Compare commits

..

3 Commits

Author SHA1 Message Date
Ashwin Bhatkal
ed85fed711 chore: resolve comments 2026-03-23 21:54:48 +05:30
Ashwin Bhatkal
194e8474b3 chore: fix tests 2026-03-23 21:54:48 +05:30
Ashwin Bhatkal
895ef98be4 fix: bugs in dashboard filter expression 2026-03-23 21:54:48 +05:30
34 changed files with 142 additions and 1378 deletions

View File

@@ -417,18 +417,6 @@ components:
message:
type: string
type: object
FactoryResponse:
properties:
healthy:
type: boolean
services:
additionalProperties:
items:
type: string
type: array
nullable: true
type: object
type: object
FeaturetypesGettableFeature:
properties:
defaultVariant:
@@ -5996,70 +5984,6 @@ paths:
summary: Search ingestion keys for workspace
tags:
- gateway
/api/v2/healthz:
get:
operationId: Healthz
responses:
"200":
content:
application/json:
schema:
properties:
data:
$ref: '#/components/schemas/FactoryResponse'
status:
type: string
required:
- status
- data
type: object
description: OK
"503":
content:
application/json:
schema:
properties:
data:
$ref: '#/components/schemas/FactoryResponse'
status:
type: string
required:
- status
- data
type: object
description: Service Unavailable
summary: Health check
tags:
- health
/api/v2/livez:
get:
deprecated: false
description: ""
operationId: Livez
responses:
"200":
content:
application/json:
schema:
properties:
data:
$ref: '#/components/schemas/FactoryResponse'
status:
type: string
required:
- status
- data
type: object
description: OK
"500":
content:
application/json:
schema:
$ref: '#/components/schemas/RenderErrorResponse'
description: Internal Server Error
summary: Liveness check
tags:
- health
/api/v2/metrics:
get:
deprecated: false
@@ -6736,41 +6660,6 @@ paths:
summary: Update my organization
tags:
- orgs
/api/v2/readyz:
get:
operationId: Readyz
responses:
"200":
content:
application/json:
schema:
properties:
data:
$ref: '#/components/schemas/FactoryResponse'
status:
type: string
required:
- status
- data
type: object
description: OK
"503":
content:
application/json:
schema:
properties:
data:
$ref: '#/components/schemas/FactoryResponse'
status:
type: string
required:
- status
- data
type: object
description: Service Unavailable
summary: Readiness check
tags:
- health
/api/v2/sessions:
delete:
deprecated: false

View File

@@ -273,7 +273,6 @@ Options can be simple (direct link) or nested (with another question):
- Place logo files in `public/Logos/`
- Use SVG format
- Reference as `"/Logos/your-logo.svg"`
- **Fetching Icons**: New icons can be easily fetched from [OpenBrand](https://openbrand.sh/). Use the pattern `https://openbrand.sh/?url=<TARGET_URL>`, where `<TARGET_URL>` is the URL-encoded link to the service's website. For example, to get Render's logo, use [https://openbrand.sh/?url=https%3A%2F%2Frender.com](https://openbrand.sh/?url=https%3A%2F%2Frender.com).
- **Optimize new SVGs**: Run any newly downloaded SVGs through an optimizer like [SVGOMG (svgo)](https://svgomg.net/) or use `npx svgo public/Logos/your-logo.svg` to minimise their size before committing.
### 4. Links

View File

@@ -57,10 +57,6 @@ func (provider *provider) Start(ctx context.Context) error {
return provider.openfgaServer.Start(ctx)
}
func (provider *provider) Healthy() <-chan struct{} {
return provider.openfgaServer.Healthy()
}
func (provider *provider) Stop(ctx context.Context) error {
return provider.openfgaServer.Stop(ctx)
}

View File

@@ -16,6 +16,7 @@ type Server struct {
}
func NewOpenfgaServer(ctx context.Context, pkgAuthzService authz.AuthZ) (*Server, error) {
return &Server{
pkgAuthzService: pkgAuthzService,
}, nil
@@ -25,10 +26,6 @@ func (server *Server) Start(ctx context.Context) error {
return server.pkgAuthzService.Start(ctx)
}
func (server *Server) Healthy() <-chan struct{} {
return server.pkgAuthzService.Healthy()
}
func (server *Server) Stop(ctx context.Context) error {
return server.pkgAuthzService.Stop(ctx)
}

View File

@@ -1 +0,0 @@
<svg xmlns="http://www.w3.org/2000/svg" fill="#fa520f" viewBox="0 0 24 24"><title>Mistral AI</title><path d="M17.143 3.429v3.428h-3.429v3.429h-3.428V6.857H6.857V3.43H3.43v13.714H0v3.428h10.286v-3.428H6.857v-3.429h3.429v3.429h3.429v-3.429h3.428v3.429h-3.428v3.428H24v-3.428h-3.43V3.429z"/></svg>

Before

Width:  |  Height:  |  Size: 294 B

View File

@@ -1 +0,0 @@
<svg xmlns="http://www.w3.org/2000/svg" fill="none" viewBox="0 0 120 120"><defs><linearGradient id="a" x1="0%" x2="100%" y1="0%" y2="100%"><stop offset="0%" stop-color="#ff4d4d"/><stop offset="100%" stop-color="#991b1b"/></linearGradient></defs><path fill="url(#a)" d="M60 10c-30 0-45 25-45 45s15 40 30 45v10h10v-10s5 2 10 0v10h10v-10c15-5 30-25 30-45S90 10 60 10"/><path fill="url(#a)" d="M20 45C5 40 0 50 5 60s15 5 20-5c3-7 0-10-5-10"/><path fill="url(#a)" d="M100 45c15-5 20 5 15 15s-15 5-20-5c-3-7 0-10 5-10"/><path stroke="#ff4d4d" stroke-linecap="round" stroke-width="3" d="M45 15Q35 5 30 8M75 15Q85 5 90 8"/><circle cx="45" cy="35" r="6" fill="#050810"/><circle cx="75" cy="35" r="6" fill="#050810"/><circle cx="46" cy="34" r="2.5" fill="#00e5cc"/><circle cx="76" cy="34" r="2.5" fill="#00e5cc"/></svg>

Before

Width:  |  Height:  |  Size: 809 B

View File

@@ -1 +0,0 @@
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><title>Render</title><path d="M18.263.007c-3.121-.147-5.744 2.109-6.192 5.082-.018.138-.045.272-.067.405-.696 3.703-3.936 6.507-7.827 6.507a7.9 7.9 0 0 1-3.825-.979.202.202 0 0 0-.302.178V24H12v-8.999c0-1.656 1.338-3 2.987-3h2.988c3.382 0 6.103-2.817 5.97-6.244-.12-3.084-2.61-5.603-5.682-5.75"/></svg>

Before

Width:  |  Height:  |  Size: 362 B

View File

@@ -1,250 +0,0 @@
/**
* ! Do not edit manually
* * The file has been auto-generated using Orval for SigNoz
* * regenerate with 'yarn generate:api'
* SigNoz
*/
import type {
InvalidateOptions,
QueryClient,
QueryFunction,
QueryKey,
UseQueryOptions,
UseQueryResult,
} from 'react-query';
import { useQuery } from 'react-query';
import type { ErrorType } from '../../../generatedAPIInstance';
import { GeneratedAPIInstance } from '../../../generatedAPIInstance';
import type {
Healthz200,
Healthz503,
Livez200,
Readyz200,
Readyz503,
RenderErrorResponseDTO,
} from '../sigNoz.schemas';
/**
* @summary Health check
*/
export const healthz = (signal?: AbortSignal) => {
return GeneratedAPIInstance<Healthz200>({
url: `/api/v2/healthz`,
method: 'GET',
signal,
});
};
export const getHealthzQueryKey = () => {
return [`/api/v2/healthz`] as const;
};
export const getHealthzQueryOptions = <
TData = Awaited<ReturnType<typeof healthz>>,
TError = ErrorType<Healthz503>
>(options?: {
query?: UseQueryOptions<Awaited<ReturnType<typeof healthz>>, TError, TData>;
}) => {
const { query: queryOptions } = options ?? {};
const queryKey = queryOptions?.queryKey ?? getHealthzQueryKey();
const queryFn: QueryFunction<Awaited<ReturnType<typeof healthz>>> = ({
signal,
}) => healthz(signal);
return { queryKey, queryFn, ...queryOptions } as UseQueryOptions<
Awaited<ReturnType<typeof healthz>>,
TError,
TData
> & { queryKey: QueryKey };
};
export type HealthzQueryResult = NonNullable<
Awaited<ReturnType<typeof healthz>>
>;
export type HealthzQueryError = ErrorType<Healthz503>;
/**
* @summary Health check
*/
export function useHealthz<
TData = Awaited<ReturnType<typeof healthz>>,
TError = ErrorType<Healthz503>
>(options?: {
query?: UseQueryOptions<Awaited<ReturnType<typeof healthz>>, TError, TData>;
}): UseQueryResult<TData, TError> & { queryKey: QueryKey } {
const queryOptions = getHealthzQueryOptions(options);
const query = useQuery(queryOptions) as UseQueryResult<TData, TError> & {
queryKey: QueryKey;
};
query.queryKey = queryOptions.queryKey;
return query;
}
/**
* @summary Health check
*/
export const invalidateHealthz = async (
queryClient: QueryClient,
options?: InvalidateOptions,
): Promise<QueryClient> => {
await queryClient.invalidateQueries(
{ queryKey: getHealthzQueryKey() },
options,
);
return queryClient;
};
/**
* @summary Liveness check
*/
export const livez = (signal?: AbortSignal) => {
return GeneratedAPIInstance<Livez200>({
url: `/api/v2/livez`,
method: 'GET',
signal,
});
};
export const getLivezQueryKey = () => {
return [`/api/v2/livez`] as const;
};
export const getLivezQueryOptions = <
TData = Awaited<ReturnType<typeof livez>>,
TError = ErrorType<RenderErrorResponseDTO>
>(options?: {
query?: UseQueryOptions<Awaited<ReturnType<typeof livez>>, TError, TData>;
}) => {
const { query: queryOptions } = options ?? {};
const queryKey = queryOptions?.queryKey ?? getLivezQueryKey();
const queryFn: QueryFunction<Awaited<ReturnType<typeof livez>>> = ({
signal,
}) => livez(signal);
return { queryKey, queryFn, ...queryOptions } as UseQueryOptions<
Awaited<ReturnType<typeof livez>>,
TError,
TData
> & { queryKey: QueryKey };
};
export type LivezQueryResult = NonNullable<Awaited<ReturnType<typeof livez>>>;
export type LivezQueryError = ErrorType<RenderErrorResponseDTO>;
/**
* @summary Liveness check
*/
export function useLivez<
TData = Awaited<ReturnType<typeof livez>>,
TError = ErrorType<RenderErrorResponseDTO>
>(options?: {
query?: UseQueryOptions<Awaited<ReturnType<typeof livez>>, TError, TData>;
}): UseQueryResult<TData, TError> & { queryKey: QueryKey } {
const queryOptions = getLivezQueryOptions(options);
const query = useQuery(queryOptions) as UseQueryResult<TData, TError> & {
queryKey: QueryKey;
};
query.queryKey = queryOptions.queryKey;
return query;
}
/**
* @summary Liveness check
*/
export const invalidateLivez = async (
queryClient: QueryClient,
options?: InvalidateOptions,
): Promise<QueryClient> => {
await queryClient.invalidateQueries({ queryKey: getLivezQueryKey() }, options);
return queryClient;
};
/**
* @summary Readiness check
*/
export const readyz = (signal?: AbortSignal) => {
return GeneratedAPIInstance<Readyz200>({
url: `/api/v2/readyz`,
method: 'GET',
signal,
});
};
export const getReadyzQueryKey = () => {
return [`/api/v2/readyz`] as const;
};
export const getReadyzQueryOptions = <
TData = Awaited<ReturnType<typeof readyz>>,
TError = ErrorType<Readyz503>
>(options?: {
query?: UseQueryOptions<Awaited<ReturnType<typeof readyz>>, TError, TData>;
}) => {
const { query: queryOptions } = options ?? {};
const queryKey = queryOptions?.queryKey ?? getReadyzQueryKey();
const queryFn: QueryFunction<Awaited<ReturnType<typeof readyz>>> = ({
signal,
}) => readyz(signal);
return { queryKey, queryFn, ...queryOptions } as UseQueryOptions<
Awaited<ReturnType<typeof readyz>>,
TError,
TData
> & { queryKey: QueryKey };
};
export type ReadyzQueryResult = NonNullable<Awaited<ReturnType<typeof readyz>>>;
export type ReadyzQueryError = ErrorType<Readyz503>;
/**
* @summary Readiness check
*/
export function useReadyz<
TData = Awaited<ReturnType<typeof readyz>>,
TError = ErrorType<Readyz503>
>(options?: {
query?: UseQueryOptions<Awaited<ReturnType<typeof readyz>>, TError, TData>;
}): UseQueryResult<TData, TError> & { queryKey: QueryKey } {
const queryOptions = getReadyzQueryOptions(options);
const query = useQuery(queryOptions) as UseQueryResult<TData, TError> & {
queryKey: QueryKey;
};
query.queryKey = queryOptions.queryKey;
return query;
}
/**
* @summary Readiness check
*/
export const invalidateReadyz = async (
queryClient: QueryClient,
options?: InvalidateOptions,
): Promise<QueryClient> => {
await queryClient.invalidateQueries(
{ queryKey: getReadyzQueryKey() },
options,
);
return queryClient;
};

View File

@@ -543,23 +543,6 @@ export interface ErrorsResponseerroradditionalDTO {
message?: string;
}
/**
* @nullable
*/
export type FactoryResponseDTOServices = { [key: string]: string[] } | null;
export interface FactoryResponseDTO {
/**
* @type boolean
*/
healthy?: boolean;
/**
* @type object
* @nullable true
*/
services?: FactoryResponseDTOServices;
}
/**
* @nullable
*/
@@ -3474,30 +3457,6 @@ export type SearchIngestionKeys200 = {
status: string;
};
export type Healthz200 = {
data: FactoryResponseDTO;
/**
* @type string
*/
status: string;
};
export type Healthz503 = {
data: FactoryResponseDTO;
/**
* @type string
*/
status: string;
};
export type Livez200 = {
data: FactoryResponseDTO;
/**
* @type string
*/
status: string;
};
export type ListMetricsParams = {
/**
* @type integer
@@ -3633,22 +3592,6 @@ export type GetMyOrganization200 = {
status: string;
};
export type Readyz200 = {
data: FactoryResponseDTO;
/**
* @type string
*/
status: string;
};
export type Readyz503 = {
data: FactoryResponseDTO;
/**
* @type string
*/
status: string;
};
export type GetSessionContext200 = {
data: AuthtypesSessionContextDTO;
/**

View File

@@ -1191,6 +1191,49 @@ describe('removeKeysFromExpression', () => {
expect(pairs).toHaveLength(2);
});
});
describe('Parenthesised expressions', () => {
it('should not leave a dangling AND when removing the last filter inside parens', () => {
const expression =
'(deployment.environment = $deployment.environment AND service.name = $service.name AND operation IN $top_level_operation)';
const result = removeKeysFromExpression(expression, ['operation'], true);
expect(result).toBe(
'(deployment.environment = $deployment.environment AND service.name = $service.name)',
);
});
it('should not leave a dangling AND when removing the first filter inside parens', () => {
const expression =
'(deployment.environment = $deployment.environment AND service.name = $service.name AND operation IN $top_level_operation)';
const result = removeKeysFromExpression(
expression,
['deployment.environment'],
true,
);
expect(result).toBe(
'(service.name = $service.name AND operation IN $top_level_operation)',
);
});
it('should not leave a dangling AND when removing a middle filter inside parens', () => {
const expression =
'(deployment.environment = $deployment.environment AND service.name = $service.name AND operation IN $top_level_operation)';
const result = removeKeysFromExpression(expression, ['service.name'], true);
expect(result).toBe(
'(deployment.environment = $deployment.environment AND operation IN $top_level_operation)',
);
});
it('should return empty parens when removing the only filter inside parens', () => {
const expression = '(operation IN $top_level_operation)';
const result = removeKeysFromExpression(expression, ['operation'], true);
expect(result).toBe('()');
});
});
});
describe('formatValueForExpression', () => {

View File

@@ -569,7 +569,7 @@ export const removeKeysFromExpression = (
const currentQueryPair = queryPairsMap.get(`${key}`.trim().toLowerCase());
if (currentQueryPair && currentQueryPair.isComplete) {
// Determine the start index of the query pair (fallback order: key → operator → value)
const queryPairStart =
let queryPairStart =
currentQueryPair.position.keyStart ??
currentQueryPair.position.operatorStart ??
currentQueryPair.position.valueStart;
@@ -587,6 +587,15 @@ export const removeKeysFromExpression = (
// If match is found, extend the queryPairEnd to include the matched part
queryPairEnd += match[0].length;
}
// If no following conjunction was absorbed (e.g. removed pair is last in expression),
// absorb the preceding AND/OR instead to avoid leaving a dangling conjunction
if (!match?.[3]) {
const beforePair = updatedExpression.slice(0, queryPairStart);
const precedingConjunctionMatch = beforePair.match(/\s+(AND|OR)\s+$/i);
if (precedingConjunctionMatch) {
queryPairStart -= precedingConjunctionMatch[0].length;
}
}
// Remove the full query pair (including any conjunction/whitespace) from the expression
updatedExpression = `${updatedExpression.slice(
0,

View File

@@ -3,6 +3,7 @@ import { useCallback } from 'react';
import { useAddDynamicVariableToPanels } from 'hooks/dashboard/useAddDynamicVariableToPanels';
import { updateLocalStorageDashboardVariable } from 'hooks/dashboard/useDashboardFromLocalStorage';
import { useUpdateDashboard } from 'hooks/dashboard/useUpdateDashboard';
import { useNotifications } from 'hooks/useNotifications';
import { IDashboardVariables } from 'providers/Dashboard/store/dashboardVariables/dashboardVariablesStoreTypes';
import { useDashboardStore } from 'providers/Dashboard/store/useDashboardStore';
import { IDashboardVariable } from 'types/api/dashboard/getAll';
@@ -51,6 +52,7 @@ export const useDashboardVariableUpdate = (): UseDashboardVariableUpdateReturn =
);
const addDynamicVariableToPanels = useAddDynamicVariableToPanels();
const updateMutation = useUpdateDashboard();
const { notifications } = useNotifications();
const onValueUpdate = useCallback(
(
@@ -180,6 +182,15 @@ export const useDashboardVariableUpdate = (): UseDashboardVariableUpdateReturn =
// Get current dashboard variables
const currentVariables = selectedDashboard.data.variables || {};
// Prevent duplicate variable names
const nameExists = Object.values(currentVariables).some(
(v) => v.name === name,
);
if (nameExists) {
notifications.error({ message: `Variable "${name}" already exists` });
return;
}
// Create tableRowData like Dashboard Settings does
const tableRowData = [];
const variableOrderArr = [];
@@ -232,7 +243,8 @@ export const useDashboardVariableUpdate = (): UseDashboardVariableUpdateReturn =
// Convert to dashboard format and update
const updatedVariables = convertVariablesToDbFormat(tableRowData);
updateVariables(updatedVariables, newVariable.id, [], false);
// Don't pass currentRequestedId — variable creation should not modify widget filters.
updateVariables(updatedVariables);
},
[selectedDashboard, updateVariables],
);

View File

@@ -6122,95 +6122,5 @@
],
"id": "huggingface-observability",
"link": "/docs/huggingface-observability/"
},
{
"dataSource": "mistral-observability",
"label": "Mistral AI",
"imgUrl": "/Logos/mistral.svg",
"tags": [
"LLM Monitoring"
],
"module": "apm",
"relatedSearchKeywords": [
"llm",
"llm monitoring",
"mistral",
"mistral ai",
"monitoring",
"observability",
"otel mistral",
"traces",
"tracing"
],
"id": "mistral-observability",
"link": "/docs/mistral-observability/"
},
{
"dataSource": "openclaw-observability",
"label": "OpenClaw",
"imgUrl": "/Logos/openclaw.svg",
"tags": [
"LLM Monitoring"
],
"module": "apm",
"relatedSearchKeywords": [
"llm",
"llm monitoring",
"monitoring",
"observability",
"openclaw",
"otel openclaw",
"traces",
"tracing"
],
"id": "openclaw-observability",
"link": "/docs/openclaw-monitoring/"
},
{
"dataSource": "claude-agent-monitoring",
"label": "Claude Agent SDK",
"imgUrl": "/Logos/claude-code.svg",
"tags": [
"LLM Monitoring"
],
"module": "apm",
"relatedSearchKeywords": [
"anthropic",
"claude",
"claude agent",
"claude agent sdk",
"claude sdk",
"llm",
"llm monitoring",
"monitoring",
"observability",
"otel claude",
"traces",
"tracing"
],
"id": "claude-agent-monitoring",
"link": "/docs/claude-agent-monitoring/"
},
{
"dataSource": "render-metrics",
"label": "Render",
"imgUrl": "/Logos/render.svg",
"tags": [
"infrastructure monitoring",
"metrics"
],
"module": "metrics",
"relatedSearchKeywords": [
"infrastructure",
"metrics",
"monitoring",
"observability",
"paas",
"render",
"render metrics",
"render monitoring"
],
"id": "render-metrics",
"link": "/docs/metrics-management/render-metrics/"
}
]

4
go.mod
View File

@@ -81,8 +81,6 @@ require (
golang.org/x/oauth2 v0.34.0
golang.org/x/sync v0.19.0
golang.org/x/text v0.33.0
gonum.org/v1/gonum v0.17.0
google.golang.org/api v0.265.0
google.golang.org/protobuf v1.36.11
gopkg.in/yaml.v2 v2.4.0
gopkg.in/yaml.v3 v3.0.1
@@ -379,6 +377,8 @@ require (
golang.org/x/sys v0.40.0 // indirect
golang.org/x/time v0.14.0 // indirect
golang.org/x/tools v0.41.0 // indirect
gonum.org/v1/gonum v0.17.0 // indirect
google.golang.org/api v0.265.0
google.golang.org/genproto/googleapis/api v0.0.0-20260203192932-546029d2fa20 // indirect
google.golang.org/genproto/googleapis/rpc v0.0.0-20260128011058-8636f8732409 // indirect
google.golang.org/grpc v1.78.0 // indirect

View File

@@ -50,7 +50,6 @@ type provider struct {
zeusHandler zeus.Handler
querierHandler querier.Handler
serviceAccountHandler serviceaccount.Handler
factoryHandler factory.Handler
}
func NewFactory(
@@ -73,7 +72,6 @@ func NewFactory(
zeusHandler zeus.Handler,
querierHandler querier.Handler,
serviceAccountHandler serviceaccount.Handler,
factoryHandler factory.Handler,
) factory.ProviderFactory[apiserver.APIServer, apiserver.Config] {
return factory.NewProviderFactory(factory.MustNewName("signoz"), func(ctx context.Context, providerSettings factory.ProviderSettings, config apiserver.Config) (apiserver.APIServer, error) {
return newProvider(
@@ -99,7 +97,6 @@ func NewFactory(
zeusHandler,
querierHandler,
serviceAccountHandler,
factoryHandler,
)
})
}
@@ -127,7 +124,6 @@ func newProvider(
zeusHandler zeus.Handler,
querierHandler querier.Handler,
serviceAccountHandler serviceaccount.Handler,
factoryHandler factory.Handler,
) (apiserver.APIServer, error) {
settings := factory.NewScopedProviderSettings(providerSettings, "github.com/SigNoz/signoz/pkg/apiserver/signozapiserver")
router := mux.NewRouter().UseEncodedPath()
@@ -153,7 +149,6 @@ func newProvider(
zeusHandler: zeusHandler,
querierHandler: querierHandler,
serviceAccountHandler: serviceAccountHandler,
factoryHandler: factoryHandler,
}
provider.authZ = middleware.NewAuthZ(settings.Logger(), orgGetter, authz)
@@ -238,10 +233,6 @@ func (provider *provider) AddToRouter(router *mux.Router) error {
return err
}
if err := provider.addRegistryRoutes(router); err != nil {
return err
}
return nil
}

View File

@@ -1,84 +0,0 @@
package signozapiserver
import (
"net/http"
"github.com/SigNoz/signoz/pkg/factory"
pkghandler "github.com/SigNoz/signoz/pkg/http/handler"
"github.com/SigNoz/signoz/pkg/http/render"
"github.com/gorilla/mux"
openapi "github.com/swaggest/openapi-go"
)
type healthOpenAPIHandler struct {
handlerFunc http.HandlerFunc
id string
summary string
}
func newHealthOpenAPIHandler(handlerFunc http.HandlerFunc, id, summary string) pkghandler.Handler {
return &healthOpenAPIHandler{
handlerFunc: handlerFunc,
id: id,
summary: summary,
}
}
func (handler *healthOpenAPIHandler) ServeHTTP(rw http.ResponseWriter, req *http.Request) {
handler.handlerFunc.ServeHTTP(rw, req)
}
func (handler *healthOpenAPIHandler) ServeOpenAPI(opCtx openapi.OperationContext) {
opCtx.SetID(handler.id)
opCtx.SetTags("health")
opCtx.SetSummary(handler.summary)
response := render.SuccessResponse{
Status: render.StatusSuccess.String(),
Data: new(factory.Response),
}
opCtx.AddRespStructure(
response,
openapi.WithContentType("application/json"),
openapi.WithHTTPStatus(http.StatusOK),
)
opCtx.AddRespStructure(
response,
openapi.WithContentType("application/json"),
openapi.WithHTTPStatus(http.StatusServiceUnavailable),
)
}
func (provider *provider) addRegistryRoutes(router *mux.Router) error {
if err := router.Handle("/api/v2/healthz", newHealthOpenAPIHandler(
provider.authZ.OpenAccess(provider.factoryHandler.Healthz),
"Healthz",
"Health check",
)).Methods(http.MethodGet).GetError(); err != nil {
return err
}
if err := router.Handle("/api/v2/readyz", newHealthOpenAPIHandler(
provider.authZ.OpenAccess(provider.factoryHandler.Readyz),
"Readyz",
"Readiness check",
)).Methods(http.MethodGet).GetError(); err != nil {
return err
}
if err := router.Handle("/api/v2/livez", pkghandler.New(provider.authZ.OpenAccess(provider.factoryHandler.Livez),
pkghandler.OpenAPIDef{
ID: "Livez",
Tags: []string{"health"},
Summary: "Liveness check",
Response: new(factory.Response),
ResponseContentType: "application/json",
SuccessStatusCode: http.StatusOK,
},
)).Methods(http.MethodGet).GetError(); err != nil {
return err
}
return nil
}

View File

@@ -11,7 +11,7 @@ import (
)
type AuthZ interface {
factory.ServiceWithHealthy
factory.Service
// CheckWithTupleCreation takes upon the responsibility for generating the tuples alongside everything Check does.
CheckWithTupleCreation(context.Context, authtypes.Claims, valuer.UUID, authtypes.Relation, authtypes.Typeable, []authtypes.Selector, []authtypes.Selector) error

View File

@@ -43,10 +43,6 @@ func (provider *provider) Start(ctx context.Context) error {
return provider.server.Start(ctx)
}
func (provider *provider) Healthy() <-chan struct{} {
return provider.server.Healthy()
}
func (provider *provider) Stop(ctx context.Context) error {
return provider.server.Stop(ctx)
}

View File

@@ -31,7 +31,6 @@ type Server struct {
modelID string
mtx sync.RWMutex
stopChan chan struct{}
healthyC chan struct{}
}
func NewOpenfgaServer(ctx context.Context, settings factory.ProviderSettings, config authz.Config, sqlstore sqlstore.SQLStore, openfgaSchema []openfgapkgtransformer.ModuleFile) (*Server, error) {
@@ -62,7 +61,6 @@ func NewOpenfgaServer(ctx context.Context, settings factory.ProviderSettings, co
openfgaSchema: openfgaSchema,
mtx: sync.RWMutex{},
stopChan: make(chan struct{}),
healthyC: make(chan struct{}),
}, nil
}
@@ -82,16 +80,10 @@ func (server *Server) Start(ctx context.Context) error {
server.storeID = storeID
server.mtx.Unlock()
close(server.healthyC)
<-server.stopChan
return nil
}
func (server *Server) Healthy() <-chan struct{} {
return server.healthyC
}
func (server *Server) Stop(ctx context.Context) error {
server.openfgaServer.Close()
close(server.stopChan)

View File

@@ -1,67 +0,0 @@
package factory
import (
"net/http"
"github.com/SigNoz/signoz/pkg/http/render"
)
// Handler provides HTTP handler functions for service health checks.
type Handler interface {
// Readyz reports whether services are ready.
Readyz(http.ResponseWriter, *http.Request)
// Livez reports whether services are alive.
Livez(http.ResponseWriter, *http.Request)
// Healthz reports overall service health.
Healthz(http.ResponseWriter, *http.Request)
}
type handler struct {
registry *Registry
}
func NewHandler(registry *Registry) Handler {
return &handler{
registry: registry,
}
}
type Response struct {
Healthy bool `json:"healthy"`
Services map[State][]Name `json:"services"`
}
func (handler *handler) Healthz(rw http.ResponseWriter, req *http.Request) {
byState := handler.registry.ServicesByState()
healthy := handler.registry.IsHealthy()
statusCode := http.StatusOK
if !healthy {
statusCode = http.StatusServiceUnavailable
}
render.Success(rw, statusCode, Response{
Healthy: healthy,
Services: byState,
})
}
func (handler *handler) Readyz(rw http.ResponseWriter, req *http.Request) {
healthy := handler.registry.IsHealthy()
statusCode := http.StatusOK
if !healthy {
statusCode = http.StatusServiceUnavailable
}
render.Success(rw, statusCode, Response{
Healthy: healthy,
Services: handler.registry.ServicesByState(),
})
}
func (handler *handler) Livez(rw http.ResponseWriter, req *http.Request) {
render.Success(rw, http.StatusOK, nil)
}

View File

@@ -5,11 +5,9 @@ import (
"regexp"
"github.com/SigNoz/signoz/pkg/errors"
"github.com/swaggest/jsonschema-go"
)
var _ slog.LogValuer = (Name{})
var _ jsonschema.Exposer = (Name{})
var (
// nameRegex is a regex that matches a valid name.
@@ -29,21 +27,6 @@ func (n Name) String() string {
return n.name
}
// MarshalText implements encoding.TextMarshaler for JSON serialization.
func (n Name) MarshalText() ([]byte, error) {
return []byte(n.name), nil
}
// MarshalJSON implements json.Marshaler so Name serializes as a JSON string.
func (n Name) MarshalJSON() ([]byte, error) {
return []byte(`"` + n.name + `"`), nil
}
// JSONSchema implements jsonschema.Exposer so OpenAPI reflects Name as a string.
func (n Name) JSONSchema() (jsonschema.Schema, error) {
return *new(jsonschema.Schema).WithType(jsonschema.String.Type()), nil
}
// NewName creates a new name.
func NewName(name string) (Name, error) {
if !nameRegex.MatchString(name) {

View File

@@ -8,26 +8,21 @@ import (
"syscall"
"github.com/SigNoz/signoz/pkg/errors"
"gonum.org/v1/gonum/graph/simple"
"gonum.org/v1/gonum/graph/topo"
)
var (
ErrCodeInvalidRegistry = errors.MustNewCode("invalid_registry")
ErrCodeDependencyFailed = errors.MustNewCode("dependency_failed")
ErrCodeServiceFailed = errors.MustNewCode("service_failed")
ErrCodeInvalidRegistry = errors.MustNewCode("invalid_registry")
)
type Registry struct {
services []*serviceWithState
servicesByName map[Name]*serviceWithState
logger *slog.Logger
startC chan error
stopC chan error
services NamedMap[NamedService]
logger *slog.Logger
startCh chan error
stopCh chan error
}
// New creates a new registry of services. It needs at least one service in the input.
func NewRegistry(ctx context.Context, logger *slog.Logger, services ...NamedService) (*Registry, error) {
func NewRegistry(logger *slog.Logger, services ...NamedService) (*Registry, error) {
if logger == nil {
return nil, errors.Newf(errors.TypeInvalidInput, ErrCodeInvalidRegistry, "cannot build registry, logger is required")
}
@@ -36,131 +31,59 @@ func NewRegistry(ctx context.Context, logger *slog.Logger, services ...NamedServ
return nil, errors.Newf(errors.TypeInvalidInput, ErrCodeInvalidRegistry, "cannot build registry, at least one service is required")
}
servicesWithState := make([]*serviceWithState, len(services))
servicesByName := make(map[Name]*serviceWithState, len(services))
for i, s := range services {
if _, ok := servicesByName[s.Name()]; ok {
return nil, errors.Newf(errors.TypeInvalidInput, ErrCodeInvalidRegistry, "cannot build registry, duplicate service name %q", s.Name())
}
ss := newServiceWithState(s)
servicesWithState[i] = ss
servicesByName[s.Name()] = ss
}
registryLogger := logger.With(slog.String("pkg", "github.com/SigNoz/signoz/pkg/factory"))
for _, ss := range servicesWithState {
for _, dep := range ss.service.DependsOn() {
if dep == ss.service.Name() {
registryLogger.ErrorContext(ctx, "ignoring self-dependency", slog.Any("service", ss.service.Name()))
continue
}
if _, ok := servicesByName[dep]; !ok {
registryLogger.ErrorContext(ctx, "ignoring unknown dependency", slog.Any("service", ss.service.Name()), slog.Any("dependency", dep))
continue
}
ss.dependsOn = append(ss.dependsOn, dep)
}
}
if err := detectCyclicDeps(servicesWithState); err != nil {
m, err := NewNamedMap(services...)
if err != nil {
return nil, err
}
return &Registry{
logger: registryLogger,
services: servicesWithState,
servicesByName: servicesByName,
startC: make(chan error, 1),
stopC: make(chan error, len(services)),
logger: logger.With(slog.String("pkg", "go.signoz.io/pkg/factory")),
services: m,
startCh: make(chan error, 1),
stopCh: make(chan error, len(services)),
}, nil
}
func (registry *Registry) Start(ctx context.Context) {
for _, ss := range registry.services {
go func(ss *serviceWithState) {
// Wait for all dependencies to be healthy before starting.
for _, dep := range ss.dependsOn {
depState := registry.servicesByName[dep]
registry.logger.InfoContext(ctx, "service waiting for dependency", slog.Any("service", ss.service.Name()), slog.Any("dependency", dep))
select {
case <-ctx.Done():
ss.mu.Lock()
ss.state = StateFailed
ss.startErr = ctx.Err()
ss.mu.Unlock()
close(ss.startReturnedC)
registry.startC <- ctx.Err()
return
case <-depState.healthyC:
// Dependency is healthy, continue.
case <-depState.startReturnedC:
// Dependency failed before becoming healthy.
err := errors.Newf(errors.TypeInternal, ErrCodeDependencyFailed, "dependency %q of service %q failed", dep, ss.service.Name())
ss.mu.Lock()
ss.state = StateFailed
ss.startErr = err
ss.mu.Unlock()
close(ss.startReturnedC)
registry.startC <- err
return
}
}
registry.logger.InfoContext(ctx, "starting service", slog.Any("service", ss.service.Name()))
go func() {
select {
case <-ss.service.Healthy():
ss.setState(StateRunning)
case <-ss.startReturnedC:
}
}()
err := ss.service.Start(ctx)
if err != nil {
ss.mu.Lock()
ss.state = StateFailed
ss.startErr = err
ss.mu.Unlock()
}
close(ss.startReturnedC)
registry.startC <- err
}(ss)
func (r *Registry) Start(ctx context.Context) {
for _, s := range r.services.GetInOrder() {
go func(s NamedService) {
r.logger.InfoContext(ctx, "starting service", slog.Any("service", s.Name()))
err := s.Start(ctx)
r.startCh <- err
}(s)
}
}
func (registry *Registry) Wait(ctx context.Context) error {
func (r *Registry) Wait(ctx context.Context) error {
interrupt := make(chan os.Signal, 1)
signal.Notify(interrupt, syscall.SIGINT, syscall.SIGTERM)
select {
case <-ctx.Done():
registry.logger.InfoContext(ctx, "caught context error, exiting", errors.Attr(ctx.Err()))
r.logger.InfoContext(ctx, "caught context error, exiting", errors.Attr(ctx.Err()))
case s := <-interrupt:
registry.logger.InfoContext(ctx, "caught interrupt signal, exiting", slog.Any("signal", s))
case err := <-registry.startC:
registry.logger.ErrorContext(ctx, "caught service error, exiting", errors.Attr(err))
r.logger.InfoContext(ctx, "caught interrupt signal, exiting", slog.Any("signal", s))
case err := <-r.startCh:
r.logger.ErrorContext(ctx, "caught service error, exiting", errors.Attr(err))
return err
}
return nil
}
func (registry *Registry) Stop(ctx context.Context) error {
for _, ss := range registry.services {
go func(ss *serviceWithState) {
registry.logger.InfoContext(ctx, "stopping service", slog.Any("service", ss.service.Name()))
err := ss.service.Stop(ctx)
registry.stopC <- err
}(ss)
func (r *Registry) Stop(ctx context.Context) error {
for _, s := range r.services.GetInOrder() {
go func(s NamedService) {
r.logger.InfoContext(ctx, "stopping service", slog.Any("service", s.Name()))
err := s.Stop(ctx)
r.stopCh <- err
}(s)
}
errs := make([]error, len(registry.services))
for i := 0; i < len(registry.services); i++ {
err := <-registry.stopC
errs := make([]error, len(r.services.GetInOrder()))
for i := 0; i < len(r.services.GetInOrder()); i++ {
err := <-r.stopCh
if err != nil {
errs = append(errs, err)
}
@@ -168,83 +91,3 @@ func (registry *Registry) Stop(ctx context.Context) error {
return errors.Join(errs...)
}
// AwaitHealthy blocks until all services reach the RUNNING state or any service fails.
func (registry *Registry) AwaitHealthy(ctx context.Context) error {
for _, ss := range registry.services {
select {
case <-ctx.Done():
return ctx.Err()
case <-ss.healthyC:
case <-ss.startReturnedC:
ss.mu.RLock()
err := ss.startErr
ss.mu.RUnlock()
if err != nil {
return errors.Wrapf(err, errors.TypeInternal, ErrCodeServiceFailed, "service %q failed before becoming healthy", ss.service.Name())
}
return errors.Newf(errors.TypeInternal, ErrCodeServiceFailed, "service %q terminated before becoming healthy", ss.service.Name())
}
}
return nil
}
// ServicesByState returns a snapshot of the current state of all services.
func (registry *Registry) ServicesByState() map[State][]Name {
result := make(map[State][]Name)
for _, ss := range registry.services {
state := ss.getState()
result[state] = append(result[state], ss.service.Name())
}
return result
}
// IsHealthy returns true if all services are in the RUNNING state.
func (registry *Registry) IsHealthy() bool {
for _, ss := range registry.services {
if ss.getState() != StateRunning {
return false
}
}
return true
}
// detectCyclicDeps returns an error listing all dependency cycles found using
// gonum's Tarjan SCC algorithm.
func detectCyclicDeps(services []*serviceWithState) error {
nameToID := make(map[Name]int64, len(services))
idToName := make(map[int64]Name, len(services))
for i, ss := range services {
id := int64(i)
nameToID[ss.service.Name()] = id
idToName[id] = ss.service.Name()
}
g := simple.NewDirectedGraph()
for _, ss := range services {
g.AddNode(simple.Node(nameToID[ss.service.Name()]))
}
for _, ss := range services {
fromID := nameToID[ss.service.Name()]
for _, dep := range ss.dependsOn {
g.SetEdge(simple.Edge{F: simple.Node(fromID), T: simple.Node(nameToID[dep])})
}
}
if _, err := topo.Sort(g); err == nil {
return nil
}
var cycles [][]Name
for _, scc := range topo.TarjanSCC(g) {
if len(scc) > 1 {
cycle := make([]Name, len(scc))
for i, n := range scc {
cycle[i] = idToName[n.ID()]
}
cycles = append(cycles, cycle)
}
}
return errors.Newf(errors.TypeInvalidInput, ErrCodeInvalidRegistry, "dependency cycles detected: %v", cycles)
}

View File

@@ -5,10 +5,7 @@ import (
"log/slog"
"sync"
"testing"
"time"
"github.com/SigNoz/signoz/pkg/errors"
"github.com/stretchr/testify/assert"
"github.com/stretchr/testify/require"
)
@@ -31,46 +28,11 @@ func (s *tservice) Stop(_ context.Context) error {
return nil
}
type healthyTestService struct {
tservice
healthyC chan struct{}
}
func newHealthyTestService(t *testing.T) *healthyTestService {
t.Helper()
return &healthyTestService{
tservice: tservice{c: make(chan struct{})},
healthyC: make(chan struct{}),
}
}
func (s *healthyTestService) Healthy() <-chan struct{} {
return s.healthyC
}
// failingHealthyService implements Healthy but fails before signaling healthy.
type failingHealthyService struct {
healthyC chan struct{}
err error
}
func (s *failingHealthyService) Start(_ context.Context) error {
return s.err
}
func (s *failingHealthyService) Stop(_ context.Context) error {
return nil
}
func (s *failingHealthyService) Healthy() <-chan struct{} {
return s.healthyC
}
func TestRegistryWith2Services(t *testing.T) {
s1 := newTestService(t)
s2 := newTestService(t)
registry, err := NewRegistry(context.Background(), slog.New(slog.DiscardHandler), NewNamedService(MustNewName("s1"), s1), NewNamedService(MustNewName("s2"), s2))
registry, err := NewRegistry(slog.New(slog.DiscardHandler), NewNamedService(MustNewName("s1"), s1), NewNamedService(MustNewName("s2"), s2))
require.NoError(t, err)
ctx, cancel := context.WithCancel(context.Background())
@@ -79,8 +41,8 @@ func TestRegistryWith2Services(t *testing.T) {
go func() {
defer wg.Done()
registry.Start(ctx)
assert.NoError(t, registry.Wait(ctx))
assert.NoError(t, registry.Stop(ctx))
require.NoError(t, registry.Wait(ctx))
require.NoError(t, registry.Stop(ctx))
}()
cancel()
@@ -91,7 +53,7 @@ func TestRegistryWith2ServicesWithoutWait(t *testing.T) {
s1 := newTestService(t)
s2 := newTestService(t)
registry, err := NewRegistry(context.Background(), slog.New(slog.DiscardHandler), NewNamedService(MustNewName("s1"), s1), NewNamedService(MustNewName("s2"), s2))
registry, err := NewRegistry(slog.New(slog.DiscardHandler), NewNamedService(MustNewName("s1"), s1), NewNamedService(MustNewName("s2"), s2))
require.NoError(t, err)
ctx := context.Background()
@@ -100,245 +62,8 @@ func TestRegistryWith2ServicesWithoutWait(t *testing.T) {
go func() {
defer wg.Done()
registry.Start(ctx)
assert.NoError(t, registry.Stop(ctx))
require.NoError(t, registry.Stop(ctx))
}()
wg.Wait()
}
func TestServiceStateTransitions(t *testing.T) {
s1 := newTestService(t)
registry, err := NewRegistry(context.Background(), slog.New(slog.DiscardHandler), NewNamedService(MustNewName("s1"), s1))
require.NoError(t, err)
ctx := context.Background()
registry.Start(ctx)
require.NoError(t, registry.AwaitHealthy(ctx))
byState := registry.ServicesByState()
assert.Len(t, byState[StateRunning], 1)
assert.True(t, registry.IsHealthy())
assert.NoError(t, registry.Stop(ctx))
}
func TestServiceStateWithHealthy(t *testing.T) {
s1 := newHealthyTestService(t)
registry, err := NewRegistry(context.Background(), slog.New(slog.DiscardHandler), NewNamedService(MustNewName("s1"), s1))
require.NoError(t, err)
ctx := context.Background()
registry.Start(ctx)
// Poll until STARTING state is observed
require.Eventually(t, func() bool {
byState := registry.ServicesByState()
return len(byState[StateStarting]) == 1
}, time.Second, time.Millisecond)
assert.False(t, registry.IsHealthy())
// Signal healthy
close(s1.healthyC)
require.NoError(t, registry.AwaitHealthy(ctx))
assert.True(t, registry.IsHealthy())
byState := registry.ServicesByState()
assert.Len(t, byState[StateRunning], 1)
assert.NoError(t, registry.Stop(ctx))
}
func TestAwaitHealthy(t *testing.T) {
s1 := newTestService(t)
s2 := newTestService(t)
registry, err := NewRegistry(context.Background(), slog.New(slog.DiscardHandler), NewNamedService(MustNewName("s1"), s1), NewNamedService(MustNewName("s2"), s2))
require.NoError(t, err)
ctx := context.Background()
registry.Start(ctx)
assert.NoError(t, registry.AwaitHealthy(ctx))
assert.True(t, registry.IsHealthy())
assert.NoError(t, registry.Stop(ctx))
}
func TestAwaitHealthyWithFailure(t *testing.T) {
s1 := &failingHealthyService{
healthyC: make(chan struct{}),
err: errors.Newf(errors.TypeInternal, errors.CodeInternal,"startup failed"),
}
registry, err := NewRegistry(context.Background(), slog.New(slog.DiscardHandler), NewNamedService(MustNewName("s1"), s1))
require.NoError(t, err)
ctx := context.Background()
registry.Start(ctx)
err = registry.AwaitHealthy(ctx)
assert.Error(t, err)
assert.Contains(t, err.Error(), "startup failed")
}
func TestServicesByState(t *testing.T) {
s1 := newTestService(t)
s2 := newHealthyTestService(t)
registry, err := NewRegistry(context.Background(), slog.New(slog.DiscardHandler), NewNamedService(MustNewName("s1"), s1), NewNamedService(MustNewName("s2"), s2))
require.NoError(t, err)
ctx := context.Background()
registry.Start(ctx)
// Wait for s1 to be running (no Healthy interface) and s2 to be starting
require.Eventually(t, func() bool {
byState := registry.ServicesByState()
return len(byState[StateRunning]) == 1 && len(byState[StateStarting]) == 1
}, time.Second, time.Millisecond)
// Make s2 healthy
close(s2.healthyC)
require.NoError(t, registry.AwaitHealthy(ctx))
byState := registry.ServicesByState()
assert.Len(t, byState[StateRunning], 2)
assert.NoError(t, registry.Stop(ctx))
}
func TestDependsOnStartsAfterDependency(t *testing.T) {
s1 := newHealthyTestService(t)
s2 := newTestService(t)
// s2 depends on s1
registry, err := NewRegistry(
context.Background(),
slog.New(slog.DiscardHandler),
NewNamedService(MustNewName("s1"), s1),
NewNamedService(MustNewName("s2"), s2, MustNewName("s1")),
)
require.NoError(t, err)
ctx := context.Background()
registry.Start(ctx)
// s2 should still be STARTING because s1 hasn't become healthy yet
require.Eventually(t, func() bool {
byState := registry.ServicesByState()
return len(byState[StateStarting]) == 2
}, time.Second, time.Millisecond)
// Make s1 healthy — s2 should then start and become RUNNING
close(s1.healthyC)
assert.NoError(t, registry.AwaitHealthy(ctx))
assert.True(t, registry.IsHealthy())
assert.NoError(t, registry.Stop(ctx))
}
func TestDependsOnFailsWhenDependencyFails(t *testing.T) {
s1 := &failingHealthyService{
healthyC: make(chan struct{}),
err: errors.Newf(errors.TypeInternal, errors.CodeInternal,"s1 crashed"),
}
s2 := newTestService(t)
// s2 depends on s1
registry, err := NewRegistry(
context.Background(),
slog.New(slog.DiscardHandler),
NewNamedService(MustNewName("s1"), s1),
NewNamedService(MustNewName("s2"), s2, MustNewName("s1")),
)
require.NoError(t, err)
ctx := context.Background()
registry.Start(ctx)
// Both should eventually fail
assert.Eventually(t, func() bool {
byState := registry.ServicesByState()
return len(byState[StateFailed]) == 2
}, time.Second, time.Millisecond)
}
func TestDependsOnUnknownServiceIsIgnored(t *testing.T) {
s1 := newTestService(t)
// Unknown dependency is logged and ignored, not an error.
registry, err := NewRegistry(
context.Background(),
slog.New(slog.DiscardHandler),
NewNamedService(MustNewName("s1"), s1, MustNewName("unknown")),
)
require.NoError(t, err)
ctx := context.Background()
registry.Start(ctx)
assert.NoError(t, registry.AwaitHealthy(ctx))
assert.True(t, registry.IsHealthy())
assert.NoError(t, registry.Stop(ctx))
}
func TestServiceStateFailed(t *testing.T) {
s1 := &failingHealthyService{
healthyC: make(chan struct{}),
err: errors.Newf(errors.TypeInternal, errors.CodeInternal,"fatal error"),
}
registry, err := NewRegistry(context.Background(), slog.New(slog.DiscardHandler), NewNamedService(MustNewName("s1"), s1))
require.NoError(t, err)
ctx := context.Background()
registry.Start(ctx)
// Wait for the service to fail
assert.Eventually(t, func() bool {
byState := registry.ServicesByState()
return len(byState[StateFailed]) == 1
}, time.Second, time.Millisecond)
assert.False(t, registry.IsHealthy())
}
func TestDependsOnSelfDependencyIsIgnored(t *testing.T) {
s1 := newTestService(t)
// Self-dependency is logged and ignored.
registry, err := NewRegistry(
context.Background(),
slog.New(slog.DiscardHandler),
NewNamedService(MustNewName("s1"), s1, MustNewName("s1")),
)
require.NoError(t, err)
ctx := context.Background()
registry.Start(ctx)
assert.NoError(t, registry.AwaitHealthy(ctx))
assert.True(t, registry.IsHealthy())
assert.NoError(t, registry.Stop(ctx))
}
func TestDependsOnCycleReturnsError(t *testing.T) {
s1 := newTestService(t)
s2 := newTestService(t)
// A -> B and B -> A is a cycle.
_, err := NewRegistry(
context.Background(),
slog.New(slog.DiscardHandler),
NewNamedService(MustNewName("s1"), s1, MustNewName("s2")),
NewNamedService(MustNewName("s2"), s2, MustNewName("s1")),
)
assert.Error(t, err)
assert.Contains(t, err.Error(), "dependency cycles detected")
}

View File

@@ -2,81 +2,30 @@ package factory
import "context"
// Service is the core lifecycle interface for long-running services.
type Service interface {
// Starts a service. It should block and should not return until the service is stopped or it fails.
Start(context.Context) error
// Stops a service.
Stop(context.Context) error
}
// Healthy is an optional interface that services can implement to signal
// when they have completed startup and are ready to serve.
// Services that do not implement this interface are considered healthy
// immediately after Start() is called.
type Healthy interface {
// Healthy returns a channel that is closed when the service is healthy.
Healthy() <-chan struct{}
}
// ServiceWithHealthy is a Service that explicitly signals when it is healthy.
type ServiceWithHealthy interface {
Service
Healthy
}
// NamedService is a Service with a Name and optional dependencies.
type NamedService interface {
Named
ServiceWithHealthy
// DependsOn returns the names of services that must be healthy before this service starts.
DependsOn() []Name
Service
}
// closedC is a pre-closed channel returned for services that don't implement Healthy.
var closedC = func() chan struct{} {
c := make(chan struct{})
close(c)
return c
}()
type namedService struct {
name Name
dependsOn []Name
service Service
}
// NewNamedService wraps a Service with a Name and optional dependency names.
func NewNamedService(name Name, service Service, dependsOn ...Name) NamedService {
return &namedService{
name: name,
dependsOn: dependsOn,
service: service,
}
name Name
Service
}
func (s *namedService) Name() Name {
return s.name
}
func (s *namedService) DependsOn() []Name {
return s.dependsOn
}
func (s *namedService) Start(ctx context.Context) error {
return s.service.Start(ctx)
}
func (s *namedService) Stop(ctx context.Context) error {
return s.service.Stop(ctx)
}
// Healthy delegates to the underlying service if it implements Healthy,
// otherwise returns an already-closed channel (immediately healthy).
func (s *namedService) Healthy() <-chan struct{} {
if h, ok := s.service.(Healthy); ok {
return h.Healthy()
func NewNamedService(name Name, service Service) NamedService {
return &namedService{
name: name,
Service: service,
}
return closedC
}

View File

@@ -1,75 +0,0 @@
package factory
import "sync"
// State represents the lifecycle state of a service.
type State struct {
s string
}
func (s State) String() string {
return s.s
}
// MarshalText implements encoding.TextMarshaler so State can be used as a JSON map key.
func (s State) MarshalText() ([]byte, error) {
return []byte(s.s), nil
}
var (
StateStarting = State{"starting"}
StateRunning = State{"running"}
StateFailed = State{"failed"}
)
// serviceWithState wraps a NamedService with thread-safe state tracking.
type serviceWithState struct {
// service is the underlying named service.
service NamedService
// dependsOn is the validated subset of declared dependencies that exist in the registry.
dependsOn []Name
// mu protects state and startErr from concurrent access.
mu sync.RWMutex
// state is the current lifecycle state of the service.
state State
// healthyC is closed when the service transitions to StateRunning.
healthyC chan struct{}
// startReturnedC is closed when Start() returns, whether with nil or an error.
startReturnedC chan struct{}
// startErr is the error returned by Start(), or nil if it returned successfully.
startErr error
}
func newServiceWithState(service NamedService) *serviceWithState {
return &serviceWithState{
service: service,
state: StateStarting,
healthyC: make(chan struct{}),
startReturnedC: make(chan struct{}),
}
}
func (ss *serviceWithState) setState(state State) {
ss.mu.Lock()
defer ss.mu.Unlock()
ss.state = state
if state == StateRunning {
select {
case <-ss.healthyC:
default:
close(ss.healthyC)
}
}
}
func (ss *serviceWithState) getState() State {
ss.mu.RLock()
defer ss.mu.RUnlock()
return ss.state
}

View File

@@ -23,7 +23,6 @@ type service struct {
authz authz.AuthZ
config user.RootConfig
stopC chan struct{}
healthyC chan struct{}
}
func NewService(
@@ -43,14 +42,12 @@ func NewService(
orgGetter: orgGetter,
authz: authz,
config: config,
stopC: make(chan struct{}),
healthyC: make(chan struct{}),
stopC: make(chan struct{}),
}
}
func (s *service) Start(ctx context.Context) error {
if !s.config.Enabled {
close(s.healthyC)
<-s.stopC
return nil
}
@@ -62,7 +59,6 @@ func (s *service) Start(ctx context.Context) error {
err := s.reconcile(ctx)
if err == nil {
s.settings.Logger().InfoContext(ctx, "root user reconciliation completed successfully")
close(s.healthyC)
<-s.stopC
return nil
}
@@ -78,10 +74,6 @@ func (s *service) Start(ctx context.Context) error {
}
}
func (s *service) Healthy() <-chan struct{} {
return s.healthyC
}
func (s *service) Stop(ctx context.Context) error {
close(s.stopC)
return nil

View File

@@ -3,5 +3,5 @@ package user
import "github.com/SigNoz/signoz/pkg/factory"
type Service interface {
factory.ServiceWithHealthy
factory.Service
}

View File

@@ -55,7 +55,6 @@ type Handlers struct {
ZeusHandler zeus.Handler
QuerierHandler querier.Handler
ServiceAccountHandler serviceaccount.Handler
RegistryHandler factory.Handler
}
func NewHandlers(
@@ -70,7 +69,6 @@ func NewHandlers(
telemetryMetadataStore telemetrytypes.MetadataStore,
authz authz.AuthZ,
zeusService zeus.Zeus,
registryHandler factory.Handler,
) Handlers {
return Handlers{
SavedView: implsavedview.NewHandler(modules.SavedView),
@@ -90,6 +88,5 @@ func NewHandlers(
ZeusHandler: zeus.NewHandler(zeusService, licensing),
QuerierHandler: querierHandler,
ServiceAccountHandler: implserviceaccount.NewHandler(modules.ServiceAccount),
RegistryHandler: registryHandler,
}
}

View File

@@ -10,7 +10,6 @@ import (
"github.com/SigNoz/signoz/pkg/alertmanager/nfmanager/nfmanagertest"
"github.com/SigNoz/signoz/pkg/alertmanager/signozalertmanager"
"github.com/SigNoz/signoz/pkg/emailing/emailingtest"
"github.com/SigNoz/signoz/pkg/factory"
"github.com/SigNoz/signoz/pkg/factory/factorytest"
"github.com/SigNoz/signoz/pkg/flagger"
"github.com/SigNoz/signoz/pkg/instrumentation/instrumentationtest"
@@ -56,8 +55,7 @@ func TestNewHandlers(t *testing.T) {
modules := NewModules(sqlstore, tokenizer, emailing, providerSettings, orgGetter, alertmanager, nil, nil, nil, nil, nil, nil, nil, queryParser, Config{}, dashboardModule, userGetter, userRoleStore)
querierHandler := querier.NewHandler(providerSettings, nil, nil)
registryHandler := factory.NewHandler(nil)
handlers := NewHandlers(modules, providerSettings, nil, querierHandler, nil, nil, nil, nil, nil, nil, nil, registryHandler)
handlers := NewHandlers(modules, providerSettings, nil, querierHandler, nil, nil, nil, nil, nil, nil, nil)
reflectVal := reflect.ValueOf(handlers)
for i := 0; i < reflectVal.NumField(); i++ {
f := reflectVal.Field(i)

View File

@@ -10,7 +10,6 @@ import (
"github.com/SigNoz/signoz/pkg/apiserver"
"github.com/SigNoz/signoz/pkg/apiserver/signozapiserver"
"github.com/SigNoz/signoz/pkg/authz"
"github.com/SigNoz/signoz/pkg/factory"
"github.com/SigNoz/signoz/pkg/flagger"
"github.com/SigNoz/signoz/pkg/gateway"
"github.com/SigNoz/signoz/pkg/global"
@@ -62,7 +61,6 @@ func NewOpenAPI(ctx context.Context, instrumentation instrumentation.Instrumenta
struct{ zeus.Handler }{},
struct{ querier.Handler }{},
struct{ serviceaccount.Handler }{},
struct{ factory.Handler }{},
).New(ctx, instrumentation.ToProviderSettings(), apiserver.Config{})
if err != nil {
return nil, err

View File

@@ -277,7 +277,6 @@ func NewAPIServerProviderFactories(orgGetter organization.Getter, authz authz.Au
handlers.ZeusHandler,
handlers.QuerierHandler,
handlers.ServiceAccountHandler,
handlers.RegistryHandler,
),
)
}

View File

@@ -422,6 +422,21 @@ func New(
// Initialize the querier handler via callback (allows EE to decorate with anomaly detection)
querierHandler := querierHandlerCallback(providerSettings, querier, analytics)
// Initialize all handlers for the modules
handlers := NewHandlers(modules, providerSettings, analytics, querierHandler, licensing, global, flagger, gateway, telemetryMetadataStore, authz, zeus)
// Initialize the API server
apiserver, err := factory.NewProviderFromNamedMap(
ctx,
providerSettings,
config.APIServer,
NewAPIServerProviderFactories(orgGetter, authz, modules, handlers),
"signoz",
)
if err != nil {
return nil, err
}
// Create a list of all stats collectors
statsCollectors := []statsreporter.StatsCollector{
alertmanager,
@@ -448,7 +463,6 @@ func New(
}
registry, err := factory.NewRegistry(
ctx,
instrumentation.Logger(),
factory.NewNamedService(factory.MustNewName("instrumentation"), instrumentation),
factory.NewNamedService(factory.MustNewName("pprof"), pprofService),
@@ -458,23 +472,7 @@ func New(
factory.NewNamedService(factory.MustNewName("statsreporter"), statsReporter),
factory.NewNamedService(factory.MustNewName("tokenizer"), tokenizer),
factory.NewNamedService(factory.MustNewName("authz"), authz),
factory.NewNamedService(factory.MustNewName("user"), userService, factory.MustNewName("authz")),
)
if err != nil {
return nil, err
}
// Initialize all handlers for the modules
registryHandler := factory.NewHandler(registry)
handlers := NewHandlers(modules, providerSettings, analytics, querierHandler, licensing, global, flagger, gateway, telemetryMetadataStore, authz, zeus, registryHandler)
// Initialize the API server (after registry so it can access service health)
apiserverInstance, err := factory.NewProviderFromNamedMap(
ctx,
providerSettings,
config.APIServer,
NewAPIServerProviderFactories(orgGetter, authz, modules, handlers),
"signoz",
factory.NewNamedService(factory.MustNewName("user"), userService),
)
if err != nil {
return nil, err
@@ -492,7 +490,7 @@ func New(
Prometheus: prometheus,
Alertmanager: alertmanager,
Querier: querier,
APIServer: apiserverInstance,
APIServer: apiserver,
Zeus: zeus,
Licensing: licensing,
Emailing: emailing,

View File

@@ -108,24 +108,16 @@ def create_signoz(
for attempt in range(10):
try:
response = requests.get(
f"http://{container.get_container_host_ip()}:{container.get_exposed_port(8080)}/api/v2/healthz",
f"http://{container.get_container_host_ip()}:{container.get_exposed_port(8080)}/api/v1/health",
timeout=2,
)
if response.status_code == HTTPStatus.OK:
return
if response.status_code == HTTPStatus.SERVICE_UNAVAILABLE:
logger.error(
"Attempt %s: SigNoz container %s not ready yet:\n%s",
attempt + 1,
container,
response.text,
)
except Exception as e: # pylint: disable=broad-exception-caught
logger.error(
"Attempt %s at readiness check for SigNoz container %s failed: %s",
except Exception: # pylint: disable=broad-exception-caught
logger.info(
"Attempt %s at readiness check for SigNoz container %s failed, going to retry ...",
attempt + 1,
container,
e,
)
time.sleep(2)
raise TimeoutError("timeout exceeded while waiting")

View File

@@ -1,4 +1,3 @@
import logging
from http import HTTPStatus
import numpy as np
@@ -6,20 +5,13 @@ import requests
from fixtures import types
logger = logging.getLogger(__name__)
def test_setup(signoz: types.SigNoz) -> None:
response = requests.get(
signoz.self.host_configs["8080"].get("/api/v1/version"), timeout=2
)
assert response.status_code == HTTPStatus.OK
healthz = requests.get(
signoz.self.host_configs["8080"].get("/api/v2/healthz"), timeout=2
)
logger.info("healthz response: %s", healthz.json())
assert healthz.status_code == HTTPStatus.OK
assert response.status_code == HTTPStatus.OK
def test_telemetry_databases_exist(signoz: types.SigNoz) -> None: