Compare commits

...

1 Commits

Author SHA1 Message Date
srikanthccv
18bb0805e1 refactor(prometheus)!: remove the v1 provider and let the provider own evaluation
Assisted-by: Claude Fable 5
2026-09-10 20:26:00 +05:30
46 changed files with 423 additions and 2789 deletions

View File

@@ -17,7 +17,7 @@ For example, the [prometheus](/pkg/prometheus) provider delivers a prometheus en
- `pkg/prometheus/prometheus.go` - Interface definition
- `pkg/prometheus/config.go` - Configuration
- `pkg/prometheus/clickhouseprometheus/provider.go` - Clickhouse-powered implementation
- `pkg/prometheus/clickhouseprometheusv2/provider.go` - Clickhouse-powered implementation
- `pkg/prometheus/prometheustest/provider.go` - Mock implementation
## How to wire it up?

View File

@@ -9,15 +9,16 @@ change breaks an invariant, flag it and discuss it first.
---
## Why a second provider
## Why the provider looks like this
The v1 provider (`pkg/prometheus/clickhouseprometheus`) serves the promql
engine through the remote-read protobuf adapter. It fetches every raw sample
of a query's union window. It serializes all of them and gives them to the
engine. The cost follows the ingested data, not the question. This is how a
dashboard of PromQL panels can take an instance down.
The removed v1 provider served the promql engine through the remote-read
protobuf adapter. It fetched every raw sample of a query's union window,
serialized all of them, and gave them to the engine. The cost followed the
ingested data, not the question. This is how a dashboard of PromQL panels
could take an instance down. v2 replaced it after a byte-level parity
rollout, and v1 was then deleted.
In v2, each query runs in one of two ways. The classifier decides per query:
Each query runs in one of two ways. The classifier decides per query:
- **Transpiled**: ClickHouse evaluates the query. Only final (or near-final)
per-group grid arrays come back. The statements use the
@@ -30,7 +31,7 @@ In v2, each query runs in one of two ways. The classifier decides per query:
lost user. A construct that cannot reproduce engine semantics exactly falls
back. It does not approximate.** The conformance suite
(`tests/integration/tests/promqlconformance/`) replays Prometheus' own test
corpus against both providers. It is the arbiter. The classification golden
corpus against the provider. It is the arbiter. The classification golden
(`testdata/classification_golden.json`) freezes the route of each corpus
expression. The rest of this document is the PromQL-to-SQL story. That
mapping is where correctness is won or lost.
@@ -263,7 +264,8 @@ per-thread partials scaled memory with the thread count. The slide then
combines each slot's at-most-W bucket partials by direct aggregation
(`arraySum(arraySlice(...))`). Window sums are added the way the engine adds
them. There is no prefix-sum differencing: its large-minus-large
cancellation would drift past the shadow tolerance on counter-sized values.
cancellation would drift past the conformance tolerance on counter-sized
values.
This is correct per slot because the bucket union is the exact window
multiset, and avg/min/max/sum/count are order-insensitive on a multiset
(sum/avg up to summation order; see the float caveat above). A slot with
@@ -333,7 +335,7 @@ can carry them.
## The engine path
Queries that do not transpile run in the stock engine over this package's
`storage.Querier`. This is still not the v1 path. Samples are fetched per
`storage.Querier`. Samples are fetched per
selector with the engine's per-selector hints, not the query-wide union
window. So `foo / foo offset 1d` reads two narrow windows, not the widest
one twice. Instant selectors of subquery-free queries fetch only the last
@@ -367,9 +369,9 @@ same predicates as a shard-local semi-join, not a GLOBAL broadcast of the
matched set. The temporality filter on every samples statement is a
semantic no-op: the matched fingerprints already come from those
temporalities. It engages the leading samples primary-key column.
Delta-temporality series stay invisible to PromQL here, exactly as in v1.
The rollout gate is parity with v1. To make Delta visible is its own change
with its own semantics to design. A Delta stream fed to `rate()`
Delta-temporality series stay invisible to PromQL here, as they were before
v2. To make Delta visible is its own change with its own semantics to
design. A Delta stream fed to `rate()`
as-if-cumulative would be wrong, not just new.
## Observability

View File

@@ -160,7 +160,7 @@ func TestManager_TestNotification_SendUnmatched_PromRule(t *testing.T) {
triggeredTestAlerts := []map[*alertmanagertypes.PostableAlert][]string{}
// Variable to store promProvider for cleanup
var promProvider *prometheustest.Provider
var promProvider prometheus.Prometheus
// Create manager using test factory with hooks
mgr := rules.NewTestManager(t, &rules.TestManagerOptions{
@@ -185,76 +185,29 @@ func TestManager_TestNotification_SendUnmatched_PromRule(t *testing.T) {
TelemetryStoreHook: func(store telemetrystore.TelemetryStore) {
mockStore := store.(*telemetrystoretest.Provider)
// Set up Prometheus-specific mock data
// Fingerprint columns for Prometheus queries
fingerprintCols := []cmock.ColumnType{
{Name: "fingerprint", Type: "UInt64"},
{Name: "any(labels)", Type: "String"},
}
// Samples columns for Prometheus queries
samplesCols := []cmock.ColumnType{
{Name: "metric_name", Type: "String"},
{Name: "fingerprint", Type: "UInt64"},
{Name: "unix_milli", Type: "Int64"},
{Name: "value", Type: "Float64"},
{Name: "flags", Type: "UInt32"},
}
// Calculate query time range similar to Prometheus rule tests
// TestNotification uses time.Now().UTC() for evaluation
// We calculate the query window based on current time to match what the actual evaluation will use
// Grid the TestNotification eval computes over (see
// Timestamps on base_rule); nil args match any window.
evalTime := baseTime
evalWindowMs := int64(5 * 60 * 1000) // 5 minutes in ms
evalTimeMs := evalTime.UnixMilli()
queryStart := ((evalTimeMs-2*evalWindowMs)/60000)*60000 + 1 // truncate to minute + 1ms
queryEnd := (evalTimeMs / 60000) * 60000 // truncate to minute
gridEnd := (evalTime.UnixMilli() / 60000) * 60000
gridStart := gridEnd - evalWindowMs
// Create fingerprint data
fingerprint := uint64(12345)
labelsJSON := `{"__name__":"test_metric"}`
fingerprintData := [][]interface{}{
{fingerprint, labelsJSON},
}
fingerprintRows := cmock.NewRows(fingerprintCols, fingerprintData)
// Create samples data from test case values, calculating timestamps relative to baseTime
validSamplesData := make([][]interface{}, 0)
tsList := make([]int64, 0, len(tc.Values))
vList := make([]float64, 0, len(tc.Values))
for _, v := range tc.Values {
// Skip NaN and Inf values in the samples data
if math.IsNaN(v.Value) || math.IsInf(v.Value, 0) {
continue
}
// Calculate timestamp relative to baseTime
sampleTimestamp := baseTime.Add(v.Offset).UnixMilli()
validSamplesData = append(validSamplesData, []interface{}{
"test_metric",
fingerprint,
sampleTimestamp,
v.Value,
uint32(0), // flags - 0 means normal value
})
tsList = append(tsList, baseTime.Add(v.Offset).UnixMilli())
vList = append(vList, v.Value)
}
samplesRows := cmock.NewRows(samplesCols, validSamplesData)
grid := prometheustest.LastSampleGrid(tsList, vList, gridStart, gridEnd, 60_000, 300_000)
mock := mockStore.Mock()
// Mock the fingerprint query (for Prometheus label matching)
// args: $1=metric_name (the __name__ matcher maps onto the column)
mock.ExpectQuery("SELECT fingerprint, any").
WithArgs("test_metric").
WillReturnRows(fingerprintRows)
// Mock the samples query (for Prometheus metric data)
// args: metric_name IN (discovered names), subquery metric_name, start, end
mock.ExpectQuery("SELECT metric_name, fingerprint, unix_milli").
WithArgs(
"test_metric",
"test_metric",
queryStart,
queryEnd,
).
WillReturnRows(samplesRows)
mock.ExpectQuery("SELECT gkey").
WithArgs("test_metric", nil, nil, "test_metric", nil, nil).
WillReturnRows(cmock.NewRows(prometheustest.GridCols, [][]any{{`[["__name__","test_metric"]]`, grid}}))
// Create Prometheus provider for this test
promProvider = prometheustest.New(context.Background(), instrumentationtest.New().ToProviderSettings(), prometheus.Config{Timeout: 2 * time.Minute}, store)
@@ -289,7 +242,6 @@ func TestManager_TestNotification_SendUnmatched_PromRule(t *testing.T) {
assert.Empty(t, triggeredTestAlerts)
}
promProvider.Close()
})
}
}

15
go.mod
View File

@@ -131,7 +131,6 @@ require (
github.com/go-playground/locales v0.14.1 // indirect
github.com/go-playground/universal-translator v0.18.1 // indirect
github.com/goccy/go-yaml v1.19.2 // indirect
github.com/google/go-cmp v0.7.0 // indirect
github.com/gorilla/websocket v1.5.4-0.20250319132907-e064f32e3674 // indirect
github.com/hashicorp/go-metrics v0.5.4 // indirect
github.com/huandu/go-clone v1.7.3 // indirect
@@ -139,8 +138,7 @@ require (
github.com/mattn/go-isatty v0.0.20 // indirect
github.com/ncruces/go-strftime v1.0.0 // indirect
github.com/nxadm/tail v1.4.11 // indirect
github.com/prometheus/client_golang/exp v0.0.0-20260325093428-d8591d0db856 // indirect
github.com/puzpuzpuz/xsync/v4 v4.4.0 // indirect
github.com/open-telemetry/opentelemetry-collector-contrib/pkg/pdatatest v0.148.0 // indirect
github.com/redis/go-redis/extra/rediscmd/v9 v9.15.1 // indirect
github.com/remyoudompheng/bigfft v0.0.0-20230129092748-24d4a6f8daec // indirect
github.com/swaggest/refl v1.4.0 // indirect
@@ -151,7 +149,6 @@ require (
github.com/x448/float16 v0.8.4 // 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
go.yaml.in/yaml/v2 v2.4.4 // indirect
golang.org/x/arch v0.20.0 // indirect
golang.org/x/term v0.43.0 // indirect
@@ -171,10 +168,6 @@ require (
cloud.google.com/go/auth v0.18.2 // indirect
cloud.google.com/go/auth/oauth2adapt v0.2.8 // indirect
cloud.google.com/go/compute/metadata v0.9.0 // indirect
github.com/Azure/azure-sdk-for-go/sdk/azcore v1.21.0 // indirect
github.com/Azure/azure-sdk-for-go/sdk/azidentity v1.13.1 // indirect
github.com/Azure/azure-sdk-for-go/sdk/internal v1.11.2 // indirect
github.com/AzureAD/microsoft-authentication-library-for-go v1.6.0 // indirect
github.com/ClickHouse/ch-go v0.71.0
github.com/Masterminds/squirrel v1.5.4 // indirect
github.com/Yiling-J/theine-go v0.6.2 // indirect
@@ -220,7 +213,6 @@ require (
github.com/gogo/protobuf v1.3.2 // indirect
github.com/gojek/valkyrie v0.0.0-20180215180059-6aee720afcdf // indirect
github.com/golang/protobuf v1.5.4 // indirect
github.com/golang/snappy v1.0.0 // indirect
github.com/google/btree v1.1.3 // indirect
github.com/google/cel-go v0.29.0 // indirect
github.com/google/s2a-go v0.1.9 // indirect
@@ -253,7 +245,6 @@ require (
github.com/jtolds/gls v4.20.0+incompatible // indirect
github.com/klauspost/compress v1.18.5 // indirect
github.com/klauspost/cpuid/v2 v2.3.0 // indirect
github.com/kylelemons/godebug v1.1.0 // indirect
github.com/lann/builder v0.0.0-20180802200727-47ae307949d0 // indirect
github.com/lann/ps v0.0.0-20150810152359-62de8c46ede0 // indirect
github.com/leodido/go-syslog/v4 v4.3.0 // indirect
@@ -278,14 +269,10 @@ require (
github.com/oklog/ulid/v2 v2.1.1
github.com/open-feature/go-sdk v1.17.0
github.com/open-telemetry/opentelemetry-collector-contrib/internal/coreinternal v0.144.0 // indirect
github.com/open-telemetry/opentelemetry-collector-contrib/internal/exp/metrics v0.148.0 // indirect
github.com/open-telemetry/opentelemetry-collector-contrib/pkg/pdatautil v0.148.0 // indirect
github.com/open-telemetry/opentelemetry-collector-contrib/processor/deltatocumulativeprocessor v0.148.0 // indirect
github.com/openfga/openfga v1.14.1
github.com/paulmach/orb v0.12.0 // indirect
github.com/pelletier/go-toml/v2 v2.2.4 // indirect
github.com/pierrec/lz4/v4 v4.1.25 // indirect
github.com/pkg/browser v0.0.0-20240102092130-5ac0b6a4141c // indirect
github.com/pmezard/go-difflib v1.0.1-0.20181226105442-5d4384ee4fb2 // indirect
github.com/power-devops/perfstat v0.0.0-20240221224432-82ca36839d55 // indirect
github.com/pressly/goose/v3 v3.27.0 // indirect

83
go.sum
View File

@@ -73,16 +73,8 @@ github.com/Azure/azure-sdk-for-go/sdk/azcore v1.21.0 h1:fou+2+WFTib47nS+nz/ozhEB
github.com/Azure/azure-sdk-for-go/sdk/azcore v1.21.0/go.mod h1:t76Ruy8AHvUAC8GfMWJMa0ElSbuIcO03NLpynfbgsPA=
github.com/Azure/azure-sdk-for-go/sdk/azidentity v1.13.1 h1:Hk5QBxZQC1jb2Fwj6mpzme37xbCDdNTxU7O9eb5+LB4=
github.com/Azure/azure-sdk-for-go/sdk/azidentity v1.13.1/go.mod h1:IYus9qsFobWIc2YVwe/WPjcnyCkPKtnHAqUYeebc8z0=
github.com/Azure/azure-sdk-for-go/sdk/azidentity/cache v0.3.2 h1:yz1bePFlP5Vws5+8ez6T3HWXPmwOK7Yvq8QxDBD3SKY=
github.com/Azure/azure-sdk-for-go/sdk/azidentity/cache v0.3.2/go.mod h1:Pa9ZNPuoNu/GztvBSKk9J1cDJW6vk/n0zLtV4mgd8N8=
github.com/Azure/azure-sdk-for-go/sdk/internal v1.11.2 h1:9iefClla7iYpfYWdzPCRDozdmndjTm8DXdpCzPajMgA=
github.com/Azure/azure-sdk-for-go/sdk/internal v1.11.2/go.mod h1:XtLgD3ZD34DAaVIIAyG3objl5DynM3CQ/vMcbBNJZGI=
github.com/Azure/azure-sdk-for-go/sdk/resourcemanager/compute/armcompute/v5 v5.7.0 h1:LkHbJbgF3YyvC53aqYGR+wWQDn2Rdp9AQdGndf9QvY4=
github.com/Azure/azure-sdk-for-go/sdk/resourcemanager/compute/armcompute/v5 v5.7.0/go.mod h1:QyiQdW4f4/BIfB8ZutZ2s+28RAgfa/pT+zS++ZHyM1I=
github.com/Azure/azure-sdk-for-go/sdk/resourcemanager/network/armnetwork/v4 v4.3.0 h1:bXwSugBiSbgtz7rOtbfGf+woewp4f06orW9OP5BjHLA=
github.com/Azure/azure-sdk-for-go/sdk/resourcemanager/network/armnetwork/v4 v4.3.0/go.mod h1:Y/HgrePTmGy9HjdSGTqZNa+apUpTVIEVKXJyARP2lrk=
github.com/AzureAD/microsoft-authentication-extensions-for-go/cache v0.1.1 h1:WJTmL004Abzc5wDB5VtZG2PJk5ndYDgVacGqfirKxjM=
github.com/AzureAD/microsoft-authentication-extensions-for-go/cache v0.1.1/go.mod h1:tCcJZ0uHAmvjsVYzEFivsRTN00oz5BEsRgQHu5JZ9WE=
github.com/AzureAD/microsoft-authentication-library-for-go v1.6.0 h1:XRzhVemXdgvJqCH0sFfrBUTnUJSBrBf7++ypk+twtRs=
github.com/AzureAD/microsoft-authentication-library-for-go v1.6.0/go.mod h1:HKpQxkWaGLJ+D/5H8QRpyQXA1eKjxkFlOMwck5+33Jk=
github.com/BurntSushi/toml v0.3.1/go.mod h1:xHWCNGjB5oqiDr8zfno3MHue2Ht5sIBksp03qcyfWMU=
@@ -91,8 +83,6 @@ github.com/ClickHouse/ch-go v0.71.0 h1:bUdZ/EZj/LcVHsMqaRUP2holqygrPWQKeMjc6nZoy
github.com/ClickHouse/ch-go v0.71.0/go.mod h1:NwbNc+7jaqfY58dmdDUbG4Jl22vThgx1cYjBw0vtgXw=
github.com/ClickHouse/clickhouse-go/v2 v2.44.0 h1:9pxs5pRwIvhni5BDRPn/n5A8DeUod5TnBaeulFBX8EQ=
github.com/ClickHouse/clickhouse-go/v2 v2.44.0/go.mod h1:giJfUVlMkcfUEPVfRpt51zZaGEx9i17gCos8gBl392c=
github.com/Code-Hex/go-generics-cache v1.5.1 h1:6vhZGc5M7Y/YD8cIUcY8kcuQLB4cHR7U+0KMqAA0KcU=
github.com/Code-Hex/go-generics-cache v1.5.1/go.mod h1:qxcC9kRVrct9rHeiYpFWSoW1vxyillCVzX13KZG8dl4=
github.com/DATA-DOG/go-sqlmock v1.5.2 h1:OcvFkGmslmlZibjAjaHm3L//6LiuBgolP7OputlJIzU=
github.com/DATA-DOG/go-sqlmock v1.5.2/go.mod h1:88MAG/4G7SMwSE3CeA0ZKzrT5CiOU3OJ+JlNzwDqpNU=
github.com/DataDog/datadog-go v3.2.0+incompatible/go.mod h1:LButxg5PwREeZtORoXG3tL4fMGNddJ+vMq1mwgfaqoQ=
@@ -162,23 +152,11 @@ github.com/aws/aws-sdk-go-v2/internal/ini v1.2.4/go.mod h1:ZcBrrI3zBKlhGFNYWvju0
github.com/aws/aws-sdk-go-v2/internal/ini v1.8.6 h1:qYQ4pzQ2Oz6WpQ8T3HvGHnZydA72MnLuFK9tJwmrbHw=
github.com/aws/aws-sdk-go-v2/internal/ini v1.8.6/go.mod h1:O3h0IK87yXci+kg6flUKzJnWeziQUKciKrLjcatSNcY=
github.com/aws/aws-sdk-go-v2/service/appconfig v1.4.2/go.mod h1:FZ3HkCe+b10uFZZkFdvf98LHW21k49W8o8J366lqVKY=
github.com/aws/aws-sdk-go-v2/service/ec2 v1.296.0 h1:98Miqj16un1WLNyM1RjVDhXYumhqZrQfAeG8i4jPG6o=
github.com/aws/aws-sdk-go-v2/service/ec2 v1.296.0/go.mod h1:T6ndRfdhnXLIY5oKBHjYZDVj706los2zGdpThppquvA=
github.com/aws/aws-sdk-go-v2/service/ecs v1.74.0 h1:YS5TXaEvzDb+sV+wdQFUtuCAk0GeFR9Ai6HFdxpz6q8=
github.com/aws/aws-sdk-go-v2/service/ecs v1.74.0/go.mod h1:10kBgdaNJz0FO/+JWDUH+0rtSjkn5yafgavDDmmhFzs=
github.com/aws/aws-sdk-go-v2/service/elasticache v1.51.12 h1:S066ajzfPRCSW4lsSHOYglne6SNi2CHt1u5omzW1RBg=
github.com/aws/aws-sdk-go-v2/service/elasticache v1.51.12/go.mod h1:86SE4NcXxbxr8KTG3yOyDmd4HyiFmKl8TexXnhYJ+Bw=
github.com/aws/aws-sdk-go-v2/service/internal/accept-encoding v1.13.7 h1:5EniKhLZe4xzL7a+fU3C2tfUN4nWIqlLesfrjkuPFTY=
github.com/aws/aws-sdk-go-v2/service/internal/accept-encoding v1.13.7/go.mod h1:x0nZssQ3qZSnIcePWLvcoFisRXJzcTVvYpAAdYX8+GI=
github.com/aws/aws-sdk-go-v2/service/internal/presigned-url v1.3.2/go.mod h1:72HRZDLMtmVQiLG2tLfQcaWLCssELvGl+Zf2WVxMmR8=
github.com/aws/aws-sdk-go-v2/service/internal/presigned-url v1.13.21 h1:c31//R3xgIJMSC8S6hEVq+38DcvUlgFY0FM6mSI5oto=
github.com/aws/aws-sdk-go-v2/service/internal/presigned-url v1.13.21/go.mod h1:r6+pf23ouCB718FUxaqzZdbpYFyDtehyZcmP5KL9FkA=
github.com/aws/aws-sdk-go-v2/service/kafka v1.49.1 h1:BgBatWcQIFqF1l6KGHjv66V0d/ISnWrTwxDx/Jf6EJM=
github.com/aws/aws-sdk-go-v2/service/kafka v1.49.1/go.mod h1:pMpys+PlrN//vj8j5s0oOAMJjauj81VkHzIZxPVWOro=
github.com/aws/aws-sdk-go-v2/service/lightsail v1.51.0 h1:cg6PxzoIide2wiEyLfikOFN+XwHafwR8p5+L9U1E8dQ=
github.com/aws/aws-sdk-go-v2/service/lightsail v1.51.0/go.mod h1:YvX7hjUWecrKX8fBkbEncyddEW85xjNH+u5JHioITOw=
github.com/aws/aws-sdk-go-v2/service/rds v1.117.0 h1:T1Xe9sYxSUUQOvd1RsFeVk/IXFPdqSiN0atXu/Hy/8A=
github.com/aws/aws-sdk-go-v2/service/rds v1.117.0/go.mod h1:QbXW4coAMakHQhf1qhE0eVVCen9gwB/Kvn+HHHKhpGY=
github.com/aws/aws-sdk-go-v2/service/signin v1.0.8 h1:0GFOLzEbOyZABS3PhYfBIx2rNBACYcKty+XGkTgw1ow=
github.com/aws/aws-sdk-go-v2/service/signin v1.0.8/go.mod h1:LXypKvk85AROkKhOG6/YEcHFPoX+prKTowKnVdcaIxE=
github.com/aws/aws-sdk-go-v2/service/sns v1.39.11 h1:Ke7RS0NuP9Xwk31prXYcFGA1Qfn8QmNWcxyjKPcXZdc=
@@ -247,8 +225,6 @@ github.com/cncf/xds/go v0.0.0-20210805033703-aa0b78936158/go.mod h1:eXthEFrGJvWH
github.com/cncf/xds/go v0.0.0-20210922020428-25de7278fc84/go.mod h1:eXthEFrGJvWHgFFCl3hGmgk+/aYT6PnTQLykKQRLhEs=
github.com/cncf/xds/go v0.0.0-20211001041855-01bcc9b48dfe/go.mod h1:eXthEFrGJvWHgFFCl3hGmgk+/aYT6PnTQLykKQRLhEs=
github.com/cncf/xds/go v0.0.0-20211011173535-cb28da3451f1/go.mod h1:eXthEFrGJvWHgFFCl3hGmgk+/aYT6PnTQLykKQRLhEs=
github.com/cncf/xds/go v0.0.0-20260202195803-dba9d589def2 h1:aBangftG7EVZoUb69Os8IaYg++6uMOdKK83QtkkvJik=
github.com/cncf/xds/go v0.0.0-20260202195803-dba9d589def2/go.mod h1:qwXFYgsP6T7XnJtbKlf1HP8AjxZZyzxMmc+Lq5GjlU4=
github.com/coder/quartz v0.3.0 h1:bUoSEJ77NBfKtUqv6CPSC0AS8dsjqAqqAv7bN02m1mg=
github.com/coder/quartz v0.3.0/go.mod h1:BgE7DOj/8NfvRgvKw0jPLDQH/2Lya2kxcTaNJ8X0rZk=
github.com/containerd/errdefs v1.0.0 h1:tg5yIfIlQIrxYtu9ajqY42W3lpS19XqdxRQeEwYG8PI=
@@ -275,12 +251,8 @@ github.com/dgryski/go-farm v0.0.0-20240924180020-3414d57e47da h1:aIftn67I1fkbMa5
github.com/dgryski/go-farm v0.0.0-20240924180020-3414d57e47da/go.mod h1:SqUrOPUnsFjfmXRMNPybcSiG0BgUW2AuFH8PAnS2iTw=
github.com/dgryski/go-rendezvous v0.0.0-20200823014737-9f7001d12a5f h1:lO4WD4F/rVNCu3HqELle0jiPLLBs70cWOduZpkS1E78=
github.com/dgryski/go-rendezvous v0.0.0-20200823014737-9f7001d12a5f/go.mod h1:cuUVRXasLTGF7a8hSLbxyZXjz+1KgoB3wDUb6vlszIc=
github.com/digitalocean/godo v1.178.0 h1:+B4xGOaoFwwwpM7TKhoyGHdmFg5eF9zDB1YfOLvNJ2E=
github.com/digitalocean/godo v1.178.0/go.mod h1:xQsWpVCCbkDrWisHA72hPzPlnC+4W5w/McZY5ij9uvU=
github.com/distribution/reference v0.6.0 h1:0IXCQ5g4/QMHHkarYzh5l+u8T3t73zM5QvfrDyIgxBk=
github.com/distribution/reference v0.6.0/go.mod h1:BbU0aIcezP1/5jX/8MP0YiH4SdvB5Y4f/wlDRiLyi3E=
github.com/docker/docker v28.5.2+incompatible h1:DBX0Y0zAjZbSrm1uzOkdr1onVghKaftjlSWt4AFexzM=
github.com/docker/docker v28.5.2+incompatible/go.mod h1:eEKB0N0r5NX/I1kEveEz05bcu8tLC/8azJZsviup8Sk=
github.com/docker/go-connections v0.6.0 h1:LlMG9azAe1TqfR7sO+NJttz1gy6KO7VJBh+pMmjSD94=
github.com/docker/go-connections v0.6.0/go.mod h1:AahvXYshr6JgfUJGdDCs2b5EZG/vmaMAntpSFH5BFKE=
github.com/docker/go-units v0.5.0 h1:69rxXcBk27SvSaaxTtLh/8llcHD8vYHT7WSdRZ/jvr4=
@@ -313,9 +285,6 @@ github.com/envoyproxy/go-control-plane v0.9.9-0.20210217033140-668b12f5399d/go.m
github.com/envoyproxy/go-control-plane v0.9.9-0.20210512163311-63b5d3c536b0/go.mod h1:hliV/p42l8fGbc6Y9bQ70uLwIvmJyVE5k4iMKlh8wCQ=
github.com/envoyproxy/go-control-plane v0.9.10-0.20210907150352-cf90f659a021/go.mod h1:AFq3mo9L8Lqqiid3OhADV3RfLJnjiw63cSpi+fDTRC0=
github.com/envoyproxy/go-control-plane v0.10.2-0.20220325020618-49ff273808a1/go.mod h1:KJwIaB5Mv44NWtYuAOFCVOjcI94vtpEz2JU/D2v6IjE=
github.com/envoyproxy/go-control-plane v0.14.0 h1:hbG2kr4RuFj222B6+7T83thSPqLjwBIfQawTkC++2HA=
github.com/envoyproxy/go-control-plane/envoy v1.37.0 h1:u3riX6BoYRfF4Dr7dwSOroNfdSbEPe9Yyl09/B6wBrQ=
github.com/envoyproxy/go-control-plane/envoy v1.37.0/go.mod h1:DReE9MMrmecPy+YvQOAOHNYMALuowAnbjjEMkkWOi6A=
github.com/envoyproxy/protoc-gen-validate v0.1.0/go.mod h1:iSmxcyjqTsJpI2R4NaDN7+kN2VEUnK/pcBlmesArF7c=
github.com/envoyproxy/protoc-gen-validate v1.3.3 h1:MVQghNeW+LZcmXe7SY1V36Z+WFMDjpqGAGacLe2T0ds=
github.com/envoyproxy/protoc-gen-validate v1.3.3/go.mod h1:TsndJ/ngyIdQRhMcVVGDDHINPLWB7C82oDArY51KfB0=
@@ -327,8 +296,6 @@ github.com/fatih/color v1.7.0/go.mod h1:Zm6kSWBoL9eyXnKyktHP6abPY2pDugNf5Kwzbycv
github.com/fatih/color v1.9.0/go.mod h1:eQcE1qtQxscV5RaZvpXrrb8Drkc3/DdQ+uUYCNjL+zU=
github.com/fatih/color v1.10.0/go.mod h1:ELkj/draVOlAH/xkhN6mQ50Qd0MPOk5AAr3maGEBuJM=
github.com/fatih/color v1.13.0/go.mod h1:kLAiJbzzSOZDVNGyDpeOxJ47H46qBXwg5ILebYFFOfk=
github.com/fatih/color v1.18.0 h1:S8gINlzdQ840/4pfAwic/ZE0djQEH3wM94VfqLTZcOM=
github.com/fatih/color v1.18.0/go.mod h1:4FelSpRwEGDpQ12mAdzqdOukCy4u8WUtOY6lkT/6HfU=
github.com/fatih/structs v1.1.0/go.mod h1:9NiDSp5zOcgEDl+j00MP/WkGVPOlPRLejGD8Ga6PJ7M=
github.com/felixge/httpsnoop v1.0.1/go.mod h1:m8KPJKqk1gH5J9DgRY2ASl2lWCfGKXixSwevea8zH2U=
github.com/felixge/httpsnoop v1.0.4 h1:NFTV2Zj1bL4mc9sqWACXbQFVBBg2W3GPvqp8/ESS2Wg=
@@ -438,16 +405,12 @@ github.com/go-playground/validator/v10 v10.27.0 h1:w8+XrWVMhGkxOaaowyKH35gFydVHO
github.com/go-playground/validator/v10 v10.27.0/go.mod h1:I5QpIEbmr8On7W0TktmJAumgzX4CA1XNl4ZmDuVHKKo=
github.com/go-redis/redismock/v9 v9.2.0 h1:ZrMYQeKPECZPjOj5u9eyOjg8Nnb0BS9lkVIZ6IpsKLw=
github.com/go-redis/redismock/v9 v9.2.0/go.mod h1:18KHfGDK4Y6c2R0H38EUGWAdc7ZQS9gfYxc94k7rWT0=
github.com/go-resty/resty/v2 v2.17.2 h1:FQW5oHYcIlkCNrMD2lloGScxcHJ0gkjshV3qcQAyHQk=
github.com/go-resty/resty/v2 v2.17.2/go.mod h1:kCKZ3wWmwJaNc7S29BRtUhJwy7iqmn+2mLtQrOyQlVA=
github.com/go-sql-driver/mysql v1.9.3 h1:U/N249h2WzJ3Ukj8SowVFjdtZKfu9vlLZxjPXV1aweo=
github.com/go-sql-driver/mysql v1.9.3/go.mod h1:qn46aNg1333BRMNU69Lq93t8du/dwxI64Gl8i5p1WMU=
github.com/go-stack/stack v1.8.0/go.mod h1:v0f6uXyyMGvRgIKkXu+yp6POWl0qKG85gN/melR3HDY=
github.com/go-test/deep v1.0.2-0.20181118220953-042da051cf31/go.mod h1:wGDj63lr65AM2AQyKZd/NYHGb0R+1RLqB8NKt3aSFNA=
github.com/go-viper/mapstructure/v2 v2.5.0 h1:vM5IJoUAy3d7zRSVtIwQgBj7BiWtMPfmPEgAXnvj1Ro=
github.com/go-viper/mapstructure/v2 v2.5.0/go.mod h1:oJDH3BJKyqBA2TXFhDsKDGDTlndYOZ6rGS0BRZIxGhM=
github.com/go-zookeeper/zk v1.0.4 h1:DPzxraQx7OrPyXq2phlGlNSIyWEsAox0RJmjTseMV6I=
github.com/go-zookeeper/zk v1.0.4/go.mod h1:nOB03cncLtlp4t+UAkGSV+9beXP/akpekBwL+UX1Qcw=
github.com/gobwas/glob v0.2.3 h1:A4xDbljILXROh+kObIiy5kIaPYD8e96x1tgBhUI5J+Y=
github.com/gobwas/glob v0.2.3/go.mod h1:d3Ez4x06l9bZtSvzIay5+Yzi0fmZzPgnTbPcKjJAkT8=
github.com/goccy/go-json v0.10.5 h1:Fq85nIqj+gXn/S5ahsiTlK3TmC85qgirsdTP/+DeaC4=
@@ -527,8 +490,6 @@ github.com/google/go-cmp v0.5.7/go.mod h1:n+brtR0CgQNWTVd5ZUFpTBC8YFBDLK/h/bpaJ8
github.com/google/go-cmp v0.5.8/go.mod h1:17dUlkBOakJ0+DkrSSNjCkIjxS6bF9zb3elmeNGIjoY=
github.com/google/go-cmp v0.7.0 h1:wk8382ETsv4JYUZwIsn6YpYiWiBsYLSJiTsyBybVuN8=
github.com/google/go-cmp v0.7.0/go.mod h1:pXiqmnSA92OHEEa9HXL2W4E7lf9JzCmGVUdgjX3N/iU=
github.com/google/go-querystring v1.2.0 h1:yhqkPbu2/OH+V9BfpCVPZkNmUXhb2gBxJArfhIxNtP0=
github.com/google/go-querystring v1.2.0/go.mod h1:8IFJqpSRITyJ8QhQ13bmbeMBDfmeEJZD5A0egEOmkqU=
github.com/google/go-tpm v0.9.8 h1:slArAR9Ft+1ybZu0lBwpSmpwhRXaa85hWtMinMyRAWo=
github.com/google/go-tpm v0.9.8/go.mod h1:h9jEsEECg7gtLis0upRBQU+GhYVH6jMjrFxI8u6bVUY=
github.com/google/gofuzz v1.0.0/go.mod h1:dBl0BpW6vV/+mYPU4Po3pmUjxk6FQPldtuIdl/M65Eg=
@@ -571,8 +532,6 @@ github.com/googleapis/gax-go/v2 v2.4.0/go.mod h1:XOTVJ59hdnfJLIP/dh8n5CGryZR2LxK
github.com/googleapis/gax-go/v2 v2.18.0 h1:jxP5Uuo3bxm3M6gGtV94P4lliVetoCB4Wk2x8QA86LI=
github.com/googleapis/gax-go/v2 v2.18.0/go.mod h1:uSzZN4a356eRG985CzJ3WfbFSpqkLTjsnhWGJR6EwrE=
github.com/googleapis/google-cloud-go-testing v0.0.0-20200911160855-bcd43fbb19e8/go.mod h1:dvDLG8qkwmyD9a/MJJN3XJcT3xFxOKAvTZGvuZmac9g=
github.com/gophercloud/gophercloud/v2 v2.11.1 h1:jCs4vLH8sJgRqrPzqVfWgl7uI6JnIIlsgeIRM0uHjxY=
github.com/gophercloud/gophercloud/v2 v2.11.1/go.mod h1:Rm0YvKQ4QYX2rY9XaDKnjRzSGwlG5ge4h6ABYnmkKQM=
github.com/gopherjs/gopherjs v0.0.0-20181017120253-0766667cb4d1/go.mod h1:wJfORRmW1u3UXTncJ5qlYoELFm8eSnnEO6hX4iZ3EWY=
github.com/gopherjs/gopherjs v1.17.2 h1:fQnZVsXk8uxXIStYb0N4bGk7jeyTalG/wsZjQ25dO0g=
github.com/gopherjs/gopherjs v1.17.2/go.mod h1:pRRIvn/QzFLrKfvEz3qUuEhtE/zLCWfreZ6J5gM2i+k=
@@ -594,11 +553,7 @@ github.com/grpc-ecosystem/grpc-gateway/v2 v2.28.0 h1:HWRh5R2+9EifMyIHV7ZV+MIZqgz
github.com/grpc-ecosystem/grpc-gateway/v2 v2.28.0/go.mod h1:JfhWUomR1baixubs02l85lZYYOm7LV6om4ceouMv45c=
github.com/hashicorp/consul/api v1.12.0/go.mod h1:6pVBMo0ebnYdt2S3H87XhekM/HHrUoTD2XXb/VrZVy0=
github.com/hashicorp/consul/api v1.13.0/go.mod h1:ZlVrynguJKcYr54zGaDbaL3fOvKC9m72FhPvA8T35KQ=
github.com/hashicorp/consul/api v1.32.1 h1:0+osr/3t/aZNAdJX558crU3PEjVrG4x6715aZHRgceE=
github.com/hashicorp/consul/api v1.32.1/go.mod h1:mXUWLnxftwTmDv4W3lzxYCPD199iNLLUyLfLGFJbtl4=
github.com/hashicorp/consul/sdk v0.8.0/go.mod h1:GBvyrGALthsZObzUGsfgHZQDXjg4lOjagTIwIR1vPms=
github.com/hashicorp/cronexpr v1.1.3 h1:rl5IkxXN2m681EfivTlccqIryzYJSXRGRNa0xeG7NA4=
github.com/hashicorp/cronexpr v1.1.3/go.mod h1:P4wA0KBl9C5q2hABiMO7cp6jcIg96CDh1Efb3g1PWA4=
github.com/hashicorp/errwrap v1.0.0/go.mod h1:YH+1FKiLXxHSkmPseP+kNlulaMuP3n2brvKWEqk/Jc4=
github.com/hashicorp/errwrap v1.1.0 h1:OxrOeh75EUXMY8TBjag2fzXGZ40LB6IKw45YeGUDY2I=
github.com/hashicorp/errwrap v1.1.0/go.mod h1:YH+1FKiLXxHSkmPseP+kNlulaMuP3n2brvKWEqk/Jc4=
@@ -610,8 +565,6 @@ github.com/hashicorp/go-hclog v0.0.0-20180709165350-ff2cf002a8dd/go.mod h1:9bjs9
github.com/hashicorp/go-hclog v0.8.0/go.mod h1:5CU+agLiy3J7N7QjHK5d05KxGsuXiQLrjA0H7acj2lQ=
github.com/hashicorp/go-hclog v0.12.0/go.mod h1:whpDNt7SSdeAju8AWKIWsul05p54N/39EeqMAyrmvFQ=
github.com/hashicorp/go-hclog v1.2.0/go.mod h1:whpDNt7SSdeAju8AWKIWsul05p54N/39EeqMAyrmvFQ=
github.com/hashicorp/go-hclog v1.6.3 h1:Qr2kF+eVWjTiYmU7Y31tYlP1h0q/X3Nl3tPGdaB11/k=
github.com/hashicorp/go-hclog v1.6.3/go.mod h1:W4Qnvbt70Wk/zYJryRzDRU/4r0kIg0PVHBcfoyhpF5M=
github.com/hashicorp/go-immutable-radix v1.0.0/go.mod h1:0y9vanUI8NX6FsYoO3zeMjhV/C5i9g4Q3DwcSNZ4P60=
github.com/hashicorp/go-immutable-radix v1.3.1 h1:DKHmCUm2hRBK510BaiZlwvpD40f8bJFeZnpfm2KLowc=
github.com/hashicorp/go-immutable-radix v1.3.1/go.mod h1:0y9vanUI8NX6FsYoO3zeMjhV/C5i9g4Q3DwcSNZ4P60=
@@ -630,7 +583,6 @@ github.com/hashicorp/go-retryablehttp v0.5.4/go.mod h1:9B5zBasrRhHXnJnui7y6sL7es
github.com/hashicorp/go-retryablehttp v0.7.8 h1:ylXZWnqa7Lhqpk0L1P1LzDtGcCR0rPVUrx/c8Unxc48=
github.com/hashicorp/go-retryablehttp v0.7.8/go.mod h1:rjiScheydd+CxvumBsIrFKlx3iS0jrZ7LvzFGFmuKbw=
github.com/hashicorp/go-rootcerts v1.0.1/go.mod h1:pqUvnprVnM5bf7AOirdbb01K4ccR319Vf4pU3K5EGc8=
github.com/hashicorp/go-rootcerts v1.0.2 h1:jzhAVGtqPKbwpyCPELlgNWhE1znq+qwJtW5Oi2viEzc=
github.com/hashicorp/go-rootcerts v1.0.2/go.mod h1:pqUvnprVnM5bf7AOirdbb01K4ccR319Vf4pU3K5EGc8=
github.com/hashicorp/go-sockaddr v1.0.0/go.mod h1:7Xibr9yA9JjQq1JpNB2Vw7kxv8xerXegt+ozgdvDeDU=
github.com/hashicorp/go-sockaddr v1.0.2/go.mod h1:rB4wwRAUzs07qva3c5SdrY/NEtAUjGlgmH/UkBUC97A=
@@ -658,18 +610,12 @@ github.com/hashicorp/mdns v1.0.4/go.mod h1:mtBihi+LeNXGtG8L9dX59gAEa12BDtBQSp4v/
github.com/hashicorp/memberlist v0.3.0/go.mod h1:MS2lj3INKhZjWNqd3N0m3J+Jxf3DAOnAH9VT3Sh9MUE=
github.com/hashicorp/memberlist v0.5.4 h1:40YY+3qq2tAUhZIMEK8kqusKZBBjdwJ3NUjvYkcxh74=
github.com/hashicorp/memberlist v0.5.4/go.mod h1:OgN6xiIo6RlHUWk+ALjP9e32xWCoQrsOCmHrWCm2MWA=
github.com/hashicorp/nomad/api v0.0.0-20260324203407-b27b0c2e019a h1:HGwfgBNl90YBiHdbzZ/+8aMxO1UL9B/yNTAXa8iB8z8=
github.com/hashicorp/nomad/api v0.0.0-20260324203407-b27b0c2e019a/go.mod h1:KkLNLU0Nyfh5jWsFoF/PsmMbKpRIAoIV4lmQoJWgKCk=
github.com/hashicorp/serf v0.9.6/go.mod h1:TXZNMjZQijwlDvp+r0b63xZ45H7JmCmgg4gpTwn9UV4=
github.com/hashicorp/serf v0.9.7/go.mod h1:TXZNMjZQijwlDvp+r0b63xZ45H7JmCmgg4gpTwn9UV4=
github.com/hashicorp/serf v0.10.1 h1:Z1H2J60yRKvfDYAOZLd2MU0ND4AH/WDz7xYHDWQsIPY=
github.com/hashicorp/serf v0.10.1/go.mod h1:yL2t6BqATOLGc5HF7qbFkTfXoPIY0WZdWHfEvMqbG+4=
github.com/hashicorp/vault/api v1.0.4/go.mod h1:gDcqh3WGcR1cpF5AJz/B1UFheUEneMoIospckxBxk6Q=
github.com/hashicorp/vault/sdk v0.1.13/go.mod h1:B+hVj7TpuQY1Y/GPbCpffmgd+tSEwvhkWnjtSYCaS2M=
github.com/hashicorp/yamux v0.0.0-20180604194846-3520598351bb/go.mod h1:+NfK9FKeTrX5uv1uIXGdwYDTeHna2qgaIlx54MXqjAM=
github.com/hashicorp/yamux v0.0.0-20181012175058-2f1d1f20f75d/go.mod h1:+NfK9FKeTrX5uv1uIXGdwYDTeHna2qgaIlx54MXqjAM=
github.com/hetznercloud/hcloud-go/v2 v2.36.0 h1:HlLL/aaVXUulqe+rsjoJmrxKhPi1MflL5O9iq5QEtvo=
github.com/hetznercloud/hcloud-go/v2 v2.36.0/go.mod h1:MnN/QJEa/RYNQiiVoJjNHPntM7Z1wlYPgJ2HA40/cDE=
github.com/hjson/hjson-go/v4 v4.0.0 h1:wlm6IYYqHjOdXH1gHev4VoXCaW20HdQAGCxdOEEg2cs=
github.com/hjson/hjson-go/v4 v4.0.0/go.mod h1:KaYt3bTw3zhBjYqnXkYywcYctk0A2nxeEFTse3rH13E=
github.com/huandu/go-assert v1.1.5/go.mod h1:yOLvuqZwmcHIC5rIzrBhT7D3Q9c3GFnd0JrPVhn/06U=
@@ -689,8 +635,6 @@ github.com/ianlancetaylor/demangle v0.0.0-20181102032728-5e5cf60278f6/go.mod h1:
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=
github.com/inconshreveable/mousetrap v1.1.0/go.mod h1:vpF70FUmC8bwa3OWnCshd2FqLfsEA9PFc4w1p2J65bw=
github.com/ionos-cloud/sdk-go/v6 v6.3.6 h1:l/TtKgdQ1wUH3DDe2SfFD78AW+TJWdEbDpQhHkWd6CM=
github.com/ionos-cloud/sdk-go/v6 v6.3.6/go.mod h1:nUGHP4kZHAZngCVr4v6C8nuargFrtvt7GrzH/hqn7c4=
github.com/jackc/pgpassfile v1.0.0 h1:/6Hmqy13Ss2zCq62VdNG8tM1wchn8zjSGOBJ6icpsIM=
github.com/jackc/pgpassfile v1.0.0/go.mod h1:CEx0iS5ambNFdcRtxPj5JhEz+xB6uRky5eyVu/W2HEg=
github.com/jackc/pgservicefile v0.0.0-20240606120523-5a60cdf6a761 h1:iCEnooe7UlwOQYpKFhBabPMi4aNAfoODPEFNiAnClxo=
@@ -727,8 +671,6 @@ github.com/jtolds/gls v4.20.0+incompatible h1:xdiiI2gbIgH/gLH7ADydsJ1uDOEzR8yvV7
github.com/jtolds/gls v4.20.0+incompatible/go.mod h1:QJZ7F/aHp+rZTRtaJ1ow/lLfFfVYBRgL+9YlvaHOwJU=
github.com/julienschmidt/httprouter v1.2.0/go.mod h1:SYymIcj16QtmaHHD7aYtjjsJG7VTCxuUUipMqKk8s4w=
github.com/julienschmidt/httprouter v1.3.0/go.mod h1:JR6WtHb+2LUe8TCKY3cZOxFyyO8IZAc4RVcycCCAKdM=
github.com/keybase/go-keychain v0.0.1 h1:way+bWYa6lDppZoZcgMbYsvC7GxljxrskdNInRtuthU=
github.com/keybase/go-keychain v0.0.1/go.mod h1:PdEILRW3i9D8JcdM+FmY6RwkHGnhHxXwkPPMeUgOK1k=
github.com/kisielk/errcheck v1.5.0/go.mod h1:pFxgyoBC7bSaBwPgfKdkLd5X25qrDl4LWUI2bnpBCr8=
github.com/kisielk/gotool v1.0.0/go.mod h1:XhKaO+MFFWcvkIS/tQcRk01m1F5IRFswLeQ+oQHNcck=
github.com/kisielk/sqlstruct v0.0.0-20201105191214-5f3e10d3ab46/go.mod h1:yyMNCyc/Ib3bDTKd379tNMpB/7/H5TjM2Y9QJ5THLbE=
@@ -741,8 +683,6 @@ github.com/knadh/koanf v1.5.0 h1:q2TSd/3Pyc/5yP9ldIrSdIz26MCcyNQzW0pEAugLPNs=
github.com/knadh/koanf v1.5.0/go.mod h1:Hgyjp4y8v44hpZtPzs7JZfRAW5AhN7KfZcwv1RYggDs=
github.com/knadh/koanf/v2 v2.3.3 h1:jLJC8XCRfLC7n4F+ZKKdBsbq1bfXTpuFhf4L7t94D94=
github.com/knadh/koanf/v2 v2.3.3/go.mod h1:gRb40VRAbd4iJMYYD5IxZ6hfuopFcXBpc9bbQpZwo28=
github.com/kolo/xmlrpc v0.0.0-20220921171641-a4b6fa1dd06b h1:udzkj9S/zlT5X367kqJis0QP7YMxobob6zhzq6Yre00=
github.com/kolo/xmlrpc v0.0.0-20220921171641-a4b6fa1dd06b/go.mod h1:pcaDhQK0/NJZEvtCO0qQPPropqV0sJOJ6YW7X+9kRwM=
github.com/konsorten/go-windows-terminal-sequences v1.0.1/go.mod h1:T0+1ngSBFLxvqU3pZ+m/2kptfBszLMUkC4ZK/EgS/cQ=
github.com/konsorten/go-windows-terminal-sequences v1.0.3/go.mod h1:T0+1ngSBFLxvqU3pZ+m/2kptfBszLMUkC4ZK/EgS/cQ=
github.com/kr/fs v0.1.0/go.mod h1:FFnZGqtBN9Gxj7eW1uZ42v5BccTP0vu6NEaFoC2HwRg=
@@ -770,8 +710,6 @@ github.com/leodido/go-urn v1.4.0 h1:WT9HwE9SGECu3lg4d/dIA+jxlljEa1/ffXKmRjqdmIQ=
github.com/leodido/go-urn v1.4.0/go.mod h1:bvxc+MVxLKB4z00jd1z+Dvzr47oO32F/QSNjSBOlFxI=
github.com/leodido/ragel-machinery v0.0.0-20190525184631-5f46317e436b h1:11UHH39z1RhZ5dc4y4r/4koJo6IYFgTRMe/LlwRTEw0=
github.com/leodido/ragel-machinery v0.0.0-20190525184631-5f46317e436b/go.mod h1:WZxr2/6a/Ar9bMDc2rN/LJrE/hF6bXE4LPyDSIxwAfg=
github.com/linode/linodego v1.66.0 h1:rK8QJFaV53LWOEJvb/evhTg/dP5ElvtuZmx4iv4RJds=
github.com/linode/linodego v1.66.0/go.mod h1:12ykGs9qsvxE+OU3SXuW2w+DTruWF35FPlXC7gGk2tU=
github.com/lufia/plan9stats v0.0.0-20251013123823-9fd1530e3ec3 h1:PwQumkgq4/acIiZhtifTV5OUqqiP82UAl0h87xj/l9k=
github.com/lufia/plan9stats v0.0.0-20251013123823-9fd1530e3ec3/go.mod h1:autxFIvghDt3jPTLoqZ9OZ7s9qTGNAWmYCjVFWPX/zg=
github.com/magefile/mage v1.15.0 h1:BvGheCMAsG3bWUDbZ8AyXXpCNwU9u5CB6sM+HNb9HYg=
@@ -787,8 +725,6 @@ github.com/mattn/go-colorable v0.1.6/go.mod h1:u6P/XSegPjTcexA+o6vUJrdnUu04hMope
github.com/mattn/go-colorable v0.1.8/go.mod h1:u6P/XSegPjTcexA+o6vUJrdnUu04hMope9wVRipJSqc=
github.com/mattn/go-colorable v0.1.9/go.mod h1:u6P/XSegPjTcexA+o6vUJrdnUu04hMope9wVRipJSqc=
github.com/mattn/go-colorable v0.1.12/go.mod h1:u5H1YNBxpqRaxsYJYSkiCWKzEfiAb1Gb520KVy5xxl4=
github.com/mattn/go-colorable v0.1.14 h1:9A9LHSqF/7dyVVX6g0U9cwm9pG3kP9gSzcuIPHPsaIE=
github.com/mattn/go-colorable v0.1.14/go.mod h1:6LmQG8QLFO4G5z1gPvYEzlUgJ2wF+stgPZH1UqBm1s8=
github.com/mattn/go-isatty v0.0.3/go.mod h1:M+lRXTBqGeGNdLjl/ufCoiOlB5xdOkqRJdNxMWT7Zi4=
github.com/mattn/go-isatty v0.0.8/go.mod h1:Iq45c/XA43vh69/j3iqttzPXn0bhXyGjM0Hdxcsrc5s=
github.com/mattn/go-isatty v0.0.10/go.mod h1:qgIWMr58cqv1PHHyhnkY9lrL7etaEgOFcMEpPG5Rm84=
@@ -815,7 +751,6 @@ github.com/mitchellh/cli v1.1.0/go.mod h1:xcISNoH86gajksDmfB23e/pu+B+GeFRMYmoHXx
github.com/mitchellh/copystructure v1.0.0/go.mod h1:SNtv71yrdKgLRyLFxmLdkAbkKEFWgYaq1OVrnRcwhnw=
github.com/mitchellh/copystructure v1.2.0 h1:vpKXTN4ewci03Vljg/q9QvCGUDttBOGBIa15WveJJGw=
github.com/mitchellh/copystructure v1.2.0/go.mod h1:qLl+cE2AmVv+CoeAwDPye/v+N2HKCj9FbZEVFJRxO9s=
github.com/mitchellh/go-homedir v1.1.0 h1:lukF9ziXFxDFPkA1vsr5zpc1XuPDn/wFntq5mG+4E0Y=
github.com/mitchellh/go-homedir v1.1.0/go.mod h1:SfyaCUpYCn1Vlf4IUYiD9fPX4A5wJrkLzIz1N1q0pr0=
github.com/mitchellh/go-testing-interface v0.0.0-20171004221916-a61a99592b77/go.mod h1:kRemZodwjscx+RGhAo8eIhFbs2+BFgRtFPeD/KE+zxI=
github.com/mitchellh/go-testing-interface v1.0.0/go.mod h1:kRemZodwjscx+RGhAo8eIhFbs2+BFgRtFPeD/KE+zxI=
@@ -875,8 +810,6 @@ github.com/open-telemetry/opentelemetry-collector-contrib/internal/common v0.144
github.com/open-telemetry/opentelemetry-collector-contrib/internal/common v0.144.0/go.mod h1:R0go5FMmUe51VpKl8YCk/rUxibA+U3lfPYMoihQ/nhw=
github.com/open-telemetry/opentelemetry-collector-contrib/internal/coreinternal v0.144.0 h1:Qv3nLVGKJ9LQCGwxteJxjSNyQ5CP99QRvYPFn6d8Y60=
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=
@@ -889,8 +822,6 @@ github.com/open-telemetry/opentelemetry-collector-contrib/pkg/stanza v0.144.0 h1
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=
github.com/open-telemetry/opentelemetry-collector-contrib/processor/logstransformprocessor v0.144.0/go.mod h1:32jR9iqxVozOJ/Lg5RkCNoW18uCNwpKSbs6h5c28Ep4=
github.com/opencontainers/go-digest v1.0.0 h1:apOUWs51W5PlhuyGyz9FCeeBIOUDA/6nW8Oi/yOhh5U=
@@ -906,8 +837,6 @@ github.com/openfga/openfga v1.14.1/go.mod h1:AqMyFFi3y24Hko1mIME6ctOdCsCru2HA3uH
github.com/opentracing/opentracing-go v1.1.0/go.mod h1:UkNAQd3GIcIGf0SeVgPpRdFStlNbqXla1AfSYxPUl2o=
github.com/opentracing/opentracing-go v1.2.0 h1:uEJPy/1a5RIPAJ0Ov+OIO8OxWu77jEv+1B0VhjKrZUs=
github.com/opentracing/opentracing-go v1.2.0/go.mod h1:GxEUsuufX4nBwe+T+Wl9TAgYrxe9dPLANfrWvHYVTgc=
github.com/ovh/go-ovh v1.9.0 h1:6K8VoL3BYjVV3In9tPJUdT7qMx9h0GExN9EXx1r2kKE=
github.com/ovh/go-ovh v1.9.0/go.mod h1:cTVDnl94z4tl8pP1uZ/8jlVxntjSIf09bNcQ5TJSC7c=
github.com/pascaldekloe/goe v0.0.0-20180627143212-57f6aae5913c/go.mod h1:lzWF7FIEvWOWxwDKqyGYQf6ZUaNfKdP144TG7ZOy1lc=
github.com/pascaldekloe/goe v0.1.0 h1:cBOtyMzM9HTpWjXfbbunk26uA6nG3a8n06Wieeh0MwY=
github.com/pascaldekloe/goe v0.1.0/go.mod h1:lzWF7FIEvWOWxwDKqyGYQf6ZUaNfKdP144TG7ZOy1lc=
@@ -934,8 +863,6 @@ github.com/pkg/errors v0.8.1/go.mod h1:bwawxfHBFNV+L2hUp1rHADufV3IMtnDRdf1r5NINE
github.com/pkg/errors v0.9.1 h1:FEBLx1zS214owpjy7qsBeixbURkuhQAwrK5UwLGTwt4=
github.com/pkg/errors v0.9.1/go.mod h1:bwawxfHBFNV+L2hUp1rHADufV3IMtnDRdf1r5NINEl0=
github.com/pkg/sftp v1.13.1/go.mod h1:3HaPG6Dq1ILlpPZRO0HVMrsydcdLt6HRDccSgb87qRg=
github.com/planetscale/vtprotobuf v0.6.1-0.20240319094008-0393e58bdf10 h1:GFCKgmp0tecUJ0sJuv4pzYCqS9+RGSn52M3FUwPs+uo=
github.com/planetscale/vtprotobuf v0.6.1-0.20240319094008-0393e58bdf10/go.mod h1:t/avpk3KcrXxUnYOhZhMXJlSEyie6gQbtLq5NM3loB8=
github.com/pmezard/go-difflib v1.0.0/go.mod h1:iKH77koFhYxTK1pcRnkKkqfTogsbg7gZNVY4sRDYZ/4=
github.com/pmezard/go-difflib v1.0.1-0.20181226105442-5d4384ee4fb2 h1:Jamvg5psRIccs7FGNTlIRMkT8wgtp5eCXdBlqhYGL6U=
github.com/pmezard/go-difflib v1.0.1-0.20181226105442-5d4384ee4fb2/go.mod h1:iKH77koFhYxTK1pcRnkKkqfTogsbg7gZNVY4sRDYZ/4=
@@ -985,8 +912,6 @@ github.com/prometheus/sigv4 v0.4.1 h1:EIc3j+8NBea9u1iV6O5ZAN8uvPq2xOIUPcqCTivHuX
github.com/prometheus/sigv4 v0.4.1/go.mod h1:eu+ZbRvsc5TPiHwqh77OWuCnWK73IdkETYY46P4dXOU=
github.com/puzpuzpuz/xsync/v3 v3.5.1 h1:GJYJZwO6IdxN/IKbneznS6yPkVC+c3zyY/j19c++5Fg=
github.com/puzpuzpuz/xsync/v3 v3.5.1/go.mod h1:VjzYrABPabuM4KyBh1Ftq6u8nhwY5tBPKP9jpmh0nnA=
github.com/puzpuzpuz/xsync/v4 v4.4.0 h1:vlSN6/CkEY0pY8KaB0yqo/pCLZvp9nhdbBdjipT4gWo=
github.com/puzpuzpuz/xsync/v4 v4.4.0/go.mod h1:VJDmTCJMBt8igNxnkQd86r+8KUeN1quSfNKu5bLYFQo=
github.com/rcrowley/go-metrics v0.0.0-20201227073835-cf1acfcdf475/go.mod h1:bCqnVzQkZxMG4s8nGwiZ5l3QUCyqpo9Y+/ZMZ9VjZe4=
github.com/redis/go-redis/extra/rediscmd/v9 v9.15.1 h1:G3pzZlMvMX9VX9TBB8zr03CAkeyMtbyW2D59PdyaGkM=
github.com/redis/go-redis/extra/rediscmd/v9 v9.15.1/go.mod h1:JiJ4f0bngycE8LQqzY/4TB23witBbFnlUS6hPvHn6Zc=
@@ -1022,8 +947,6 @@ github.com/samber/lo v1.47.0 h1:z7RynLwP5nbyRscyvcD043DWYoOcYRv3mV8lBeqOCLc=
github.com/samber/lo v1.47.0/go.mod h1:RmDH9Ct32Qy3gduHQuKJ3gW1fMHAnE/fAzQuf6He5cU=
github.com/santhosh-tekuri/jsonschema/v3 v3.1.0 h1:levPcBfnazlA1CyCMC3asL/QLZkq9pa8tQZOH513zQw=
github.com/santhosh-tekuri/jsonschema/v3 v3.1.0/go.mod h1:8kzK2TC0k0YjOForaAHdNEa7ik0fokNa2k30BKJ/W7Y=
github.com/scaleway/scaleway-sdk-go v1.0.0-beta.36 h1:ObX9hZmK+VmijreZO/8x9pQ8/P/ToHD/bdSb4Eg4tUo=
github.com/scaleway/scaleway-sdk-go v1.0.0-beta.36/go.mod h1:LEsDu4BubxK7/cWhtlQWfuxwL4rf/2UEpxXz1o1EMtM=
github.com/sean-/seed v0.0.0-20170313163322-e2103e2c3529 h1:nn5Wsu0esKSJiIVhscUtVbo7ada43DJhG55ua/hjS5I=
github.com/sean-/seed v0.0.0-20170313163322-e2103e2c3529/go.mod h1:DxrIzT+xaE7yg65j358z/aeFdxmN0P9QXhEzd20vsDc=
github.com/sebdah/goldie/v2 v2.5.3 h1:9ES/mNN+HNUbNWpVAlrzuZ7jE+Nrczbj8uFRjM7624Y=
@@ -1078,8 +1001,6 @@ github.com/spf13/viper v1.20.1 h1:ZMi+z/lvLyPSCoNtFCpqjy0S4kPbirhpTMwl8BkW9X4=
github.com/spf13/viper v1.20.1/go.mod h1:P9Mdzt1zoHIG8m2eZQinpiBjo6kCmZSKBClNNqjJvu4=
github.com/srikanthccv/ClickHouse-go-mock v0.12.0 h1:KUzaWTwuqMc2uf5FylM/oAcTFdE2DdZjvISm9V0/NAA=
github.com/srikanthccv/ClickHouse-go-mock v0.12.0/go.mod h1:1oUmLtXEXOyS0EEWVKlKEfLfv9y02agCMAvD3tVnhlo=
github.com/stackitcloud/stackit-sdk-go/core v0.23.0 h1:zPrOhf3Xe47rKRs1fg/AqKYUiJJRYjdcv+3qsS50mEs=
github.com/stackitcloud/stackit-sdk-go/core v0.23.0/go.mod h1:osMglDby4csGZ5sIfhNyYq1bS1TxIdPY88+skE/kkmI=
github.com/stretchr/objx v0.1.0/go.mod h1:HFkY916IF+rwdDfMAkV7OtwuqBVzrE8GR6GFx+wExME=
github.com/stretchr/objx v0.1.1/go.mod h1:HFkY916IF+rwdDfMAkV7OtwuqBVzrE8GR6GFx+wExME=
github.com/stretchr/objx v0.3.0/go.mod h1:qt09Ya8vawLte6SNmTgCsAVtYtaKzEcn8ATUoHMkEqE=
@@ -1158,8 +1079,6 @@ github.com/vmihailenco/msgpack/v5 v5.4.1 h1:cQriyiUvjTwOHg8QZaPihLWeRAAVoCpE00IU
github.com/vmihailenco/msgpack/v5 v5.4.1/go.mod h1:GaZTsDaehaPpQVyxrf5mtQlH+pc21PIudVV/E3rRQok=
github.com/vmihailenco/tagparser/v2 v2.0.0 h1:y09buUbR+b5aycVFQs/g70pqKVZNBmxwAhO7/IwNM9g=
github.com/vmihailenco/tagparser/v2 v2.0.0/go.mod h1:Wri+At7QHww0WTrCBeu4J6bNtoV6mEfg5OIWRZA9qds=
github.com/vultr/govultr/v3 v3.28.1 h1:KR3LhppYARlBujY7+dcrE7YKL0Yo9qXL+msxykKQrLI=
github.com/vultr/govultr/v3 v3.28.1/go.mod h1:2zyUw9yADQaGwKnwDesmIOlBNLrm7edsCfWHFJpWKf8=
github.com/x448/float16 v0.8.4 h1:qLwI1I70+NjRFUR3zs1JPUCgaCXSh3SW62uAKT1mSBM=
github.com/x448/float16 v0.8.4/go.mod h1:14CWIYCyZA/cWjXOioeEpHeN/83MdbZDRQHoFcYsOfg=
github.com/xdg-go/pbkdf2 v1.0.0/go.mod h1:jrpuAogTd400dnrH08LKmI/xc1MbPOebTwRqcT5RDeI=
@@ -1921,8 +1840,6 @@ gopkg.in/evanphx/json-patch.v4 v4.13.0/go.mod h1:p8EYWUEYMpynmqDbY58zCKCFZw8pRWM
gopkg.in/inf.v0 v0.9.1 h1:73M5CoZyi3ZLMOyDlQh031Cx6N9NDJ2Vvfl76EDAgDc=
gopkg.in/inf.v0 v0.9.1/go.mod h1:cWUDdTG/fYaXco+Dcufb5Vnc6Gp2YChqWtbxRZE0mXw=
gopkg.in/ini.v1 v1.67.0/go.mod h1:pNLf8WUiyNEtQjuu5G5vTm06TEv9tsIgeAvK8hOrP4k=
gopkg.in/ini.v1 v1.67.1 h1:tVBILHy0R6e4wkYOn3XmiITt/hEVH4TFMYvAX2Ytz6k=
gopkg.in/ini.v1 v1.67.1/go.mod h1:x/cyOwCgZqOkJoDIJ3c1KNHMo10+nLGAhh+kn3Zizss=
gopkg.in/square/go-jose.v2 v2.3.1/go.mod h1:M9dMgbHiYLoDGQrXy7OpJDJWiKiU//h+vD76mk0e1AI=
gopkg.in/telebot.v3 v3.3.8 h1:uVDGjak9l824FN9YARWUHMsiNZnlohAVwUycw21k6t8=
gopkg.in/telebot.v3 v3.3.8/go.mod h1:1mlbqcLTVSfK9dx7fdp+Nb5HZsy4LLPtpZTKmwhwtzM=

View File

@@ -3,16 +3,15 @@ package flagger
import "github.com/SigNoz/signoz/pkg/types/featuretypes"
var (
FeatureUseSpanMetrics = featuretypes.MustNewName("use_span_metrics")
FeatureKafkaSpanEval = featuretypes.MustNewName("kafka_span_eval")
FeatureHideRootUser = featuretypes.MustNewName("hide_root_user")
FeaturePutMetersInZeus = featuretypes.MustNewName("put_meters_in_zeus")
FeatureUseMeterReporter = featuretypes.MustNewName("use_meter_reporter")
FeatureUseJSONBody = featuretypes.MustNewName("use_json_body")
FeatureEnableAIObservability = featuretypes.MustNewName("enable_ai_observability")
FeatureEnableMetricsReduction = featuretypes.MustNewName("enable_metrics_reduction")
FeatureUsePrometheusClickhouseV2 = featuretypes.MustNewName("use_prometheus_clickhouse_v2")
FeatureResolveSemconvFamilies = featuretypes.MustNewName("resolve_semconv_families")
FeatureUseSpanMetrics = featuretypes.MustNewName("use_span_metrics")
FeatureKafkaSpanEval = featuretypes.MustNewName("kafka_span_eval")
FeatureHideRootUser = featuretypes.MustNewName("hide_root_user")
FeaturePutMetersInZeus = featuretypes.MustNewName("put_meters_in_zeus")
FeatureUseMeterReporter = featuretypes.MustNewName("use_meter_reporter")
FeatureUseJSONBody = featuretypes.MustNewName("use_json_body")
FeatureEnableAIObservability = featuretypes.MustNewName("enable_ai_observability")
FeatureEnableMetricsReduction = featuretypes.MustNewName("enable_metrics_reduction")
FeatureResolveSemconvFamilies = featuretypes.MustNewName("resolve_semconv_families")
)
func MustNewRegistry() featuretypes.Registry {
@@ -81,14 +80,6 @@ func MustNewRegistry() featuretypes.Registry {
DefaultVariant: featuretypes.MustNewName("disabled"),
Variants: featuretypes.NewBooleanVariants(),
},
&featuretypes.Feature{
Name: FeatureUsePrometheusClickhouseV2,
Kind: featuretypes.KindBoolean,
Stage: featuretypes.StageExperimental,
Description: "Runs PromQL queries on the clickhousev2 provider alongside the served engine result and logs any difference; serving is unaffected.",
DefaultVariant: featuretypes.MustNewName("disabled"),
Variants: featuretypes.NewBooleanVariants(),
},
&featuretypes.Feature{
Name: FeatureResolveSemconvFamilies,
Kind: featuretypes.KindBoolean,

View File

@@ -1,90 +0,0 @@
package clickhouseprometheus
import (
"context"
"sync"
"github.com/SigNoz/signoz/pkg/prometheus"
"github.com/prometheus/prometheus/prompb"
"github.com/prometheus/prometheus/storage"
)
// statementRecorder collects the statements a PromQL evaluation would run.
// Safe for concurrent use: the engine may Select selectors concurrently.
type statementRecorder struct {
mu sync.Mutex
statements []prometheus.CapturedStatement
}
func (r *statementRecorder) record(query string, args []any) {
r.mu.Lock()
defer r.mu.Unlock()
r.statements = append(r.statements, prometheus.CapturedStatement{Query: query, Args: args})
}
func (r *statementRecorder) Statements() []prometheus.CapturedStatement {
r.mu.Lock()
defer r.mu.Unlock()
out := make([]prometheus.CapturedStatement, len(r.statements))
copy(out, r.statements)
return out
}
// captureClient builds the same SQL as the real client but records it and
// returns an empty result instead of executing.
type captureClient struct {
*client
recorder *statementRecorder
}
func (c *captureClient) Read(ctx context.Context, query *prompb.Query, _ bool) (storage.SeriesSet, error) {
// Raw-SQL passthrough ({job="rawsql", query="..."}): record the raw query.
if len(query.Matchers) == 2 {
var hasJob bool
var queryString string
for _, m := range query.Matchers {
if m.Type == prompb.LabelMatcher_EQ && m.Name == "job" && m.Value == "rawsql" {
hasJob = true
}
if m.Type == prompb.LabelMatcher_EQ && m.Name == "query" {
queryString = m.Value
}
}
if hasJob && queryString != "" {
c.recorder.record(queryString, nil)
return storage.EmptySeriesSet(), nil
}
}
// Without executing the series lookup, only an exact-name selector's
// metric name is known.
var metricNames []string
for _, matcher := range query.Matchers {
if matcher.Name == "__name__" && matcher.Type == prompb.LabelMatcher_EQ {
metricNames = []string{matcher.Value}
}
}
// Build the executing path's queries, but only record them.
sub, err := seriesLookupQuery(query, true)
if err != nil {
return nil, err
}
samplesQuery, samplesArgs := buildSamplesQuery(int64(query.StartTimestampMs), int64(query.EndTimestampMs), metricNames, sub)
c.recorder.record(samplesQuery, samplesArgs)
return storage.EmptySeriesSet(), nil
}
// captureQueryable adapts the capturing read client to storage.Queryable.
type captureQueryable struct {
inner storage.SampleAndChunkQueryable
}
func (c captureQueryable) Querier(mint, maxt int64) (storage.Querier, error) {
querier, err := c.inner.Querier(mint, maxt)
if err != nil {
return nil, err
}
return storage.NewMergeQuerier(nil, []storage.Querier{querier}, storage.ChainedSeriesMerge), nil
}

View File

@@ -1,517 +0,0 @@
package clickhouseprometheus
import (
"context"
"fmt"
"math"
"sort"
"sync"
"github.com/SigNoz/signoz/pkg/errors"
"github.com/SigNoz/signoz/pkg/factory"
"github.com/SigNoz/signoz/pkg/telemetrystore"
"github.com/SigNoz/signoz/pkg/types/ctxtypes"
"github.com/SigNoz/signoz/pkg/types/instrumentationtypes"
"github.com/SigNoz/signoz/pkg/types/telemetrytypes"
"github.com/cespare/xxhash/v2"
"github.com/huandu/go-sqlbuilder"
promValue "github.com/prometheus/prometheus/model/value"
"github.com/prometheus/prometheus/prompb"
"github.com/prometheus/prometheus/storage"
"github.com/prometheus/prometheus/storage/remote"
)
type client struct {
settings factory.ScopedProviderSettings
telemetryStore telemetrystore.TelemetryStore
}
func NewReadClient(settings factory.ScopedProviderSettings, telemetryStore telemetrystore.TelemetryStore) remote.ReadClient {
return &client{
settings: settings,
telemetryStore: telemetryStore,
}
}
func (client *client) Read(ctx context.Context, query *prompb.Query, sortSeries bool) (storage.SeriesSet, error) {
if len(query.Matchers) == 2 {
var hasJob bool
var queryString string
for _, m := range query.Matchers {
if m.Type == prompb.LabelMatcher_EQ && m.Name == "job" && m.Value == "rawsql" {
hasJob = true
}
if m.Type == prompb.LabelMatcher_EQ && m.Name == "query" {
queryString = m.Value
}
}
if hasJob && queryString != "" {
res, err := client.queryRaw(ctx, queryString, int64(query.EndTimestampMs))
if err != nil {
return nil, err
}
return remote.FromQueryResult(sortSeries, res), nil
}
}
lookup, err := seriesLookupQuery(query, false)
if err != nil {
return nil, err
}
lookupSQL, lookupArgs := lookup.BuildWithFlavor(sqlbuilder.ClickHouse)
fingerprints, metricNames, err := client.getFingerprintsFromClickhouseQuery(ctx, lookupSQL, lookupArgs)
if err != nil {
return nil, err
}
if len(fingerprints) == 0 {
return remote.FromQueryResult(sortSeries, new(prompb.QueryResult)), nil
}
sub, err := seriesLookupQuery(query, true)
if err != nil {
return nil, err
}
samplesSQL, samplesArgs := buildSamplesQuery(int64(query.StartTimestampMs), int64(query.EndTimestampMs), metricNames, sub)
res := new(prompb.QueryResult)
timeseries, err := client.querySamples(ctx, samplesSQL, samplesArgs, fingerprints)
if err != nil {
return nil, err
}
res.Timeseries = timeseries
return remote.FromQueryResult(sortSeries, res), nil
}
func (c *client) ReadMultiple(ctx context.Context, queries []*prompb.Query, sortSeries bool) (storage.SeriesSet, error) {
if len(queries) == 0 {
return storage.EmptySeriesSet(), nil
}
if len(queries) == 1 {
return c.Read(ctx, queries[0], sortSeries)
}
type result struct {
ss storage.SeriesSet
err error
}
results := make([]result, len(queries))
var wg sync.WaitGroup
wg.Add(len(queries))
for i, q := range queries {
go func(i int, q *prompb.Query) {
defer wg.Done()
ss, err := c.Read(ctx, q, sortSeries)
results[i] = result{ss, err}
}(i, q)
}
wg.Wait()
sets := make([]storage.SeriesSet, 0, len(queries))
for _, r := range results {
if r.err != nil {
return nil, r.err
}
sets = append(sets, r.ss)
}
return storage.NewMergeSeriesSet(sets, 0, storage.ChainedSeriesMerge), nil
}
// anchorRegex makes a pattern fully anchored, the way Prometheus compiles
// matcher regexes; ClickHouse's match() would otherwise substring-match.
func anchorRegex(pattern string) string {
return "^(?:" + pattern + ")$"
}
// seriesLookupQuery builds the time-series lookup. It returns a builder so
// the samples query can embed it as a subquery with the args merged in
// render order by the builder instead of hand-numbered placeholders.
func seriesLookupQuery(query *prompb.Query, subQuery bool) (*sqlbuilder.SelectBuilder, error) {
sb := sqlbuilder.NewSelectBuilder()
if subQuery {
sb.Select("fingerprint")
} else {
sb.Select("fingerprint", "any(labels)")
}
start, end, tableName := getStartAndEndAndTableName(query.StartTimestampMs, query.EndTimestampMs)
sb.From(databaseName + "." + tableName)
sb.Where("temporality IN ['Cumulative', 'Unspecified']")
// Inclusive upper bound: registration rows are hour-floored by the
// exporter, so a series first registered in the hour starting exactly at
// `end` would otherwise be invisible while its samples (<= end) are in
// range.
sb.Where(fmt.Sprintf("unix_milli >= %d AND unix_milli <= %d", start, end))
for _, m := range query.Matchers {
if m.Name == "__name__" {
// __name__ maps onto the metric_name column per matcher type;
// reducing regex/negated/absent name matchers to one equality
// made such selectors silently return empty.
switch m.Type {
case prompb.LabelMatcher_EQ:
sb.Where(sb.E("metric_name", m.Value))
case prompb.LabelMatcher_NEQ:
sb.Where(sb.NE("metric_name", m.Value))
case prompb.LabelMatcher_RE:
sb.Where(fmt.Sprintf("match(metric_name, %s)", sb.Var(anchorRegex(m.Value))))
case prompb.LabelMatcher_NRE:
sb.Where(fmt.Sprintf("not match(metric_name, %s)", sb.Var(anchorRegex(m.Value))))
default:
return nil, errors.NewInvalidInputf(errors.CodeInvalidInput, "unsupported or invalid matcher type: %s", m.Type.String())
}
continue
}
switch m.Type {
case prompb.LabelMatcher_EQ:
sb.Where(fmt.Sprintf("JSONExtractString(labels, %s) = %s", sb.Var(m.Name), sb.Var(m.Value)))
case prompb.LabelMatcher_NEQ:
sb.Where(fmt.Sprintf("JSONExtractString(labels, %s) != %s", sb.Var(m.Name), sb.Var(m.Value)))
case prompb.LabelMatcher_RE:
sb.Where(fmt.Sprintf("match(JSONExtractString(labels, %s), %s)", sb.Var(m.Name), sb.Var(anchorRegex(m.Value))))
case prompb.LabelMatcher_NRE:
sb.Where(fmt.Sprintf("not match(JSONExtractString(labels, %s), %s)", sb.Var(m.Name), sb.Var(anchorRegex(m.Value))))
default:
return nil, errors.NewInvalidInputf(errors.CodeInvalidInput, "unsupported or invalid matcher type: %s", m.Type.String())
}
}
sb.GroupBy("fingerprint")
return sb, nil
}
func (client *client) getFingerprintsFromClickhouseQuery(ctx context.Context, query string, args []any) (map[uint64][]prompb.Label, []string, error) {
ctx = client.withClickhousePrometheusContext(ctx, "getFingerprintsFromClickhouseQuery")
rows, err := client.telemetryStore.ClickhouseDB().Query(ctx, query, args...)
if err != nil {
return nil, nil, err
}
defer rows.Close()
fingerprints := make(map[uint64][]prompb.Label)
nameSet := make(map[string]struct{})
var fingerprint uint64
var labelString string
for rows.Next() {
if err = rows.Scan(&fingerprint, &labelString); err != nil {
return nil, nil, err
}
labels, metricName, err := unmarshalLabels(labelString)
if err != nil {
return nil, nil, err
}
fingerprints[fingerprint] = labels
if metricName != "" {
nameSet[metricName] = struct{}{}
}
}
if err := rows.Err(); err != nil {
return nil, nil, err
}
metricNames := make([]string, 0, len(nameSet))
for name := range nameSet {
metricNames = append(metricNames, name)
}
sort.Strings(metricNames)
return fingerprints, metricNames, nil
}
// buildSamplesQuery renders the samples SQL for the series selected by
// subQuery. The metric_name condition exists only for primary-key pruning;
// the fingerprint filter already selects the right rows.
//
// Time bounds are inclusive on both ends because that is Prometheus's
// storage contract: Select(mint, maxt) returns [start, end] and the engine
// itself trims each evaluation window to left-open (T-window, T], so the
// sample at exactly `end` belongs to the last point. This deliberately
// differs from the query builder's `unix_milli < end`, which is correct for
// its own model — toStartOfInterval buckets covering [t, t+step), where a
// sample at `end` falls in an unrendered bucket and end-exclusive ranges
// tile exactly across cached time slices.
func buildSamplesQuery(start int64, end int64, metricNames []string, sub *sqlbuilder.SelectBuilder) (string, []any) {
sb := sqlbuilder.NewSelectBuilder()
sb.Select("metric_name", "fingerprint", "unix_milli", "value", "flags")
sb.From(databaseName + "." + distributedSamplesV4)
if len(metricNames) > 0 {
names := make([]any, len(metricNames))
for i, name := range metricNames {
names[i] = name
}
sb.Where(sb.In("metric_name", names...))
}
sb.Where(fmt.Sprintf("fingerprint GLOBAL IN (%s)", sb.Var(sub)))
sb.Where(sb.GTE("unix_milli", start), sb.LTE("unix_milli", end))
sb.OrderBy("fingerprint", "unix_milli")
return sb.BuildWithFlavor(sqlbuilder.ClickHouse)
}
func (client *client) querySamples(ctx context.Context, query string, args []any, fingerprints map[uint64][]prompb.Label) ([]*prompb.TimeSeries, error) {
ctx = client.withClickhousePrometheusContext(ctx, "querySamples")
rows, err := client.telemetryStore.ClickhouseDB().Query(ctx, query, args...)
if err != nil {
return nil, err
}
defer rows.Close()
var res []*prompb.TimeSeries
var ts *prompb.TimeSeries
var metricName string
var fingerprint, prevFingerprint uint64
var timestampMs, prevTimestamp int64
var value float64
var flags uint32
prevTimestamp = math.MinInt64
for rows.Next() {
if err := rows.Scan(&metricName, &fingerprint, &timestampMs, &value, &flags); err != nil {
return nil, err
}
// collect samples in time series
if fingerprint != prevFingerprint {
// add collected time series to result
prevFingerprint = fingerprint
if ts != nil {
res = append(res, ts)
}
labels := fingerprints[fingerprint]
ts = &prompb.TimeSeries{
Labels: labels,
}
prevTimestamp = math.MinInt64
}
if flags&1 == 1 {
value = math.Float64frombits(promValue.StaleNaN)
}
if timestampMs == prevTimestamp {
continue
}
prevTimestamp = timestampMs
// add samples to current time series
ts.Samples = append(ts.Samples, prompb.Sample{
Timestamp: timestampMs,
Value: value,
})
}
// add last time series
if ts != nil {
res = append(res, ts)
}
if err := rows.Err(); err != nil {
return nil, err
}
return mergeSeriesWithIdenticalLabels(res), nil
}
// mergeSeriesWithIdenticalLabels collapses series sharing one labelset into
// one series each. Distinct fingerprints can map to one labelset: a label
// value goes empty over a series' lifetime (#8563), the fingerprint
// algorithm changes across exporter versions, or the env changes. The
// engine treats the labelset as series identity — duplicates raise
// "duplicate series", and #8563's workaround of injecting a synthetic
// fingerprint label silently broke without() and vector matching. Merging
// at the last point before hand-off keeps any future input-side label
// normalization collision-safe. Grouping is by an order-insensitive 64-bit
// hash so the common no-collision case costs one hash and one map insert
// per series; hash-equal groups are confirmed by exact labelset equality
// before any merge. Regression:
// TestClient_QuerySamplesMergesIdenticalLabelSets and
// tests/integration/tests/promqlconformance/02_fingerprint_probe.py.
func mergeSeriesWithIdenticalLabels(series []*prompb.TimeSeries) []*prompb.TimeSeries {
if len(series) < 2 {
return series
}
groups := make(map[uint64][]*prompb.TimeSeries, len(series))
order := make([]uint64, 0, len(series))
for _, ts := range series {
key := labelsHash(ts.Labels)
if _, ok := groups[key]; !ok {
order = append(order, key)
}
groups[key] = append(groups[key], ts)
}
if len(order) == len(series) {
return series
}
res := make([]*prompb.TimeSeries, 0, len(order))
for _, key := range order {
group := groups[key]
if len(group) == 1 {
res = append(res, group[0])
continue
}
for _, sub := range splitByLabelSet(group) {
if len(sub) == 1 {
res = append(res, sub[0])
continue
}
res = append(res, mergeSamples(sub))
}
}
return res
}
var labelHashSep = []byte{0xff}
// labelsHash combines per-label hashes commutatively, so the stored JSON's
// key order (not canonical across fingerprints) needs no sort.
func labelsHash(lbls []prompb.Label) uint64 {
var h uint64
var d xxhash.Digest
for _, l := range lbls {
d.Reset()
_, _ = d.WriteString(l.Name)
_, _ = d.Write(labelHashSep)
_, _ = d.WriteString(l.Value)
h += d.Sum64()
}
return h
}
// splitByLabelSet partitions a hash-equal group into sub-groups of exactly
// equal labelsets, preserving input order; series that merely collide on the
// 64-bit hash must not be merged.
func splitByLabelSet(group []*prompb.TimeSeries) [][]*prompb.TimeSeries {
var out [][]*prompb.TimeSeries
outer:
for _, ts := range group {
for i, sub := range out {
if labelSetsEqual(sub[0].Labels, ts.Labels) {
out[i] = append(out[i], ts)
continue outer
}
}
out = append(out, []*prompb.TimeSeries{ts})
}
return out
}
func labelSetsEqual(a, b []prompb.Label) bool {
if len(a) != len(b) {
return false
}
for _, la := range a {
found := false
for _, lb := range b {
if la.Name == lb.Name {
found = la.Value == lb.Value
break
}
}
if !found {
return false
}
}
return true
}
// mergeSamples k-way merges sample streams that share one labelset. On
// equal timestamps the highest fingerprint wins: the input is in ascending
// fingerprint order (samples SQL), keeping the choice deterministic.
func mergeSamples(group []*prompb.TimeSeries) *prompb.TimeSeries {
merged := &prompb.TimeSeries{Labels: group[0].Labels}
idx := make([]int, len(group))
for {
minTs := int64(math.MaxInt64)
for i, ts := range group {
if idx[i] < len(ts.Samples) && ts.Samples[idx[i]].Timestamp < minTs {
minTs = ts.Samples[idx[i]].Timestamp
}
}
if minTs == math.MaxInt64 {
return merged
}
var chosen prompb.Sample
for i, ts := range group {
if idx[i] < len(ts.Samples) && ts.Samples[idx[i]].Timestamp == minTs {
chosen = ts.Samples[idx[i]]
idx[i]++
}
}
merged.Samples = append(merged.Samples, chosen)
}
}
func (client *client) queryRaw(ctx context.Context, query string, ts int64) (*prompb.QueryResult, error) {
ctx = client.withClickhousePrometheusContext(ctx, "queryRaw")
rows, err := client.telemetryStore.ClickhouseDB().Query(ctx, query)
if err != nil {
return nil, err
}
defer rows.Close()
columns := rows.Columns()
var res prompb.QueryResult
targets := make([]any, len(columns))
for i := range targets {
targets[i] = new(scanner)
}
for rows.Next() {
if err = rows.Scan(targets...); err != nil {
return nil, err
}
labels := make([]prompb.Label, 0, len(columns))
var value float64
for i, c := range columns {
v := targets[i].(*scanner)
switch c {
case "value":
value = v.f
default:
labels = append(labels, prompb.Label{
Name: c,
Value: v.s,
})
}
}
res.Timeseries = append(res.Timeseries, &prompb.TimeSeries{
Labels: labels,
Samples: []prompb.Sample{{
Value: value,
Timestamp: ts,
}},
})
}
if err = rows.Err(); err != nil {
return nil, err
}
return &res, nil
}
func (client *client) withClickhousePrometheusContext(ctx context.Context, functionName string) context.Context {
comments := map[string]string{
instrumentationtypes.TelemetrySignal: telemetrytypes.SignalMetrics.StringValue(),
instrumentationtypes.CodeNamespace: "clickhouse-prometheus",
instrumentationtypes.CodeFunctionName: functionName,
}
return ctxtypes.NewContextWithCommentVals(ctx, comments)
}

View File

@@ -1,382 +0,0 @@
package clickhouseprometheus
import (
"context"
"sort"
"testing"
cmock "github.com/SigNoz/clickhouse-go-mock"
"github.com/SigNoz/signoz/pkg/telemetrystore/telemetrystoretest"
"github.com/stretchr/testify/require"
"github.com/DATA-DOG/go-sqlmock"
"github.com/SigNoz/signoz/pkg/telemetrystore"
"github.com/huandu/go-sqlbuilder"
"github.com/prometheus/prometheus/prompb"
"github.com/stretchr/testify/assert"
)
// Test for querySamples method.
func TestClient_QuerySamples(t *testing.T) {
ctx := context.Background()
cols := make([]cmock.ColumnType, 0)
cols = append(cols, cmock.ColumnType{Name: "metric_name", Type: "String"})
cols = append(cols, cmock.ColumnType{Name: "fingerprint", Type: "UInt64"})
cols = append(cols, cmock.ColumnType{Name: "unix_milli", Type: "Int64"})
cols = append(cols, cmock.ColumnType{Name: "value", Type: "Float64"})
cols = append(cols, cmock.ColumnType{Name: "flags", Type: "UInt32"})
tests := []struct {
name string
start int64
end int64
fingerprints map[uint64][]prompb.Label
metricNames []string
subQuery string
args []any
setupMock func(mock cmock.ClickConnMockCommon, args ...any)
expectedTimeSeries int
expectError bool
description string
result []*prompb.TimeSeries
}{
{
name: "successful samples retrieval",
start: int64(1000),
end: int64(2000),
fingerprints: map[uint64][]prompb.Label{
123: {
{Name: "__name__", Value: "cpu_usage"},
{Name: "instance", Value: "localhost:9090"},
},
456: {
{Name: "__name__", Value: "cpu_usage"},
{Name: "instance", Value: "localhost:9091"},
},
},
metricNames: []string{"cpu_usage"},
subQuery: "SELECT metric_name, fingerprint, unix_milli, value, flags",
expectedTimeSeries: 2,
expectError: false,
description: "Should successfully retrieve samples for multiple time series",
setupMock: func(mock cmock.ClickConnMockCommon, args ...any) {
values := [][]interface{}{
{"cpu_usage", uint64(123), int64(1001), float64(1.1), uint32(0)},
{"cpu_usage", uint64(123), int64(1001), float64(1.1), uint32(0)},
{"cpu_usage", uint64(456), int64(1001), float64(1.2), uint32(0)},
{"cpu_usage", uint64(456), int64(1001), float64(1.2), uint32(0)},
{"cpu_usage", uint64(456), int64(1001), float64(1.2), uint32(0)},
}
mock.ExpectQuery("SELECT metric_name, fingerprint, unix_milli, value, flags").WithArgs(args...).WillReturnRows(
cmock.NewRows(cols, values),
)
},
result: []*prompb.TimeSeries{
{
Labels: []prompb.Label{
{Name: "__name__", Value: "cpu_usage"},
{Name: "instance", Value: "localhost:9090"},
},
Samples: []prompb.Sample{
{Timestamp: 1001, Value: 1.1},
},
},
{
Labels: []prompb.Label{
{Name: "__name__", Value: "cpu_usage"},
{Name: "instance", Value: "localhost:9091"},
},
Samples: []prompb.Sample{
{Timestamp: 1001, Value: 1.2},
},
},
},
},
}
for _, tt := range tests {
t.Run(tt.name, func(t *testing.T) {
telemetryStore := telemetrystoretest.New(telemetrystore.Config{Provider: "clickhouse"}, sqlmock.QueryMatcherRegexp)
readClient := client{telemetryStore: telemetryStore}
if tt.setupMock != nil {
tt.setupMock(telemetryStore.Mock(), "cpu_usage", tt.start, tt.end)
}
result, err := readClient.querySamples(ctx, tt.subQuery, []any{"cpu_usage", tt.start, tt.end}, tt.fingerprints)
if tt.expectError {
assert.Error(t, err)
assert.Nil(t, result)
} else {
assert.NoError(t, err)
assert.Equal(t, tt.expectedTimeSeries, len(result))
assert.Equal(t, result, tt.result)
}
})
}
}
// Regression for the duplicate-series class behind #8563: fingerprints
// sharing one labelset must come back as one merged series, the higher
// fingerprint winning equal timestamps.
func TestClient_QuerySamplesMergesIdenticalLabelSets(t *testing.T) {
ctx := context.Background()
cols := []cmock.ColumnType{
{Name: "metric_name", Type: "String"},
{Name: "fingerprint", Type: "UInt64"},
{Name: "unix_milli", Type: "Int64"},
{Name: "value", Type: "Float64"},
{Name: "flags", Type: "UInt32"},
}
canary := []prompb.Label{
{Name: "__name__", Value: "requests"},
{Name: "group", Value: "canary"},
}
production := []prompb.Label{
{Name: "__name__", Value: "requests"},
{Name: "group", Value: "production"},
}
fingerprints := map[uint64][]prompb.Label{
100: canary,
200: canary,
300: production,
}
telemetryStore := telemetrystoretest.New(telemetrystore.Config{Provider: "clickhouse"}, sqlmock.QueryMatcherRegexp)
// Rows arrive ordered by (fingerprint, unix_milli), matching the SQL.
values := [][]any{
{"requests", uint64(100), int64(1000), float64(1.0), uint32(0)},
{"requests", uint64(100), int64(2000), float64(2.0), uint32(0)},
{"requests", uint64(200), int64(2000), float64(20.0), uint32(0)},
{"requests", uint64(200), int64(3000), float64(30.0), uint32(0)},
{"requests", uint64(300), int64(1500), float64(5.0), uint32(0)},
}
telemetryStore.Mock().ExpectQuery("SELECT metric_name, fingerprint, unix_milli, value, flags").
WithArgs("requests", int64(1000), int64(3000)).
WillReturnRows(cmock.NewRows(cols, values))
readClient := client{telemetryStore: telemetryStore}
result, err := readClient.querySamples(ctx, "SELECT metric_name, fingerprint, unix_milli, value, flags", []any{"requests", int64(1000), int64(3000)}, fingerprints)
require.NoError(t, err)
assert.Equal(t, []*prompb.TimeSeries{
{
Labels: canary,
Samples: []prompb.Sample{
{Timestamp: 1000, Value: 1.0},
{Timestamp: 2000, Value: 20.0},
{Timestamp: 3000, Value: 30.0},
},
},
{
Labels: production,
Samples: []prompb.Sample{
{Timestamp: 1500, Value: 5.0},
},
},
}, result)
}
func TestClient_getFingerprintsFromClickhouseQuery(t *testing.T) {
cols := []cmock.ColumnType{
{Name: "fingerprint", Type: "UInt64"},
{Name: "labels", Type: "String"},
}
sortLabels := func(ls []prompb.Label) {
sort.Slice(ls, func(i, j int) bool {
if ls[i].Name == ls[j].Name {
return ls[i].Value < ls[j].Value
}
return ls[i].Name < ls[j].Name
})
}
tests := []struct {
name string
start, end int64
metricName string
subQuery string
args []any
setupMock func(m cmock.ClickConnMockCommon, args ...any)
want map[uint64][]prompb.Label
wantNames []string
wantErr bool
}{
{
name: "happy-path - two fingerprints",
start: 1000,
end: 2000,
metricName: "cpu_usage",
subQuery: `SELECT fingerprint,labels`,
// args slice is empty here, but testcase still owns it
args: []any{},
setupMock: func(m cmock.ClickConnMockCommon, args ...any) {
rows := [][]any{
{uint64(123), `{"__name__":"cpu_usage","t1":"s1","t2":"s2"}`},
{uint64(234), `{"__name__":"cpu_usage","t1":"s1","t2":"s2","empty":""}`},
}
m.ExpectQuery(`SELECT fingerprint,labels`).WithArgs(args...).WillReturnRows(
cmock.NewRows(cols, rows),
)
},
// No synthetic fingerprint label (#8563), empty-valued labels
// dropped: both fingerprints present one labelset for
// querySamples to merge.
want: map[uint64][]prompb.Label{
123: {
{Name: "__name__", Value: "cpu_usage"},
{Name: "t1", Value: "s1"},
{Name: "t2", Value: "s2"},
},
234: {
{Name: "__name__", Value: "cpu_usage"},
{Name: "t1", Value: "s1"},
{Name: "t2", Value: "s2"},
},
},
wantNames: []string{"cpu_usage"},
},
}
for _, tc := range tests {
t.Run(tc.name, func(t *testing.T) {
ctx := context.Background()
store := telemetrystoretest.New(
telemetrystore.Config{Provider: "clickhouse"},
sqlmock.QueryMatcherRegexp,
)
if tc.setupMock != nil {
tc.setupMock(store.Mock(), tc.args...)
}
c := client{telemetryStore: store}
got, gotNames, err := c.getFingerprintsFromClickhouseQuery(ctx, tc.subQuery, tc.args)
if tc.wantErr {
require.Error(t, err)
require.Nil(t, got)
return
}
require.NoError(t, err)
assert.Equal(t, tc.wantNames, gotNames, "discovered metric names mismatch")
require.Equal(t, len(tc.want), len(got), "fingerprint map length mismatch")
for fp, expLabels := range tc.want {
gotLabels, ok := got[fp]
require.Truef(t, ok, "missing fingerprint %d", fp)
sortLabels(expLabels)
sortLabels(gotLabels)
assert.Equalf(t, expLabels, gotLabels, "labels mismatch for fingerprint %d", fp)
}
})
}
}
// Regression for nameless/regex-name selectors silently returning empty:
// the old code reduced every __name__ matcher to `metric_name = <value>`
// (empty string when absent). Regexes must come out anchored — Prometheus
// matcher semantics, while ClickHouse match() substring-matches.
func TestQueryToClickhouseQueryNameMatchers(t *testing.T) {
query := func(matchers ...*prompb.LabelMatcher) *prompb.Query {
return &prompb.Query{StartTimestampMs: 0, EndTimestampMs: 1000, Matchers: matchers}
}
tests := []struct {
name string
query *prompb.Query
contains []string
absent []string
args []any
}{
{
name: "exact name",
query: query(&prompb.LabelMatcher{Type: prompb.LabelMatcher_EQ, Name: "__name__", Value: "cpu_usage"}),
contains: []string{"metric_name = ?"},
args: []any{"cpu_usage"},
},
{
name: "regex name is anchored",
query: query(&prompb.LabelMatcher{Type: prompb.LabelMatcher_RE, Name: "__name__", Value: ".+"}),
contains: []string{"match(metric_name, ?)"},
args: []any{"^(?:.+)$"},
},
{
name: "nameless selector has no metric_name condition",
query: query(
&prompb.LabelMatcher{Type: prompb.LabelMatcher_EQ, Name: "job", Value: "api"},
&prompb.LabelMatcher{Type: prompb.LabelMatcher_NRE, Name: "group", Value: "can.*"},
),
contains: []string{
"JSONExtractString(labels, ?) = ?",
"not match(JSONExtractString(labels, ?), ?)",
},
absent: []string{"metric_name"},
args: []any{"job", "api", "group", "^(?:can.*)$"},
},
}
for _, tt := range tests {
t.Run(tt.name, func(t *testing.T) {
lookup, err := seriesLookupQuery(tt.query, false)
require.NoError(t, err)
sql, args := lookup.BuildWithFlavor(sqlbuilder.ClickHouse)
for _, want := range tt.contains {
assert.Contains(t, sql, want)
}
for _, notWant := range tt.absent {
assert.NotContains(t, sql, notWant)
}
assert.Equal(t, tt.args, args)
})
}
}
// The samples query narrows by the metric names the lookup discovered and
// embeds the series lookup as a subquery, the builder merging its args in
// render order.
func TestBuildSamplesQueryMetricNames(t *testing.T) {
sub := sqlbuilder.NewSelectBuilder()
sub.Select("fingerprint")
sub.From("t")
sub.Where(sub.E("k", "v"))
sql, args := buildSamplesQuery(5, 9, []string{"a_total", "b_total"}, sub)
assert.Contains(t, sql, "metric_name IN (?, ?)")
assert.Contains(t, sql, "fingerprint GLOBAL IN (SELECT fingerprint FROM t WHERE k = ?)")
assert.Contains(t, sql, "unix_milli >= ? AND unix_milli <= ?")
assert.Equal(t, []any{"a_total", "b_total", "v", int64(5), int64(9)}, args)
sub2 := sqlbuilder.NewSelectBuilder()
sub2.Select("fingerprint")
sub2.From("t")
sql, args = buildSamplesQuery(5, 9, nil, sub2)
assert.NotContains(t, sql, "metric_name IN")
assert.Equal(t, []any{int64(5), int64(9)}, args)
}
// Hash grouping must stay order-insensitive (stored JSON key order is not
// canonical across fingerprints), and a 64-bit hash collision between
// distinct labelsets must not merge them — splitByLabelSet is that guard.
func TestLabelsHashAndCollisionSplit(t *testing.T) {
lbls := []prompb.Label{
{Name: "__name__", Value: "requests"},
{Name: "job", Value: "api"},
{Name: "instance", Value: "0"},
}
reversed := []prompb.Label{lbls[2], lbls[1], lbls[0]}
assert.Equal(t, labelsHash(lbls), labelsHash(reversed))
a := &prompb.TimeSeries{Labels: []prompb.Label{{Name: "job", Value: "x"}}}
b := &prompb.TimeSeries{Labels: []prompb.Label{{Name: "job", Value: "y"}}}
c := &prompb.TimeSeries{Labels: []prompb.Label{{Name: "job", Value: "x"}}}
got := splitByLabelSet([]*prompb.TimeSeries{a, b, c})
require.Len(t, got, 2)
assert.Equal(t, []*prompb.TimeSeries{a, c}, got[0])
assert.Equal(t, []*prompb.TimeSeries{b}, got[1])
}

View File

@@ -1,34 +0,0 @@
package clickhouseprometheus
import (
"encoding/json"
"github.com/prometheus/prometheus/prompb"
)
// Unmarshals JSON into Prometheus labels. It does not preserve order.
// Empty-valued labels are dropped: Prometheus treats them as absent, and
// keeping them lets two fingerprints present duplicate labelsets to the
// engine (the incident behind #8563).
func unmarshalLabels(s string) ([]prompb.Label, string, error) {
var metricName string
m := make(map[string]string)
if err := json.Unmarshal([]byte(s), &m); err != nil {
return nil, metricName, err
}
res := make([]prompb.Label, 0, len(m))
for n, v := range m {
if v == "" {
continue
}
if n == "__name__" {
metricName = v
}
res = append(res, prompb.Label{
Name: n,
Value: v,
})
}
return res, metricName, nil
}

View File

@@ -1,82 +0,0 @@
package clickhouseprometheus
import (
"testing"
"github.com/prometheus/prometheus/prompb"
"github.com/stretchr/testify/assert"
)
func mkSeries(value string, samples ...prompb.Sample) *prompb.TimeSeries {
return &prompb.TimeSeries{
Labels: []prompb.Label{{Name: "job", Value: value}},
Samples: samples,
}
}
func TestMergeSeriesWithIdenticalLabels(t *testing.T) {
s := func(ts int64, v float64) prompb.Sample { return prompb.Sample{Timestamp: ts, Value: v} }
t.Run("empty and single series pass through untouched", func(t *testing.T) {
assert.Nil(t, mergeSeriesWithIdenticalLabels(nil))
one := []*prompb.TimeSeries{mkSeries("a", s(1, 1))}
got := mergeSeriesWithIdenticalLabels(one)
assert.Equal(t, one, got)
})
t.Run("no collisions returns the input slice as is", func(t *testing.T) {
in := []*prompb.TimeSeries{mkSeries("a", s(1, 1)), mkSeries("b", s(1, 2))}
got := mergeSeriesWithIdenticalLabels(in)
// same backing slice: the fast path must not rebuild anything
assert.Equal(t, &in[0], &got[0])
})
t.Run("disjoint streams concatenate in timestamp order", func(t *testing.T) {
// the #8563 shape: the series transitioned fingerprints at a point
// in time, so the streams do not overlap at all
got := mergeSeriesWithIdenticalLabels([]*prompb.TimeSeries{
mkSeries("a", s(1, 1), s(2, 2)),
mkSeries("a", s(3, 3), s(4, 4)),
})
assert.Equal(t, []prompb.Sample{s(1, 1), s(2, 2), s(3, 3), s(4, 4)}, got[0].Samples)
})
t.Run("three fingerprints one labelset", func(t *testing.T) {
got := mergeSeriesWithIdenticalLabels([]*prompb.TimeSeries{
mkSeries("a", s(1, 1), s(4, 4)),
mkSeries("a", s(2, 2)),
mkSeries("a", s(3, 3)),
})
assert.Len(t, got, 1)
assert.Equal(t, []prompb.Sample{s(1, 1), s(2, 2), s(3, 3), s(4, 4)}, got[0].Samples)
})
t.Run("equal timestamps everywhere keep the last stream's value", func(t *testing.T) {
// input is in ascending fingerprint order; the highest wins each tie
got := mergeSeriesWithIdenticalLabels([]*prompb.TimeSeries{
mkSeries("a", s(1, 1), s(2, 1)),
mkSeries("a", s(1, 9), s(2, 9)),
})
assert.Equal(t, []prompb.Sample{s(1, 9), s(2, 9)}, got[0].Samples)
})
t.Run("zero-sample series in a group is harmless", func(t *testing.T) {
got := mergeSeriesWithIdenticalLabels([]*prompb.TimeSeries{
mkSeries("a"),
mkSeries("a", s(1, 1)),
})
assert.Len(t, got, 1)
assert.Equal(t, []prompb.Sample{s(1, 1)}, got[0].Samples)
})
t.Run("colliding and distinct series interleave without cross-talk", func(t *testing.T) {
got := mergeSeriesWithIdenticalLabels([]*prompb.TimeSeries{
mkSeries("a", s(1, 1)),
mkSeries("b", s(1, 2)),
mkSeries("a", s(2, 3)),
})
assert.Len(t, got, 2)
assert.Equal(t, []prompb.Sample{s(1, 1), s(2, 3)}, got[0].Samples)
assert.Equal(t, []prompb.Sample{s(1, 2)}, got[1].Samples)
})
}

View File

@@ -1,78 +0,0 @@
package clickhouseprometheus
import (
"context"
"github.com/SigNoz/signoz/pkg/factory"
"github.com/SigNoz/signoz/pkg/prometheus"
"github.com/SigNoz/signoz/pkg/telemetrystore"
"github.com/prometheus/common/model"
"github.com/prometheus/prometheus/model/labels"
"github.com/prometheus/prometheus/storage"
"github.com/prometheus/prometheus/storage/remote"
)
var stCallback = func() (int64, error) {
return int64(model.Latest), nil
}
type provider struct {
settings factory.ScopedProviderSettings
telemetryStore telemetrystore.TelemetryStore
engine *prometheus.Engine
parser prometheus.Parser
queryable storage.SampleAndChunkQueryable
}
func NewFactory(telemetryStore telemetrystore.TelemetryStore) factory.ProviderFactory[prometheus.Prometheus, prometheus.Config] {
return factory.NewProviderFactory(factory.MustNewName("clickhouse"), func(ctx context.Context, providerSettings factory.ProviderSettings, config prometheus.Config) (prometheus.Prometheus, error) {
return New(ctx, providerSettings, config, telemetryStore)
})
}
func New(ctx context.Context, providerSettings factory.ProviderSettings, config prometheus.Config, telemetryStore telemetrystore.TelemetryStore) (prometheus.Prometheus, error) {
settings := factory.NewScopedProviderSettings(providerSettings, "github.com/SigNoz/signoz/pkg/prometheus/clickhouseprometheus")
readClient := NewReadClient(settings, telemetryStore)
return &provider{
settings: settings,
telemetryStore: telemetryStore,
engine: prometheus.NewEngine(settings.Logger(), config),
parser: prometheus.NewParser(),
queryable: remote.NewSampleAndChunkQueryableClient(readClient, labels.EmptyLabels(), []*labels.Matcher{}, false, stCallback),
}, nil
}
func (provider *provider) Engine() *prometheus.Engine {
return provider.engine
}
func (provider *provider) Parser() prometheus.Parser {
return provider.parser
}
func (provider *provider) Storage() storage.Queryable {
return provider
}
func (provider *provider) Querier(mint, maxt int64) (storage.Querier, error) {
querier, err := provider.queryable.Querier(mint, maxt)
if err != nil {
return nil, err
}
return storage.NewMergeQuerier(nil, []storage.Querier{querier}, storage.ChainedSeriesMerge), nil
}
// CapturingStorage implements prometheus.StatementCapturer. Uses a fresh
// recorder per call so concurrent dry-runs don't share state.
func (provider *provider) CapturingStorage() (storage.Queryable, prometheus.StatementRecorder) {
recorder := &statementRecorder{}
capture := &captureClient{
client: &client{settings: provider.settings, telemetryStore: provider.telemetryStore},
recorder: recorder,
}
queryable := remote.NewSampleAndChunkQueryableClient(capture, labels.EmptyLabels(), []*labels.Matcher{}, false, stCallback)
return captureQueryable{inner: queryable}, recorder
}

View File

@@ -1,31 +0,0 @@
package clickhouseprometheus
import (
"database/sql"
"fmt"
)
var _ sql.Scanner = (*scanner)(nil)
type scanner struct {
f float64
s string
}
func (s *scanner) Scan(val any) error {
s.f = 0
s.s = ""
s.s = fmt.Sprintf("%v", val)
switch val := val.(type) {
case int64:
s.f = float64(val)
case uint64:
s.f = float64(val)
case float64:
s.f = val
case []byte:
s.s = string(val)
}
return nil
}

View File

@@ -1,41 +0,0 @@
package clickhouseprometheus
import "time"
const (
databaseName string = "signoz_metrics"
distributedTimeSeriesV4 string = "distributed_time_series_v4"
distributedTimeSeriesV46hrs string = "distributed_time_series_v4_6hrs"
distributedTimeSeriesV41day string = "distributed_time_series_v4_1day"
distributedSamplesV4 string = "distributed_samples_v4"
)
var (
sixHoursInMilliseconds = time.Hour.Milliseconds() * 6
oneDayInMilliseconds = time.Hour.Milliseconds() * 24
)
// Returns the start time, end time and the table name to use for the query.
//
// If time range is less than 6 hours, we need to use the `time_series_v4` table
// else if time range is less than 1 day and greater than 6 hours, we need to use the `time_series_v4_6hrs` table
// else we need to use the `time_series_v4_1day` table
func getStartAndEndAndTableName(start, end int64) (int64, int64, string) {
var tableName string
if end-start <= sixHoursInMilliseconds {
// adjust the start time to nearest 1 hour
start = start - (start % (time.Hour.Milliseconds() * 1))
tableName = distributedTimeSeriesV4
} else if end-start <= oneDayInMilliseconds {
// adjust the start time to nearest 6 hours
start = start - (start % (time.Hour.Milliseconds() * 6))
tableName = distributedTimeSeriesV46hrs
} else {
// adjust the start time to nearest 1 day
start = start - (start % (time.Hour.Milliseconds() * 24))
tableName = distributedTimeSeriesV41day
}
return start, end, tableName
}

View File

@@ -19,11 +19,7 @@ type provider struct {
executor *executor
}
var (
_ prometheus.Prometheus = (*provider)(nil)
_ prometheus.StatementCapturer = (*provider)(nil)
_ prometheus.RangeExecutor = (*provider)(nil)
)
var _ prometheus.Prometheus = (*provider)(nil)
func NewFactory(telemetryStore telemetrystore.TelemetryStore) factory.ProviderFactory[prometheus.Prometheus, prometheus.Config] {
return factory.NewProviderFactory(factory.MustNewName("clickhousev2"), func(ctx context.Context, providerSettings factory.ProviderSettings, config prometheus.Config) (prometheus.Prometheus, error) {
@@ -47,30 +43,69 @@ func New(_ context.Context, providerSettings factory.ProviderSettings, config pr
}, nil
}
func (p *provider) TryExecuteRange(ctx context.Context, query string, start, end time.Time, step time.Duration) (promql.Matrix, bool, error) {
return p.executor.TryExecuteRange(ctx, query, start, end, step)
func (p *provider) QueryRange(ctx context.Context, query string, start, end time.Time, step time.Duration) (*prometheus.Result, error) {
matrix, served, err := p.executor.TryExecuteRange(ctx, query, start, end, step)
if err != nil {
return nil, err
}
if served {
return &prometheus.Result{Value: matrix}, nil
}
qry, err := p.engine.NewRangeQuery(p.traitsContext(ctx, query), p, nil, query, start, end, step)
if err != nil {
return nil, err
}
return finishQuery(ctx, qry)
}
func (p *provider) Engine() *prometheus.Engine {
return p.engine
func (p *provider) Query(ctx context.Context, query string, ts time.Time) (*prometheus.Result, error) {
qry, err := p.engine.NewInstantQuery(p.traitsContext(ctx, query), p, nil, query, ts)
if err != nil {
return nil, err
}
return finishQuery(ctx, qry)
}
func (p *provider) Parser() prometheus.Parser {
return p.parser
// A fresh recorder per call keeps concurrent dry-runs isolated. Exec drives
// a Select per selector (recording SQL) but reads no data.
func (p *provider) Statements(ctx context.Context, query string, start, end time.Time, step time.Duration) ([]prometheus.CapturedStatement, error) {
recorder := &statementRecorder{}
capture := &captureQueryable{client: p.client, recorder: recorder}
qry, err := p.engine.NewRangeQuery(p.traitsContext(ctx, query), capture, nil, query, start, end, step)
if err != nil {
return nil, err
}
defer qry.Close()
if res := qry.Exec(ctx); res.Err != nil {
return nil, res.Err
}
return recorder.Statements(), nil
}
func (p *provider) Storage() storage.Queryable {
return p
// traitsContext attaches the query's traits so the storage can prove
// step-aligned optimizations safe (see prometheus.QueryTraits). A parse
// failure surfaces from the engine with its own error.
func (p *provider) traitsContext(ctx context.Context, query string) context.Context {
expr, err := p.parser.ParseExpr(query)
if err != nil {
return ctx
}
return prometheus.NewContextWithQueryTraits(ctx, prometheus.DetectQueryTraits(expr))
}
// finishQuery packages an engine evaluation. The query is closed only on
// error: Close returns the result's sample slices to the engine's pool, and
// the returned Value must stay valid for the caller.
func finishQuery(ctx context.Context, qry promql.Query) (*prometheus.Result, error) {
res := qry.Exec(ctx)
if res.Err != nil {
qry.Close()
return nil, res.Err
}
return &prometheus.Result{Value: res.Value, Warnings: res.Warnings, Stats: qry.Stats()}, nil
}
func (p *provider) Querier(mint, maxt int64) (storage.Querier, error) {
return &querier{mint: mint, maxt: maxt, client: p.client}, nil
}
// CapturingStorage implements prometheus.StatementCapturer: a storage that
// records each selector's SQL without executing it, for the preview path.
// A fresh recorder per call keeps concurrent dry-runs isolated.
func (p *provider) CapturingStorage() (storage.Queryable, prometheus.StatementRecorder) {
recorder := &statementRecorder{}
return &captureQueryable{client: p.client, recorder: recorder}, recorder
}

View File

@@ -24,10 +24,6 @@ type Config struct {
// Timeout is the maximum time a query is allowed to run before being aborted.
Timeout time.Duration `mapstructure:"timeout"`
// ProviderName selects the storage provider: "clickhouse" (default) or
// "clickhousev2".
ProviderName string `mapstructure:"provider"`
}
func NewConfigFactory() factory.ConfigFactory {
@@ -41,8 +37,7 @@ func newConfig() factory.Config {
Path: "",
MaxConcurrent: 20,
},
Timeout: 2 * time.Minute,
ProviderName: "clickhouse",
Timeout: 2 * time.Minute,
}
}
@@ -50,15 +45,9 @@ func (c Config) Validate() error {
if c.Timeout <= 0 {
return errors.Newf(errors.TypeInvalidInput, errors.CodeInvalidInput, "prometheus::timeout must be greater than 0")
}
if c.ProviderName != "" && c.ProviderName != "clickhouse" && c.ProviderName != "clickhousev2" {
return errors.Newf(errors.TypeInvalidInput, errors.CodeInvalidInput, "prometheus::provider must be one of [clickhouse, clickhousev2], got %q", c.ProviderName)
}
return nil
}
func (c Config) Provider() string {
if c.ProviderName == "" {
return "clickhouse"
}
return c.ProviderName
return "clickhousev2"
}

View File

@@ -10,6 +10,7 @@ import (
promModel "github.com/prometheus/common/model"
"github.com/prometheus/prometheus/promql"
"github.com/prometheus/prometheus/promql/parser"
"github.com/prometheus/prometheus/util/stats"
"github.com/SigNoz/signoz/pkg/errors"
@@ -81,36 +82,8 @@ func (h *handler) QueryRange(w http.ResponseWriter, r *http.Request) {
}
defer cancel()
if h.tryRangeExecutor(ctx, w, r, start, end, step) {
return
}
qry, err := h.prom.Engine().NewRangeQuery(ctx, h.prom.Storage(), nil, r.FormValue("query"), start, end, step)
if err != nil {
h.respondError(r.Context(), w, errBadData, err)
return
}
h.exec(ctx, w, r, qry)
}
// tryRangeExecutor serves the query the way a RangeExecutor provider is
// designed to serve: evaluated inside the datastore when the shape allows.
// It reports whether the response was written.
func (h *handler) tryRangeExecutor(ctx context.Context, w http.ResponseWriter, r *http.Request, start, end time.Time, step time.Duration) bool {
re, ok := h.prom.(RangeExecutor)
if !ok {
return false
}
matrix, served, err := re.TryExecuteRange(ctx, r.FormValue("query"), start, end, step)
if err != nil {
h.respondError(ctx, w, errExec, err)
return true
}
if !served {
return false
}
h.respond(ctx, w, &queryData{ResultType: matrix.Type(), Result: matrix}, nil, nil)
return true
res, err := h.prom.QueryRange(ctx, r.FormValue("query"), start, end, step)
h.respondResult(ctx, w, r, res, err)
}
// Query evaluates an expression at a single instant: query and optional
@@ -134,35 +107,34 @@ func (h *handler) Query(w http.ResponseWriter, r *http.Request) {
}
defer cancel()
qry, err := h.prom.Engine().NewInstantQuery(ctx, h.prom.Storage(), nil, r.FormValue("query"), ts)
if err != nil {
h.respondError(r.Context(), w, errBadData, err)
return
}
h.exec(ctx, w, r, qry)
res, err := h.prom.Query(ctx, r.FormValue("query"), ts)
h.respondResult(ctx, w, r, res, err)
}
func (h *handler) exec(ctx context.Context, w http.ResponseWriter, r *http.Request, qry promql.Query) {
defer qry.Close()
res := qry.Exec(ctx)
if res.Err != nil {
h.logger.ErrorContext(ctx, "error evaluating promql query", errors.Attr(res.Err))
switch res.Err.(type) {
func (h *handler) respondResult(ctx context.Context, w http.ResponseWriter, r *http.Request, res *Result, err error) {
if err != nil {
h.logger.ErrorContext(ctx, "error evaluating promql query", errors.Attr(err))
var parseErrs parser.ParseErrors
if errors.As(err, &parseErrs) {
h.respondError(ctx, w, errBadData, err)
return
}
switch err.(type) {
case promql.ErrQueryCanceled:
h.respondError(ctx, w, errCanceled, res.Err)
h.respondError(ctx, w, errCanceled, err)
case promql.ErrQueryTimeout:
h.respondError(ctx, w, errTimeout, res.Err)
h.respondError(ctx, w, errTimeout, err)
case promql.ErrStorage:
h.respondError(ctx, w, errInternal, res.Err)
h.respondError(ctx, w, errInternal, err)
default:
h.respondError(ctx, w, errExec, res.Err)
h.respondError(ctx, w, errExec, err)
}
return
}
data := &queryData{ResultType: res.Value.Type(), Result: res.Value}
if r.FormValue("stats") != "" {
data.Stats = stats.NewQueryStats(qry.Stats())
if r.FormValue("stats") != "" && res.Stats != nil {
data.Stats = stats.NewQueryStats(res.Stats)
}
warnings, infos := res.Warnings.AsStrings(r.FormValue("query"), 10, 10)
h.respond(ctx, w, data, warnings, infos)

View File

@@ -6,7 +6,8 @@ import (
"github.com/prometheus/prometheus/promql"
"github.com/prometheus/prometheus/promql/parser"
"github.com/prometheus/prometheus/storage"
"github.com/prometheus/prometheus/util/annotations"
"github.com/prometheus/prometheus/util/stats"
)
type Engine = promql.Engine
@@ -14,9 +15,25 @@ type Engine = promql.Engine
type Parser = parser.Parser
type Prometheus interface {
Engine() *Engine
Storage() storage.Queryable
Parser() Parser
// QueryRange evaluates a range query: inside the datastore when the
// query's shape allows it, else in the engine over the provider's
// storage, which is always exact.
QueryRange(ctx context.Context, query string, start, end time.Time, step time.Duration) (*Result, error)
// Query evaluates an instant query in the engine.
Query(ctx context.Context, query string, ts time.Time) (*Result, error)
// Statements returns the datastore statements the engine path of a
// range query would run, captured without executing them.
Statements(ctx context.Context, query string, start, end time.Time, step time.Duration) ([]CapturedStatement, error)
}
// Result is one evaluation's outcome. The caller owns Value: the provider
// never returns its sample slices to the engine's pools.
type Result struct {
Value parser.Value
Warnings annotations.Annotations
Stats *stats.Statistics
}
// CapturedStatement is one datastore statement a PromQL query would run,
@@ -25,33 +42,3 @@ type CapturedStatement struct {
Query string
Args []any
}
// StatementRecorder reads back the statements captured against a capturing
// Storage (see StatementCapturer).
type StatementRecorder interface {
Statements() []CapturedStatement
}
// StatementCapturer is an optional Prometheus-provider capability, discovered
// via type assertion: it returns a Storage that records each Select's statement
// without executing it, plus a recorder to read them back.
type StatementCapturer interface {
CapturingStorage() (storage.Queryable, StatementRecorder)
}
// ProviderClickhouseV2 is the clickhousev2 provider name: the factory
// registration, the prometheus::provider config value and the
// X-SigNoz-PromQL-Provider request header all use it, so they cannot drift
// apart.
const ProviderClickhouseV2 = "clickhousev2"
// RangeExecutor is the optional capability of a provider that can evaluate
// some range queries entirely inside the datastore. ok=false means the
// query is not evaluable that way. The caller then runs the engine over the
// provider's Storage, which is always exact. Only the clickhousev2 provider
// implements this capability. When that provider is the only one, the
// capability folds into Prometheus itself, and the engine-vs-datastore
// decision becomes internal.
type RangeExecutor interface {
TryExecuteRange(ctx context.Context, query string, start, end time.Time, step time.Duration) (promql.Matrix, bool, error)
}

View File

@@ -0,0 +1,31 @@
package prometheustest
import (
cmock "github.com/SigNoz/clickhouse-go-mock"
)
// GridCols is the result shape of a transpiled unit statement.
var GridCols = []cmock.ColumnType{
{Name: "gkey", Type: "String"},
{Name: "grid", Type: "Array(Nullable(Float64))"},
}
// LastSampleGrid builds the grid a transpiled instant selector returns: per
// slot t, the latest sample in the left-open lookback window (t-lookback, t].
func LastSampleGrid(tsMs []int64, values []float64, startMs, endMs, stepMs, lookbackMs int64) []*float64 {
grid := make([]*float64, (endMs-startMs)/stepMs+1)
for i := range grid {
slot := startMs + int64(i)*stepMs
best := -1
for j, ts := range tsMs {
if ts > slot-lookbackMs && ts <= slot && (best == -1 || ts >= tsMs[best]) {
best = j
}
}
if best >= 0 {
v := values[best]
grid[i] = &v
}
}
return grid
}

View File

@@ -5,58 +5,16 @@ import (
"github.com/SigNoz/signoz/pkg/factory"
"github.com/SigNoz/signoz/pkg/prometheus"
"github.com/SigNoz/signoz/pkg/prometheus/clickhouseprometheus"
"github.com/SigNoz/signoz/pkg/prometheus/clickhouseprometheusv2"
"github.com/SigNoz/signoz/pkg/telemetrystore"
"github.com/prometheus/common/model"
"github.com/prometheus/prometheus/model/labels"
"github.com/prometheus/prometheus/storage"
"github.com/prometheus/prometheus/storage/remote"
)
var _ prometheus.Prometheus = (*Provider)(nil)
type Provider struct {
queryable storage.SampleAndChunkQueryable
engine *prometheus.Engine
parser prometheus.Parser
}
var stCallback = func() (int64, error) {
return int64(model.Latest), nil
}
func New(ctx context.Context, providerSettings factory.ProviderSettings, config prometheus.Config, telemetryStore telemetrystore.TelemetryStore) *Provider {
settings := factory.NewScopedProviderSettings(providerSettings, "github.com/SigNoz/signoz/pkg/prometheus/prometheustest")
engine := prometheus.NewEngine(settings.Logger(), config)
readClient := clickhouseprometheus.NewReadClient(settings, telemetryStore)
queryable := remote.NewSampleAndChunkQueryableClient(readClient, labels.EmptyLabels(), []*labels.Matcher{}, false, stCallback)
return &Provider{
engine: engine,
parser: prometheus.NewParser(),
queryable: queryable,
// New returns the clickhousev2 provider over the given telemetry store, so
// tests exercise the production read path against a mock store.
func New(ctx context.Context, providerSettings factory.ProviderSettings, config prometheus.Config, telemetryStore telemetrystore.TelemetryStore) prometheus.Prometheus {
provider, err := clickhouseprometheusv2.New(ctx, providerSettings, config, telemetryStore)
if err != nil {
panic(err)
}
}
func (provider *Provider) Engine() *prometheus.Engine {
return provider.engine
}
func (provider *Provider) Storage() storage.Queryable {
return provider.queryable
}
func (provider *Provider) Parser() prometheus.Parser {
return provider.parser
}
func (provider *Provider) Close() error {
if provider.engine != nil {
provider.engine.Close()
}
return nil
return provider
}

View File

@@ -57,7 +57,6 @@ func (handler *handler) QueryRange(rw http.ResponseWriter, req *http.Request) {
render.Error(rw, err)
return
}
queryRangeRequest.PromQLProvider = req.Header.Get("X-SigNoz-PromQL-Provider")
// Validate the query request
if err := queryRangeRequest.Validate(); err != nil {

View File

@@ -231,7 +231,7 @@ func (q *querier) buildPreviewProviders(
sub.CompositeQuery = qbtypes.CompositeQuery{Queries: []qbtypes.QueryEnvelope{query}}
}
built, _, bErr := q.buildQueries(orgID, &sub, deps, missingMetricQuerySet, event, promqlOptions{})
built, _, bErr := q.buildQueries(orgID, &sub, deps, missingMetricQuerySet, event)
if bErr != nil {
errs[name] = bErr
continue

View File

@@ -102,24 +102,6 @@ type promqlQuery struct {
tr qbv5.TimeRange
requestType qbv5.RequestType
vars map[string]qbv5.VariableItem
opts promqlOptions
}
// promqlOptions is how a PromQL query relates to the clickhousev2 provider
// (see querier.promqlOptions for where the fields come from and why they are
// flag-gated). Both providers are nil for a plain request, so a plain
// request costs nothing extra.
type promqlOptions struct {
// shadow, when set, runs the query on this provider after serving and
// logs any result difference; the response is never affected.
shadow prometheus.Prometheus
// shadowSlots is the querier-wide admission for shadow runs, shared by
// every query so the bound holds per process.
shadowSlots chan struct{}
// serve, when set, serves the response from this provider instead of the
// default path. Comparison callers fetch the default and the pinned
// result as two API calls and diff them.
serve prometheus.Prometheus
}
var _ qbv5.Query = (*promqlQuery)(nil)
@@ -132,29 +114,19 @@ func newPromqlQuery(
tr qbv5.TimeRange,
requestType qbv5.RequestType,
variables map[string]qbv5.VariableItem,
opts promqlOptions,
) *promqlQuery {
return &promqlQuery{
logger: logger,
promEngine: promEngine,
parser: promEngine.Parser(),
parser: prometheus.NewParser(),
query: query,
tr: tr,
requestType: requestType,
vars: variables,
opts: opts,
}
}
func (q *promqlQuery) Fingerprint() string {
// A pinned request must not share cache entries with default serving: a
// cached default result would satisfy the pin without running the pinned
// provider, and a pinned result would poison normal serving. No
// fingerprint means no caching at all — the pin exists to observe a
// provider, so a cache in front of it defeats the point.
if q.opts.serve != nil {
return ""
}
if q.requestType != qbv5.RequestTypeTimeSeries {
return ""
}
@@ -267,15 +239,9 @@ func (q *promqlQuery) Statement(_ context.Context) (*qbv5.Statement, error) {
return &qbv5.Statement{Query: rendered}, nil
}
// PreviewStatements returns the ClickHouse statement(s) this PromQL query would
// run, captured by driving the engine with a Storage that records each selector's
// SQL and returns no data. Returns nil if capture is unsupported.
// PreviewStatements returns the ClickHouse statement(s) this PromQL query
// would run on the engine path, captured without executing them.
func (q *promqlQuery) PreviewStatements(ctx context.Context) ([]prometheus.CapturedStatement, error) {
storer, ok := q.promEngine.(prometheus.StatementCapturer)
if !ok {
return nil, nil
}
rendered, err := q.renderVars(q.query.Query, q.vars, q.tr.From, q.tr.To)
if err != nil {
return nil, err
@@ -284,42 +250,11 @@ func (q *promqlQuery) PreviewStatements(ctx context.Context) ([]prometheus.Captu
start := int64(querybuilder.ToNanoSecs(q.tr.From))
end := int64(querybuilder.ToNanoSecs(q.tr.To))
// Attach the same query traits as Execute so the captured statements
// match what the live path would run.
if expr, parseErr := q.parser.ParseExpr(rendered); parseErr == nil {
ctx = prometheus.NewContextWithQueryTraits(ctx, prometheus.DetectQueryTraits(expr))
}
capStorage, recorder := storer.CapturingStorage()
if capStorage == nil {
return nil, nil
}
qry, err := q.promEngine.Engine().NewRangeQuery(
ctx,
capStorage,
nil,
rendered,
time.Unix(0, start),
time.Unix(0, end),
q.query.Step.Duration,
)
statements, err := q.promEngine.Statements(ctx, rendered, time.Unix(0, start), time.Unix(0, end), q.query.Step.Duration)
if err != nil {
if e := tryEnhancePromQLExecError(err); e != nil {
return nil, e
}
return nil, enhancePromQLError(rendered, err)
return nil, q.evalError(rendered, err)
}
defer qry.Close()
// Exec drives a Select per selector (recording SQL) but reads no data.
if res := qry.Exec(ctx); res.Err != nil {
if e := tryEnhancePromQLExecError(res.Err); e != nil {
return nil, e
}
return nil, errors.Newf(errors.TypeInternal, errors.CodeInternal, "query execution error: %v", res.Err)
}
return recorder.Statements(), nil
return statements, nil
}
func (q *promqlQuery) Execute(ctx context.Context) (*qbv5.Result, error) {
@@ -337,13 +272,6 @@ func (q *promqlQuery) Execute(ctx context.Context) (*qbv5.Result, error) {
return nil, err
}
// Attach query traits so the storage can prove step-aligned optimizations
// safe (see prometheus.QueryTraits). A parse failure surfaces below via
// the engine with the enhanced error message.
if expr, parseErr := q.parser.ParseExpr(query); parseErr == nil {
ctx = prometheus.NewContextWithQueryTraits(ctx, prometheus.DetectQueryTraits(expr))
}
// Accumulate ClickHouse-side scan stats across every storage query this
// evaluation issues (engine selectors or the compiled executor): progress
// options propagate to each ClickHouse query through the context.
@@ -358,97 +286,37 @@ func (q *promqlQuery) Execute(ctx context.Context) (*qbv5.Result, error) {
began := time.Now()
// A pinned provider serves directly from it: comparison callers fetch
// the default result and the pinned result as two API calls and diff
// them.
if q.opts.serve != nil {
matrix, err := q.serveFromProvider(ctx, query, start, end)
if err != nil {
if enhanced := tryEnhancePromQLExecError(err); enhanced != nil {
return nil, enhanced
}
return nil, err
}
return q.toResult(matrix, nil, began, &statsMu, &rowsScanned, &bytesScanned), nil
}
// When the serving provider has the RangeExecutor capability
// (prometheus::provider: clickhousev2), serve the way the provider is
// designed to serve: transpiled when the shape allows. Without this the
// override would silently run the engine path only.
if re, ok := q.promEngine.(prometheus.RangeExecutor); ok {
matrix, served, err := re.TryExecuteRange(ctx, query, time.Unix(0, start), time.Unix(0, end), q.query.Step.Duration)
if err != nil {
if enhanced := tryEnhancePromQLExecError(err); enhanced != nil {
return nil, enhanced
}
return nil, err
}
if served {
return q.toResult(matrix, nil, began, &statsMu, &rowsScanned, &bytesScanned), nil
}
}
qry, err := q.promEngine.Engine().NewRangeQuery(
ctx,
q.promEngine.Storage(),
nil,
query,
time.Unix(0, start),
time.Unix(0, end),
q.query.Step.Duration,
)
res, err := q.promEngine.QueryRange(ctx, query, time.Unix(0, start), time.Unix(0, end), q.query.Step.Duration)
if err != nil {
// NewRangeQuery can fail with execution errors (e.g. context deadline exceeded)
// during the query queue/scheduling stage, not just parse errors.
if err := tryEnhancePromQLExecError(err); err != nil {
return nil, err
}
return nil, enhancePromQLError(query, err)
return nil, q.evalError(query, err)
}
res := qry.Exec(ctx)
if res.Err != nil {
if err := tryEnhancePromQLExecError(res.Err); err != nil {
return nil, err
}
return nil, errors.Newf(errors.TypeInternal, errors.CodeInternal, "query execution error: %v", res.Err)
}
defer qry.Close()
matrix, promErr := res.Matrix()
if promErr != nil {
return nil, errors.WrapInternalf(promErr, errors.CodeInternal, "error getting matrix from promql query %q", query)
}
if q.opts.shadow != nil {
// Shadows detach from the request, so without admission a dashboard
// burst would stack unbounded ClickHouse work for up to the shadow
// timeout — the concurrency pattern behind the original outages.
// Non-blocking: at the cap the comparison is skipped, not queued;
// a sampled shadow stream is exactly as useful for rollout evidence.
select {
case q.opts.shadowSlots <- struct{}{}:
// The engine pools the result's sample slices on Close; the
// shadow comparison needs a stable copy of what was served.
served := copyMatrix(matrix)
servedIn := time.Since(began)
go func() {
defer func() { <-q.opts.shadowSlots }()
q.runShadowCompare(context.WithoutCancel(ctx), query, start, end, served, servedIn)
}()
default:
q.logger.DebugContext(ctx, "promql shadow skipped: at concurrency cap", slog.String("query", query))
}
matrix, ok := res.Value.(promql.Matrix)
if !ok {
return nil, errors.Newf(errors.TypeInternal, errors.CodeInternal, "promql query %q returned %T, expected a matrix", query, res.Value)
}
warnings, _ := res.Warnings.AsStrings(query, 10, 0)
return q.toResult(matrix, warnings, began, &statsMu, &rowsScanned, &bytesScanned), nil
}
// evalError types an evaluation error: engine execution classes first, then
// parse errors with the migration hints, everything else internal.
func (q *promqlQuery) evalError(query string, err error) error {
if enhanced := tryEnhancePromQLExecError(err); enhanced != nil {
return enhanced
}
var parseErrs parser.ParseErrors
if errors.As(err, &parseErrs) {
return enhancePromQLError(query, err)
}
// The transpiled path raises typed user errors of its own; keep them.
if errors.Ast(err, errors.TypeInvalidInput) {
return err
}
return errors.Newf(errors.TypeInternal, errors.CodeInternal, "query execution error: %v", err)
}
// toResult converts an evaluated matrix into the v5 result shape, attaching
// the ClickHouse scan stats accumulated during evaluation.
func (q *promqlQuery) toResult(matrix promql.Matrix, warnings []string, began time.Time, statsMu *sync.Mutex, rowsScanned, bytesScanned *uint64) *qbv5.Result {

View File

@@ -13,7 +13,6 @@ import (
"github.com/SigNoz/signoz/pkg/errors"
"github.com/SigNoz/signoz/pkg/prometheus"
"github.com/SigNoz/signoz/pkg/prometheus/prometheustest"
qbv5 "github.com/SigNoz/signoz/pkg/types/querybuildertypes/querybuildertypesv5"
"github.com/stretchr/testify/assert"
"github.com/stretchr/testify/require"
@@ -449,18 +448,6 @@ func TestQuotedMetricOutsideBracesPattern(t *testing.T) {
}
}
// A pinned request must not share cache entries with default serving: a
// cached default result would satisfy the pin without running the pinned
// provider.
func TestFingerprint_PinnedProviderBypassesCache(t *testing.T) {
q := &promqlQuery{
logger: slog.Default(),
query: qbv5.PromQuery{Query: "up"},
opts: promqlOptions{serve: &prometheustest.Provider{}},
}
assert.Empty(t, q.Fingerprint())
}
func TestToResultDropsNonFiniteValues(t *testing.T) {
tests := []struct {
description string

View File

@@ -1,183 +0,0 @@
package querier
import (
"context"
"fmt"
"log/slog"
"math"
"sort"
"time"
"github.com/ClickHouse/clickhouse-go/v2"
"github.com/SigNoz/signoz/pkg/prometheus"
"github.com/prometheus/prometheus/model/labels"
"github.com/prometheus/prometheus/promql"
)
// shadowTimeout bounds a shadow evaluation; a shadow run must never outlive
// the request by much or pile up.
const shadowTimeout = 2 * time.Minute
// runShadowCompare executes the query on the clickhousev2 provider exactly
// as it would serve (transpiled when the shape allows, engine over the v2
// querier otherwise), compares against the served result and logs the
// outcome. Serving is never affected: this runs after the response, off the
// request context, and only logs. The mismatch and failure logs are the
// rollout evidence — serving cuts over to v2 only after they stay clean.
func (q *promqlQuery) runShadowCompare(ctx context.Context, query string, startNs, endNs int64, served promql.Matrix, servedIn time.Duration) {
defer func() {
if r := recover(); r != nil {
q.logger.ErrorContext(ctx, "promql shadow comparison panicked", slog.Any("panic", r), slog.String("query", query))
}
}()
ctx, cancel := context.WithTimeout(ctx, shadowTimeout)
defer cancel()
// The request context carries the served response's scan-stats progress
// callback; without replacing it the shadow's ClickHouse progress would
// race into the served stats. The response itself was already sent.
ctx = clickhouse.Context(ctx, clickhouse.WithProgress(func(*clickhouse.Progress) {}))
if expr, parseErr := q.parser.ParseExpr(query); parseErr == nil {
ctx = prometheus.NewContextWithQueryTraits(ctx, prometheus.DetectQueryTraits(expr))
}
start, end := time.Unix(0, startNs), time.Unix(0, endNs)
began := time.Now()
shadow, transpiled, err := executeOnProvider(ctx, q.opts.shadow, query, start, end, q.query.Step.Duration)
shadowIn := time.Since(began)
logAttrs := []any{
slog.String("query", query),
slog.Int64("start_ms", startNs/int64(time.Millisecond)),
slog.Int64("end_ms", endNs/int64(time.Millisecond)),
slog.Duration("step", q.query.Step.Duration),
slog.Bool("transpiled", transpiled),
slog.Duration("served_in", servedIn),
slog.Duration("shadow_in", shadowIn),
}
if err != nil {
// A shadow failure would be a serving failure after rollout; surface
// it at the same level as a result mismatch.
q.logger.WarnContext(ctx, "promql shadow execution failed", append(logAttrs, slog.Any("error", err))...)
return
}
servedNorm := normalizeShadowMatrix(served)
shadowNorm := normalizeShadowMatrix(shadow)
if diff := diffShadowMatrices(servedNorm, shadowNorm); diff != "" {
q.logger.WarnContext(ctx, "promql shadow comparison mismatch", append(logAttrs,
slog.String("diff", diff),
slog.Int("served_series", len(servedNorm)),
slog.Int("shadow_series", len(shadowNorm)),
)...)
return
}
// Matches log the timings: served_in vs shadow_in across the fleet is
// the perf evidence for the cutover, gathered for free.
q.logger.DebugContext(ctx, "promql shadow comparison matched", logAttrs...)
}
func (q *promqlQuery) serveFromProvider(ctx context.Context, query string, startNs, endNs int64) (promql.Matrix, error) {
matrix, _, err := executeOnProvider(ctx, q.opts.serve, query, time.Unix(0, startNs), time.Unix(0, endNs), q.query.Step.Duration)
return matrix, err
}
// The returned matrix is an owned copy.
func executeOnProvider(ctx context.Context, prov prometheus.Prometheus, query string, start, end time.Time, step time.Duration) (promql.Matrix, bool, error) {
if re, ok := prov.(prometheus.RangeExecutor); ok {
matrix, served, err := re.TryExecuteRange(ctx, query, start, end, step)
if err != nil {
return nil, true, err
}
if served {
return matrix, true, nil
}
}
qry, err := prov.Engine().NewRangeQuery(ctx, prov.Storage(), nil, query, start, end, step)
if err != nil {
return nil, false, err
}
defer qry.Close()
res := qry.Exec(ctx)
if res.Err != nil {
return nil, false, res.Err
}
matrix, err := res.Matrix()
if err != nil {
return nil, false, err
}
// Close returns the result's sample slices to the engine pool.
return copyMatrix(matrix), false, nil
}
func copyMatrix(matrix promql.Matrix) promql.Matrix {
out := make(promql.Matrix, 0, len(matrix))
for _, s := range matrix {
floats := make([]promql.FPoint, len(s.Floats))
copy(floats, s.Floats)
out = append(out, promql.Series{Metric: s.Metric.Copy(), Floats: floats})
}
return out
}
// normalizeShadowMatrix sorts by label set for order-independent
// comparison. Both providers now resolve series identity the same way
// (empty-valued labels dropped at read, no synthetic fingerprint label
// since the v1 series-identity fix), so labels need no normalization.
func normalizeShadowMatrix(matrix promql.Matrix) promql.Matrix {
out := make(promql.Matrix, 0, len(matrix))
out = append(out, matrix...)
sort.Slice(out, func(i, j int) bool { return labels.Compare(out[i].Metric, out[j].Metric) < 0 })
return out
}
// diffShadowMatrices returns a description of the first difference, or "".
// Values compare with relative tolerance: spatial aggregations accumulate
// floats in storage order, which differs between the providers in the last
// ULP.
func diffShadowMatrices(served, shadow promql.Matrix) string {
const relTol = 1e-9
if len(served) != len(shadow) {
return fmt.Sprintf("series count: served=%d shadow=%d", len(served), len(shadow))
}
for i := range served {
if labels.Compare(served[i].Metric, shadow[i].Metric) != 0 {
return fmt.Sprintf("series %d labels: served=%s shadow=%s", i, served[i].Metric, shadow[i].Metric)
}
if len(served[i].Floats) != len(shadow[i].Floats) {
return fmt.Sprintf("series %s points: served=%d shadow=%d", served[i].Metric, len(served[i].Floats), len(shadow[i].Floats))
}
for j := range served[i].Floats {
a, b := served[i].Floats[j], shadow[i].Floats[j]
if a.T != b.T {
return fmt.Sprintf("series %s point %d ts: served=%d shadow=%d", served[i].Metric, j, a.T, b.T)
}
// NaN and infinities first: NaN != NaN and Inf-Inf arithmetic
// would otherwise make one-sided NaN and Inf-vs-finite compare
// as equal (NaN > x and Inf > Inf are both false).
if math.IsNaN(a.F) || math.IsNaN(b.F) {
if math.IsNaN(a.F) != math.IsNaN(b.F) {
return fmt.Sprintf("series %s @%d value: served=%v shadow=%v", served[i].Metric, a.T, a.F, b.F)
}
continue
}
if math.IsInf(a.F, 0) || math.IsInf(b.F, 0) {
if a.F != b.F {
return fmt.Sprintf("series %s @%d value: served=%v shadow=%v", served[i].Metric, a.T, a.F, b.F)
}
continue
}
diff := math.Abs(a.F - b.F)
scale := math.Max(math.Abs(a.F), math.Abs(b.F))
if diff > relTol*math.Max(scale, 1e-300) && diff > 1e-12 {
return fmt.Sprintf("series %s @%d value: served=%v shadow=%v", served[i].Metric, a.T, a.F, b.F)
}
}
}
return ""
}

View File

@@ -1,67 +0,0 @@
package querier
import (
"math"
"testing"
"github.com/prometheus/prometheus/model/labels"
"github.com/prometheus/prometheus/promql"
"github.com/stretchr/testify/assert"
)
func TestNormalizeShadowMatrix(t *testing.T) {
matrix := promql.Matrix{
{
Metric: labels.FromStrings("__name__", "up", "job", "api"),
Floats: []promql.FPoint{{T: 1000, F: 1}},
},
{
Metric: labels.FromStrings("a", "1"),
Floats: []promql.FPoint{{T: 1000, F: 2}},
},
}
norm := normalizeShadowMatrix(matrix)
// sorted by label set; labels pass through untouched — both providers
// resolve series identity identically since the v1 series-identity fix
assert.Equal(t, labels.FromStrings("__name__", "up", "job", "api"), norm[0].Metric)
assert.Equal(t, labels.FromStrings("a", "1"), norm[1].Metric)
}
func TestDiffShadowMatrices(t *testing.T) {
series := func(v float64) promql.Matrix {
return promql.Matrix{{Metric: labels.FromStrings("a", "1"), Floats: []promql.FPoint{{T: 1000, F: v}}}}
}
assert.Empty(t, diffShadowMatrices(series(1.5), series(1.5)))
// last-ULP differences from storage-order float accumulation are expected
assert.Empty(t, diffShadowMatrices(series(0.08888888888888889), series(0.08888888888888888)))
assert.Empty(t, diffShadowMatrices(series(math.NaN()), series(math.NaN())))
assert.Contains(t, diffShadowMatrices(series(1.5), series(1.6)), "value")
assert.Contains(t, diffShadowMatrices(series(1.5), promql.Matrix{}), "series count")
assert.Contains(t, diffShadowMatrices(
series(1.5),
promql.Matrix{{Metric: labels.FromStrings("a", "2"), Floats: []promql.FPoint{{T: 1000, F: 1.5}}}},
), "labels")
assert.Contains(t, diffShadowMatrices(
series(1.5),
promql.Matrix{{Metric: labels.FromStrings("a", "1"), Floats: []promql.FPoint{{T: 2000, F: 1.5}}}},
), "ts")
}
// One-sided NaN makes every float comparison false, and Inf-Inf arithmetic
// yields Inf > Inf == false; without explicit handling both divergences log
// as matched — a shadow comparator that cannot see them would green-light a
// broken rollout.
func TestDiffShadowMatrices_SpecialFloats(t *testing.T) {
point := func(v float64) promql.Matrix {
return promql.Matrix{{Metric: labels.FromStrings("a", "1"), Floats: []promql.FPoint{{T: 1000, F: v}}}}
}
assert.NotEmpty(t, diffShadowMatrices(point(math.NaN()), point(1.5)), "one-sided NaN must diff")
assert.NotEmpty(t, diffShadowMatrices(point(1.5), point(math.NaN())), "one-sided NaN must diff either way")
assert.NotEmpty(t, diffShadowMatrices(point(math.Inf(1)), point(1.5)), "Inf vs finite must diff")
assert.NotEmpty(t, diffShadowMatrices(point(math.Inf(1)), point(math.Inf(-1))), "opposite infinities must diff")
assert.Empty(t, diffShadowMatrices(point(math.Inf(1)), point(math.Inf(1))), "equal infinities match")
assert.Empty(t, diffShadowMatrices(point(math.NaN()), point(math.NaN())), "both NaN match")
}

View File

@@ -24,7 +24,6 @@ import (
"github.com/SigNoz/signoz/pkg/statsreporter"
"github.com/SigNoz/signoz/pkg/telemetrystore"
"github.com/SigNoz/signoz/pkg/types/ctxtypes"
"github.com/SigNoz/signoz/pkg/types/featuretypes"
"github.com/SigNoz/signoz/pkg/types/instrumentationtypes"
"github.com/SigNoz/signoz/pkg/types/metrictypes"
"github.com/SigNoz/signoz/pkg/types/telemetrytypes"
@@ -47,19 +46,11 @@ type Querier interface {
}
type querier struct {
logger *slog.Logger
fl flagger.Flagger
telemetryStore telemetrystore.TelemetryStore
metadataStore telemetrytypes.MetadataStore
promEngine prometheus.Prometheus
// promV2 is the clickhousev2 prometheus provider, wired only when the
// serving provider is the default one (nil otherwise). It reads the same
// ClickHouse data through a different implementation; PromQL queries
// shadow-compare against it behind the use_prometheus_clickhouse_v2 flag
// and can be pinned to it for a response (see promqlOptions). It never
// serves by default — that cutover happens only after the shadow logs
// stay clean.
promV2 prometheus.Prometheus
logger *slog.Logger
fl flagger.Flagger
telemetryStore telemetrystore.TelemetryStore
metadataStore telemetrytypes.MetadataStore
promEngine prometheus.Prometheus
traceStmtBuilder qbtypes.StatementBuilder[qbtypes.TraceAggregation]
aiTraceStmtBuilder qbtypes.StatementBuilder[qbtypes.TraceAggregation]
logStmtBuilder qbtypes.StatementBuilder[qbtypes.LogAggregation]
@@ -71,16 +62,8 @@ type querier struct {
liveDataRefresh time.Duration
builderConfig builderConfig
maxConcurrentQueries int
// shadowSlots bounds concurrent shadow comparisons per process; shadows
// detach from their requests, so nothing else limits how many pile up.
shadowSlots chan struct{}
}
// maxConcurrentShadows is deliberately small: a shadow is a full extra
// ClickHouse evaluation, and a sampled stream of comparisons is exactly as
// useful for rollout evidence as an exhaustive one under load.
const maxConcurrentShadows = 8
var _ Querier = (*querier)(nil)
func New(
@@ -88,7 +71,6 @@ func New(
telemetryStore telemetrystore.TelemetryStore,
metadataStore telemetrytypes.MetadataStore,
promEngine prometheus.Prometheus,
promV2 prometheus.Prometheus,
traceStmtBuilder qbtypes.StatementBuilder[qbtypes.TraceAggregation],
aiTraceStmtBuilder qbtypes.StatementBuilder[qbtypes.TraceAggregation],
logStmtBuilder qbtypes.StatementBuilder[qbtypes.LogAggregation],
@@ -111,7 +93,6 @@ func New(
telemetryStore: telemetryStore,
metadataStore: metadataStore,
promEngine: promEngine,
promV2: promV2,
traceStmtBuilder: traceStmtBuilder,
aiTraceStmtBuilder: aiTraceStmtBuilder,
logStmtBuilder: logStmtBuilder,
@@ -125,7 +106,6 @@ func New(
logTraceIDWindowPaddingMS: uint64(logTraceIDWindowPadding.Milliseconds()),
},
maxConcurrentQueries: maxConcurrentQueries,
shadowSlots: make(chan struct{}, maxConcurrentShadows),
}
}
@@ -165,11 +145,7 @@ func (q *querier) QueryRange(ctx context.Context, orgID valuer.UUID, req *qbtype
missingMetricQuerySet[name] = true
}
promqlOpts, err := q.promqlOptions(ctx, orgID, req)
if err != nil {
return nil, err
}
queries, steps, err := q.buildQueries(orgID, req, dependencyQueries, missingMetricQuerySet, event, promqlOpts)
queries, steps, err := q.buildQueries(orgID, req, dependencyQueries, missingMetricQuerySet, event)
if err != nil {
return nil, err
}
@@ -212,41 +188,12 @@ func (q *querier) QueryRange(ctx context.Context, orgID valuer.UUID, req *qbtype
return qbResp, qbErr
}
// promqlOptions derives the PromQL execution options for a request. With the
// org's use_prometheus_clickhouse_v2 flag on, queries are shadow-compared
// against the clickhousev2 provider (serving unaffected, diffs logged; see
// promql_shadow.go). The X-SigNoz-PromQL-Provider header may instead pin the
// response to that provider — integration tests and support fetch both
// results for comparison — so it is deliberately flag-gated too: without the
// gate the header would be an unaudited switch onto a provider still under
// validation.
func (q *querier) promqlOptions(ctx context.Context, orgID valuer.UUID, req *qbtypes.QueryRangeRequest) (promqlOptions, error) {
enabled := q.fl.BooleanOrEmpty(ctx, flagger.FeatureUsePrometheusClickhouseV2, featuretypes.NewFlaggerEvaluationContext(orgID))
if req.PromQLProvider == "" {
if enabled && q.promV2 != nil {
return promqlOptions{shadow: q.promV2, shadowSlots: q.shadowSlots}, nil
}
return promqlOptions{}, nil
}
if req.PromQLProvider != prometheus.ProviderClickhouseV2 {
return promqlOptions{}, errors.NewInvalidInputf(errors.CodeInvalidInput, "unknown promql provider %q", req.PromQLProvider)
}
if !enabled {
return promqlOptions{}, errors.NewInvalidInputf(errors.CodeInvalidInput, "promql provider %q requires the use_prometheus_clickhouse_v2 flag", req.PromQLProvider)
}
if q.promV2 == nil {
return promqlOptions{}, errors.NewInvalidInputf(errors.CodeInvalidInput, "promql provider %q is not available", req.PromQLProvider)
}
return promqlOptions{serve: q.promV2}, nil
}
func (q *querier) buildQueries(
orgID valuer.UUID,
req *qbtypes.QueryRangeRequest,
dependencyQueries map[string]bool,
missingMetricQuerySet map[string]bool,
event *qbtypes.QBEvent,
promqlOpts promqlOptions,
) (map[string]qbtypes.Query, map[string]qbtypes.Step, error) {
tmplVars := req.Variables
@@ -271,7 +218,7 @@ func (q *querier) buildQueries(
if !ok {
return nil, nil, errors.NewInvalidInputf(errors.CodeInvalidInput, "invalid promql query spec %T", query.Spec)
}
promqlQuery := newPromqlQuery(q.logger, q.promEngine, promQuery, qbtypes.TimeRange{From: req.Start, To: req.End}, req.RequestType, tmplVars, promqlOpts)
promqlQuery := newPromqlQuery(q.logger, q.promEngine, promQuery, qbtypes.TimeRange{From: req.Start, To: req.End}, req.RequestType, tmplVars)
queries[promQuery.Name] = promqlQuery
steps[promQuery.Name] = promQuery.Step
case qbtypes.QueryTypeClickHouseSQL:
@@ -929,7 +876,7 @@ func (q *querier) createRangedQuery(_ valuer.UUID, originalQuery qbtypes.Query,
switch qt := originalQuery.(type) {
case *promqlQuery:
queryCopy := qt.query.Copy()
return newPromqlQuery(q.logger, qt.promEngine, queryCopy, timeRange, qt.requestType, qt.vars, qt.opts)
return newPromqlQuery(q.logger, qt.promEngine, queryCopy, timeRange, qt.requestType, qt.vars)
case *chSQLQuery:
queryCopy := qt.query.Copy()

View File

@@ -48,7 +48,6 @@ func TestQueryRange_MetricTypeMissing(t *testing.T) {
nil, // telemetryStore
metadataStore,
nil, // prometheus
nil, // promV2
nil, // traceStmtBuilder
nil, // aiTraceStmtBuilder
nil, // logStmtBuilder
@@ -122,7 +121,6 @@ func TestQueryRange_MetricTypeFromStore(t *testing.T) {
telemetryStore,
metadataStore,
nil, // prometheus
nil, // promV2
nil, // traceStmtBuilder
nil, // aiTraceStmtBuilder
nil, // logStmtBuilder

View File

@@ -18,7 +18,6 @@ import (
func NewFactory(
telemetryStore telemetrystore.TelemetryStore,
prometheus prometheus.Prometheus,
promV2 prometheus.Prometheus,
metadataStore telemetrytypes.MetadataStore,
traceStmtBuilder qbtypes.StatementBuilder[qbtypes.TraceAggregation],
aiTraceStmtBuilder qbtypes.StatementBuilder[qbtypes.TraceAggregation],
@@ -42,7 +41,6 @@ func NewFactory(
telemetryStore,
metadataStore,
prometheus,
promV2,
traceStmtBuilder,
aiTraceStmtBuilder,
logStmtBuilder,

View File

@@ -35,6 +35,7 @@ import (
errorsV2 "github.com/SigNoz/signoz/pkg/errors"
"github.com/prometheus/prometheus/promql"
"github.com/prometheus/prometheus/promql/parser"
"github.com/prometheus/prometheus/util/stats"
"github.com/ClickHouse/clickhouse-go/v2"
@@ -230,41 +231,43 @@ func NewReader(
}
func (r *ClickHouseReader) GetInstantQueryMetricsResult(ctx context.Context, queryParams *model.InstantQueryMetricsParams) (*promql.Result, *stats.QueryStats, *model.ApiError) {
qry, err := r.prometheus.Engine().NewInstantQuery(ctx, r.prometheus.Storage(), nil, queryParams.Query, queryParams.Time)
res, err := r.prometheus.Query(ctx, queryParams.Query, queryParams.Time)
var qs stats.QueryStats
if err != nil {
return nil, nil, &model.ApiError{Typ: model.ErrorBadData, Err: err}
var parseErrs parser.ParseErrors
if errorsV2.As(err, &parseErrs) {
return nil, nil, &model.ApiError{Typ: model.ErrorBadData, Err: err}
}
// Evaluation errors travel inside the result, as the engine reports
// them; the handler maps them from there.
return &promql.Result{Err: err}, &qs, nil
}
res := qry.Exec(ctx)
// Optional stats field in response if parameter "stats" is not empty.
var qs stats.QueryStats
if queryParams.Stats != "" {
qs = stats.NewQueryStats(qry.Stats())
if queryParams.Stats != "" && res.Stats != nil {
qs = stats.NewQueryStats(res.Stats)
}
qry.Close()
return res, &qs, nil
return &promql.Result{Value: res.Value, Warnings: res.Warnings}, &qs, nil
}
func (r *ClickHouseReader) GetQueryRangeResult(ctx context.Context, query *model.QueryRangeParams) (*promql.Result, *stats.QueryStats, *model.ApiError) {
qry, err := r.prometheus.Engine().NewRangeQuery(ctx, r.prometheus.Storage(), nil, query.Query, query.Start, query.End, query.Step)
res, err := r.prometheus.QueryRange(ctx, query.Query, query.Start, query.End, query.Step)
var qs stats.QueryStats
if err != nil {
return nil, nil, &model.ApiError{Typ: model.ErrorBadData, Err: err}
var parseErrs parser.ParseErrors
if errorsV2.As(err, &parseErrs) {
return nil, nil, &model.ApiError{Typ: model.ErrorBadData, Err: err}
}
return &promql.Result{Err: err}, &qs, nil
}
res := qry.Exec(ctx)
// Optional stats field in response if parameter "stats" is not empty.
var qs stats.QueryStats
if query.Stats != "" {
qs = stats.NewQueryStats(qry.Stats())
if query.Stats != "" && res.Stats != nil {
qs = stats.NewQueryStats(res.Stats)
}
qry.Close()
return res, &qs, nil
return &promql.Result{Value: res.Value, Warnings: res.Warnings}, &qs, nil
}
func (r *ClickHouseReader) GetServicesList(ctx context.Context) (*[]string, error) {

View File

@@ -156,7 +156,7 @@ func TestManager_TestNotification_SendUnmatched_PromRule(t *testing.T) {
triggeredTestAlerts := []map[*alertmanagertypes.PostableAlert][]string{}
// Variable to store promProvider for cleanup
var promProvider *prometheustest.Provider
var promProvider prometheus.Prometheus
// Create manager using test factory with hooks
mgr := NewTestManager(t, &TestManagerOptions{
@@ -181,74 +181,29 @@ func TestManager_TestNotification_SendUnmatched_PromRule(t *testing.T) {
TelemetryStoreHook: func(store telemetrystore.TelemetryStore) {
mockStore := store.(*telemetrystoretest.Provider)
// Set up Prometheus-specific mock data
// Fingerprint columns for Prometheus queries
fingerprintCols := []cmock.ColumnType{
{Name: "fingerprint", Type: "UInt64"},
{Name: "any(labels)", Type: "String"},
}
// Samples columns for Prometheus queries
samplesCols := []cmock.ColumnType{
{Name: "metric_name", Type: "String"},
{Name: "fingerprint", Type: "UInt64"},
{Name: "unix_milli", Type: "Int64"},
{Name: "value", Type: "Float64"},
{Name: "flags", Type: "UInt32"},
}
// Calculate query time range similar to Prometheus rule tests
// TestNotification uses time.Now().UTC() for evaluation
// We calculate the query window based on current time to match what the actual evaluation will use
// Grid the TestNotification eval computes over (see
// Timestamps on base_rule); nil args match any window.
evalTime := baseTime
evalWindowMs := int64(5 * 60 * 1000) // 5 minutes in ms
evalTimeMs := evalTime.UnixMilli()
queryStart := ((evalTimeMs-2*evalWindowMs)/60000)*60000 + 1 // truncate to minute + 1ms
queryEnd := (evalTimeMs / 60000) * 60000 // truncate to minute
gridEnd := (evalTime.UnixMilli() / 60000) * 60000
gridStart := gridEnd - evalWindowMs
// Create fingerprint data
fingerprint := uint64(12345)
labelsJSON := `{"__name__":"test_metric"}`
fingerprintData := [][]any{
{fingerprint, labelsJSON},
}
fingerprintRows := cmock.NewRows(fingerprintCols, fingerprintData)
// Create samples data from test case values, calculating timestamps relative to baseTime
validSamplesData := make([][]any, 0)
tsList := make([]int64, 0, len(tc.Values))
vList := make([]float64, 0, len(tc.Values))
for _, v := range tc.Values {
// Skip NaN and Inf values in the samples data
if math.IsNaN(v.Value) || math.IsInf(v.Value, 0) {
continue
}
// Calculate timestamp relative to baseTime
sampleTimestamp := baseTime.Add(v.Offset).UnixMilli()
validSamplesData = append(validSamplesData, []any{
"test_metric",
fingerprint,
sampleTimestamp,
v.Value,
uint32(0), // flags - 0 means normal value
})
tsList = append(tsList, baseTime.Add(v.Offset).UnixMilli())
vList = append(vList, v.Value)
}
samplesRows := cmock.NewRows(samplesCols, validSamplesData)
grid := prometheustest.LastSampleGrid(tsList, vList, gridStart, gridEnd, 60_000, 300_000)
mock := mockStore.Mock()
// Mock the fingerprint query (for Prometheus label matching)
mock.ExpectQuery("SELECT fingerprint, any").
WithArgs("test_metric").
WillReturnRows(fingerprintRows)
// Mock the samples query (for Prometheus metric data)
mock.ExpectQuery("SELECT metric_name, fingerprint, unix_milli").
WithArgs(
"test_metric",
"test_metric",
queryStart,
queryEnd,
).
WillReturnRows(samplesRows)
mock.ExpectQuery("SELECT gkey").
WithArgs("test_metric", nil, nil, "test_metric", nil, nil).
WillReturnRows(cmock.NewRows(prometheustest.GridCols, [][]any{{`[["__name__","test_metric"]]`, grid}}))
// Create Prometheus provider for this test
promProvider = prometheustest.New(context.Background(), instrumentationtest.New().ToProviderSettings(), prometheus.Config{Timeout: 2 * time.Minute}, store)
@@ -282,7 +237,6 @@ func TestManager_TestNotification_SendUnmatched_PromRule(t *testing.T) {
assert.Empty(t, triggeredTestAlerts)
}
promProvider.Close()
})
}
}

View File

@@ -131,7 +131,7 @@ func NewTestManager(t *testing.T, testOpts *TestManagerOptions) *Manager {
meterStmtBuilder, err := meterstatementbuilder.NewFactory(metadataStore, flagger).New(ctx, providerSettings, cfg)
require.NoError(t, err)
bucketCache := querier.NewBucketCache(providerSettings, cache, 0, 0)
providerFactory := signozquerier.NewFactory(telemetryStore, prometheus, nil, metadataStore, traceStmtBuilder, aiTraceStmtBuilder, logStmtBuilder, auditStmtBuilder, metricStmtBuilder, meterStmtBuilder, traceOperatorStmtBuilder, bucketCache, flagger)
providerFactory := signozquerier.NewFactory(telemetryStore, prometheus, metadataStore, traceStmtBuilder, aiTraceStmtBuilder, logStmtBuilder, auditStmtBuilder, metricStmtBuilder, meterStmtBuilder, traceOperatorStmtBuilder, bucketCache, flagger)
mockQuerier, err := providerFactory.New(context.Background(), providerSettings, querier.Config{})
require.NoError(t, err)

View File

@@ -376,17 +376,11 @@ func (r *PromRule) String() string {
}
func (r *PromRule) RunAlertQuery(ctx context.Context, qs string, start, end time.Time, interval time.Duration) (promql.Matrix, error) {
q, err := r.prometheus.Engine().NewRangeQuery(ctx, r.prometheus.Storage(), nil, qs, start, end, interval)
res, err := r.prometheus.QueryRange(ctx, qs, start, end, interval)
if err != nil {
return nil, err
}
res := q.Exec(ctx)
if res.Err != nil {
return nil, res.Err
}
switch typ := res.Value.(type) {
case promql.Vector:
series := make([]promql.Series, 0, len(typ))

View File

@@ -9,8 +9,8 @@ import (
"github.com/stretchr/testify/assert"
"github.com/stretchr/testify/require"
pql "github.com/prometheus/prometheus/promql"
cmock "github.com/SigNoz/clickhouse-go-mock"
pql "github.com/prometheus/prometheus/promql"
"github.com/SigNoz/signoz/pkg/instrumentation/instrumentationtest"
"github.com/SigNoz/signoz/pkg/prometheus"
@@ -768,26 +768,11 @@ func TestPromRuleUnitCombinations(t *testing.T) {
},
}
// time_series_v4 cols of interest
fingerprintCols := []cmock.ColumnType{
{Name: "fingerprint", Type: "UInt64"},
{Name: "any(labels)", Type: "String"},
}
// samples_v4 columns
samplesCols := []cmock.ColumnType{
{Name: "metric_name", Type: "String"},
{Name: "fingerprint", Type: "UInt64"},
{Name: "unix_milli", Type: "Int64"},
{Name: "value", Type: "Float64"},
{Name: "flags", Type: "UInt32"},
}
// see Timestamps on base_rule
evalWindowMs := int64(5 * 60 * 1000) // 5 minutes in ms
evalTimeMs := evalTime.UnixMilli()
queryStart := ((evalTimeMs-2*evalWindowMs)/60000)*60000 + 1 // truncate to minute + 1ms
queryEnd := (evalTimeMs / 60000) * 60000 // truncate to minute
queryEnd := (evalTimeMs / 60000) * 60000 // truncate to minute
gridStart := queryEnd - evalWindowMs
cases := []struct {
targetUnit string
@@ -904,43 +889,19 @@ func TestPromRuleUnitCombinations(t *testing.T) {
for idx, c := range cases {
telemetryStore := telemetrystoretest.New(telemetrystore.Config{}, &queryMatcherAny{})
// single fingerprint with labels JSON
fingerprint := uint64(12345)
labelsJSON := `{"__name__":"test_metric"}`
fingerprintData := [][]any{
{fingerprint, labelsJSON},
}
fingerprintRows := cmock.NewRows(fingerprintCols, fingerprintData)
// create samples data from test case values
samplesData := make([][]any, len(c.values))
tsList := make([]int64, len(c.values))
vList := make([]float64, len(c.values))
for i, v := range c.values {
samplesData[i] = []any{
"test_metric",
fingerprint,
v.timestamp.UnixMilli(),
v.value,
uint32(0), // flags - 0 means normal value, 1 means stale, we are not doing staleness tests
}
tsList[i] = v.timestamp.UnixMilli()
vList[i] = v.value
}
samplesRows := cmock.NewRows(samplesCols, samplesData)
grid := prometheustest.LastSampleGrid(tsList, vList, gridStart, queryEnd, 60_000, 300_000)
// args: $1=metric_name (the __name__ matcher maps onto the column)
// args: $1-$3=group-key join conditions, $4-$6=samples conditions
telemetryStore.Mock().
ExpectQuery("SELECT fingerprint, any").
WithArgs("test_metric").
WillReturnRows(fingerprintRows)
// args: $1=metric_name IN (discovered names), $2=metric_name (subquery), $3=start, $4=end
telemetryStore.Mock().
ExpectQuery("SELECT metric_name, fingerprint, unix_milli").
WithArgs(
"test_metric",
"test_metric",
queryStart,
queryEnd,
).
WillReturnRows(samplesRows)
ExpectQuery("SELECT gkey").
WithArgs("test_metric", nil, nil, "test_metric", nil, nil).
WillReturnRows(cmock.NewRows(prometheustest.GridCols, [][]any{{`[["__name__","test_metric"]]`, grid}}))
promProvider := prometheustest.New(context.Background(), instrumentationtest.New().ToProviderSettings(), prometheus.Config{Timeout: 2 * time.Minute}, telemetryStore)
@@ -970,14 +931,12 @@ func TestPromRuleUnitCombinations(t *testing.T) {
rule, err := NewPromRule("69", valuer.GenerateUUID(), &postableRule, logger, promProvider, externalUrl)
if err != nil {
assert.NoError(t, err)
promProvider.Close()
continue
}
alertsFound, err := rule.Eval(context.Background(), evalTime)
if err != nil {
assert.NoError(t, err)
promProvider.Close()
continue
}
@@ -995,7 +954,6 @@ func TestPromRuleUnitCombinations(t *testing.T) {
assert.Equal(t, c.expectAlerts, foundCount, "case %d", idx)
}
promProvider.Close()
}
}
@@ -1027,12 +985,6 @@ func TestPromRuleNoData(t *testing.T) {
},
}
// time_series_v4 cols of interest
fingerprintCols := []cmock.ColumnType{
{Name: "fingerprint", Type: "UInt64"},
{Name: "any(labels)", Type: "String"},
}
cases := []struct {
values []struct {
timestamp time.Time
@@ -1054,15 +1006,11 @@ func TestPromRuleNoData(t *testing.T) {
for idx, c := range cases {
telemetryStore := telemetrystoretest.New(telemetrystore.Config{}, &queryMatcherAny{})
// no data
fingerprintData := [][]any{}
fingerprintRows := cmock.NewRows(fingerprintCols, fingerprintData)
// no rows == no data
telemetryStore.Mock().
ExpectQuery("SELECT fingerprint, any").
WithArgs("test_metric").
WillReturnRows(fingerprintRows)
ExpectQuery("SELECT gkey").
WithArgs("test_metric", nil, nil, "test_metric", nil, nil).
WillReturnRows(cmock.NewRows(prometheustest.GridCols, [][]any{}))
promProvider := prometheustest.New(context.Background(), instrumentationtest.New().ToProviderSettings(), prometheus.Config{Timeout: 2 * time.Minute}, telemetryStore)
@@ -1087,14 +1035,12 @@ func TestPromRuleNoData(t *testing.T) {
rule, err := NewPromRule("69", valuer.GenerateUUID(), &postableRule, logger, promProvider, externalUrl)
if err != nil {
assert.NoError(t, err)
promProvider.Close()
continue
}
alertsFound, err := rule.Eval(context.Background(), evalTime)
if err != nil {
assert.NoError(t, err)
promProvider.Close()
continue
}
@@ -1107,7 +1053,6 @@ func TestPromRuleNoData(t *testing.T) {
}
}
promProvider.Close()
}
}
@@ -1139,24 +1084,11 @@ func TestMultipleThresholdPromRule(t *testing.T) {
},
}
fingerprintCols := []cmock.ColumnType{
{Name: "fingerprint", Type: "UInt64"},
{Name: "any(labels)", Type: "String"},
}
samplesCols := []cmock.ColumnType{
{Name: "metric_name", Type: "String"},
{Name: "fingerprint", Type: "UInt64"},
{Name: "unix_milli", Type: "Int64"},
{Name: "value", Type: "Float64"},
{Name: "flags", Type: "UInt32"},
}
// see .Timestamps of base rule
evalWindowMs := int64(5 * 60 * 1000)
evalTimeMs := evalTime.UnixMilli()
queryStart := ((evalTimeMs-2*evalWindowMs)/60000)*60000 + 1
queryEnd := (evalTimeMs / 60000) * 60000
gridStart := queryEnd - evalWindowMs
cases := []struct {
targetUnit string
@@ -1250,39 +1182,19 @@ func TestMultipleThresholdPromRule(t *testing.T) {
for idx, c := range cases {
telemetryStore := telemetrystoretest.New(telemetrystore.Config{}, &queryMatcherAny{})
fingerprint := uint64(12345)
labelsJSON := `{"__name__":"test_metric"}`
fingerprintData := [][]any{
{fingerprint, labelsJSON},
}
fingerprintRows := cmock.NewRows(fingerprintCols, fingerprintData)
samplesData := make([][]any, len(c.values))
tsList := make([]int64, len(c.values))
vList := make([]float64, len(c.values))
for i, v := range c.values {
samplesData[i] = []any{
"test_metric",
fingerprint,
v.timestamp.UnixMilli(),
v.value,
uint32(0),
}
tsList[i] = v.timestamp.UnixMilli()
vList[i] = v.value
}
samplesRows := cmock.NewRows(samplesCols, samplesData)
grid := prometheustest.LastSampleGrid(tsList, vList, gridStart, queryEnd, 60_000, 300_000)
// args: $1-$3=group-key join conditions, $4-$6=samples conditions
telemetryStore.Mock().
ExpectQuery("SELECT fingerprint, any").
WithArgs("test_metric").
WillReturnRows(fingerprintRows)
telemetryStore.Mock().
ExpectQuery("SELECT metric_name, fingerprint, unix_milli").
WithArgs(
"test_metric",
"test_metric",
queryStart,
queryEnd,
).
WillReturnRows(samplesRows)
ExpectQuery("SELECT gkey").
WithArgs("test_metric", nil, nil, "test_metric", nil, nil).
WillReturnRows(cmock.NewRows(prometheustest.GridCols, [][]any{{`[["__name__","test_metric"]]`, grid}}))
promProvider := prometheustest.New(context.Background(), instrumentationtest.New().ToProviderSettings(), prometheus.Config{Timeout: 2 * time.Minute}, telemetryStore)
@@ -1319,14 +1231,12 @@ func TestMultipleThresholdPromRule(t *testing.T) {
rule, err := NewPromRule("69", valuer.GenerateUUID(), &postableRule, logger, promProvider, externalUrl)
if err != nil {
assert.NoError(t, err)
promProvider.Close()
continue
}
alertsFound, err := rule.Eval(context.Background(), evalTime)
if err != nil {
assert.NoError(t, err)
promProvider.Close()
continue
}
@@ -1344,7 +1254,6 @@ func TestMultipleThresholdPromRule(t *testing.T) {
assert.Equal(t, c.expectAlerts, foundCount, "case %d", idx)
}
promProvider.Close()
}
}
@@ -1378,27 +1287,6 @@ func TestPromRule_NoData(t *testing.T) {
},
}
// time_series_v4 cols of interest
fingerprintCols := []cmock.ColumnType{
{Name: "fingerprint", Type: "UInt64"},
{Name: "any(labels)", Type: "String"},
}
// samples_v4 columns
samplesCols := []cmock.ColumnType{
{Name: "metric_name", Type: "String"},
{Name: "fingerprint", Type: "UInt64"},
{Name: "unix_milli", Type: "Int64"},
{Name: "value", Type: "Float64"},
{Name: "flags", Type: "UInt32"},
}
// see Timestamps on base_rule
evalWindowMs := int64(5 * 60 * 1000) // 5 minutes in ms
evalTimeMs := evalTime.UnixMilli()
queryStart := ((evalTimeMs-2*evalWindowMs)/60000)*60000 + 1 // truncate to minute + 1ms
queryEnd := (evalTimeMs / 60000) * 60000 // truncate to minute
cases := []struct {
description string
alertOnAbsent bool
@@ -1430,18 +1318,11 @@ func TestPromRule_NoData(t *testing.T) {
telemetryStore := telemetrystoretest.New(telemetrystore.Config{}, &queryMatcherAny{})
// single fingerprint with labels JSON
fingerprint := uint64(12345)
labelsJSON := `{"__name__":"test_metric"}`
// no rows == no data
telemetryStore.Mock().
ExpectQuery("SELECT fingerprint, any").
WithArgs("test_metric").
WillReturnRows(cmock.NewRows(fingerprintCols, [][]any{{fingerprint, labelsJSON}}))
telemetryStore.Mock().
ExpectQuery("SELECT metric_name, fingerprint, unix_milli").
WithArgs("test_metric", "test_metric", queryStart, queryEnd).
WillReturnRows(cmock.NewRows(samplesCols, [][]any{}))
ExpectQuery("SELECT gkey").
WithArgs("test_metric", nil, nil, "test_metric", nil, nil).
WillReturnRows(cmock.NewRows(prometheustest.GridCols, [][]any{}))
promProvider := prometheustest.New(
context.Background(),
@@ -1450,7 +1331,6 @@ func TestPromRule_NoData(t *testing.T) {
telemetryStore,
)
defer func() {
_ = promProvider.Close()
}()
externalUrl := mustParseURL(t, "http://localhost:8080")
@@ -1510,19 +1390,6 @@ func TestPromRule_NoData_AbsentFor(t *testing.T) {
},
}
fingerprintCols := []cmock.ColumnType{
{Name: "fingerprint", Type: "UInt64"},
{Name: "any(labels)", Type: "String"},
}
samplesCols := []cmock.ColumnType{
{Name: "metric_name", Type: "String"},
{Name: "fingerprint", Type: "UInt64"},
{Name: "unix_milli", Type: "Int64"},
{Name: "value", Type: "Float64"},
{Name: "flags", Type: "UInt32"},
}
cases := []struct {
description string
absentFor uint64 // grace period in minutes
@@ -1556,43 +1423,30 @@ func TestPromRule_NoData_AbsentFor(t *testing.T) {
telemetryStore := telemetrystoretest.New(telemetrystore.Config{}, &queryMatcherAny{})
fingerprint := uint64(12345)
labelsJSON := `{"__name__":"test_metric"}`
// Helper to calculate query time range for an eval time
calcQueryRange := func(evalTime time.Time) (int64, int64) {
evalTimeMs := evalTime.UnixMilli()
queryStart := ((evalTimeMs-2*evalWindow.Milliseconds())/60000)*60000 + 1
queryEnd := (evalTimeMs / 60000) * 60000
return queryStart, queryEnd
// Grid an eval at this time evaluates over (see Timestamps on
// base_rule).
calcGrid := func(evalTime time.Time) (int64, int64) {
gridEnd := (evalTime.UnixMilli() / 60000) * 60000
return gridEnd - evalWindow.Milliseconds(), gridEnd
}
// First eval (t1) - with data
queryStart1, queryEnd1 := calcQueryRange(t1)
// First eval (t1) - with data: points in the past relative to t1
gridStart1, gridEnd1 := calcGrid(t1)
grid1 := prometheustest.LastSampleGrid(
[]int64{baseTime.UnixMilli(), baseTime.Add(1 * time.Minute).UnixMilli(), baseTime.Add(2 * time.Minute).UnixMilli()},
[]float64{100, 100, 100},
gridStart1, gridEnd1, 60_000, 300_000,
)
telemetryStore.Mock().
ExpectQuery("SELECT fingerprint, any").
WithArgs("test_metric").
WillReturnRows(cmock.NewRows(fingerprintCols, [][]any{{fingerprint, labelsJSON}}))
telemetryStore.Mock().
ExpectQuery("SELECT metric_name, fingerprint, unix_milli").
WithArgs("test_metric", "test_metric", queryStart1, queryEnd1).
WillReturnRows(cmock.NewRows(samplesCols, [][]any{
// Data points in the past relative to t1
{"test_metric", fingerprint, baseTime.UnixMilli(), 100.0, uint32(0)},
{"test_metric", fingerprint, baseTime.Add(1 * time.Minute).UnixMilli(), 100.0, uint32(0)},
{"test_metric", fingerprint, baseTime.Add(2 * time.Minute).UnixMilli(), 100.0, uint32(0)},
}))
ExpectQuery("SELECT gkey").
WithArgs("test_metric", nil, nil, "test_metric", nil, nil).
WillReturnRows(cmock.NewRows(prometheustest.GridCols, [][]any{{`[["__name__","test_metric"]]`, grid1}}))
// Second eval (t2) - no data
queryStart2, queryEnd2 := calcQueryRange(t2)
telemetryStore.Mock().
ExpectQuery("SELECT fingerprint, any").
WithArgs("test_metric").
WillReturnRows(cmock.NewRows(fingerprintCols, [][]any{{fingerprint, labelsJSON}}))
telemetryStore.Mock().
ExpectQuery("SELECT metric_name, fingerprint, unix_milli").
WithArgs("test_metric", "test_metric", queryStart2, queryEnd2).
WillReturnRows(cmock.NewRows(samplesCols, [][]any{})) // empty - no data
ExpectQuery("SELECT gkey").
WithArgs("test_metric", nil, nil, "test_metric", nil, nil).
WillReturnRows(cmock.NewRows(prometheustest.GridCols, [][]any{}))
promProvider := prometheustest.New(
context.Background(),
@@ -1601,7 +1455,6 @@ func TestPromRule_NoData_AbsentFor(t *testing.T) {
telemetryStore,
)
defer func() {
_ = promProvider.Close()
}()
externalUrl := mustParseURL(t, "http://localhost:8080")
@@ -1652,32 +1505,15 @@ func TestPromRuleEval_RequireMinPoints(t *testing.T) {
},
}
fingerprintCols := []cmock.ColumnType{
{Name: "fingerprint", Type: "UInt64"},
{Name: "any(labels)", Type: "String"},
}
fingerprint := uint64(12345)
fingerprintData := [][]any{{fingerprint, `{"__name__":"test_metric"}`}}
samplesCols := []cmock.ColumnType{
{Name: "metric_name", Type: "String"},
{Name: "fingerprint", Type: "UInt64"},
{Name: "unix_milli", Type: "Int64"},
{Name: "value", Type: "Float64"},
{Name: "flags", Type: "UInt32"},
}
samplesData := [][]any{
{"test_metric", fingerprint, baseTime.UnixMilli(), 100.0, 0},
{"test_metric", fingerprint, baseTime.Add(time.Minute).UnixMilli(), 150.0, 0},
{"test_metric", fingerprint, baseTime.Add(2 * time.Minute).UnixMilli(), 250.0, 0},
}
sampleTs := []int64{baseTime.UnixMilli(), baseTime.Add(time.Minute).UnixMilli(), baseTime.Add(2 * time.Minute).UnixMilli()}
sampleVs := []float64{100, 150, 250}
targetForAlert := 200.0
targetForNoAlert := 500.0
// see Timestamps on base_rule
evalTimeMs := evalTime.UnixMilli()
queryStart := ((evalTimeMs-evalWindow.Milliseconds()-lookBackDelta.Milliseconds())/60000)*60000 + 1 // truncate to minute + 1ms
queryEnd := (evalTimeMs / 60000) * 60000 // truncate to minute
queryEnd := (evalTimeMs / 60000) * 60000 // truncate to minute
gridStart := queryEnd - evalWindow.Milliseconds()
cases := []struct {
description string
@@ -1746,14 +1582,11 @@ func TestPromRuleEval_RequireMinPoints(t *testing.T) {
t.Run(c.description, func(t *testing.T) {
telemetryStore := telemetrystoretest.New(telemetrystore.Config{}, &queryMatcherAny{})
grid := prometheustest.LastSampleGrid(sampleTs, sampleVs, gridStart, queryEnd, 60_000, lookBackDelta.Milliseconds())
telemetryStore.Mock().
ExpectQuery("SELECT fingerprint, any").
WithArgs("test_metric").
WillReturnRows(cmock.NewRows(fingerprintCols, fingerprintData))
telemetryStore.Mock().
ExpectQuery("SELECT metric_name, fingerprint, unix_milli").
WithArgs("test_metric", "test_metric", queryStart, queryEnd).
WillReturnRows(cmock.NewRows(samplesCols, samplesData))
ExpectQuery("SELECT gkey").
WithArgs("test_metric", nil, nil, "test_metric", nil, nil).
WillReturnRows(cmock.NewRows(prometheustest.GridCols, [][]any{{`[["__name__","test_metric"]]`, grid}}))
promProvider := prometheustest.New(
context.Background(),
instrumentationtest.New().ToProviderSettings(),
@@ -1761,7 +1594,6 @@ func TestPromRuleEval_RequireMinPoints(t *testing.T) {
telemetryStore,
)
defer func() {
_ = promProvider.Close()
}()
externalUrl := mustParseURL(t, "http://localhost:8080")

View File

@@ -40,7 +40,6 @@ func prepareQuerierForMetrics(t *testing.T, telemetryStore telemetrystore.Teleme
telemetryStore,
metadataStore,
nil, // prometheus
nil, // promV2
nil, // traceStmtBuilder
nil, // aiTraceStmtBuilder
nil, // logStmtBuilder
@@ -76,7 +75,6 @@ func prepareQuerierForLogs(t *testing.T, telemetryStore telemetrystore.Telemetry
telemetryStore,
metadataStore,
nil, // prometheus
nil, // promV2
nil, // traceStmtBuilder
nil, // aiTraceStmtBuilder
logStmtBuilder,
@@ -113,7 +111,6 @@ func prepareQuerierForTraces(t *testing.T, telemetryStore telemetrystore.Telemet
telemetryStore,
metadataStore,
nil, // prometheus
nil, // promV2
traceStmtBuilder,
nil, // aiTraceStmtBuilder
nil, // logStmtBuilder

View File

@@ -45,7 +45,6 @@ import (
"github.com/SigNoz/signoz/pkg/pprof/httppprof"
"github.com/SigNoz/signoz/pkg/pprof/nooppprof"
"github.com/SigNoz/signoz/pkg/prometheus"
"github.com/SigNoz/signoz/pkg/prometheus/clickhouseprometheus"
"github.com/SigNoz/signoz/pkg/prometheus/clickhouseprometheusv2"
"github.com/SigNoz/signoz/pkg/querier"
"github.com/SigNoz/signoz/pkg/querier/signozquerier"
@@ -270,7 +269,6 @@ func NewTelemetryStoreProviderFactories() factory.NamedMap[factory.ProviderFacto
func NewPrometheusProviderFactories(telemetryStore telemetrystore.TelemetryStore) factory.NamedMap[factory.ProviderFactory[prometheus.Prometheus, prometheus.Config]] {
return factory.MustNewNamedMap(
clickhouseprometheus.NewFactory(telemetryStore),
clickhouseprometheusv2.NewFactory(telemetryStore),
)
}
@@ -313,9 +311,9 @@ func NewStatsReporterProviderFactories(aggregator statsreporter.Aggregator, orgG
)
}
func NewQuerierProviderFactories(telemetryStore telemetrystore.TelemetryStore, prometheus prometheus.Prometheus, promV2 prometheus.Prometheus, metadataStore telemetrytypes.MetadataStore, traceStmtBuilder qbtypes.StatementBuilder[qbtypes.TraceAggregation], aiTraceStmtBuilder qbtypes.StatementBuilder[qbtypes.TraceAggregation], logStmtBuilder qbtypes.StatementBuilder[qbtypes.LogAggregation], auditStmtBuilder qbtypes.StatementBuilder[qbtypes.LogAggregation], metricStmtBuilder qbtypes.StatementBuilder[qbtypes.MetricAggregation], meterStmtBuilder qbtypes.StatementBuilder[qbtypes.MetricAggregation], traceOperatorStmtBuilder qbtypes.TraceOperatorStatementBuilder, bucketCache querier.BucketCache, flagger flagger.Flagger) factory.NamedMap[factory.ProviderFactory[querier.Querier, querier.Config]] {
func NewQuerierProviderFactories(telemetryStore telemetrystore.TelemetryStore, prometheus prometheus.Prometheus, metadataStore telemetrytypes.MetadataStore, traceStmtBuilder qbtypes.StatementBuilder[qbtypes.TraceAggregation], aiTraceStmtBuilder qbtypes.StatementBuilder[qbtypes.TraceAggregation], logStmtBuilder qbtypes.StatementBuilder[qbtypes.LogAggregation], auditStmtBuilder qbtypes.StatementBuilder[qbtypes.LogAggregation], metricStmtBuilder qbtypes.StatementBuilder[qbtypes.MetricAggregation], meterStmtBuilder qbtypes.StatementBuilder[qbtypes.MetricAggregation], traceOperatorStmtBuilder qbtypes.TraceOperatorStatementBuilder, bucketCache querier.BucketCache, flagger flagger.Flagger) factory.NamedMap[factory.ProviderFactory[querier.Querier, querier.Config]] {
return factory.MustNewNamedMap(
signozquerier.NewFactory(telemetryStore, prometheus, promV2, metadataStore, traceStmtBuilder, aiTraceStmtBuilder, logStmtBuilder, auditStmtBuilder, metricStmtBuilder, meterStmtBuilder, traceOperatorStmtBuilder, bucketCache, flagger),
signozquerier.NewFactory(telemetryStore, prometheus, metadataStore, traceStmtBuilder, aiTraceStmtBuilder, logStmtBuilder, auditStmtBuilder, metricStmtBuilder, meterStmtBuilder, traceOperatorStmtBuilder, bucketCache, flagger),
)
}

View File

@@ -40,7 +40,6 @@ import (
"github.com/SigNoz/signoz/pkg/modules/tag/impltag"
"github.com/SigNoz/signoz/pkg/modules/user/impluser"
"github.com/SigNoz/signoz/pkg/prometheus"
"github.com/SigNoz/signoz/pkg/prometheus/clickhouseprometheusv2"
"github.com/SigNoz/signoz/pkg/querier"
"github.com/SigNoz/signoz/pkg/queryparser"
"github.com/SigNoz/signoz/pkg/ruler"
@@ -309,11 +308,6 @@ func New(
retentionGetter := implretention.NewGetter(implretention.NewStore(sqlstore))
// promV2 is the clickhousev2 provider handed to the querier for shadow
// comparison and pinned serving (declared before the serving provider,
// whose variable shadows the package name below).
var promV2 prometheus.Prometheus
// Initialize prometheus from the available prometheus provider factories
prometheus, err := factory.NewProviderFromNamedMap(
ctx,
@@ -326,23 +320,6 @@ func New(
return nil, err
}
// With the default provider, also stand up the clickhousev2 provider for
// the querier: PromQL queries shadow-compare against it behind the
// use_prometheus_clickhouse_v2 flag (see pkg/querier/promql_shadow.go).
// It never serves by default. An explicit
// prometheus::provider: clickhousev2 makes v2 the serving provider
// outright, so there is nothing to compare against.
if config.Prometheus.Provider() == "clickhouse" {
v2Config := config.Prometheus
// The v2 engine only evaluates shadow and pinned queries; disable its
// active query tracker so two trackers never share a file.
v2Config.ActiveQueryTrackerConfig.Enabled = false
promV2, err = clickhouseprometheusv2.New(ctx, providerSettings, v2Config, telemetrystore)
if err != nil {
return nil, err
}
}
// Assemble the query stack (metadata store, statement builders, bucket cache) once,
// and reuse the single metadata store everywhere downstream.
telemetryMetadataStore, traceStmtBuilder, aiTraceStmtBuilder, logStmtBuilder, auditStmtBuilder, metricStmtBuilder, meterStmtBuilder, traceOperatorStmtBuilder, bucketCache, err := newQueryStack(ctx, providerSettings, config, telemetrystore, cache, flagger)
@@ -355,7 +332,7 @@ func New(
ctx,
providerSettings,
config.Querier,
NewQuerierProviderFactories(telemetrystore, prometheus, promV2, telemetryMetadataStore, traceStmtBuilder, aiTraceStmtBuilder, logStmtBuilder, auditStmtBuilder, metricStmtBuilder, meterStmtBuilder, traceOperatorStmtBuilder, bucketCache, flagger),
NewQuerierProviderFactories(telemetrystore, prometheus, telemetryMetadataStore, traceStmtBuilder, aiTraceStmtBuilder, logStmtBuilder, auditStmtBuilder, metricStmtBuilder, meterStmtBuilder, traceOperatorStmtBuilder, bucketCache, flagger),
config.Querier.Provider(),
)
if err != nil {

View File

@@ -388,14 +388,6 @@ type QueryRangeRequest struct {
// NoCache is a flag to disable caching for the request.
NoCache bool `json:"noCache,omitempty"`
// PromQLProvider serves this request's PromQL queries via the named
// prometheus provider ("clickhousev2") instead of the default — the same
// data read through a different implementation. It is set from the
// X-SigNoz-PromQL-Provider header by the API handler, never from the
// body: a rollout-scoped comparison hook for integration tests and
// support should not become part of the public request schema.
PromQLProvider string `json:"-"`
FormatOptions *FormatOptions `json:"formatOptions,omitempty"`
}

View File

@@ -175,7 +175,6 @@ def make_query_request(
variables: dict | None = None,
no_cache: bool = True,
timeout: int = QUERY_TIMEOUT,
headers: dict | None = None,
) -> requests.Response:
if format_options is None:
format_options = {"formatTableResultForUI": False, "fillGaps": False}
@@ -195,7 +194,7 @@ def make_query_request(
return requests.post(
signoz.self.host_configs["8080"].get("/api/v5/query_range"),
timeout=timeout,
headers={"authorization": f"Bearer {token}", **(headers or {})},
headers={"authorization": f"Bearer {token}"},
json=payload,
)

View File

@@ -1,5 +1,5 @@
{
"note": "Divergences of the CURRENT promql serving path from the upstream reference engine, enforced exactly by 01_upstream_corpus.py in both directions. These document shipped defects, not test debt: the dominant class is the v1 remote-read fetch injecting a synthetic 'fingerprint' label into every series (pkg/prometheus/clickhouseprometheus/json.go), which breaks without() grouping and default vector matching. Entries must be REMOVED as the serving path is fixed or swapped. Second class, and the bulk of the entries below: promql_query.go drops NaN and +/-Inf from results, mirroring the builder path in consume.go, so every case whose expected output carries a non-finite value diverges on both legs. That class is a product decision rather than a defect, so it is not part of the burn-down.",
"note": "Divergences of the clickhousev2 provider from the upstream reference engine, enforced exactly by 01_upstream_corpus.py in both directions: a new divergence is a regression, and an entry that starts passing must be removed. The entries are the non-finite values the API filters and the Kahan-summation class.",
"divergences": {
"aggregators.test:630[base]": "expected output is entirely Inf; promql_query.go drops non-finite values, so no series is emitted",
"aggregators.test:630[instant-coarse]": "expected output is entirely Inf; promql_query.go drops non-finite values, so no series is emitted",
@@ -15,8 +15,16 @@
"aggregators.test:645[instant-coarse]": "expected output is entirely NaN; promql_query.go drops non-finite values, so no series is emitted",
"aggregators.test:648[base]": "expected output is entirely NaN; promql_query.go drops non-finite values, so no series is emitted",
"aggregators.test:648[instant-coarse]": "expected output is entirely NaN; promql_query.go drops non-finite values, so no series is emitted",
"aggregators.test:651[base]": "avg over near-max-float64 values: engine's incremental mean never forms the overflowing sum; avgForEach sums then divides, overflowing to +Inf",
"aggregators.test:651[instant-coarse]": "same as aggregators.test:651[base] on the coarse-step grid variant",
"aggregators.test:654[base]": "avg over near-min-float64 values: engine's incremental mean never forms the overflowing sum; avgForEach overflows to -Inf",
"aggregators.test:654[instant-coarse]": "same as aggregators.test:654[base] on the coarse-step grid variant",
"aggregators.test:661[base]": "expected output is entirely NaN; promql_query.go drops non-finite values, so no series is emitted",
"aggregators.test:661[instant-coarse]": "expected output is entirely NaN; promql_query.go drops non-finite values, so no series is emitted",
"aggregators.test:687[base]": "sum over {1e100, -1e100, small}: engine uses Kahan compensated summation; sumForEach's naive summation loses the small terms to cancellation and returns 0",
"aggregators.test:687[instant-coarse]": "same as aggregators.test:687[base] on the coarse-step grid variant",
"aggregators.test:695[base]": "avg over {1e100, -1e100, small}: same Kahan-vs-naive cancellation as aggregators.test:687, divided by count",
"aggregators.test:695[instant-coarse]": "same as aggregators.test:695[base] on the coarse-step grid variant",
"aggregators.test:698[base]": "expected output is entirely Inf; promql_query.go drops non-finite values, so no series is emitted",
"aggregators.test:698[instant-coarse]": "expected output is entirely Inf; promql_query.go drops non-finite values, so no series is emitted",
"aggregators.test:702[base]": "expected output is entirely Inf; promql_query.go drops non-finite values, so no series is emitted",
@@ -73,6 +81,10 @@
"aggregators.test:963[instant-coarse]": "expected output is entirely NaN; promql_query.go drops non-finite values, so no series is emitted",
"aggregators.test:966[base]": "expected output is entirely NaN; promql_query.go drops non-finite values, so no series is emitted",
"aggregators.test:966[instant-coarse]": "expected output is entirely NaN; promql_query.go drops non-finite values, so no series is emitted",
"functions.test:1084[instant-coarse]": "sum_over_time over a window containing ±1e100: the disjoint coarse-step form's arraySum slide is naive summation, cancelling to 0 (the base variant's W>64 shape falls back to the engine and is exact)",
"functions.test:1087[instant-coarse]": "avg_over_time, same window and cancellation as functions.test:1084[instant-coarse]",
"functions.test:1149[base]": "avg_over_time over ±2.258e220-magnitude samples: engine's Kahan-compensated incremental mean cancels exactly to 0; the bucketed form's naive slide summation leaves a ~1e202 residue",
"functions.test:1149[instant-coarse]": "same as functions.test:1149[base] through the disjoint coarse-step form",
"operators.test:533[base]": "expected output is entirely NaN; promql_query.go drops non-finite values, so no series is emitted",
"operators.test:533[instant-coarse]": "expected output is entirely NaN; promql_query.go drops non-finite values, so no series is emitted",
"operators.test:539[base]": "expected output is entirely NaN; promql_query.go drops non-finite values, so no series is emitted",

View File

@@ -1,128 +0,0 @@
{
"note": "Divergences of the clickhousev2 provider (pinned via X-SigNoz-PromQL-Provider) from the upstream reference engine, enforced exactly by 01_upstream_corpus.py in both directions. This ledger is the rollout scorecard for the provider swap: the default provider cannot be replaced by clickhousev2 while anything is listed here. Entries must carry the defect's cause and be REMOVED as the provider is fixed. Current class: the engine aggregates floats with Kahan compensated summation (sum, sum_over_time) and an overflow-free incremental mean (avg); ClickHouse's sumForEach/avgForEach/arraySum are naive, so extreme-magnitude corpus data (±1e100 cancellation, ±1.8e308 overflow) diverges on transpiled plans. Burn-down candidates: sumKahanForEach for the cancellation class; the overflow class needs an incremental-mean aggregate ClickHouse does not have. Second class, and the bulk of the entries below: promql_query.go drops NaN and +/-Inf from results, mirroring the builder path in consume.go, so every case whose expected output carries a non-finite value diverges on both legs. That class is a product decision rather than a defect, so it is not part of the burn-down.",
"divergences": {
"aggregators.test:630[base]": "expected output is entirely Inf; promql_query.go drops non-finite values, so no series is emitted",
"aggregators.test:630[instant-coarse]": "expected output is entirely Inf; promql_query.go drops non-finite values, so no series is emitted",
"aggregators.test:633[base]": "expected output is entirely Inf; promql_query.go drops non-finite values, so no series is emitted",
"aggregators.test:633[instant-coarse]": "expected output is entirely Inf; promql_query.go drops non-finite values, so no series is emitted",
"aggregators.test:636[base]": "expected output is entirely NaN; promql_query.go drops non-finite values, so no series is emitted",
"aggregators.test:636[instant-coarse]": "expected output is entirely NaN; promql_query.go drops non-finite values, so no series is emitted",
"aggregators.test:639[base]": "expected output is entirely -Inf; promql_query.go drops non-finite values, so no series is emitted",
"aggregators.test:639[instant-coarse]": "expected output is entirely -Inf; promql_query.go drops non-finite values, so no series is emitted",
"aggregators.test:642[base]": "expected output is entirely -Inf; promql_query.go drops non-finite values, so no series is emitted",
"aggregators.test:642[instant-coarse]": "expected output is entirely -Inf; promql_query.go drops non-finite values, so no series is emitted",
"aggregators.test:645[base]": "expected output is entirely NaN; promql_query.go drops non-finite values, so no series is emitted",
"aggregators.test:645[instant-coarse]": "expected output is entirely NaN; promql_query.go drops non-finite values, so no series is emitted",
"aggregators.test:648[base]": "expected output is entirely NaN; promql_query.go drops non-finite values, so no series is emitted",
"aggregators.test:648[instant-coarse]": "expected output is entirely NaN; promql_query.go drops non-finite values, so no series is emitted",
"aggregators.test:651[base]": "avg over near-max-float64 values: engine's incremental mean never forms the overflowing sum; avgForEach sums then divides, overflowing to +Inf",
"aggregators.test:651[instant-coarse]": "same as aggregators.test:651[base] on the coarse-step grid variant",
"aggregators.test:654[base]": "avg over near-min-float64 values: engine's incremental mean never forms the overflowing sum; avgForEach overflows to -Inf",
"aggregators.test:654[instant-coarse]": "same as aggregators.test:654[base] on the coarse-step grid variant",
"aggregators.test:661[base]": "expected output is entirely NaN; promql_query.go drops non-finite values, so no series is emitted",
"aggregators.test:661[instant-coarse]": "expected output is entirely NaN; promql_query.go drops non-finite values, so no series is emitted",
"aggregators.test:687[base]": "sum over {1e100, -1e100, small}: engine uses Kahan compensated summation; sumForEach's naive summation loses the small terms to cancellation and returns 0",
"aggregators.test:687[instant-coarse]": "same as aggregators.test:687[base] on the coarse-step grid variant",
"aggregators.test:695[base]": "avg over {1e100, -1e100, small}: same Kahan-vs-naive cancellation as aggregators.test:687, divided by count",
"aggregators.test:695[instant-coarse]": "same as aggregators.test:695[base] on the coarse-step grid variant",
"aggregators.test:698[base]": "expected output is entirely Inf; promql_query.go drops non-finite values, so no series is emitted",
"aggregators.test:698[instant-coarse]": "expected output is entirely Inf; promql_query.go drops non-finite values, so no series is emitted",
"aggregators.test:702[base]": "expected output is entirely Inf; promql_query.go drops non-finite values, so no series is emitted",
"aggregators.test:702[instant-coarse]": "expected output is entirely Inf; promql_query.go drops non-finite values, so no series is emitted",
"aggregators.test:706[base]": "expected output is entirely -Inf; promql_query.go drops non-finite values, so no series is emitted",
"aggregators.test:706[instant-coarse]": "expected output is entirely -Inf; promql_query.go drops non-finite values, so no series is emitted",
"aggregators.test:710[base]": "expected output is entirely -Inf; promql_query.go drops non-finite values, so no series is emitted",
"aggregators.test:710[instant-coarse]": "expected output is entirely -Inf; promql_query.go drops non-finite values, so no series is emitted",
"aggregators.test:714[base]": "expected output is entirely NaN; promql_query.go drops non-finite values, so no series is emitted",
"aggregators.test:714[instant-coarse]": "expected output is entirely NaN; promql_query.go drops non-finite values, so no series is emitted",
"aggregators.test:717[base]": "expected output is entirely NaN; promql_query.go drops non-finite values, so no series is emitted",
"aggregators.test:717[instant-coarse]": "expected output is entirely NaN; promql_query.go drops non-finite values, so no series is emitted",
"aggregators.test:720[base]": "expected output is entirely NaN; promql_query.go drops non-finite values, so no series is emitted",
"aggregators.test:720[instant-coarse]": "expected output is entirely NaN; promql_query.go drops non-finite values, so no series is emitted",
"aggregators.test:724[base]": "expected output is entirely NaN; promql_query.go drops non-finite values, so no series is emitted",
"aggregators.test:724[instant-coarse]": "expected output is entirely NaN; promql_query.go drops non-finite values, so no series is emitted",
"aggregators.test:862[base]": "expected output is entirely NaN; promql_query.go drops non-finite values, so no series is emitted",
"aggregators.test:862[instant-coarse]": "expected output is entirely NaN; promql_query.go drops non-finite values, so no series is emitted",
"aggregators.test:865[base]": "expected output is entirely NaN; promql_query.go drops non-finite values, so no series is emitted",
"aggregators.test:865[instant-coarse]": "expected output is entirely NaN; promql_query.go drops non-finite values, so no series is emitted",
"aggregators.test:868[base]": "1 of 3 expected points are NaN; promql_query.go drops non-finite values, so those timestamps are missing",
"aggregators.test:868[instant-coarse]": "1 of 3 expected points are NaN; promql_query.go drops non-finite values, so those timestamps are missing",
"aggregators.test:873[base]": "1 of 3 expected points are NaN; promql_query.go drops non-finite values, so those timestamps are missing",
"aggregators.test:873[instant-coarse]": "1 of 3 expected points are NaN; promql_query.go drops non-finite values, so those timestamps are missing",
"aggregators.test:885[base]": "expected output is entirely NaN; promql_query.go drops non-finite values, so no series is emitted",
"aggregators.test:885[instant-coarse]": "expected output is entirely NaN; promql_query.go drops non-finite values, so no series is emitted",
"aggregators.test:888[base]": "expected output is entirely NaN; promql_query.go drops non-finite values, so no series is emitted",
"aggregators.test:888[instant-coarse]": "expected output is entirely NaN; promql_query.go drops non-finite values, so no series is emitted",
"aggregators.test:891[base]": "1 of 3 expected points are NaN; promql_query.go drops non-finite values, so those timestamps are missing",
"aggregators.test:891[instant-coarse]": "1 of 3 expected points are NaN; promql_query.go drops non-finite values, so those timestamps are missing",
"aggregators.test:896[base]": "1 of 3 expected points are NaN; promql_query.go drops non-finite values, so those timestamps are missing",
"aggregators.test:896[instant-coarse]": "1 of 3 expected points are NaN; promql_query.go drops non-finite values, so those timestamps are missing",
"aggregators.test:906[base]": "expected output is entirely NaN; promql_query.go drops non-finite values, so no series is emitted",
"aggregators.test:906[instant-coarse]": "expected output is entirely NaN; promql_query.go drops non-finite values, so no series is emitted",
"aggregators.test:909[base]": "expected output is entirely NaN; promql_query.go drops non-finite values, so no series is emitted",
"aggregators.test:909[instant-coarse]": "expected output is entirely NaN; promql_query.go drops non-finite values, so no series is emitted",
"aggregators.test:919[base]": "expected output is entirely NaN; promql_query.go drops non-finite values, so no series is emitted",
"aggregators.test:919[instant-coarse]": "expected output is entirely NaN; promql_query.go drops non-finite values, so no series is emitted",
"aggregators.test:922[base]": "expected output is entirely NaN; promql_query.go drops non-finite values, so no series is emitted",
"aggregators.test:922[instant-coarse]": "expected output is entirely NaN; promql_query.go drops non-finite values, so no series is emitted",
"aggregators.test:925[base]": "1 of 3 expected points are NaN; promql_query.go drops non-finite values, so those timestamps are missing",
"aggregators.test:925[instant-coarse]": "1 of 3 expected points are NaN; promql_query.go drops non-finite values, so those timestamps are missing",
"aggregators.test:930[base]": "1 of 3 expected points are NaN; promql_query.go drops non-finite values, so those timestamps are missing",
"aggregators.test:930[instant-coarse]": "1 of 3 expected points are NaN; promql_query.go drops non-finite values, so those timestamps are missing",
"aggregators.test:942[base]": "expected output is entirely NaN; promql_query.go drops non-finite values, so no series is emitted",
"aggregators.test:942[instant-coarse]": "expected output is entirely NaN; promql_query.go drops non-finite values, so no series is emitted",
"aggregators.test:945[base]": "expected output is entirely NaN; promql_query.go drops non-finite values, so no series is emitted",
"aggregators.test:945[instant-coarse]": "expected output is entirely NaN; promql_query.go drops non-finite values, so no series is emitted",
"aggregators.test:948[base]": "1 of 3 expected points are NaN; promql_query.go drops non-finite values, so those timestamps are missing",
"aggregators.test:948[instant-coarse]": "1 of 3 expected points are NaN; promql_query.go drops non-finite values, so those timestamps are missing",
"aggregators.test:953[base]": "1 of 3 expected points are NaN; promql_query.go drops non-finite values, so those timestamps are missing",
"aggregators.test:953[instant-coarse]": "1 of 3 expected points are NaN; promql_query.go drops non-finite values, so those timestamps are missing",
"aggregators.test:963[base]": "expected output is entirely NaN; promql_query.go drops non-finite values, so no series is emitted",
"aggregators.test:963[instant-coarse]": "expected output is entirely NaN; promql_query.go drops non-finite values, so no series is emitted",
"aggregators.test:966[base]": "expected output is entirely NaN; promql_query.go drops non-finite values, so no series is emitted",
"aggregators.test:966[instant-coarse]": "expected output is entirely NaN; promql_query.go drops non-finite values, so no series is emitted",
"functions.test:1084[instant-coarse]": "sum_over_time over a window containing ±1e100: the disjoint coarse-step form's arraySum slide is naive summation, cancelling to 0 (the base variant's W>64 shape falls back to the engine and is exact)",
"functions.test:1087[instant-coarse]": "avg_over_time, same window and cancellation as functions.test:1084[instant-coarse]",
"functions.test:1149[base]": "avg_over_time over ±2.258e220-magnitude samples: engine's Kahan-compensated incremental mean cancels exactly to 0; the bucketed form's naive slide summation leaves a ~1e202 residue",
"functions.test:1149[instant-coarse]": "same as functions.test:1149[base] through the disjoint coarse-step form",
"operators.test:533[base]": "expected output is entirely NaN; promql_query.go drops non-finite values, so no series is emitted",
"operators.test:533[instant-coarse]": "expected output is entirely NaN; promql_query.go drops non-finite values, so no series is emitted",
"operators.test:539[base]": "expected output is entirely NaN; promql_query.go drops non-finite values, so no series is emitted",
"trig_functions.test:13[base]": "1 of 3 expected points are NaN; promql_query.go drops non-finite values, so those timestamps are missing",
"trig_functions.test:13[instant-coarse]": "1 of 3 expected points are NaN; promql_query.go drops non-finite values, so those timestamps are missing",
"trig_functions.test:18[base]": "1 of 3 expected points are NaN; promql_query.go drops non-finite values, so those timestamps are missing",
"trig_functions.test:18[instant-coarse]": "1 of 3 expected points are NaN; promql_query.go drops non-finite values, so those timestamps are missing",
"trig_functions.test:23[base]": "2 of 3 expected points are NaN; promql_query.go drops non-finite values, so those timestamps are missing",
"trig_functions.test:23[instant-coarse]": "2 of 3 expected points are NaN; promql_query.go drops non-finite values, so those timestamps are missing",
"trig_functions.test:28[base]": "2 of 3 expected points are NaN; promql_query.go drops non-finite values, so those timestamps are missing",
"trig_functions.test:28[instant-coarse]": "2 of 3 expected points are NaN; promql_query.go drops non-finite values, so those timestamps are missing",
"trig_functions.test:33[base]": "1 of 3 expected points are NaN; promql_query.go drops non-finite values, so those timestamps are missing",
"trig_functions.test:33[instant-coarse]": "1 of 3 expected points are NaN; promql_query.go drops non-finite values, so those timestamps are missing",
"trig_functions.test:38[base]": "1 of 3 expected points are NaN; promql_query.go drops non-finite values, so those timestamps are missing",
"trig_functions.test:38[instant-coarse]": "1 of 3 expected points are NaN; promql_query.go drops non-finite values, so those timestamps are missing",
"trig_functions.test:43[base]": "1 of 3 expected points are NaN; promql_query.go drops non-finite values, so those timestamps are missing",
"trig_functions.test:43[instant-coarse]": "1 of 3 expected points are NaN; promql_query.go drops non-finite values, so those timestamps are missing",
"trig_functions.test:48[base]": "1 of 3 expected points are NaN; promql_query.go drops non-finite values, so those timestamps are missing",
"trig_functions.test:48[instant-coarse]": "1 of 3 expected points are NaN; promql_query.go drops non-finite values, so those timestamps are missing",
"trig_functions.test:53[base]": "1 of 3 expected points are NaN; promql_query.go drops non-finite values, so those timestamps are missing",
"trig_functions.test:53[instant-coarse]": "1 of 3 expected points are NaN; promql_query.go drops non-finite values, so those timestamps are missing",
"trig_functions.test:58[base]": "1 of 3 expected points are NaN; promql_query.go drops non-finite values, so those timestamps are missing",
"trig_functions.test:58[instant-coarse]": "1 of 3 expected points are NaN; promql_query.go drops non-finite values, so those timestamps are missing",
"trig_functions.test:63[base]": "2 of 3 expected points are NaN; promql_query.go drops non-finite values, so those timestamps are missing",
"trig_functions.test:63[instant-coarse]": "2 of 3 expected points are NaN; promql_query.go drops non-finite values, so those timestamps are missing",
"trig_functions.test:68[base]": "1 of 3 expected points are NaN; promql_query.go drops non-finite values, so those timestamps are missing",
"trig_functions.test:68[instant-coarse]": "1 of 3 expected points are NaN; promql_query.go drops non-finite values, so those timestamps are missing",
"trig_functions.test:73[base]": "1 of 3 expected points are NaN; promql_query.go drops non-finite values, so those timestamps are missing",
"trig_functions.test:73[instant-coarse]": "1 of 3 expected points are NaN; promql_query.go drops non-finite values, so those timestamps are missing",
"trig_functions.test:78[base]": "1 of 3 expected points are NaN; promql_query.go drops non-finite values, so those timestamps are missing",
"trig_functions.test:78[instant-coarse]": "1 of 3 expected points are NaN; promql_query.go drops non-finite values, so those timestamps are missing",
"trig_functions.test:83[base]": "1 of 3 expected points are NaN; promql_query.go drops non-finite values, so those timestamps are missing",
"trig_functions.test:83[instant-coarse]": "1 of 3 expected points are NaN; promql_query.go drops non-finite values, so those timestamps are missing",
"trig_functions.test:88[base]": "1 of 3 expected points are NaN; promql_query.go drops non-finite values, so those timestamps are missing",
"trig_functions.test:88[instant-coarse]": "1 of 3 expected points are NaN; promql_query.go drops non-finite values, so those timestamps are missing",
"trig_functions.test:8[base]": "1 of 3 expected points are NaN; promql_query.go drops non-finite values, so those timestamps are missing",
"trig_functions.test:8[instant-coarse]": "1 of 3 expected points are NaN; promql_query.go drops non-finite values, so those timestamps are missing",
"trig_functions.test:93[base]": "1 of 3 expected points are NaN; promql_query.go drops non-finite values, so those timestamps are missing",
"trig_functions.test:93[instant-coarse]": "1 of 3 expected points are NaN; promql_query.go drops non-finite values, so those timestamps are missing"
}
}

View File

@@ -12,11 +12,9 @@ from fixtures.promqltestcorpus import ingest_promqltest_corpus
# The same frozen corpus the promqlconformance package replays through
# /api/v5/query_range, here replayed against the /prometheus/api/v1 endpoints
# with clickhousev2 as the serving provider (see conftest.py) — the two paths
# nothing else exercises. Range cases go to query_range, where a
# RangeExecutor provider serves transpiled statements when the shape allows.
# Instant cases go to /query with a real `time` parameter, so they need no
# grid encoding.
# — the path nothing else exercises. Range cases go to query_range, which
# serves transpiled statements when the shape allows. Instant cases go to
# /query with a real `time` parameter, so they need no grid encoding.
#
# Prometheus API sample values are strings, "NaN"/"+Inf"/"-Inf" included.
SPECIALS = {"NaN": math.nan, "Inf": math.inf, "+Inf": math.inf, "-Inf": -math.inf}
@@ -38,8 +36,7 @@ def test_prometheus_api_corpus(
# range because the v5 API cannot run true instants. This API can:
# the [base] form of the same eval goes through /query below, and the
# transpiled coarse-step serving the encoding exercises is covered
# (and its known divergences ledgered) by promqlconformance's
# clickhousev2 leg.
# (and its known divergences ledgered) by promqlconformance.
if case["variant"] == "instant-coarse":
continue

View File

@@ -1,37 +0,0 @@
import pytest
from testcontainers.core.container import Network
from fixtures import types
from fixtures.signoz import create_signoz
@pytest.fixture(name="signoz", scope="package")
def signoz_promapi_v2(
network: Network,
migrator: types.Operation, # pylint: disable=unused-argument
zeus: types.TestContainerDocker,
gateway: types.TestContainerDocker,
sqlstore: types.TestContainerSQL,
clickhouse: types.TestContainerClickhouse,
request: pytest.FixtureRequest,
pytestconfig: pytest.Config,
) -> types.SigNoz:
"""
SigNoz with clickhousev2 as the serving prometheus provider. The corpus
replays against the /prometheus/api/v1 endpoints, so this package covers
the two paths nothing else serves: v2 as the provider (range queries
transpile when the shape allows), and the Prometheus HTTP API contract.
"""
return create_signoz(
network=network,
zeus=zeus,
gateway=gateway,
sqlstore=sqlstore,
clickhouse=clickhouse,
request=request,
pytestconfig=pytestconfig,
cache_key="signoz-promapi-v2",
env_overrides={
"SIGNOZ_PROMETHEUS_PROVIDER": "clickhousev2",
},
)

View File

@@ -18,27 +18,11 @@ TESTDATA_DIR = os.path.join(os.path.dirname(__file__), "..", "..", "testdata")
# itself is the thing being changed — the one situation where comparing two
# live paths against each other is blind.
# One ledger per leg, enforced exactly in both directions. The default leg's
# ledger is empty and pinned there; the clickhousev2 ledger is the rollout
# scorecard — the provider swap is measured by burning it down to empty.
LEDGER_FILES = {
"default": os.path.join(TESTDATA_DIR, "promqltestcorpus", "known_divergences.json"),
"clickhousev2": os.path.join(TESTDATA_DIR, "promqltestcorpus", "known_divergences_v2.json"),
}
# Every case replays on both legs, each asserted against the same frozen
# expectations and its own ledger — deliberately never against each other: both
# legs can sit within one rounding quantum of the expected value yet differ from
# each other by up to two quanta when a true value straddles a rounding boundary,
# so a leg-vs-leg equality check would reintroduce exactly the boundary noise the
# quantum tolerance absorbs. A case failing on one leg while passing on the other
# already localizes the defect to that provider; the printed DIVERGED lines for
# both legs are the side-by-side triage view. The clickhousev2 header is
# flag-gated (see conftest.py).
LEGS: list[tuple[str, dict | None]] = [
("default", None),
("clickhousev2", {"X-SigNoz-PromQL-Provider": "clickhousev2"}),
]
# The ledger is enforced exactly in both directions: a new divergence is a
# regression, and a known divergence that starts passing must be removed. Its
# entries are the frozen defects of the serving path (the non-finite API
# filtering, and the clickhousev2 Kahan-summation class).
LEDGER_FILE = os.path.join(TESTDATA_DIR, "promqltestcorpus", "known_divergences.json")
SPECIALS = {"NaN": math.nan, "Inf": math.inf, "-Inf": -math.inf}
@@ -52,7 +36,7 @@ def test_upstream_promqltest_corpus(
corpus, bases = ingest_promqltest_corpus(insert_metrics)
token = get_token(USER_ADMIN_EMAIL, USER_ADMIN_PASSWORD)
failures: dict[str, list[str]] = {leg: [] for leg, _ in LEGS}
failures: list[str] = []
for case in corpus["cases"]:
base = bases[case["dataset"]]
start_ms = base + case["start_ms"]
@@ -71,104 +55,96 @@ def test_upstream_promqltest_corpus(
}
case_id = f"{case['source']}[{case['variant']}]"
for leg, headers in LEGS:
response = make_query_request(signoz, token, req_start_ms, end_ms, [query], headers=headers)
if response.status_code != HTTPStatus.OK:
failures[leg].append(f"{case_id}: HTTP {response.status_code} for {case['expr']!r}: {response.text[:200]}")
continue
response = make_query_request(signoz, token, req_start_ms, end_ms, [query])
if response.status_code != HTTPStatus.OK:
failures.append(f"{case_id}: HTTP {response.status_code} for {case['expr']!r}: {response.text[:200]}")
continue
# A response carrying several series with identical visible labels
# is itself a defect signal (e.g. a hidden grouping label stripped
# on the way out) and must not be silently collapsed into one entry.
actual: dict[tuple, dict[int, float]] = {}
duplicates: list[tuple] = []
# Empty results serialize with null aggregations/series/values fields.
for series in get_all_series(response.json(), "A") or []:
lbls = {l["key"]["name"]: str(l["value"]) for l in series.get("labels") or []}
points = {int(v["timestamp"]): SPECIALS[v["value"]] if isinstance(v["value"], str) else float(v["value"]) for v in series.get("values") or []}
key = tuple(sorted(lbls.items()))
if key in actual:
duplicates.append(key)
actual[key] = points
if duplicates:
failures[leg].append(f"{case_id}: response carries multiple series with identical labels for {case['expr']!r}: {[dict(d) for d in duplicates[:3]]}")
continue
# A response carrying several series with identical visible labels
# is itself a defect signal (e.g. a hidden grouping label stripped
# on the way out) and must not be silently collapsed into one entry.
actual: dict[tuple, dict[int, float]] = {}
duplicates: list[tuple] = []
# Empty results serialize with null aggregations/series/values fields.
for series in get_all_series(response.json(), "A") or []:
lbls = {l["key"]["name"]: str(l["value"]) for l in series.get("labels") or []}
points = {int(v["timestamp"]): SPECIALS[v["value"]] if isinstance(v["value"], str) else float(v["value"]) for v in series.get("values") or []}
key = tuple(sorted(lbls.items()))
if key in actual:
duplicates.append(key)
actual[key] = points
if duplicates:
failures.append(f"{case_id}: response carries multiple series with identical labels for {case['expr']!r}: {[dict(d) for d in duplicates[:3]]}")
continue
if case["instant"]:
# Keep only the instant point; the extra grid step is a request
# encoding byproduct, not part of the assertion.
actual = {lset: {ts: v for ts, v in pts.items() if ts == end_ms} for lset, pts in actual.items()}
actual = {lset: pts for lset, pts in actual.items() if pts}
expected: dict[tuple, dict[int, float]] = {}
for res in case["expected"]:
points = {base + off_ms: SPECIALS[v] if isinstance(v, str) else float(v) for off_ms, v in res["points"]}
expected[tuple(sorted(res["labels"].items()))] = points
if case["instant"]:
# Keep only the instant point; the extra grid step is a request
# encoding byproduct, not part of the assertion.
actual = {lset: {ts: v for ts, v in pts.items() if ts == end_ms} for lset, pts in actual.items()}
actual = {lset: pts for lset, pts in actual.items() if pts}
expected: dict[tuple, dict[int, float]] = {}
for res in case["expected"]:
points = {base + off_ms: SPECIALS[v] if isinstance(v, str) else float(v) for off_ms, v in res["points"]}
expected[tuple(sorted(res["labels"].items()))] = points
if set(actual) != set(expected):
missing = set(expected) - set(actual)
extra = set(actual) - set(expected)
failures[leg].append(f"{case_id}: series mismatch for {case['expr']!r} (missing={sorted(missing)[:3]} extra={sorted(extra)[:3]}) actual={[(dict(k), {t - base: v for t, v in pts.items()}) for k, pts in actual.items()]}")
continue
if set(actual) != set(expected):
missing = set(expected) - set(actual)
extra = set(actual) - set(expected)
failures.append(f"{case_id}: series mismatch for {case['expr']!r} (missing={sorted(missing)[:3]} extra={sorted(extra)[:3]}) actual={[(dict(k), {t - base: v for t, v in pts.items()}) for k, pts in actual.items()]}")
continue
mismatch = None
for lset, exp_points in expected.items():
act_points = actual[lset]
if set(act_points) != set(exp_points):
mismatch = f"{case_id}: timestamp mismatch for {case['expr']!r} series {dict(lset)} (expected {len(exp_points)} points, got {len(act_points)})"
break
for ts, exp_v in exp_points.items():
act_v = act_points[ts]
if math.isnan(act_v) or math.isnan(exp_v):
close = math.isnan(act_v) and math.isnan(exp_v)
elif math.isinf(act_v) or math.isinf(exp_v):
close = act_v == exp_v
elif act_v == exp_v:
close = True
mismatch = None
for lset, exp_points in expected.items():
act_points = actual[lset]
if set(act_points) != set(exp_points):
mismatch = f"{case_id}: timestamp mismatch for {case['expr']!r} series {dict(lset)} (expected {len(exp_points)} points, got {len(act_points)})"
break
for ts, exp_v in exp_points.items():
act_v = act_points[ts]
if math.isnan(act_v) or math.isnan(exp_v):
close = math.isnan(act_v) and math.isnan(exp_v)
elif math.isinf(act_v) or math.isinf(exp_v):
close = act_v == exp_v
elif act_v == exp_v:
close = True
else:
# Both sides carry the API's rounding (>=1: three decimal places; <1:
# three significant digits). A true value sitting exactly on a rounding
# boundary can round either way when the two computations differ at ULP
# level (float aggregation order over series is storage-iteration
# dependent), so allow one rounding quantum.
scale = max(abs(act_v), abs(exp_v))
if scale >= 1:
# Values too large to round pass through unrounded; give those an
# ULP-class relative grace on top of the rounding quantum.
quantum = max(1e-3, scale * 1e-9)
else:
# Both sides carry the API's rounding (>=1: three decimal places; <1:
# three significant digits). A true value sitting exactly on a rounding
# boundary can round either way when the two computations differ at ULP
# level (float aggregation order over series is storage-iteration
# dependent), so allow one rounding quantum.
scale = max(abs(act_v), abs(exp_v))
if scale >= 1:
# Values too large to round pass through unrounded; give those an
# ULP-class relative grace on top of the rounding quantum.
quantum = max(1e-3, scale * 1e-9)
else:
quantum = 10 ** (math.floor(math.log10(scale)) - 2)
close = abs(act_v - exp_v) <= quantum + 1e-12
if not close:
mismatch = f"{case_id}: value mismatch for {case['expr']!r} series {dict(lset)} at {ts}: expected {exp_v}, got {act_v}"
break
if mismatch:
quantum = 10 ** (math.floor(math.log10(scale)) - 2)
close = abs(act_v - exp_v) <= quantum + 1e-12
if not close:
mismatch = f"{case_id}: value mismatch for {case['expr']!r} series {dict(lset)} at {ts}: expected {exp_v}, got {act_v}"
break
if mismatch:
failures[leg].append(mismatch)
break
if mismatch:
failures.append(mismatch)
for leg, _ in LEGS:
for f_line in failures[leg]:
print("DIVERGED", f"[{leg}]", f_line)
for f_line in failures:
print("DIVERGED", f_line)
known: dict[str, str] = {}
if os.path.exists(LEDGER_FILE):
with open(LEDGER_FILE, encoding="utf-8") as f:
known = json.load(f)["divergences"]
failed_ids = {f_line.split(": ", 1)[0] for f_line in failures}
unexpected = [f_line for f_line in failures if f_line.split(": ", 1)[0] not in known]
now_passing = sorted(set(known) - failed_ids)
# Known divergences are defects of that leg's serving path, frozen with
# reasons. Each set is enforced exactly in both directions: a NEW
# divergence is a regression, and a known divergence that starts passing
# must be removed from the file. Problems across both legs are collected
# before asserting so one leg's failure never hides the other's.
problems: list[str] = []
for leg, _ in LEGS:
known: dict[str, str] = {}
if os.path.exists(LEDGER_FILES[leg]):
with open(LEDGER_FILES[leg], encoding="utf-8") as f:
known = json.load(f)["divergences"]
failed_ids = {f_line.split(": ", 1)[0] for f_line in failures[leg]}
unexpected = [f_line for f_line in failures[leg] if f_line.split(": ", 1)[0] not in known]
now_passing = sorted(set(known) - failed_ids)
if unexpected:
problems.append(f"[{leg}] {len(unexpected)} corpus cases diverged beyond the known set:\n" + "\n".join(unexpected[:25]))
if now_passing:
problems.append(f"[{leg}] {len(now_passing)} known divergences now pass — remove them from {os.path.basename(LEDGER_FILES[leg])}: {now_passing[:25]}")
if unexpected:
problems.append(f"{len(unexpected)} corpus cases diverged beyond the known set:\n" + "\n".join(unexpected[:25]))
if now_passing:
problems.append(f"{len(now_passing)} known divergences now pass — remove them from {os.path.basename(LEDGER_FILE)}: {now_passing[:25]}")
assert not problems, "\n\n".join(problems)

View File

@@ -10,11 +10,6 @@ from fixtures.querier import get_all_series, make_query_request
MINUTE_MS = 60_000
LEGS: list[tuple[str, dict | None]] = [
("default", None),
("clickhousev2", {"X-SigNoz-PromQL-Provider": "clickhousev2"}),
]
def test_promql_subquery_without_step_evaluates(
signoz: types.SigNoz,
@@ -45,16 +40,15 @@ def test_promql_subquery_without_step_evaluates(
token = get_token(USER_ADMIN_EMAIL, USER_ADMIN_PASSWORD)
for leg, headers in LEGS:
query = {"type": "promql", "spec": {"name": "A", "query": f"max_over_time({metric}[5m:])"}}
response = make_query_request(signoz, token, start_ms, end_ms, [query], headers=headers)
assert response.status_code == HTTPStatus.OK, f"{leg}: {response.text[:300]}"
series = get_all_series(response.json(), "A")
assert series, f"{leg}: the subquery must return the inserted series"
values = {point["value"] for entry in series for point in entry.get("values") or []}
assert values == {42.0}, f"{leg}: {sorted(values)[:5]}"
query = {"type": "promql", "spec": {"name": "A", "query": f"max_over_time({metric}[5m:])"}}
response = make_query_request(signoz, token, start_ms, end_ms, [query])
assert response.status_code == HTTPStatus.OK, response.text[:300]
series = get_all_series(response.json(), "A")
assert series, "the subquery must return the inserted series"
values = {point["value"] for entry in series for point in entry.get("values") or []}
assert values == {42.0}, sorted(values)[:5]
# A plain follow-up query proves the process survived the subquery legs.
# A plain follow-up query proves the process survived the subquery.
response = make_query_request(
signoz,
token,

View File

@@ -1,39 +0,0 @@
import pytest
from testcontainers.core.container import Network
from fixtures import types
from fixtures.signoz import create_signoz
@pytest.fixture(name="signoz", scope="package")
def signoz_promql_conformance(
network: Network,
migrator: types.Operation, # pylint: disable=unused-argument
zeus: types.TestContainerDocker,
gateway: types.TestContainerDocker,
sqlstore: types.TestContainerSQL,
clickhouse: types.TestContainerClickhouse,
request: pytest.FixtureRequest,
pytestconfig: pytest.Config,
) -> types.SigNoz:
"""
Package-scoped SigNoz with use_prometheus_clickhouse_v2 on, so the corpus
can replay every case twice: once against the default provider and once
pinned to the clickhousev2 provider via the X-SigNoz-PromQL-Provider
header (which the flag gates). Each leg is asserted against the same
frozen expectations — see 01_upstream_corpus.py for why the legs are
never asserted against each other.
"""
return create_signoz(
network=network,
zeus=zeus,
gateway=gateway,
sqlstore=sqlstore,
clickhouse=clickhouse,
request=request,
pytestconfig=pytestconfig,
cache_key="signoz-promql-conformance",
env_overrides={
"SIGNOZ_FLAGGER_CONFIG_BOOLEAN_USE__PROMETHEUS__CLICKHOUSE__V2": True,
},
)