJSON, err := json.Marshal(a.QueryResultLabels)
labelsJSON, err := json.Marshal(a.QueryResultLables)
if err != nil {
r.logger.ErrorContext(ctx, "error marshaling labels", slog.String("rule.id", r.ID()), errors.Attr(err), slog.Any("alert.labels", a.Labels))
r.logger.ErrorContext(ctx, "error marshaling labels", errors.Attr(err), "labels", a.Labels)
}
if _, ok := resultFPs[fp]; !ok {
// If the alert was previously firing, keep it around for a given
// retention time so it is reported as resolved to the AlertManager.
if a.State == ruletypes.StatePending || (!a.ResolvedAt.IsZero() && ts.Sub(a.ResolvedAt) > ruletypes.ResolvedRetention) {
if a.State == model.StatePending || (!a.ResolvedAt.IsZero() && ts.Sub(a.ResolvedAt) > ruletypes.ResolvedRetention) {
delete(r.Active, fp)
}
if a.State != ruletypes.StateInactive {
a.State = ruletypes.StateInactive
if a.State != model.StateInactive {
a.State = model.StateInactive
a.ResolvedAt = ts
itemsToAdd = append(itemsToAdd, rulestatehistorytypes.RuleStateHistory{
itemsToAdd = append(itemsToAdd, model.RuleStateHistory{
RuleID: r.ID(),
RuleName: r.Name(),
State: ruletypes.StateInactive,
State: model.StateInactive,
StateChanged: true,
UnixMilli: ts.UnixMilli(),
Labels: rulestatehistorytypes.LabelsString(labelsJSON),
Fingerprint: a.QueryResultLabels.Hash(),
Labels: model.LabelsString(labelsJSON),
Fingerprint: a.QueryResultLables.Hash(),
Value: a.Value,
})
}
continue
}
if a.State == ruletypes.StatePending && ts.Sub(a.ActiveAt) >= r.HoldDuration().Duration() {
a.State = ruletypes.StateFiring
if a.State == model.StatePending && ts.Sub(a.ActiveAt) >= r.HoldDuration().Duration() {
a.State = model.StateFiring
a.FiredAt = ts
state := ruletypes.StateFiring
state := model.StateFiring
if a.Missing {
state = ruletypes.StateNoData
state = model.StateNoData
}
itemsToAdd = append(itemsToAdd, rulestatehistorytypes.RuleStateHistory{
itemsToAdd = append(itemsToAdd, model.RuleStateHistory{
RuleID: r.ID(),
RuleName: r.Name(),
State: state,
StateChanged: true,
UnixMilli: ts.UnixMilli(),
Labels: rulestatehistorytypes.LabelsString(labelsJSON),
Fingerprint: a.QueryResultLabels.Hash(),
Labels: model.LabelsString(labelsJSON),
Fingerprint: a.QueryResultLables.Hash(),
Value: a.Value,
})
}
// We need to change firing alert to recovering if the returned sample meets recovery threshold
changeFiringToRecovering := a.State == ruletypes.StateFiring && a.IsRecovering
changeFiringToRecovering := a.State == model.StateFiring && a.IsRecovering
// We need to change recovering alerts to firing if the returned sample meets target threshold
changeRecoveringToFiring := a.State == ruletypes.StateRecovering && !a.IsRecovering && !a.Missing
changeRecoveringToFiring := a.State == model.StateRecovering && !a.IsRecovering && !a.Missing
// in any of the above case we need to update the status of alert
if changeFiringToRecovering || changeRecoveringToFiring {
state := ruletypes.StateRecovering
state := model.StateRecovering
if changeRecoveringToFiring {
state = ruletypes.StateFiring
state = model.StateFiring
}
a.State = state
r.logger.DebugContext(ctx, "converting alert state", slog.String("rule.id", r.ID()), slog.Any("alert.state", state))
itemsToAdd = append(itemsToAdd, rulestatehistorytypes.RuleStateHistory{
r.logger.DebugContext(ctx, "converting alert state", "name", r.Name(), "state", state)
itemsToAdd = append(itemsToAdd, model.RuleStateHistory{
RuleID: r.ID(),
RuleName: r.Name(),
State: state,
StateChanged: true,
UnixMilli: ts.UnixMilli(),
Labels: rulestatehistorytypes.LabelsString(labelsJSON),
Fingerprint: a.QueryResultLabels.Hash(),
Labels: model.LabelsString(labelsJSON),
Fingerprint: a.QueryResultLables.Hash(),
Value: a.Value,
})
}

View File

@@ -2,19 +2,21 @@ package rules
import (
"context"
"log/slog"
"testing"
"time"
"github.com/stretchr/testify/assert"
"github.com/stretchr/testify/require"
"github.com/SigNoz/signoz/ee/query-service/anomaly"
"github.com/SigNoz/signoz/pkg/instrumentation/instrumentationtest"
qbtypes "github.com/SigNoz/signoz/pkg/types/querybuildertypes/querybuildertypesv5"
"github.com/SigNoz/signoz/pkg/query-service/app/clickhouseReader"
v3 "github.com/SigNoz/signoz/pkg/query-service/model/v3"
"github.com/SigNoz/signoz/pkg/telemetrystore"
"github.com/SigNoz/signoz/pkg/telemetrystore/telemetrystoretest"
"github.com/SigNoz/signoz/pkg/types/ruletypes"
"github.com/SigNoz/signoz/pkg/types/telemetrytypes"
"github.com/SigNoz/signoz/pkg/valuer"
"github.com/SigNoz/signoz/ee/anomaly"
)
// mockAnomalyProvider is a mock implementation of anomaly.Provider for testing.
@@ -22,13 +24,13 @@ import (
// time periods (current, past period, current season, past season, past 2 seasons,
// past 3 seasons), making it cumbersome to create mock data.
type mockAnomalyProvider struct {
responses []*anomaly.AnomaliesResponse
responses []*anomaly.GetAnomaliesResponse
callCount int
}
func (m *mockAnomalyProvider) GetAnomalies(ctx context.Context, orgID valuer.UUID, req *anomaly.AnomaliesRequest) (*anomaly.AnomaliesResponse, error) {
func (m *mockAnomalyProvider) GetAnomalies(ctx context.Context, orgID valuer.UUID, req *anomaly.GetAnomaliesRequest) (*anomaly.GetAnomaliesResponse, error) {
if m.callCount >= len(m.responses) {
return &anomaly.AnomaliesResponse{Results: []*qbtypes.TimeSeriesData{}}, nil
return &anomaly.GetAnomaliesResponse{Results: []*v3.Result{}}, nil
}
resp := m.responses[m.callCount]
m.callCount++
@@ -47,46 +49,45 @@ func TestAnomalyRule_NoData_AlertOnAbsent(t *testing.T) {
postableRule := ruletypes.PostableRule{
AlertName: "Test anomaly no data",
AlertType: ruletypes.AlertTypeMetric,
RuleType: ruletypes.RuleTypeAnomaly,
RuleType: RuleTypeAnomaly,
Evaluation: &ruletypes.EvaluationEnvelope{Kind: ruletypes.RollingEvaluation, Spec: ruletypes.RollingWindow{
EvalWindow: evalWindow,
Frequency: valuer.MustParseTextDuration("1m"),
}},
RuleCondition: &ruletypes.RuleCondition{
CompareOperator: ruletypes.ValueIsAbove,
MatchType: ruletypes.AtleastOnce,
Target: &target,
CompositeQuery: &ruletypes.AlertCompositeQuery{
QueryType: ruletypes.QueryTypeBuilder,
Queries: []qbtypes.QueryEnvelope{{
Type: qbtypes.QueryTypeBuilder,
Spec: qbtypes.QueryBuilderQuery[qbtypes.MetricAggregation]{
Name: "A",
Signal: telemetrytypes.SignalMetrics,
CompareOp: ruletypes.ValueIsAbove,
MatchType: ruletypes.AtleastOnce,
Target: &target,
CompositeQuery: &v3.CompositeQuery{
QueryType: v3.QueryTypeBuilder,
BuilderQueries: map[string]*v3.BuilderQuery{
"A": {
QueryName: "A",
Expression: "A",
DataSource: v3.DataSourceMetrics,
Temporality: v3.Unspecified,
},
}},
},
},
SelectedQuery: "A",
Seasonality: "daily",
Thresholds: &ruletypes.RuleThresholdData{
Kind: ruletypes.BasicThresholdKind,
Spec: ruletypes.BasicRuleThresholds{{
Name: "Test anomaly no data",
TargetValue: &target,
MatchType: ruletypes.AtleastOnce,
CompareOperator: ruletypes.ValueIsAbove,
Name: "Test anomaly no data",
TargetValue: &target,
MatchType: ruletypes.AtleastOnce,
CompareOp: ruletypes.ValueIsAbove,
}},
},
},
}
responseNoData := &anomaly.AnomaliesResponse{
Results: []*qbtypes.TimeSeriesData{
responseNoData := &anomaly.GetAnomaliesResponse{
Results: []*v3.Result{
{
QueryName: "A",
Aggregations: []*qbtypes.AggregationBucket{{
AnomalyScores: []*qbtypes.TimeSeries{},
}},
QueryName: "A",
AnomalyScores: []*v3.Series{},
},
},
}
@@ -114,17 +115,23 @@ func TestAnomalyRule_NoData_AlertOnAbsent(t *testing.T) {
t.Run(c.description, func(t *testing.T) {
postableRule.RuleCondition.AlertOnAbsent = c.alertOnAbsent
telemetryStore := telemetrystoretest.New(telemetrystore.Config{}, nil)
options := clickhouseReader.NewOptions("primaryNamespace")
reader := clickhouseReader.NewReader(slog.Default(), nil, telemetryStore, nil, "", time.Second, nil, nil, options)
rule, err := NewAnomalyRule(
"test-anomaly-rule",
valuer.GenerateUUID(),
&postableRule,
reader,
nil,
logger,
nil,
)
require.NoError(t, err)
rule.provider = &mockAnomalyProvider{
responses: []*anomaly.AnomaliesResponse{responseNoData},
responses: []*anomaly.GetAnomaliesResponse{responseNoData},
}
alertsFound, err := rule.Eval(context.Background(), evalTime)
@@ -149,47 +156,46 @@ func TestAnomalyRule_NoData_AbsentFor(t *testing.T) {
postableRule := ruletypes.PostableRule{
AlertName: "Test anomaly no data with AbsentFor",
AlertType: ruletypes.AlertTypeMetric,
RuleType: ruletypes.RuleTypeAnomaly,
RuleType: RuleTypeAnomaly,
Evaluation: &ruletypes.EvaluationEnvelope{Kind: ruletypes.RollingEvaluation, Spec: ruletypes.RollingWindow{
EvalWindow: evalWindow,
Frequency: valuer.MustParseTextDuration("1m"),
}},
RuleCondition: &ruletypes.RuleCondition{
CompareOperator: ruletypes.ValueIsAbove,
MatchType: ruletypes.AtleastOnce,
AlertOnAbsent: true,
Target: &target,
CompositeQuery: &ruletypes.AlertCompositeQuery{
QueryType: ruletypes.QueryTypeBuilder,
Queries: []qbtypes.QueryEnvelope{{
Type: qbtypes.QueryTypeBuilder,
Spec: qbtypes.QueryBuilderQuery[qbtypes.MetricAggregation]{
Name: "A",
Signal: telemetrytypes.SignalMetrics,
CompareOp: ruletypes.ValueIsAbove,
MatchType: ruletypes.AtleastOnce,
AlertOnAbsent: true,
Target: &target,
CompositeQuery: &v3.CompositeQuery{
QueryType: v3.QueryTypeBuilder,
BuilderQueries: map[string]*v3.BuilderQuery{
"A": {
QueryName: "A",
Expression: "A",
DataSource: v3.DataSourceMetrics,
Temporality: v3.Unspecified,
},
}},
},
},
SelectedQuery: "A",
Seasonality: "daily",
Thresholds: &ruletypes.RuleThresholdData{
Kind: ruletypes.BasicThresholdKind,
Spec: ruletypes.BasicRuleThresholds{{
Name: "Test anomaly no data with AbsentFor",
TargetValue: &target,
MatchType: ruletypes.AtleastOnce,
CompareOperator: ruletypes.ValueIsAbove,
Name: "Test anomaly no data with AbsentFor",
TargetValue: &target,
MatchType: ruletypes.AtleastOnce,
CompareOp: ruletypes.ValueIsAbove,
}},
},
},
}
responseNoData := &anomaly.AnomaliesResponse{
Results: []*qbtypes.TimeSeriesData{
responseNoData := &anomaly.GetAnomaliesResponse{
Results: []*v3.Result{
{
QueryName: "A",
Aggregations: []*qbtypes.AggregationBucket{{
AnomalyScores: []*qbtypes.TimeSeries{},
}},
QueryName: "A",
AnomalyScores: []*v3.Series{},
},
},
}
@@ -223,35 +229,32 @@ func TestAnomalyRule_NoData_AbsentFor(t *testing.T) {
t1 := baseTime.Add(5 * time.Minute)
t2 := t1.Add(c.timeBetweenEvals)
responseWithData := &anomaly.AnomaliesResponse{
Results: []*qbtypes.TimeSeriesData{
responseWithData := &anomaly.GetAnomaliesResponse{
Results: []*v3.Result{
{
QueryName: "A",
Aggregations: []*qbtypes.AggregationBucket{{
AnomalyScores: []*qbtypes.TimeSeries{
{
Labels: []*qbtypes.Label{
{
Key: telemetrytypes.TelemetryFieldKey{Name: "Test"},
Value: "labels",
},
},
Values: []*qbtypes.TimeSeriesValue{
{Timestamp: baseTime.UnixMilli(), Value: 1.0},
{Timestamp: baseTime.Add(time.Minute).UnixMilli(), Value: 1.5},
},
AnomalyScores: []*v3.Series{
{
Labels: map[string]string{"test": "label"},
Points: []v3.Point{
{Timestamp: baseTime.UnixMilli(), Value: 1.0},
{Timestamp: baseTime.Add(time.Minute).UnixMilli(), Value: 1.5},
},
},
}},
},
},
},
}
rule, err := NewAnomalyRule("test-anomaly-rule", valuer.GenerateUUID(), &postableRule, nil, logger)
telemetryStore := telemetrystoretest.New(telemetrystore.Config{}, nil)
options := clickhouseReader.NewOptions("primaryNamespace")
reader := clickhouseReader.NewReader(slog.Default(), nil, telemetryStore, nil, "", time.Second, nil, nil, options)
rule, err := NewAnomalyRule("test-anomaly-rule", valuer.GenerateUUID(), &postableRule, reader, nil, logger, nil)
require.NoError(t, err)
rule.provider = &mockAnomalyProvider{
responses: []*anomaly.AnomaliesResponse{responseWithData, responseNoData},
responses: []*anomaly.GetAnomaliesResponse{responseWithData, responseNoData},
}
alertsFound1, err := rule.Eval(context.Background(), t1)

View File

@@ -11,7 +11,9 @@ import (
"github.com/google/uuid"
"github.com/SigNoz/signoz/pkg/errors"
basemodel "github.com/SigNoz/signoz/pkg/query-service/model"
baserules "github.com/SigNoz/signoz/pkg/query-service/rules"
"github.com/SigNoz/signoz/pkg/query-service/utils/labels"
"github.com/SigNoz/signoz/pkg/types/ruletypes"
"github.com/SigNoz/signoz/pkg/valuer"
)
@@ -21,7 +23,7 @@ func PrepareTaskFunc(opts baserules.PrepareTaskOptions) (baserules.Task, error)
rules := make([]baserules.Rule, 0)
var task baserules.Task
ruleID := baserules.RuleIDFromTaskName(opts.TaskName)
ruleId := baserules.RuleIdFromTaskName(opts.TaskName)
evaluation, err := opts.Rule.Evaluation.GetEvaluation()
if err != nil {
return nil, errors.NewInvalidInputf(errors.CodeInvalidInput, "evaluation is invalid: %v", err)
@@ -30,9 +32,10 @@ func PrepareTaskFunc(opts baserules.PrepareTaskOptions) (baserules.Task, error)
if opts.Rule.RuleType == ruletypes.RuleTypeThreshold {
// create a threshold rule
tr, err := baserules.NewThresholdRule(
ruleID,
ruleId,
opts.OrgID,
opts.Rule,
opts.Reader,
opts.Querier,
opts.Logger,
baserules.WithEvalDelay(opts.ManagerOpts.EvalDelay),
@@ -55,10 +58,11 @@ func PrepareTaskFunc(opts baserules.PrepareTaskOptions) (baserules.Task, error)
// create promql rule
pr, err := baserules.NewPromRule(
ruleID,
ruleId,
opts.OrgID,
opts.Rule,
opts.Logger,
opts.Reader,
opts.ManagerOpts.Prometheus,
baserules.WithSQLStore(opts.SQLStore),
baserules.WithQueryParser(opts.ManagerOpts.QueryParser),
@@ -78,11 +82,13 @@ func PrepareTaskFunc(opts baserules.PrepareTaskOptions) (baserules.Task, error)
} else if opts.Rule.RuleType == ruletypes.RuleTypeAnomaly {
// create anomaly rule
ar, err := NewAnomalyRule(
ruleID,
ruleId,
opts.OrgID,
opts.Rule,
opts.Reader,
opts.Querier,
opts.Logger,
opts.Cache,
baserules.WithEvalDelay(opts.ManagerOpts.EvalDelay),
baserules.WithSQLStore(opts.SQLStore),
baserules.WithQueryParser(opts.ManagerOpts.QueryParser),
@@ -99,7 +105,7 @@ func PrepareTaskFunc(opts baserules.PrepareTaskOptions) (baserules.Task, error)
task = newTask(baserules.TaskTypeCh, opts.TaskName, evaluation.GetFrequency().Duration(), rules, opts.ManagerOpts, opts.NotifyFunc, opts.MaintenanceStore, opts.OrgID)
} else {
return nil, errors.NewInvalidInputf(errors.CodeInvalidInput, "unsupported rule type %s. Supported types: %s, %s", opts.Rule.RuleType, ruletypes.RuleTypeProm, ruletypes.RuleTypeThreshold)
return nil, fmt.Errorf("unsupported rule type %s. Supported types: %s, %s", opts.Rule.RuleType, ruletypes.RuleTypeProm, ruletypes.RuleTypeThreshold)
}
return task, nil
@@ -107,12 +113,12 @@ func PrepareTaskFunc(opts baserules.PrepareTaskOptions) (baserules.Task, error)
// TestNotification prepares a dummy rule for given rule parameters and
// sends a test notification. returns alert count and error (if any)
func TestNotification(opts baserules.PrepareTestRuleOptions) (int, error) {
func TestNotification(opts baserules.PrepareTestRuleOptions) (int, *basemodel.ApiError) {
ctx := context.Background()
if opts.Rule == nil {
return 0, errors.NewInvalidInputf(errors.CodeInvalidInput, "rule is required")
return 0, basemodel.BadRequest(fmt.Errorf("rule is required"))
}
parsedRule := opts.Rule
@@ -132,14 +138,15 @@ func TestNotification(opts baserules.PrepareTestRuleOptions) (int, error) {
if parsedRule.RuleType == ruletypes.RuleTypeThreshold {
// add special labels for test alerts
parsedRule.Labels[ruletypes.RuleSourceLabel] = ""
parsedRule.Labels[ruletypes.AlertRuleIDLabel] = ""
parsedRule.Labels[labels.RuleSourceLabel] = ""
parsedRule.Labels[labels.AlertRuleIdLabel] = ""
// create a threshold rule
rule, err = baserules.NewThresholdRule(
alertname,
opts.OrgID,
parsedRule,
opts.Reader,
opts.Querier,
opts.Logger,
baserules.WithSendAlways(),
@@ -151,7 +158,7 @@ func TestNotification(opts baserules.PrepareTestRuleOptions) (int, error) {
if err != nil {
slog.Error("failed to prepare a new threshold rule for test", "name", alertname, errors.Attr(err))
return 0, err
return 0, basemodel.BadRequest(err)
}
} else if parsedRule.RuleType == ruletypes.RuleTypeProm {
@@ -162,6 +169,7 @@ func TestNotification(opts baserules.PrepareTestRuleOptions) (int, error) {
opts.OrgID,
parsedRule,
opts.Logger,
opts.Reader,
opts.ManagerOpts.Prometheus,
baserules.WithSendAlways(),
baserules.WithSendUnmatched(),
@@ -172,7 +180,7 @@ func TestNotification(opts baserules.PrepareTestRuleOptions) (int, error) {
if err != nil {
slog.Error("failed to prepare a new promql rule for test", "name", alertname, errors.Attr(err))
return 0, err
return 0, basemodel.BadRequest(err)
}
} else if parsedRule.RuleType == ruletypes.RuleTypeAnomaly {
// create anomaly rule
@@ -180,8 +188,10 @@ func TestNotification(opts baserules.PrepareTestRuleOptions) (int, error) {
alertname,
opts.OrgID,
parsedRule,
opts.Reader,
opts.Querier,
opts.Logger,
opts.Cache,
baserules.WithSendAlways(),
baserules.WithSendUnmatched(),
baserules.WithSQLStore(opts.SQLStore),
@@ -190,10 +200,10 @@ func TestNotification(opts baserules.PrepareTestRuleOptions) (int, error) {
)
if err != nil {
slog.Error("failed to prepare a new anomaly rule for test", "name", alertname, errors.Attr(err))
return 0, err
return 0, basemodel.BadRequest(err)
}
} else {
return 0, errors.NewInvalidInputf(errors.CodeInvalidInput, "failed to derive ruletype with given information")
return 0, basemodel.BadRequest(fmt.Errorf("failed to derive ruletype with given information"))
}
// set timestamp to current utc time
@@ -202,7 +212,7 @@ func TestNotification(opts baserules.PrepareTestRuleOptions) (int, error) {
alertsFound, err := rule.Eval(ctx, ts)
if err != nil {
slog.Error("evaluating rule failed", "rule", rule.Name(), errors.Attr(err))
return 0, err
return 0, basemodel.InternalError(fmt.Errorf("rule evaluation failed"))
}
rule.SendAlerts(ctx, ts, 0, time.Minute, opts.NotifyFunc)

View File

@@ -114,8 +114,11 @@ func TestManager_TestNotification_SendUnmatched_ThresholdRule(t *testing.T) {
},
})
count, err := mgr.TestNotification(context.Background(), orgID, string(ruleBytes))
require.Nil(t, err)
count, apiErr := mgr.TestNotification(context.Background(), orgID, string(ruleBytes))
if apiErr != nil {
t.Logf("TestNotification error: %v, type: %s", apiErr.Err, apiErr.Typ)
}
require.Nil(t, apiErr)
assert.Equal(t, tc.ExpectAlerts, count)
if tc.ExpectAlerts > 0 {
@@ -265,8 +268,11 @@ func TestManager_TestNotification_SendUnmatched_PromRule(t *testing.T) {
},
})
count, err := mgr.TestNotification(context.Background(), orgID, string(ruleBytes))
require.Nil(t, err)
count, apiErr := mgr.TestNotification(context.Background(), orgID, string(ruleBytes))
if apiErr != nil {
t.Logf("TestNotification error: %v, type: %s", apiErr.Err, apiErr.Typ)
}
require.Nil(t, apiErr)
assert.Equal(t, tc.ExpectAlerts, count)
if tc.ExpectAlerts > 0 {

View File

@@ -68,8 +68,8 @@
"@signozhq/toggle-group": "0.0.1",
"@signozhq/tooltip": "0.0.2",
"@signozhq/ui": "0.0.5",
"@tanstack/react-table": "8.21.3",
"@tanstack/react-virtual": "3.13.22",
"@tanstack/react-table": "8.20.6",
"@tanstack/react-virtual": "3.11.2",
"@uiw/codemirror-theme-copilot": "4.23.11",
"@uiw/codemirror-theme-github": "4.24.1",
"@uiw/react-codemirror": "4.23.10",

View File

Before

Width:  |  Height:  |  Size: 9.1 KiB

After

Width:  |  Height:  |  Size: 9.1 KiB

View File

Before

Width:  |  Height:  |  Size: 2.3 KiB

After

Width:  |  Height:  |  Size: 2.3 KiB

View File

Before

Width:  |  Height:  |  Size: 11 KiB

After

Width:  |  Height:  |  Size: 11 KiB

View File

Before

Width:  |  Height:  |  Size: 2.9 KiB

After

Width:  |  Height:  |  Size: 2.9 KiB

View File

Before

Width:  |  Height:  |  Size: 507 B

After

Width:  |  Height:  |  Size: 507 B

View File

Before

Width:  |  Height:  |  Size: 9.0 KiB

After

Width:  |  Height:  |  Size: 9.0 KiB

View File

Before

Width:  |  Height:  |  Size: 644 B

After

Width:  |  Height:  |  Size: 644 B

View File

Before

Width:  |  Height:  |  Size: 5.2 KiB

After

Width:  |  Height:  |  Size: 5.2 KiB

View File

Before

Width:  |  Height:  |  Size: 1.6 KiB

After

Width:  |  Height:  |  Size: 1.6 KiB

View File

Before

Width:  |  Height:  |  Size: 4.5 KiB

After

Width:  |  Height:  |  Size: 4.5 KiB

View File

Before

Width:  |  Height:  |  Size: 12 KiB

After

Width:  |  Height:  |  Size: 12 KiB

View File

Before

Width:  |  Height:  |  Size: 2.0 KiB

After

Width:  |  Height:  |  Size: 2.0 KiB

View File

Before

Width:  |  Height:  |  Size: 5.2 KiB

After

Width:  |  Height:  |  Size: 5.2 KiB

View File

Before

Width:  |  Height:  |  Size: 15 KiB

After

Width:  |  Height:  |  Size: 15 KiB

View File

Before

Width:  |  Height:  |  Size: 2.0 KiB

After

Width:  |  Height:  |  Size: 2.0 KiB

View File

Before

Width:  |  Height:  |  Size: 5.9 KiB

After

Width:  |  Height:  |  Size: 5.9 KiB

View File

Before

Width:  |  Height:  |  Size: 5.6 KiB

After

Width:  |  Height:  |  Size: 5.6 KiB

View File

Before

Width:  |  Height:  |  Size: 1.2 KiB

After

Width:  |  Height:  |  Size: 1.2 KiB

View File

Before

Width:  |  Height:  |  Size: 418 B

After

Width:  |  Height:  |  Size: 418 B

View File

Before

Width:  |  Height:  |  Size: 604 B

After

Width:  |  Height:  |  Size: 604 B

View File

Before

Width:  |  Height:  |  Size: 878 B

After

Width:  |  Height:  |  Size: 878 B

View File

Before

Width:  |  Height:  |  Size: 7.3 KiB

After

Width:  |  Height:  |  Size: 7.3 KiB

View File

Before

Width:  |  Height:  |  Size: 7.5 KiB

After

Width:  |  Height:  |  Size: 7.5 KiB

View File

Before

Width:  |  Height:  |  Size: 3.2 KiB

After

Width:  |  Height:  |  Size: 3.2 KiB

View File

Before

Width:  |  Height:  |  Size: 6.1 KiB

After

Width:  |  Height:  |  Size: 6.1 KiB

View File

Before

Width:  |  Height:  |  Size: 88 KiB

After

Width:  |  Height:  |  Size: 88 KiB

View File

Before

Width:  |  Height:  |  Size: 1.0 KiB

After

Width:  |  Height:  |  Size: 1.0 KiB

View File

Before

Width:  |  Height:  |  Size: 3.4 KiB

After

Width:  |  Height:  |  Size: 3.4 KiB

View File

Before

Width:  |  Height:  |  Size: 303 B

After

Width:  |  Height:  |  Size: 303 B

View File

Before

Width:  |  Height:  |  Size: 2.3 KiB

After

Width:  |  Height:  |  Size: 2.3 KiB

View File

Before

Width:  |  Height:  |  Size: 629 B

After

Width:  |  Height:  |  Size: 629 B

View File

Before

Width:  |  Height:  |  Size: 439 B

After

Width:  |  Height:  |  Size: 439 B

View File

Before

Width:  |  Height:  |  Size: 467 B

After

Width:  |  Height:  |  Size: 467 B

View File

Before

Width:  |  Height:  |  Size: 2.1 KiB

After

Width:  |  Height:  |  Size: 2.1 KiB

View File

Before

Width:  |  Height:  |  Size: 2.1 KiB

After

Width:  |  Height:  |  Size: 2.1 KiB

View File

Before

Width:  |  Height:  |  Size: 300 B

After

Width:  |  Height:  |  Size: 300 B

View File

Before

Width:  |  Height:  |  Size: 348 B

After

Width:  |  Height:  |  Size: 348 B

View File

Before

Width:  |  Height:  |  Size: 3.6 KiB

After

Width:  |  Height:  |  Size: 3.6 KiB

View File

Before

Width:  |  Height:  |  Size: 3.2 KiB

After

Width:  |  Height:  |  Size: 3.2 KiB

View File

Before

Width:  |  Height:  |  Size: 7.2 KiB

After

Width:  |  Height:  |  Size: 7.2 KiB

View File

Before

Width:  |  Height:  |  Size: 6.8 KiB

After

Width:  |  Height:  |  Size: 6.8 KiB

View File

Before

Width:  |  Height:  |  Size: 910 B

After

Width:  |  Height:  |  Size: 910 B

View File

Before

Width:  |  Height:  |  Size: 105 KiB

After

Width:  |  Height:  |  Size: 105 KiB

View File

Before

Width:  |  Height:  |  Size: 214 KiB

After

Width:  |  Height:  |  Size: 214 KiB

View File

Before

Width:  |  Height:  |  Size: 204 KiB

After

Width:  |  Height:  |  Size: 204 KiB

View File

Before

Width:  |  Height:  |  Size: 5.4 KiB

After

Width:  |  Height:  |  Size: 5.4 KiB

View File

Before

Width:  |  Height:  |  Size: 31 KiB

After

Width:  |  Height:  |  Size: 31 KiB

View File

Before

Width:  |  Height:  |  Size: 3.3 KiB

After

Width:  |  Height:  |  Size: 3.3 KiB

View File

Before

Width:  |  Height:  |  Size: 408 KiB

After

Width:  |  Height:  |  Size: 408 KiB

View File

Before

Width:  |  Height:  |  Size: 194 KiB

After

Width:  |  Height:  |  Size: 194 KiB

View File

Before

Width:  |  Height:  |  Size: 43 KiB

After

Width:  |  Height:  |  Size: 43 KiB

View File

Before

Width:  |  Height:  |  Size: 95 KiB

After

Width:  |  Height:  |  Size: 95 KiB

View File

Before

Width:  |  Height:  |  Size: 1.7 MiB

After

Width:  |  Height:  |  Size: 1.7 MiB

View File

Before

Width:  |  Height:  |  Size: 62 KiB

After

Width:  |  Height:  |  Size: 62 KiB

View File

Before

Width:  |  Height:  |  Size: 1.7 KiB

After

Width:  |  Height:  |  Size: 1.7 KiB

View File

Before

Width:  |  Height:  |  Size: 3.0 KiB

After

Width:  |  Height:  |  Size: 3.0 KiB

View File

Before

Width:  |  Height:  |  Size: 2.7 KiB

After

Width:  |  Height:  |  Size: 2.7 KiB

View File

Before

Width:  |  Height:  |  Size: 1.5 KiB

After

Width:  |  Height:  |  Size: 1.5 KiB

View File

Before

Width:  |  Height:  |  Size: 1.4 KiB

After

Width:  |  Height:  |  Size: 1.4 KiB

View File

Before

Width:  |  Height:  |  Size: 695 B

After

Width:  |  Height:  |  Size: 695 B

View File

Before

Width:  |  Height:  |  Size: 714 B

After

Width:  |  Height:  |  Size: 714 B

View File

Before

Width:  |  Height:  |  Size: 3.1 KiB

After

Width:  |  Height:  |  Size: 3.1 KiB

View File

Before

Width:  |  Height:  |  Size: 872 B

After

Width:  |  Height:  |  Size: 872 B

View File

Before

Width:  |  Height:  |  Size: 6.1 KiB

After

Width:  |  Height:  |  Size: 6.1 KiB

View File

Before

Width:  |  Height:  |  Size: 20 KiB

After

Width:  |  Height:  |  Size: 20 KiB

View File

Before

Width:  |  Height:  |  Size: 1.1 KiB

After

Width:  |  Height:  |  Size: 1.1 KiB

View File

Before

Width:  |  Height:  |  Size: 6.1 KiB

After

Width:  |  Height:  |  Size: 6.1 KiB

View File

Before

Width:  |  Height:  |  Size: 2.8 KiB

After

Width:  |  Height:  |  Size: 2.8 KiB

View File

Before

Width:  |  Height:  |  Size: 3.0 KiB

After

Width:  |  Height:  |  Size: 3.0 KiB

View File

Before

Width:  |  Height:  |  Size: 2.3 KiB

After

Width:  |  Height:  |  Size: 2.3 KiB

View File

Before

Width:  |  Height:  |  Size: 6.0 KiB

After

Width:  |  Height:  |  Size: 6.0 KiB

View File

Before

Width:  |  Height:  |  Size: 2.4 KiB

After

Width:  |  Height:  |  Size: 2.4 KiB

View File

Before

Width:  |  Height:  |  Size: 1.3 KiB

After

Width:  |  Height:  |  Size: 1.3 KiB

View File

Before

Width:  |  Height:  |  Size: 1.3 KiB

After

Width:  |  Height:  |  Size: 1.3 KiB

View File

Before

Width:  |  Height:  |  Size: 1.3 KiB

After

Width:  |  Height:  |  Size: 1.3 KiB

View File

Before

Width:  |  Height:  |  Size: 2.1 KiB

After

Width:  |  Height:  |  Size: 2.1 KiB

View File

Before

Width:  |  Height:  |  Size: 936 B

After

Width:  |  Height:  |  Size: 936 B

View File

Before

Width:  |  Height:  |  Size: 1.1 KiB

After

Width:  |  Height:  |  Size: 1.1 KiB

View File

Before

Width:  |  Height:  |  Size: 1.7 KiB

After

Width:  |  Height:  |  Size: 1.7 KiB

View File

Before

Width:  |  Height:  |  Size: 1.3 KiB

After

Width:  |  Height:  |  Size: 1.3 KiB

View File

Before

Width:  |  Height:  |  Size: 1.0 KiB

After

Width:  |  Height:  |  Size: 1.0 KiB

View File

Before

Width:  |  Height:  |  Size: 962 B

After

Width:  |  Height:  |  Size: 962 B

View File

Before

Width:  |  Height:  |  Size: 51 KiB

After

Width:  |  Height:  |  Size: 51 KiB

View File

Before

Width:  |  Height:  |  Size: 687 B

After

Width:  |  Height:  |  Size: 687 B

View File

Before

Width:  |  Height:  |  Size: 1.9 KiB

After

Width:  |  Height:  |  Size: 1.9 KiB

View File

Before

Width:  |  Height:  |  Size: 811 B

After

Width:  |  Height:  |  Size: 811 B

View File

Before

Width:  |  Height:  |  Size: 1.8 KiB

After

Width:  |  Height:  |  Size: 1.8 KiB

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