Compare commits

..

25 Commits

Author SHA1 Message Date
nityanandagohain
b9ec4a5efd fix: support for quick filters 2026-07-17 12:54:45 +05:30
nityanandagohain
247c3c4aee feat: support for trace aggregate in metadata endpoint 2026-07-17 00:41:07 +05:30
nityanandagohain
cce080e1ae fix: add back the flag in metadata 2026-07-16 11:37:57 +05:30
nityanandagohain
deca060a4d Merge remote-tracking branch 'origin/main' into issue_5601 2026-07-16 11:00:55 +05:30
Vinicius Lourenço
f24102c0db feat(infrastructure-monitoring-v2): pod status/counts & couple more fixes (#12127)
* refactor(infrastructure-monitoring-v2): remove pod phase and add pod status/counts

* fix(column-header): align to left

* fix(cell-value): ensure tooltip is correctly aligned

* fix(entity-traces): use - instead of N/A

* test(entity-traces): fix broken test
2026-07-16 03:34:12 +00:00
Vinicius Lourenço
edee102b52 feat(infrastructure-monitoring): add pod metrics tab (#12106)
* fix(k8s-base-details): do not allow untoggle tabs

* feat(constants): add base queries for all workloads

Ref: https://github.com/SigNoz/engineering-pod/issues/4032#issuecomment-4893103716

* feat(daemon-sets): add pod metrics tab

* feat(deployments): add pod metrics tab

* feat(jobs): add pod metrics tab

* feat(namespaces): add pod metrics tab

* feat(statefulsets): add pod metrics tab

* fix(k8s-base-details): do not keep selected invalid tab

* fix(pod-metrics): add new badge

* Revert "fix(pod-metrics): add new badge"

This reverts commit 09b8624f52.

* chore(k8s-base-details): mark tab as possible null
2026-07-16 03:30:33 +00:00
Srikanth Chekuri
9a26998d18 chore: add integration tests for metrics under reduction - query part (#11979)
Some checks failed
build-staging / prepare (push) Has been cancelled
build-staging / js-build (push) Has been cancelled
build-staging / go-build (push) Has been cancelled
build-staging / staging (push) Has been cancelled
Release Drafter / update_release_draft (push) Has been cancelled
* chore: add integration tests for metrics under reduction - query part

* chore: add to ci

* chore: add todos

* chore: update tests

* chore: trigger build

* chore: address review comments

* chore: undo the changes to tests/fixtures/http.py

* chore: remove __normalized and add fast path

* chore: fix unit tests

* chore: update test

* chore: sunset 25.5.6, update migrator version, and remove version arg

* chore: also update devenv

---------

Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
2026-07-15 21:27:39 +00:00
Vinicius Lourenço
fbf2e62044 feat(infrastructure-monitoring-v2): add onboarding checks (#12119)
* feat(infrastructure-monitoring): add onboarding checks

* refactor(infrastructure-monitoring): use error content to show error message

* test(infrastructure-monitoring): add tests for onboarding checks
2026-07-15 19:47:30 +00:00
Tushar Vats
62c44f5eac chore: pass org id for flagger (#12126) 2026-07-15 19:47:24 +00:00
nityanandagohain
03c7e524e7 fix: fix tests 2026-07-15 20:23:33 +05:30
nityanandagohain
815dc7d88b Merge remote-tracking branch 'origin/main' into issue_5601 2026-07-15 20:10:05 +05:30
nityanandagohain
f50d9199fe fix: address comments 2026-07-15 19:47:39 +05:30
Vinicius Lourenço
65fde71b72 feat(infrastructure-monitoring-v2): add counts cards (#12120)
Some checks failed
build-staging / prepare (push) Has been cancelled
build-staging / js-build (push) Has been cancelled
build-staging / go-build (push) Has been cancelled
build-staging / staging (push) Has been cancelled
Release Drafter / update_release_draft (push) Has been cancelled
* feat(entity-count): add base structure to show count

* feat(entity-count): add count for clusters

* feat(entity-count): add count for namespaces

* chore(infra-monitoring): move component to be under components folder

* fix(pr): address comments
2026-07-15 13:39:48 +00:00
Vinicius Lourenço
7f5f63b20a feat(infra-monitoring): add docs for every chart (#12037)
* feat(infra-monitoring): add docs for every chart

* fix(docs): add missing docs for each column/chart

* fix(infra-monitoring): keep referer

---------

Co-authored-by: Nikhil Mantri <nikhil.mantri1999@gmail.com>
2026-07-15 13:25:53 +00:00
Tushar Vats
63cfbe8bfb fix: convert key not found to warnings for traces (#12091) 2026-07-15 12:33:47 +00:00
nityanandagohain
31efe177a4 fix: address comments 2026-07-14 18:53:30 +05:30
nityanandagohain
d502d12ac3 fix: update openapi 2026-07-10 14:27:07 +05:30
nityanandagohain
bd9f15a716 fix: update integration test 2026-07-10 14:21:16 +05:30
nityanandagohain
813ef988c9 fix: edge cases and correct cost key 2026-07-10 12:06:34 +05:30
nityanandagohain
40e6799285 fix: add resource fingerprint cte 2026-07-10 00:36:25 +05:30
nityanandagohain
1caa60a3cd fix: cleanup and more tests 2026-07-09 23:54:05 +05:30
nityanandagohain
3f781f0083 fix: more cleanup 2026-07-09 12:39:01 +05:30
nityanandagohain
6aec05cf7a fix: more tests 2026-07-09 08:45:22 +05:30
nityanandagohain
683a52f35a fix: take perf into consideration 2026-07-09 08:45:22 +05:30
nityanandagohain
e924fa1e62 feat: support llm trace list and span list 2026-07-09 08:45:20 +05:30
231 changed files with 9910 additions and 6314 deletions

View File

@@ -1,6 +1,6 @@
services:
init-clickhouse:
image: clickhouse/clickhouse-server:25.5.6
image: clickhouse/clickhouse-server:25.12.5
container_name: init-clickhouse
command:
- bash
@@ -18,7 +18,7 @@ services:
volumes:
- ${PWD}/fs/tmp/var/lib/clickhouse/user_scripts/:/var/lib/clickhouse/user_scripts/
clickhouse:
image: clickhouse/clickhouse-server:25.5.6
image: clickhouse/clickhouse-server:25.12.5
container_name: clickhouse
volumes:
- ${PWD}/fs/etc/clickhouse-server/config.d/config.xml:/etc/clickhouse-server/config.d/config.xml
@@ -67,7 +67,7 @@ services:
timeout: 5s
retries: 3
telemetrystore-migrator:
image: signoz/signoz-otel-collector:v0.142.0
image: signoz/signoz-otel-collector:v0.144.6
container_name: telemetrystore-migrator
environment:
- SIGNOZ_OTEL_COLLECTOR_CLICKHOUSE_DSN=tcp://clickhouse:9000

View File

@@ -53,24 +53,25 @@ jobs:
- queriermetrics
- querierscalar
- queriercommon
- querierai
- rawexportdata
- role
- rootuser
- serviceaccount
- querier_json_body
- promqlparity
- querier_skip_resource_fingerprint
- ttl
- clickhousecluster
- metricreduction
sqlstore-provider:
- postgres
- sqlite
sqlite-mode:
- wal
clickhouse-version:
- 25.5.6
- 25.12.5
schema-migrator-version:
- v0.144.3
- v0.144.6
postgres-version:
- 15
if: |

View File

@@ -8565,6 +8565,7 @@ components:
TelemetrytypesSource:
enum:
- meter
- ai
type: string
TelemetrytypesTelemetryFieldKey:
properties:

View File

@@ -3631,6 +3631,7 @@ export enum Querybuildertypesv5QueryBuilderQueryGithubComSigNozSignozPkgTypesQue
}
export enum TelemetrytypesSourceDTO {
meter = 'meter',
ai = 'ai',
}
export interface Querybuildertypesv5QueryBuilderQueryGithubComSigNozSignozPkgTypesQuerybuildertypesQuerybuildertypesv5LogAggregationDTO {
/**

View File

@@ -1,13 +1,17 @@
import { useCallback, useEffect, useRef, useState } from 'react';
import { Button, Tooltip } from 'antd';
import { Typography } from '@signozhq/ui/typography';
import { convertToApiError } from 'api/ErrorResponseHandlerForGeneratedAPIs';
import { listHosts } from 'api/generated/services/inframonitoring';
import {
InframonitoringtypesHostRecordDTO,
InframonitoringtypesHostStatusDTO,
InframonitoringtypesResponseTypeDTO,
Querybuildertypesv5OrderDirectionDTO,
RenderErrorResponseDTO,
} from 'api/generated/services/sigNoz.schemas';
import { AxiosError } from 'axios';
import APIError from 'types/api/error';
import QuickFilters from 'components/QuickFilters/QuickFilters';
import { QuickFiltersSource } from 'components/QuickFilters/types';
import { InfraMonitoringEvents } from 'constants/events';
@@ -122,13 +126,12 @@ function Hosts(): JSX.Element {
endTimeBeforeRetention: data.endTimeBeforeRetention,
};
} catch (error) {
const errMsg =
error instanceof Error ? error.message : 'Failed to fetch hosts';
return {
type: 'list' as const,
records: [] as InframonitoringtypesHostRecordDTO[],
total: 0,
error: errMsg,
error:
convertToApiError(error as AxiosError<RenderErrorResponseDTO>) ?? null,
};
}
},
@@ -141,7 +144,7 @@ function Hosts(): JSX.Element {
signal?: AbortSignal,
): Promise<{
data: InframonitoringtypesHostRecordDTO | null;
error?: string | null;
error?: APIError | null;
}> => {
try {
const response = await listHosts(
@@ -159,11 +162,10 @@ function Hosts(): JSX.Element {
data: response.data.records.length > 0 ? response.data.records[0] : null,
};
} catch (error) {
const errMsg =
error instanceof Error ? error.message : 'Failed to fetch host';
return {
data: null,
error: errMsg,
error:
convertToApiError(error as AxiosError<RenderErrorResponseDTO>) ?? null,
};
}
},

View File

@@ -11,8 +11,6 @@ import { INFRA_MONITORING_ATTR_KEYS } from 'container/InfraMonitoringK8sV2/const
import { CellValueTooltip } from 'container/InfraMonitoringK8sV2/components';
import { DataTypes } from 'types/api/queryBuilder/queryAutocompleteResponse';
import { DataSource } from 'types/common/queryBuilder';
import TanStackTable from 'components/TanStackTableView';
const HOSTNAME_DOCS_URL =
'https://signoz.io/docs/infrastructure-monitoring/hostmetrics/#host-name-is-blankempty';
@@ -23,11 +21,7 @@ export function HostnameCell({
}): React.ReactElement {
const isEmpty = !hostName || !hostName.trim();
if (!isEmpty) {
return (
<CellValueTooltip value={hostName}>
<TanStackTable.Text>{hostName}</TanStackTable.Text>
</CellValueTooltip>
);
return <CellValueTooltip value={hostName} />;
}
return (
<>

View File

@@ -11,6 +11,6 @@
}
.columnHeaderLabel {
text-align: center;
text-align: left;
padding: var(--spacing-2) var(--spacing-2) var(--spacing-2) 0px;
}

View File

@@ -51,7 +51,7 @@ function ColumnHeader({
<a
href={`${DOCS_BASE_URL}${docPath}`}
target="_blank"
rel="noopener noreferrer"
rel="noopener"
onClick={(e): void => e.stopPropagation()}
>
Learn more.

View File

@@ -30,7 +30,7 @@ function EntityGroupHeader({
<a
href={`${DOCS_BASE_URL}${docPath}`}
target="_blank"
rel="noopener noreferrer"
rel="noopener"
onClick={(e): void => e.stopPropagation()}
>
Learn more.

View File

@@ -12,6 +12,8 @@ import { ToggleGroupSimple } from '@signozhq/ui/toggle-group';
import { Divider } from '@signozhq/ui/divider';
import { Typography } from '@signozhq/ui/typography';
import logEvent from 'api/common/logEvent';
import ErrorContent from 'components/ErrorModal/components/ErrorContent';
import APIError from 'types/api/error';
import { combineInitialAndUserExpression } from 'components/QueryBuilderV2/QueryV2/QuerySearch/utils';
import { InfraMonitoringEvents } from 'constants/events';
import { QueryParams } from 'constants/query';
@@ -63,6 +65,10 @@ import LoadingContainer from '../LoadingContainer';
import '../EntityDetailsUtils/entityDetails.styles.scss';
import { parseAsString, useQueryState } from 'nuqs';
import {
EntityCountConfig,
EntityCountsSection,
} from './components/EntityCountsSection/EntityCountsSection';
const TimeRangeOffset = 1000000000;
@@ -72,12 +78,31 @@ export interface K8sDetailsMetadataConfig<T> {
render?: (value: string | number, entity: T) => React.ReactNode;
}
export type K8sDetailsCountConfig<T> = EntityCountConfig<T>;
export interface K8sDetailsFilters {
filter: { expression: string };
start: number;
end: number;
}
export interface CustomTabRenderProps<T> {
entity: T;
timeRange: { startTime: number; endTime: number };
selectedInterval: Time;
handleTimeChange: (
interval: Time | CustomTimeType,
dateTimeRange?: [number, number],
) => void;
}
export interface CustomTab<T> {
key: string;
label: string;
icon: React.ReactNode;
render: (props: CustomTabRenderProps<T>) => React.ReactNode;
}
export interface K8sBaseDetailsProps<T> {
category: InfraMonitoringEntity;
eventCategory: string;
@@ -86,15 +111,18 @@ export interface K8sBaseDetailsProps<T> {
fetchEntityData: (
filters: K8sDetailsFilters,
signal?: AbortSignal,
) => Promise<{ data: T | null; error?: string | null }>;
) => Promise<{ data: T | null; error?: APIError | null }>;
// Entity configuration
getEntityName: (entity: T) => string;
getInitialLogTracesExpression: (entity: T) => string;
getInitialEventsExpression: (entity: T) => string;
metadataConfig: K8sDetailsMetadataConfig<T>[];
countsConfig?: K8sDetailsCountConfig<T>[];
getCountsFilterExpression?: (entity: T) => string;
entityWidgetInfo: {
title: string;
yAxisUnit: string;
docPath?: string;
}[];
getEntityQueryPayload: (
entity: T,
@@ -111,20 +139,7 @@ export interface K8sBaseDetailsProps<T> {
showTraces?: boolean;
showEvents?: boolean;
};
customTabs?: Array<{
key: string;
label: string;
icon: React.ReactNode;
render: (props: {
entity: T;
timeRange: { startTime: number; endTime: number };
selectedInterval: Time;
handleTimeChange: (
interval: Time | CustomTimeType,
dateTimeRange?: [number, number],
) => void;
}) => React.ReactNode;
}>;
customTabs?: Array<CustomTab<T>>;
}
// eslint-disable-next-line sonarjs/cognitive-complexity
@@ -137,6 +152,8 @@ export default function K8sBaseDetails<T>({
getInitialLogTracesExpression,
getInitialEventsExpression,
metadataConfig,
countsConfig,
getCountsFilterExpression,
entityWidgetInfo,
getEntityQueryPayload,
queryKeyPrefix,
@@ -258,6 +275,33 @@ export default function K8sBaseDetails<T>({
const [selectedView, setSelectedView] = useInfraMonitoringView();
const effectiveView = hideDetailViewTabs ? VIEW_TYPES.METRICS : selectedView;
const validTabs = useMemo(() => {
const tabs: string[] = [];
if (tabVisibility.showMetrics) {
tabs.push(VIEW_TYPES.METRICS);
}
if (tabVisibility.showLogs) {
tabs.push(VIEW_TYPES.LOGS);
}
if (tabVisibility.showTraces) {
tabs.push(VIEW_TYPES.TRACES);
}
if (tabVisibility.showEvents) {
tabs.push(VIEW_TYPES.EVENTS);
}
if (customTabs) {
tabs.push(...customTabs.map((t) => t.key));
}
return tabs;
}, [tabVisibility, customTabs]);
useEffect(() => {
if (!hideDetailViewTabs && !validTabs.includes(selectedView)) {
const firstValid = validTabs[0] || VIEW_TYPES.METRICS;
void setSelectedView(firstValid);
}
}, [hideDetailViewTabs, selectedView, validTabs, setSelectedView]);
const [, setLogFiltersParam] = useInfraMonitoringLogFilters();
const [, setTracesFiltersParam] = useInfraMonitoringTracesFilters();
const [, setEventsFiltersParam] = useInfraMonitoringEventsFilters();
@@ -293,7 +337,10 @@ export default function K8sBaseDetails<T>({
}
}, [getMinMaxTime, selectedTime]);
const handleTabChange = (value: string): void => {
const handleTabChange = (value: string | null): void => {
if (!value) {
return;
}
setSelectedView(value);
setLogFiltersParam(null);
setTracesFiltersParam(null);
@@ -436,12 +483,18 @@ export default function K8sBaseDetails<T>({
{isEntityLoading && <LoadingContainer />}
{(isEntityError || hasResponseError) && (
<div className="entity-error-container">
<Typography.Text color="danger">
{entityResponse?.error ||
(entityError instanceof Error
? entityError.message
: 'Failed to load entity details')}
</Typography.Text>
<ErrorContent
error={
entityResponse?.error ??
(entityError instanceof APIError ? entityError : null) ?? {
code: 500,
message:
entityError instanceof Error
? entityError.message
: 'Failed to load entity details',
}
}
/>
</div>
)}
{entity && !isEntityLoading && !hasResponseError && (
@@ -479,6 +532,19 @@ export default function K8sBaseDetails<T>({
})}
</div>
</div>
{countsConfig &&
countsConfig.length > 0 &&
selectedItem &&
getCountsFilterExpression && (
<EntityCountsSection
entity={entity}
countsConfig={countsConfig}
selectedItem={selectedItem}
filterExpression={getCountsFilterExpression(entity)}
closeDrawer={handleClose}
/>
)}
</div>
{!hideDetailViewTabs && (

View File

@@ -14,6 +14,7 @@ import { useGlobalTimeStore } from 'store/globalTime';
import { NANO_SECOND_MULTIPLIER } from 'store/globalTime/utils';
import { Querybuildertypesv5QueryWarnDataDTO } from 'api/generated/services/sigNoz.schemas';
import { openInNewTab } from 'utils/navigation';
import APIError from 'types/api/error';
import {
INFRA_MONITORING_K8S_PARAMS_KEYS,
@@ -33,13 +34,14 @@ import K8sHeader from './K8sHeader';
import { K8sPaginationWarning } from './K8sPaginationWarning';
import { K8sBaseFilters } from './types';
import { getGroupedByMeta } from './utils';
import { K8sInstrumentationChecksCallout } from './components/K8sInstrumentationChecksCallout/K8sInstrumentationChecksCallout';
import styles from './K8sBaseList.module.scss';
import cx from 'classnames';
export type K8sBaseListEmptyStateContext = {
isError: boolean;
error?: string | null;
error?: APIError | null;
totalCount: number;
hasFilters: boolean;
isLoading: boolean;
@@ -66,7 +68,7 @@ export type K8sBaseListProps<
records?: T[];
data?: T[];
total: number;
error?: string | null;
error?: APIError | null;
rawData?: unknown;
endTimeBeforeRetention?: boolean;
warning?: Querybuildertypesv5QueryWarnDataDTO | null;
@@ -377,6 +379,8 @@ export function K8sBaseList<
cancelQuery={cancelQuery}
/>
<div ref={containerRef} className={styles.tableContainer}>
<K8sInstrumentationChecksCallout entity={entity} />
{isError && (
<Typography>
{data?.error?.toString() || 'Something went wrong'}

View File

@@ -44,13 +44,11 @@
width: 32px;
}
.errorIcon {
color: var(--danger-background);
}
.actions {
.errorContent {
display: flex;
flex-direction: column;
align-items: center;
gap: 8px;
margin-top: 16px;
gap: var(--spacing-3);
max-width: 500px;
padding: 24px;
}

View File

@@ -1,8 +1,4 @@
import { useCallback } from 'react';
import { Button } from '@signozhq/ui/button';
import { useGetTenantLicense } from 'hooks/useGetTenantLicense';
import history from 'lib/history';
import { LifeBuoy, TriangleAlert } from '@signozhq/icons';
import ErrorContent from 'components/ErrorModal/components/ErrorContent';
import emptyStateUrl from '@/assets/Icons/emptyState.svg';
import eyesEmojiUrl from '@/assets/Images/eyesEmoji.svg';
@@ -13,26 +9,12 @@ import styles from './K8sEmptyState.module.scss';
type K8sEmptyStateProps = Partial<K8sBaseListEmptyStateContext>;
const handleContactSupport = (isCloudUser: boolean): void => {
if (isCloudUser) {
history.push('/support');
} else {
window.open('https://signoz.io/slack', '_blank');
}
};
export function K8sEmptyState({
isError,
error,
isLoading,
endTimeBeforeRetention,
}: K8sEmptyStateProps): JSX.Element | null {
const { isCloudUser } = useGetTenantLicense();
const handleSupport = useCallback(() => {
handleContactSupport(isCloudUser);
}, [isCloudUser]);
if (isLoading) {
return null;
}
@@ -40,25 +22,15 @@ export function K8sEmptyState({
if (isError || error) {
return (
<div className={styles.container}>
<div className={styles.content}>
<TriangleAlert size={32} className={styles.errorIcon} />
<span className={styles.message}>
{error || 'An error occurred while fetching data.'}
</span>
<p>
Our team is getting on top to resolve this. Please reach out to support if
the issue persists.
</p>
<div className={styles.actions}>
<Button
onClick={handleSupport}
variant="solid"
color="secondary"
prefix={<LifeBuoy size={14} />}
>
Contact Support
</Button>
</div>
<div className={styles.errorContent}>
<ErrorContent
error={
error ?? {
code: 500,
message: 'An error occurred while fetching data.',
}
}
/>
</div>
</div>
);

View File

@@ -4,6 +4,7 @@ import { useLocation } from 'react-router-dom';
import { Querybuildertypesv5QueryWarnDataDTO } from 'api/generated/services/sigNoz.schemas';
import { Button } from '@signozhq/ui/button';
import { Typography } from '@signozhq/ui/typography';
import APIError from 'types/api/error';
import TanStackTable, {
SortState,
TableColumnDef,
@@ -51,7 +52,7 @@ export type K8sExpandedRowProps<T, TItemKey = string> = {
records?: T[];
data?: T[];
total: number;
error?: string | null;
error?: APIError | null;
rawData?: unknown;
warning?: Querybuildertypesv5QueryWarnDataDTO | null;
}>;

View File

@@ -0,0 +1,221 @@
import { Box } from '@signozhq/icons';
import { screen } from '@testing-library/react';
import userEvent from '@testing-library/user-event';
import { NuqsTestingAdapter } from 'nuqs/adapters/testing';
import { act, render, waitFor } from 'tests/test-utils';
import {
InfraMonitoringEntity,
INFRA_MONITORING_K8S_PARAMS_KEYS,
VIEW_TYPES,
} from '../../constants';
import K8sBaseDetails from '../K8sBaseDetails';
jest.mock('container/TopNav/DateTimeSelectionV2/index.tsx', () => ({
__esModule: true,
default: (): JSX.Element => <div data-testid="mock-datetime" />,
}));
type TestEntity = {
name: string;
namespace: string;
cluster: string;
};
const mockEntity: TestEntity = {
name: 'test-pod',
namespace: 'default',
cluster: 'test-cluster',
};
function createBaseProps() {
return {
category: InfraMonitoringEntity.PODS,
eventCategory: 'Pod',
getSelectedItemExpression: (): string => 'k8s.pod.name = "test-pod"',
fetchEntityData: jest
.fn()
.mockResolvedValue({ data: mockEntity, error: null }),
getEntityName: (e: TestEntity): string => e.name,
getInitialLogTracesExpression: (): string => 'k8s.pod.name = "test-pod"',
getInitialEventsExpression: (): string => 'k8s.pod.name = "test-pod"',
metadataConfig: [
{ label: 'Name', getValue: (e: TestEntity): string => e.name },
],
entityWidgetInfo: [{ title: 'CPU', yAxisUnit: 'percent' }],
getEntityQueryPayload: jest.fn().mockReturnValue([]),
queryKeyPrefix: 'testPod',
};
}
interface RenderOptions {
view?: string;
tabsConfig?: {
showMetrics?: boolean;
showLogs?: boolean;
showTraces?: boolean;
showEvents?: boolean;
};
customTabs?: Array<{
key: string;
label: string;
icon: React.ReactNode;
render: () => React.ReactNode;
}>;
}
function renderK8sBaseDetails({
view = VIEW_TYPES.METRICS,
tabsConfig,
customTabs,
}: RenderOptions = {}) {
const searchParams: Record<string, string> = {
[INFRA_MONITORING_K8S_PARAMS_KEYS.SELECTED_ITEM]: 'test-pod',
[INFRA_MONITORING_K8S_PARAMS_KEYS.VIEW]: view,
};
return render(
<NuqsTestingAdapter searchParams={searchParams}>
<K8sBaseDetails<TestEntity>
{...createBaseProps()}
tabsConfig={tabsConfig}
customTabs={customTabs}
/>
</NuqsTestingAdapter>,
);
}
function getSelectedTabText(): string | null {
const selectedTab = document.querySelector('[aria-checked="true"]');
return selectedTab?.textContent ?? null;
}
describe('K8sBaseDetails - Tab Validation', () => {
it('should reset view to METRICS when selected view is invalid', async () => {
act(() => {
renderK8sBaseDetails({ view: 'invalid-tab' });
});
await waitFor(() => {
expect(screen.getAllByText('test-pod').length).toBeGreaterThan(0);
});
await waitFor(() => {
expect(getSelectedTabText()).toContain('Metrics');
});
});
it('should reset to first available tab when METRICS is disabled and view is invalid', async () => {
act(() => {
renderK8sBaseDetails({
view: 'invalid-tab',
tabsConfig: { showMetrics: false },
});
});
await waitFor(() => {
expect(screen.getAllByText('test-pod').length).toBeGreaterThan(0);
});
await waitFor(() => {
expect(getSelectedTabText()).toContain('Logs');
});
});
it('should reset to custom tab when all standard tabs disabled and custom tab exists', async () => {
const customTabKey = 'pod-metrics';
act(() => {
renderK8sBaseDetails({
view: 'invalid-tab',
tabsConfig: {
showMetrics: false,
showLogs: false,
showTraces: false,
showEvents: false,
},
customTabs: [
{
key: customTabKey,
label: 'Pod Metrics',
icon: <Box size={14} />,
render: (): React.ReactNode => <div>Custom Tab</div>,
},
],
});
});
await waitFor(() => {
expect(screen.getAllByText('test-pod').length).toBeGreaterThan(0);
});
await waitFor(() => {
expect(getSelectedTabText()).toContain('Pod Metrics');
});
});
it('should NOT reset view when selected view is valid', async () => {
act(() => {
renderK8sBaseDetails({ view: VIEW_TYPES.LOGS });
});
await waitFor(() => {
expect(screen.getAllByText('test-pod').length).toBeGreaterThan(0);
});
await waitFor(() => {
expect(getSelectedTabText()).toContain('Logs');
});
});
it('should NOT reset view when custom tab is selected and exists', async () => {
const customTabKey = 'pod-metrics';
act(() => {
renderK8sBaseDetails({
view: customTabKey,
customTabs: [
{
key: customTabKey,
label: 'Pod Metrics',
icon: <Box size={14} />,
render: (): React.ReactNode => <div>Custom Tab</div>,
},
],
});
});
await waitFor(() => {
expect(screen.getAllByText('test-pod').length).toBeGreaterThan(0);
});
await waitFor(() => {
expect(getSelectedTabText()).toContain('Pod Metrics');
});
});
it('should keep the selected tab when the active tab is clicked again (untoggle guard)', async () => {
const user = userEvent.setup();
act(() => {
renderK8sBaseDetails({ view: VIEW_TYPES.LOGS });
});
await waitFor(() => {
expect(screen.getAllByText('test-pod').length).toBeGreaterThan(0);
});
await waitFor(() => {
expect(getSelectedTabText()).toContain('Logs');
});
const selectedTab = document.querySelector('[aria-checked="true"]');
expect(selectedTab).not.toBeNull();
await user.click(selectedTab as Element);
await waitFor(() => {
expect(getSelectedTabText()).toContain('Logs');
});
});
});

View File

@@ -9,6 +9,8 @@ import { TooltipProvider } from '@signozhq/ui/tooltip';
import { fireEvent, render, screen, waitFor } from '@testing-library/react';
import userEvent from '@testing-library/user-event';
import { InfraMonitoringEvents } from 'constants/events';
import { server } from 'mocks-server/server';
import { rest } from 'msw';
import {
NuqsTestingAdapter,
OnUrlUpdateFunction,
@@ -17,6 +19,7 @@ import {
import { AppProvider } from 'providers/App/App';
import TimezoneProvider from 'providers/Timezone';
import store from 'store';
import APIError from 'types/api/error';
import { openInNewTab } from 'utils/navigation';
import { TableColumnDef } from 'components/TanStackTableView';
@@ -630,7 +633,15 @@ describe('K8sBaseList', () => {
fetchListDataMock.mockResolvedValue({
data: [],
total: 0,
error: 'Failed to fetch pods',
error: new APIError({
httpStatusCode: 500,
error: {
code: '500',
message: 'Failed to fetch pods',
url: '',
errors: [],
},
}),
});
renderComponent<TestItem>({
@@ -1054,4 +1065,304 @@ describe('K8sBaseList', () => {
expect(url).not.toContain('selectedItemNamespaceName');
});
});
describe('instrumentation checks callout', () => {
const fetchListDataMock = jest.fn<
ReturnType<NonNullable<K8sBaseListProps<TestItem>['fetchListData']>>,
Parameters<NonNullable<K8sBaseListProps<TestItem>['fetchListData']>>
>();
beforeEach(() => {
fetchListDataMock.mockClear();
fetchListDataMock.mockResolvedValue({
data: [{ id: 'item-1' }],
total: 1,
error: null,
});
});
it('should not render callout when ready is true', async () => {
server.use(
rest.get('http://localhost/api/v2/infra_monitoring/checks', (_, res, ctx) =>
res(
ctx.json({
status: 'success',
data: {
ready: true,
type: 'pods',
presentDefaultEnabledMetrics: [
{
associatedComponent: { name: 'otel-collector' },
metrics: ['k8s.pod.cpu.usage'],
},
],
},
}),
),
),
);
renderComponent<TestItem>({
entity: InfraMonitoringEntity.PODS,
eventCategory: InfraMonitoringEvents.Pod,
fetchListData: fetchListDataMock,
tableColumns: createTestColumns(),
getRowKey: (row): string => row.id,
getItemKey: (row): string => row.id,
});
await screen.findByText('item-1');
expect(screen.queryByText('Instrumentation checks')).not.toBeInTheDocument();
});
it('should not render callout when no entries exist', async () => {
server.use(
rest.get('http://localhost/api/v2/infra_monitoring/checks', (_, res, ctx) =>
res(
ctx.json({
status: 'success',
data: {
ready: false,
type: 'pods',
presentDefaultEnabledMetrics: null,
presentOptionalMetrics: null,
presentRequiredAttributes: null,
missingDefaultEnabledMetrics: null,
missingOptionalMetrics: null,
missingRequiredAttributes: null,
},
}),
),
),
);
renderComponent<TestItem>({
entity: InfraMonitoringEntity.PODS,
eventCategory: InfraMonitoringEvents.Pod,
fetchListData: fetchListDataMock,
tableColumns: createTestColumns(),
getRowKey: (row): string => row.id,
getItemKey: (row): string => row.id,
});
await screen.findByText('item-1');
expect(screen.queryByText('Instrumentation checks')).not.toBeInTheDocument();
});
it('should render callout with present entries', async () => {
server.use(
rest.get('http://localhost/api/v2/infra_monitoring/checks', (_, res, ctx) =>
res(
ctx.json({
status: 'success',
data: {
ready: false,
type: 'pods',
presentDefaultEnabledMetrics: [
{
associatedComponent: { name: 'otel-collector' },
metrics: ['k8s.pod.cpu.usage', 'k8s.pod.memory.usage'],
},
],
presentOptionalMetrics: null,
presentRequiredAttributes: null,
missingDefaultEnabledMetrics: null,
missingOptionalMetrics: null,
missingRequiredAttributes: null,
},
}),
),
),
);
renderComponent<TestItem>({
entity: InfraMonitoringEntity.PODS,
eventCategory: InfraMonitoringEvents.Pod,
fetchListData: fetchListDataMock,
tableColumns: createTestColumns(),
getRowKey: (row): string => row.id,
getItemKey: (row): string => row.id,
});
await screen.findByText('Instrumentation checks');
await expect(
screen.findByText('Default enabled metrics'),
).resolves.toBeInTheDocument();
await expect(
screen.findByText('k8s.pod.cpu.usage, k8s.pod.memory.usage'),
).resolves.toBeInTheDocument();
await expect(
screen.findByText('otel-collector'),
).resolves.toBeInTheDocument();
});
it('should render callout with missing entries', async () => {
server.use(
rest.get('http://localhost/api/v2/infra_monitoring/checks', (_, res, ctx) =>
res(
ctx.json({
status: 'success',
data: {
ready: false,
type: 'pods',
presentDefaultEnabledMetrics: null,
presentOptionalMetrics: null,
presentRequiredAttributes: null,
missingDefaultEnabledMetrics: [
{
associatedComponent: { name: 'otel-collector' },
metrics: ['k8s.pod.cpu.limit'],
documentationLink: 'https://example.com/docs',
},
],
missingOptionalMetrics: null,
missingRequiredAttributes: null,
},
}),
),
),
);
renderComponent<TestItem>({
entity: InfraMonitoringEntity.PODS,
eventCategory: InfraMonitoringEvents.Pod,
fetchListData: fetchListDataMock,
tableColumns: createTestColumns(),
getRowKey: (row): string => row.id,
getItemKey: (row): string => row.id,
});
await screen.findByText('Instrumentation checks');
await expect(
screen.findByText('Missing default metrics'),
).resolves.toBeInTheDocument();
await expect(
screen.findByText('k8s.pod.cpu.limit'),
).resolves.toBeInTheDocument();
await expect(screen.findByText('Learn here')).resolves.toBeInTheDocument();
});
it('should trigger recheck on button click', async () => {
let recheckCallCount = 0;
server.use(
rest.get(
'http://localhost/api/v2/infra_monitoring/checks',
(_, res, ctx) => {
recheckCallCount++;
return res(
ctx.json({
status: 'success',
data: {
ready: false,
type: 'pods',
presentDefaultEnabledMetrics: [
{
associatedComponent: { name: 'otel-collector' },
metrics: ['k8s.pod.cpu.usage'],
},
],
},
}),
);
},
),
);
const user = userEvent.setup();
renderComponent<TestItem>({
entity: InfraMonitoringEntity.PODS,
eventCategory: InfraMonitoringEvents.Pod,
fetchListData: fetchListDataMock,
tableColumns: createTestColumns(),
getRowKey: (row): string => row.id,
getItemKey: (row): string => row.id,
});
await screen.findByText('Instrumentation checks');
const initialCallCount = recheckCallCount;
const recheckBtn = screen.getByTestId('instrumentation-checks-recheck-btn');
await user.click(recheckBtn);
await waitFor(() => {
expect(recheckCallCount).toBeGreaterThan(initialCallCount);
});
});
it('should render both present and missing entries', async () => {
server.use(
rest.get('http://localhost/api/v2/infra_monitoring/checks', (_, res, ctx) =>
res(
ctx.json({
status: 'success',
data: {
ready: false,
type: 'pods',
presentDefaultEnabledMetrics: [
{
associatedComponent: { name: 'otel-collector' },
metrics: ['k8s.pod.cpu.usage'],
},
],
presentOptionalMetrics: null,
presentRequiredAttributes: [
{
associatedComponent: { name: 'otel-collector' },
attributes: ['k8s.namespace.name'],
},
],
missingDefaultEnabledMetrics: [
{
associatedComponent: { name: 'otel-collector' },
metrics: ['k8s.pod.memory.limit'],
},
],
missingOptionalMetrics: null,
missingRequiredAttributes: null,
},
}),
),
),
);
renderComponent<TestItem>({
entity: InfraMonitoringEntity.PODS,
eventCategory: InfraMonitoringEvents.Pod,
fetchListData: fetchListDataMock,
tableColumns: createTestColumns(),
getRowKey: (row): string => row.id,
getItemKey: (row): string => row.id,
});
await screen.findByText('Instrumentation checks');
// Present entries
await expect(
screen.findByText('Default enabled metrics'),
).resolves.toBeInTheDocument();
await expect(
screen.findByText('k8s.pod.cpu.usage'),
).resolves.toBeInTheDocument();
await expect(
screen.findByText('Required attributes'),
).resolves.toBeInTheDocument();
await expect(
screen.findByText('k8s.namespace.name'),
).resolves.toBeInTheDocument();
// Missing entries
await expect(
screen.findByText('Missing default metrics'),
).resolves.toBeInTheDocument();
await expect(
screen.findByText('k8s.pod.memory.limit'),
).resolves.toBeInTheDocument();
});
});
});

View File

@@ -0,0 +1,41 @@
.countsContainer {
display: flex;
gap: var(--spacing-6);
margin-top: var(--spacing-8);
flex-wrap: wrap;
}
.countCard {
position: relative;
flex: 1;
min-width: 120px;
max-width: 180px;
border: 1px solid var(--l3-border);
border-radius: 4px;
display: flex;
flex-direction: column;
gap: var(--spacing-2);
padding: var(--spacing-6);
}
.countLabel {
color: var(--l2-foreground);
letter-spacing: var(--letter-spacing-wide);
text-transform: uppercase;
}
.countValue {
color: var(--l1-foreground);
font-family: var(--periscope-font-family-mono);
font-size: var(--font-size-xl);
}
.navigateButton {
position: absolute;
top: var(--spacing-4);
right: var(--spacing-4);
--button-padding: var(--spacing-1);
--button-height: 24px;
--button-width: 24px;
}

View File

@@ -0,0 +1,107 @@
import { Tooltip } from 'antd';
import { Button } from '@signozhq/ui/button';
import { Typography } from '@signozhq/ui/typography';
import { Compass } from '@signozhq/icons';
import { QueryParams } from 'constants/query';
import { initialQueriesMap } from 'constants/queryBuilder';
import ROUTES from 'constants/routes';
import { Link } from 'react-router-dom';
import { DataSource } from 'types/common/queryBuilder';
import { v4 as uuid } from 'uuid';
import {
INFRA_MONITORING_K8S_PARAMS_KEYS,
InfraMonitoringEntity,
} from '../../../constants';
import styles from './EntityCountsSection.module.scss';
export interface EntityCountConfig<T> {
label: string;
getValue: (entity: T) => number;
targetCategory: InfraMonitoringEntity;
}
interface EntityCountsSectionProps<T> {
entity: T;
countsConfig: EntityCountConfig<T>[];
selectedItem: string;
filterExpression: string;
closeDrawer: () => void;
}
export function EntityCountsSection<T>({
entity,
countsConfig,
selectedItem,
filterExpression,
closeDrawer,
}: EntityCountsSectionProps<T>): JSX.Element {
const buildNavigationUrl = (targetCategory: InfraMonitoringEntity): string => {
const defaultQuery = initialQueriesMap[DataSource.METRICS];
const compositeQuery = {
...defaultQuery,
id: uuid(),
builder: {
...defaultQuery.builder,
queryData: defaultQuery.builder.queryData.map((query) => ({
...query,
filter: { expression: filterExpression },
filters: { items: [], op: 'AND' as const },
})),
},
};
// TODO(H4ad): After https://github.com/SigNoz/signoz/pull/12038, inherit custom time of drawer to list
const urlParams = new URLSearchParams();
urlParams.set(INFRA_MONITORING_K8S_PARAMS_KEYS.CATEGORY, targetCategory);
urlParams.set(
QueryParams.compositeQuery,
encodeURIComponent(JSON.stringify(compositeQuery)),
);
return `${ROUTES.INFRASTRUCTURE_MONITORING_KUBERNETES}?${urlParams.toString()}`;
};
return (
<div className={styles.countsContainer}>
{countsConfig.map((config) => (
<div
key={config.label}
className={styles.countCard}
data-testid={`count-card-${config.label.toLowerCase().replace(/\s+/g, '-')}`}
>
<Typography.Text
color="muted"
size="small"
weight="medium"
className={styles.countLabel}
>
{config.label}
</Typography.Text>
<Typography.Text className={styles.countValue} size="xl" weight="semibold">
{config.getValue(entity) || '-'}
</Typography.Text>
<Link
to={buildNavigationUrl(config.targetCategory)}
onClick={closeDrawer}
data-testid={`navigate-${config.label.toLowerCase().replace(/\s+/g, '-')}`}
>
<Tooltip
title={`View ${config.label.toLowerCase()} of '${selectedItem}'`}
placement="top"
>
<Button
size="icon"
variant="ghost"
color="secondary"
className={styles.navigateButton}
prefix={<Compass size={14} />}
/>
</Tooltip>
</Link>
</div>
))}
</div>
);
}

View File

@@ -0,0 +1,24 @@
.checkContainer {
padding: 0px var(--spacing-4) var(--spacing-4) var(--spacing-4);
position: relative;
}
.container {
display: flex;
flex-direction: column;
gap: 8px;
width: 100%;
}
.header {
display: flex;
align-items: center;
justify-content: space-between;
}
.entriesList {
display: flex;
flex-direction: column;
gap: 4px;
}

View File

@@ -0,0 +1,162 @@
import { MouseEvent, useCallback, useMemo, useState } from 'react';
import { useQueryClient } from 'react-query';
import { Button } from '@signozhq/ui/button';
import { Callout } from '@signozhq/ui/callout';
import { RefreshCw } from '@signozhq/icons';
import setLocalStorage from 'api/browser/localstorage/set';
import {
invalidateGetChecks,
useGetChecks,
} from 'api/generated/services/inframonitoring';
import { InframonitoringtypesCheckTypeDTO } from 'api/generated/services/sigNoz.schemas';
import { InfraMonitoringEntity } from '../../../constants';
import styles from './K8sInstrumentationChecksCallout.module.scss';
import { MissingEntryRow } from './MissingEntryRow';
import { PresentEntryRow } from './PresentEntryRow';
import {
ENTITY_TO_CHECK_TYPE,
getStorageKey,
hasAnyEntries,
hasMissingEntries,
readExpandedState,
} from './utils';
export interface InstrumentationChecksCalloutProps {
entity: InfraMonitoringEntity;
}
export function K8sInstrumentationChecksCallout({
entity,
}: InstrumentationChecksCalloutProps): JSX.Element | null {
const checkType = ENTITY_TO_CHECK_TYPE[entity];
const queryClient = useQueryClient();
const [isExpanded, setIsExpanded] = useState(() => readExpandedState(entity));
const { data, isLoading, isFetching } = useGetChecks(
{ type: checkType as InframonitoringtypesCheckTypeDTO },
{ query: { enabled: !!checkType } },
);
const handleRecheck = useCallback(
(e: MouseEvent): void => {
e.preventDefault();
e.stopPropagation();
if (checkType) {
void invalidateGetChecks(queryClient, { type: checkType });
}
},
[queryClient, checkType],
);
const handleExpandToggle = useCallback((): void => {
setIsExpanded((prev) => {
const next = !prev;
setLocalStorage(getStorageKey(entity), String(next));
return next;
});
}, [entity]);
const checksData = data?.data;
const hasMissingItems = useMemo(
() => (checksData ? hasMissingEntries(checksData) : false),
[checksData],
);
if (!checkType || isLoading) {
return null;
}
if (!checksData || checksData.ready) {
return null;
}
if (!hasAnyEntries(checksData)) {
return null;
}
return (
<div className={styles.checkContainer}>
<Callout
type={hasMissingItems ? 'warning' : 'info'}
showIcon
size="medium"
title={
<div className={styles.header}>
Instrumentation checks
<Button
variant="outlined"
color="warning"
size="sm"
onClick={handleRecheck}
loading={isFetching}
prefix={<RefreshCw size={12} />}
data-testid="instrumentation-checks-recheck-btn"
>
Recheck
</Button>
</div>
}
action="expandable"
defaultExpanded={isExpanded}
onClick={handleExpandToggle}
>
<div className={styles.container} onClick={(e) => e.stopPropagation()}>
<div className={styles.entriesList}>
{checksData.presentDefaultEnabledMetrics?.map((entry) => (
<PresentEntryRow
key={`present-default-${entry.associatedComponent.name}`}
entry={entry}
typeLabel="Default enabled metrics"
itemType="metrics"
/>
))}
{checksData.presentOptionalMetrics?.map((entry) => (
<PresentEntryRow
key={`present-optional-${entry.associatedComponent.name}`}
entry={entry}
typeLabel="Optional metrics"
itemType="metrics"
/>
))}
{checksData.presentRequiredAttributes?.map((entry) => (
<PresentEntryRow
key={`present-attrs-${entry.associatedComponent.name}`}
entry={entry}
typeLabel="Required attributes"
itemType="attributes"
/>
))}
{checksData.missingDefaultEnabledMetrics?.map((entry) => (
<MissingEntryRow
key={`missing-default-${entry.associatedComponent.name}`}
entry={entry}
typeLabel="Missing default metrics"
itemType="metrics"
/>
))}
{checksData.missingOptionalMetrics?.map((entry) => (
<MissingEntryRow
key={`missing-optional-${entry.associatedComponent.name}`}
entry={entry}
typeLabel="Missing optional metrics"
itemType="metrics"
/>
))}
{checksData.missingRequiredAttributes?.map((entry) => (
<MissingEntryRow
key={`missing-attrs-${entry.associatedComponent.name}`}
entry={entry}
typeLabel="Missing required attributes"
itemType="attributes"
/>
))}
</div>
</div>
</Callout>
</div>
);
}

View File

@@ -0,0 +1,27 @@
.entryRow {
display: flex;
align-items: center;
gap: 6px;
flex-wrap: wrap;
color: var(--l1-foreground);
}
.missingIcon {
color: var(--warning-background);
flex-shrink: 0;
}
.learnMoreLink {
display: inline-flex;
align-items: center;
gap: 4px;
margin-left: 4px;
svg {
margin-left: 4px;
}
}
.divider {
--divider-color: var(--callout-warning-border);
}

View File

@@ -0,0 +1,66 @@
import styles from './MissingEntryRow.module.scss';
import { ExternalLink, TriangleAlert } from '@signozhq/icons';
import { Typography } from '@signozhq/ui/typography';
import { Divider } from '@signozhq/ui/divider';
import type {
InframonitoringtypesMissingAttributesComponentEntryDTO,
InframonitoringtypesMissingMetricsComponentEntryDTO,
} from 'api/generated/services/sigNoz.schemas';
type MissingEntryRowProps =
| {
entry: InframonitoringtypesMissingMetricsComponentEntryDTO;
typeLabel: string;
itemType: 'metrics';
}
| {
entry: InframonitoringtypesMissingAttributesComponentEntryDTO;
typeLabel: string;
itemType: 'attributes';
};
export function MissingEntryRow({
entry,
typeLabel,
itemType,
}: MissingEntryRowProps): JSX.Element {
const items = itemType === 'metrics' ? entry.metrics : entry.attributes;
return (
<div className={styles.entryRow}>
<TriangleAlert size={14} className={styles.missingIcon} />
<Typography.Text size="base" weight="medium">
{typeLabel}
</Typography.Text>
<Typography.Text size="base" color="muted">
-
</Typography.Text>
<Typography.Text
size="base"
weight="semibold"
className={styles.entryRowMetric}
>
{items?.join(', ')}
</Typography.Text>
<Typography.Text size="base" color="muted">
-
</Typography.Text>
<Typography.Text size="base" italic color="muted">
{entry.associatedComponent.name}
</Typography.Text>
{entry.documentationLink && (
<Typography.Link
href={entry.documentationLink}
target="_blank"
rel="noopener noreferrer"
size="base"
className={styles.learnMoreLink}
>
Learn here
<ExternalLink size={12} />
</Typography.Link>
)}
<Divider className={styles.divider} />
</div>
);
}

View File

@@ -0,0 +1,16 @@
.entryRow {
display: flex;
align-items: center;
gap: 6px;
flex-wrap: wrap;
color: var(--l1-foreground);
}
.presentIcon {
color: var(--success-background);
flex-shrink: 0;
}
.divider {
--divider-color: var(--callout-warning-border);
}

View File

@@ -0,0 +1,54 @@
import styles from './PresentEntryRow.module.scss';
import { CircleCheck } from '@signozhq/icons';
import { Typography } from '@signozhq/ui/typography';
import { Divider } from '@signozhq/ui/divider';
import type {
InframonitoringtypesAttributesComponentEntryDTO,
InframonitoringtypesMetricsComponentEntryDTO,
} from 'api/generated/services/sigNoz.schemas';
type PresentEntryRowProps =
| {
entry: InframonitoringtypesMetricsComponentEntryDTO;
typeLabel: string;
itemType: 'metrics';
}
| {
entry: InframonitoringtypesAttributesComponentEntryDTO;
typeLabel: string;
itemType: 'attributes';
};
export function PresentEntryRow({
entry,
typeLabel,
itemType,
}: PresentEntryRowProps): JSX.Element {
const items = itemType === 'metrics' ? entry.metrics : entry.attributes;
return (
<div className={styles.entryRow}>
<CircleCheck size={14} className={styles.presentIcon} />
<Typography.Text size="base" weight="medium">
{typeLabel}
</Typography.Text>
<Typography.Text size="base" color="muted">
-
</Typography.Text>
<Typography.Text
size="base"
weight="semibold"
className={styles.entryRowMetric}
>
{items?.join(', ')}
</Typography.Text>
<Typography.Text size="base" color="muted">
-
</Typography.Text>
<Typography.Text size="base" italic color="muted">
{entry.associatedComponent.name}
</Typography.Text>
<Divider className={styles.divider} />
</div>
);
}

View File

@@ -0,0 +1,60 @@
import getLocalStorage from 'api/browser/localstorage/get';
import {
InframonitoringtypesChecksDTO,
InframonitoringtypesCheckTypeDTO,
} from 'api/generated/services/sigNoz.schemas';
import { InfraMonitoringEntity } from '../../../constants';
export const ENTITY_TO_CHECK_TYPE: Record<
InfraMonitoringEntity,
InframonitoringtypesCheckTypeDTO
> = {
[InfraMonitoringEntity.HOSTS]: InframonitoringtypesCheckTypeDTO.hosts,
[InfraMonitoringEntity.PODS]: InframonitoringtypesCheckTypeDTO.pods,
[InfraMonitoringEntity.NODES]: InframonitoringtypesCheckTypeDTO.nodes,
[InfraMonitoringEntity.NAMESPACES]:
InframonitoringtypesCheckTypeDTO.namespaces,
[InfraMonitoringEntity.CLUSTERS]: InframonitoringtypesCheckTypeDTO.clusters,
[InfraMonitoringEntity.DEPLOYMENTS]:
InframonitoringtypesCheckTypeDTO.deployments,
[InfraMonitoringEntity.STATEFULSETS]:
InframonitoringtypesCheckTypeDTO.statefulsets,
[InfraMonitoringEntity.DAEMONSETS]:
InframonitoringtypesCheckTypeDTO.daemonsets,
[InfraMonitoringEntity.JOBS]: InframonitoringtypesCheckTypeDTO.jobs,
[InfraMonitoringEntity.VOLUMES]: InframonitoringtypesCheckTypeDTO.volumes,
[InfraMonitoringEntity.CONTAINERS]:
InframonitoringtypesCheckTypeDTO.kube_containers,
};
export function hasMissingEntries(
data: InframonitoringtypesChecksDTO,
): boolean {
return (
(data.missingDefaultEnabledMetrics?.length ?? 0) > 0 ||
(data.missingOptionalMetrics?.length ?? 0) > 0 ||
(data.missingRequiredAttributes?.length ?? 0) > 0
);
}
export function hasAnyEntries(data: InframonitoringtypesChecksDTO): boolean {
return (
(data.presentDefaultEnabledMetrics?.length ?? 0) > 0 ||
(data.presentOptionalMetrics?.length ?? 0) > 0 ||
(data.presentRequiredAttributes?.length ?? 0) > 0 ||
(data.missingDefaultEnabledMetrics?.length ?? 0) > 0 ||
(data.missingOptionalMetrics?.length ?? 0) > 0 ||
(data.missingRequiredAttributes?.length ?? 0) > 0
);
}
const STORAGE_PREFIX = '@signozhq/k8s-instrumentation-checks-expanded';
export function getStorageKey(entity: InfraMonitoringEntity): string {
return `${STORAGE_PREFIX}-${entity}`;
}
export function readExpandedState(entity: InfraMonitoringEntity): boolean {
const stored = getLocalStorage(getStorageKey(entity));
return stored === null ? true : stored === 'true';
}

View File

@@ -1,11 +1,15 @@
import { useCallback } from 'react';
import { convertToApiError } from 'api/ErrorResponseHandlerForGeneratedAPIs';
import { listClusters } from 'api/generated/services/inframonitoring';
import { RenderErrorResponseDTO } from 'api/generated/services/sigNoz.schemas';
import { AxiosError } from 'axios';
import {
InframonitoringtypesClusterRecordDTO,
InframonitoringtypesResponseTypeDTO,
Querybuildertypesv5OrderDirectionDTO,
} from 'api/generated/services/sigNoz.schemas';
import { InfraMonitoringEvents } from 'constants/events';
import APIError from 'types/api/error';
import K8sBaseDetails, { K8sDetailsFilters } from '../Base/K8sBaseDetails';
import { K8sBaseList } from '../Base/K8sBaseList';
@@ -14,7 +18,9 @@ import { InfraMonitoringEntity } from '../constants';
import {
clusterWidgetInfo,
getClusterMetricsQueryPayload,
k8sClusterDetailsCountsConfig,
k8sClusterDetailsMetadataConfig,
k8sClusterGetCountsFilterExpression,
k8sClusterGetEntityName,
k8sClusterGetSelectedItemExpression,
k8sClusterInitialEventsExpression,
@@ -67,13 +73,12 @@ function K8sClustersList({
warning: data.warning,
};
} catch (error) {
const errMsg =
error instanceof Error ? error.message : 'Failed to fetch clusters';
return {
type: 'list' as const,
records: [] as InframonitoringtypesClusterRecordDTO[],
total: 0,
error: errMsg,
error:
convertToApiError(error as AxiosError<RenderErrorResponseDTO>) ?? null,
};
}
},
@@ -86,7 +91,7 @@ function K8sClustersList({
signal?: AbortSignal,
): Promise<{
data: InframonitoringtypesClusterRecordDTO | null;
error?: string | null;
error?: APIError | null;
}> => {
try {
const response = await listClusters(
@@ -104,11 +109,10 @@ function K8sClustersList({
data: response.data.records.length > 0 ? response.data.records[0] : null,
};
} catch (error) {
const errMsg =
error instanceof Error ? error.message : 'Failed to fetch cluster';
return {
data: null,
error: errMsg,
error:
convertToApiError(error as AxiosError<RenderErrorResponseDTO>) ?? null,
};
}
},
@@ -136,6 +140,8 @@ function K8sClustersList({
getInitialLogTracesExpression={k8sClusterInitialLogTracesExpression}
getInitialEventsExpression={k8sClusterInitialEventsExpression}
metadataConfig={k8sClusterDetailsMetadataConfig}
countsConfig={k8sClusterDetailsCountsConfig}
getCountsFilterExpression={k8sClusterGetCountsFilterExpression}
entityWidgetInfo={clusterWidgetInfo}
getEntityQueryPayload={getClusterMetricsQueryPayload}
queryKeyPrefix="cluster"

View File

@@ -6,9 +6,15 @@ import { EQueryType } from 'types/common/dashboard';
import { DataSource, ReduceOperators } from 'types/common/queryBuilder';
import { v4 } from 'uuid';
import { K8sDetailsMetadataConfig } from '../Base/K8sBaseDetails';
import {
K8sDetailsCountConfig,
K8sDetailsMetadataConfig,
} from '../Base/K8sBaseDetails';
import { formatValueForExpression } from 'components/QueryBuilderV2/utils';
import { INFRA_MONITORING_ATTR_KEYS } from '../constants';
import {
INFRA_MONITORING_ATTR_KEYS,
InfraMonitoringEntity,
} from '../constants';
import { SelectedItemParams } from '../hooks';
import {
buildEventsExpression,
@@ -23,6 +29,40 @@ export const k8sClusterGetSelectedItemExpression = (
export const k8sClusterDetailsMetadataConfig: K8sDetailsMetadataConfig<InframonitoringtypesClusterRecordDTO>[] =
[{ label: 'Cluster Name', getValue: (p): string => p.clusterName || '' }];
export const k8sClusterDetailsCountsConfig: K8sDetailsCountConfig<InframonitoringtypesClusterRecordDTO>[] =
[
{
label: 'Namespaces',
getValue: (p): number => p.counts?.namespaces ?? 0,
targetCategory: InfraMonitoringEntity.NAMESPACES,
},
{
label: 'Nodes',
getValue: (p): number => p.counts?.nodes ?? 0,
targetCategory: InfraMonitoringEntity.NODES,
},
{
label: 'Deployments',
getValue: (p): number => p.counts?.deployments ?? 0,
targetCategory: InfraMonitoringEntity.DEPLOYMENTS,
},
{
label: 'StatefulSets',
getValue: (p): number => p.counts?.statefulSets ?? 0,
targetCategory: InfraMonitoringEntity.STATEFULSETS,
},
{
label: 'DaemonSets',
getValue: (p): number => p.counts?.daemonSets ?? 0,
targetCategory: InfraMonitoringEntity.DAEMONSETS,
},
{
label: 'Jobs',
getValue: (p): number => p.counts?.jobs ?? 0,
targetCategory: InfraMonitoringEntity.JOBS,
},
];
export const k8sClusterInitialEventsExpression = (
item: InframonitoringtypesClusterRecordDTO,
): string =>
@@ -43,38 +83,54 @@ export const k8sClusterGetEntityName = (
item: InframonitoringtypesClusterRecordDTO,
): string => item.clusterName || '';
export const k8sClusterGetCountsFilterExpression = (
item: InframonitoringtypesClusterRecordDTO,
): string =>
`k8s.cluster.name = ${formatValueForExpression(item.clusterName ?? '')}`;
export const clusterWidgetInfo = [
{
title: 'CPU Usage, allocatable',
yAxisUnit: '',
docPath:
'/infrastructure-monitoring/kubernetes/clusters/#cpu-usage-allocatable',
},
{
title: 'Memory Usage, allocatable',
yAxisUnit: 'bytes',
docPath:
'/infrastructure-monitoring/kubernetes/clusters/#memory-usage-allocatable',
},
{
title: 'Ready Nodes',
yAxisUnit: '',
docPath: '/infrastructure-monitoring/kubernetes/clusters/#ready-nodes',
},
{
title: 'NotReady Nodes',
yAxisUnit: '',
docPath: '/infrastructure-monitoring/kubernetes/clusters/#notready-nodes',
},
{
title: 'Deployments available and desired',
yAxisUnit: '',
docPath:
'/infrastructure-monitoring/kubernetes/clusters/#deployments-available-and-desired',
},
{
title: 'Statefulset pods',
yAxisUnit: '',
docPath: '/infrastructure-monitoring/kubernetes/clusters/#statefulset-pods',
},
{
title: 'Daemonset nodes',
yAxisUnit: '',
docPath: '/infrastructure-monitoring/kubernetes/clusters/#daemonset-nodes',
},
{
title: 'Jobs',
yAxisUnit: '',
docPath: '/infrastructure-monitoring/kubernetes/clusters/#jobs',
},
];

View File

@@ -8,7 +8,7 @@ import { ExpandButtonWrapper } from 'container/InfraMonitoringK8sV2/components';
import ColumnHeader from '../Base/ColumnHeader';
import EntityGroupHeader from '../Base/EntityGroupHeader';
import K8sGroupCell from '../Base/K8sGroupCell';
import { formatBytes, getPodPhaseStatusItems } from '../commonUtils';
import { formatBytes, getPodStatusItems } from '../commonUtils';
import {
CellValueTooltip,
GroupedStatusCounts,
@@ -77,11 +77,7 @@ export const k8sClustersColumnsConfig: ClusterTableColumnConfig[] = [
visibilityBehavior: 'hidden-on-expand',
cell: ({ value }): React.ReactNode => {
const clusterName = value as string;
return (
<CellValueTooltip value={clusterName}>
<TanStackTable.Text>{clusterName}</TanStackTable.Text>
</CellValueTooltip>
);
return <CellValueTooltip value={clusterName} />;
},
},
{
@@ -121,23 +117,25 @@ export const k8sClustersColumnsConfig: ClusterTableColumnConfig[] = [
},
},
{
id: 'podCountsByPhase',
id: 'podCountsByStatus',
header: (): React.ReactNode => (
<ColumnHeader docPath="/infrastructure-monitoring/kubernetes/clusters#pod-counts-by-phase">
Pod Phases
<ColumnHeader docPath="/infrastructure-monitoring/kubernetes/clusters#pod-counts-by-status">
Pod Status
</ColumnHeader>
),
accessorFn: (row): InframonitoringtypesClusterRecordDTO['podCountsByPhase'] =>
row.podCountsByPhase,
accessorFn: (
row,
): InframonitoringtypesClusterRecordDTO['podCountsByStatus'] =>
row.podCountsByStatus,
width: { min: 250 },
enableSort: false,
cell: ({ row }): React.ReactNode => {
const podCountsByPhase = row.podCountsByPhase;
if (!podCountsByPhase) {
const podCountsByStatus = row.podCountsByStatus;
if (!podCountsByStatus) {
return <TanStackTable.Text>-</TanStackTable.Text>;
}
return (
<GroupedStatusCounts items={getPodPhaseStatusItems(row.podCountsByPhase)} />
<GroupedStatusCounts items={getPodStatusItems(row.podCountsByStatus)} />
);
},
},

View File

@@ -1,11 +1,16 @@
import { useCallback } from 'react';
import { useCallback, useMemo } from 'react';
import { convertToApiError } from 'api/ErrorResponseHandlerForGeneratedAPIs';
import { listDaemonSets } from 'api/generated/services/inframonitoring';
import { RenderErrorResponseDTO } from 'api/generated/services/sigNoz.schemas';
import { AxiosError } from 'axios';
import {
InframonitoringtypesDaemonSetRecordDTO,
InframonitoringtypesResponseTypeDTO,
Querybuildertypesv5OrderDirectionDTO,
} from 'api/generated/services/sigNoz.schemas';
import { InfraMonitoringEvents } from 'constants/events';
import APIError from 'types/api/error';
import K8sBaseDetails, { K8sDetailsFilters } from '../Base/K8sBaseDetails';
import { K8sBaseList } from '../Base/K8sBaseList';
import { K8sBaseFilters } from '../Base/types';
@@ -14,6 +19,7 @@ import { SelectedItemParams } from '../hooks';
import {
daemonSetWidgetInfo,
getDaemonSetMetricsQueryPayload,
getDaemonSetPodMetricsQueryPayload,
k8sDaemonSetDetailsMetadataConfig,
k8sDaemonSetGetEntityName,
k8sDaemonSetGetSelectedItemExpression,
@@ -25,6 +31,8 @@ import {
getK8sDaemonSetRowKey,
k8sDaemonSetsColumnsConfig,
} from './table.config';
import { createPodMetricsTab } from 'container/InfraMonitoringK8sV2/EntityDetailsUtils/createPodMetricsTab';
function K8sDaemonSetsList({
controlListPrefix,
}: {
@@ -65,13 +73,12 @@ function K8sDaemonSetsList({
warning: data.warning,
};
} catch (error) {
const errMsg =
error instanceof Error ? error.message : 'Failed to fetch daemonsets';
return {
type: 'list' as const,
records: [] as InframonitoringtypesDaemonSetRecordDTO[],
total: 0,
error: errMsg,
error:
convertToApiError(error as AxiosError<RenderErrorResponseDTO>) ?? null,
};
}
},
@@ -83,7 +90,7 @@ function K8sDaemonSetsList({
signal?: AbortSignal,
): Promise<{
data: InframonitoringtypesDaemonSetRecordDTO | null;
error?: string | null;
error?: APIError | null;
}> => {
try {
const response = await listDaemonSets(
@@ -100,16 +107,26 @@ function K8sDaemonSetsList({
data: response.data.records.length > 0 ? response.data.records[0] : null,
};
} catch (error) {
const errMsg =
error instanceof Error ? error.message : 'Failed to fetch daemonset';
return {
data: null,
error: errMsg,
error:
convertToApiError(error as AxiosError<RenderErrorResponseDTO>) ?? null,
};
}
},
[],
);
const customTabs = useMemo(
() => [
createPodMetricsTab<InframonitoringtypesDaemonSetRecordDTO>({
getQueryPayload: getDaemonSetPodMetricsQueryPayload,
category: InfraMonitoringEntity.DAEMONSETS,
queryKey: 'daemonSetPodMetrics',
}),
],
[],
);
return (
<>
<K8sBaseList<InframonitoringtypesDaemonSetRecordDTO, SelectedItemParams>
@@ -133,6 +150,7 @@ function K8sDaemonSetsList({
entityWidgetInfo={daemonSetWidgetInfo}
getEntityQueryPayload={getDaemonSetMetricsQueryPayload}
queryKeyPrefix="daemonset"
customTabs={customTabs}
/>
</>
);

View File

@@ -7,7 +7,10 @@ import { DataSource, ReduceOperators } from 'types/common/queryBuilder';
import { v4 } from 'uuid';
import { K8sDetailsMetadataConfig } from '../Base/K8sBaseDetails';
import { INFRA_MONITORING_ATTR_KEYS } from '../constants';
import {
getPodUtilizationByPodQueryPayloads,
INFRA_MONITORING_ATTR_KEYS,
} from '../constants';
import { SelectedItemParams } from '../hooks';
import {
buildEventsExpression,
@@ -71,18 +74,25 @@ export const daemonSetWidgetInfo = [
{
title: 'CPU usage, request, limits',
yAxisUnit: '',
docPath:
'/infrastructure-monitoring/kubernetes/daemonsets/#cpu-usage-request-limits',
},
{
title: 'Memory usage, request, limits',
yAxisUnit: 'bytes',
docPath:
'/infrastructure-monitoring/kubernetes/daemonsets/#memory-usage-request-limits',
},
{
title: 'Network IO',
yAxisUnit: 'binBps',
docPath: '/infrastructure-monitoring/kubernetes/daemonsets/#network-io',
},
{
title: 'Network errors count',
yAxisUnit: '',
docPath:
'/infrastructure-monitoring/kubernetes/daemonsets/#network-errors-count',
},
];
@@ -669,3 +679,29 @@ export const getDaemonSetMetricsQueryPayload = (
},
];
};
export const getDaemonSetPodMetricsQueryPayload = (
daemonSet: InframonitoringtypesDaemonSetRecordDTO,
start: number,
end: number,
dotMetricsEnabled: boolean,
): GetQueryResultsProps[] => {
const k8sDaemonSetNameKey = dotMetricsEnabled
? 'k8s.daemonset.name'
: 'k8s_daemonset_name';
return getPodUtilizationByPodQueryPayloads(
{
workloadNameKey: k8sDaemonSetNameKey,
workloadNameValue:
daemonSet.meta?.[INFRA_MONITORING_ATTR_KEYS.K8S_DAEMONSET_NAME] ?? '',
clusterName:
daemonSet.meta?.[INFRA_MONITORING_ATTR_KEYS.K8S_CLUSTER_NAME] ?? '',
namespaceName:
daemonSet.meta?.[INFRA_MONITORING_ATTR_KEYS.K8S_NAMESPACE_NAME] ?? '',
},
start,
end,
dotMetricsEnabled,
);
};

View File

@@ -7,7 +7,7 @@ import ColumnHeader from '../Base/ColumnHeader';
import EntityGroupHeader from '../Base/EntityGroupHeader';
import K8sGroupCell from '../Base/K8sGroupCell';
import { SelectedItemParams } from '../hooks';
import { formatBytes, getPodPhaseStatusItems } from '../commonUtils';
import { formatBytes, getPodStatusItems } from '../commonUtils';
import {
CellValueTooltip,
EntityProgressBar,
@@ -87,11 +87,7 @@ export const k8sDaemonSetsColumnsConfig: DaemonSetTableColumnConfig[] = [
visibilityBehavior: 'hidden-on-expand',
cell: ({ value }): React.ReactNode => {
const daemonsetName = value as string;
return (
<CellValueTooltip value={daemonsetName}>
<TanStackTable.Text>{daemonsetName}</TanStackTable.Text>
</CellValueTooltip>
);
return <CellValueTooltip value={daemonsetName} />;
},
},
{
@@ -108,42 +104,36 @@ export const k8sDaemonSetsColumnsConfig: DaemonSetTableColumnConfig[] = [
enableResize: true,
cell: ({ value }): React.ReactNode => {
const namespaceName = value as string;
return (
<CellValueTooltip value={namespaceName}>
<TanStackTable.Text>{namespaceName}</TanStackTable.Text>
</CellValueTooltip>
);
return <CellValueTooltip value={namespaceName} />;
},
},
{
id: 'pod_counts_by_phase',
id: 'pod_counts_by_status',
header: (): React.ReactNode => (
<ColumnHeader docPath="/infrastructure-monitoring/kubernetes/daemonsets#pod-counts-by-phase">
Pod Phases
<ColumnHeader docPath="/infrastructure-monitoring/kubernetes/daemonsets#pod-counts-by-status">
Pod Status
</ColumnHeader>
),
accessorFn: (
row,
): InframonitoringtypesDaemonSetRecordDTO['podCountsByPhase'] =>
row.podCountsByPhase,
): InframonitoringtypesDaemonSetRecordDTO['podCountsByStatus'] =>
row.podCountsByStatus,
width: { min: 250 },
enableSort: false,
enableResize: true,
cell: ({ row }): React.ReactNode => {
const podCountsByPhase = row.podCountsByPhase;
if (!podCountsByPhase) {
const podCountsByStatus = row.podCountsByStatus;
if (!podCountsByStatus) {
return <TanStackTable.Text>-</TanStackTable.Text>;
}
return (
<GroupedStatusCounts items={getPodPhaseStatusItems(podCountsByPhase)} />
);
return <GroupedStatusCounts items={getPodStatusItems(podCountsByStatus)} />;
},
},
{
id: 'node_status',
id: 'scheduled_nodes',
header: (): React.ReactNode => (
<ColumnHeader docPath="/infrastructure-monitoring/kubernetes/daemonsets#node-status">
Node Status
<ColumnHeader docPath="/infrastructure-monitoring/kubernetes/daemonsets#scheduled-nodes">
Scheduled Nodes
</ColumnHeader>
),
accessorFn: (row): number => row.currentNodes,

View File

@@ -1,11 +1,15 @@
import { useCallback } from 'react';
import { useCallback, useMemo } from 'react';
import { convertToApiError } from 'api/ErrorResponseHandlerForGeneratedAPIs';
import { listDeployments } from 'api/generated/services/inframonitoring';
import { RenderErrorResponseDTO } from 'api/generated/services/sigNoz.schemas';
import { AxiosError } from 'axios';
import {
InframonitoringtypesDeploymentRecordDTO,
InframonitoringtypesResponseTypeDTO,
Querybuildertypesv5OrderDirectionDTO,
} from 'api/generated/services/sigNoz.schemas';
import { InfraMonitoringEvents } from 'constants/events';
import APIError from 'types/api/error';
import K8sBaseDetails, { K8sDetailsFilters } from '../Base/K8sBaseDetails';
import { K8sBaseList } from '../Base/K8sBaseList';
@@ -15,6 +19,7 @@ import { SelectedItemParams } from '../hooks';
import {
deploymentWidgetInfo,
getDeploymentMetricsQueryPayload,
getDeploymentPodMetricsQueryPayload,
k8sDeploymentDetailsMetadataConfig,
k8sDeploymentGetEntityName,
k8sDeploymentGetSelectedItemExpression,
@@ -26,6 +31,7 @@ import {
getK8sDeploymentRowKey,
k8sDeploymentsColumnsConfig,
} from './table.config';
import { createPodMetricsTab } from 'container/InfraMonitoringK8sV2/EntityDetailsUtils/createPodMetricsTab';
function K8sDeploymentsList({
controlListPrefix,
@@ -68,13 +74,12 @@ function K8sDeploymentsList({
warning: data.warning,
};
} catch (error) {
const errMsg =
error instanceof Error ? error.message : 'Failed to fetch deployments';
return {
type: 'list' as const,
records: [] as InframonitoringtypesDeploymentRecordDTO[],
total: 0,
error: errMsg,
error:
convertToApiError(error as AxiosError<RenderErrorResponseDTO>) ?? null,
};
}
},
@@ -87,7 +92,7 @@ function K8sDeploymentsList({
signal?: AbortSignal,
): Promise<{
data: InframonitoringtypesDeploymentRecordDTO | null;
error?: string | null;
error?: APIError | null;
}> => {
try {
const response = await listDeployments(
@@ -105,17 +110,27 @@ function K8sDeploymentsList({
data: response.data.records.length > 0 ? response.data.records[0] : null,
};
} catch (error) {
const errMsg =
error instanceof Error ? error.message : 'Failed to fetch deployment';
return {
data: null,
error: errMsg,
error:
convertToApiError(error as AxiosError<RenderErrorResponseDTO>) ?? null,
};
}
},
[],
);
const customTabs = useMemo(
() => [
createPodMetricsTab<InframonitoringtypesDeploymentRecordDTO>({
getQueryPayload: getDeploymentPodMetricsQueryPayload,
category: InfraMonitoringEntity.DEPLOYMENTS,
queryKey: 'deploymentPodMetrics',
}),
],
[],
);
return (
<>
<K8sBaseList<InframonitoringtypesDeploymentRecordDTO, SelectedItemParams>
@@ -140,6 +155,7 @@ function K8sDeploymentsList({
entityWidgetInfo={deploymentWidgetInfo}
getEntityQueryPayload={getDeploymentMetricsQueryPayload}
queryKeyPrefix="deployment"
customTabs={customTabs}
/>
</>
);

View File

@@ -7,7 +7,10 @@ import { DataSource, ReduceOperators } from 'types/common/queryBuilder';
import { v4 } from 'uuid';
import { K8sDetailsMetadataConfig } from '../Base/K8sBaseDetails';
import { INFRA_MONITORING_ATTR_KEYS } from '../constants';
import {
getPodUtilizationByPodQueryPayloads,
INFRA_MONITORING_ATTR_KEYS,
} from '../constants';
import { SelectedItemParams } from '../hooks';
import {
buildEventsExpression,
@@ -71,18 +74,25 @@ export const deploymentWidgetInfo = [
{
title: 'CPU usage, request, limits',
yAxisUnit: '',
docPath:
'/infrastructure-monitoring/kubernetes/deployments/#cpu-usage-request-limits',
},
{
title: 'Memory usage, request, limits',
yAxisUnit: 'bytes',
docPath:
'/infrastructure-monitoring/kubernetes/deployments/#memory-usage-request-limits',
},
{
title: 'Network IO',
yAxisUnit: 'binBps',
docPath: '/infrastructure-monitoring/kubernetes/deployments/#network-io',
},
{
title: 'Network error count',
yAxisUnit: '',
docPath:
'/infrastructure-monitoring/kubernetes/deployments/#network-error-count',
},
];
@@ -668,3 +678,29 @@ export const getDeploymentMetricsQueryPayload = (
},
];
};
export const getDeploymentPodMetricsQueryPayload = (
deployment: InframonitoringtypesDeploymentRecordDTO,
start: number,
end: number,
dotMetricsEnabled: boolean,
): GetQueryResultsProps[] => {
const k8sDeploymentNameKey = dotMetricsEnabled
? 'k8s.deployment.name'
: 'k8s_deployment_name';
return getPodUtilizationByPodQueryPayloads(
{
workloadNameKey: k8sDeploymentNameKey,
workloadNameValue:
deployment.meta?.[INFRA_MONITORING_ATTR_KEYS.K8S_DEPLOYMENT_NAME] ?? '',
clusterName:
deployment.meta?.[INFRA_MONITORING_ATTR_KEYS.K8S_CLUSTER_NAME] ?? '',
namespaceName:
deployment.meta?.[INFRA_MONITORING_ATTR_KEYS.K8S_NAMESPACE_NAME] ?? '',
},
start,
end,
dotMetricsEnabled,
);
};

View File

@@ -7,7 +7,7 @@ import ColumnHeader from '../Base/ColumnHeader';
import EntityGroupHeader from '../Base/EntityGroupHeader';
import K8sGroupCell from '../Base/K8sGroupCell';
import { SelectedItemParams } from '../hooks';
import { formatBytes, getPodPhaseStatusItems } from '../commonUtils';
import { formatBytes, getPodStatusItems } from '../commonUtils';
import {
CellValueTooltip,
EntityProgressBar,
@@ -88,11 +88,7 @@ export const k8sDeploymentsColumnsConfig: TableColumnDef<InframonitoringtypesDep
visibilityBehavior: 'hidden-on-expand',
cell: ({ value }): React.ReactNode => {
const deploymentName = value as string;
return (
<CellValueTooltip value={deploymentName}>
<TanStackTable.Text>{deploymentName}</TanStackTable.Text>
</CellValueTooltip>
);
return <CellValueTooltip value={deploymentName} />;
},
},
{
@@ -112,31 +108,29 @@ export const k8sDeploymentsColumnsConfig: TableColumnDef<InframonitoringtypesDep
),
},
{
id: 'podCountsByPhase',
id: 'podCountsByStatus',
header: (): React.ReactNode => (
<ColumnHeader docPath="/infrastructure-monitoring/kubernetes/deployments#pod-counts-by-phase">
Pod Phases
<ColumnHeader docPath="/infrastructure-monitoring/kubernetes/deployments#pod-counts-by-status">
Pod Status
</ColumnHeader>
),
accessorFn: (row): object | undefined => row.podCountsByPhase,
accessorFn: (row): object | undefined => row.podCountsByStatus,
width: { min: 250 },
enableSort: false,
enableResize: true,
cell: ({ row }): React.ReactNode => {
const podCountsByPhase = row.podCountsByPhase;
if (!podCountsByPhase) {
const podCountsByStatus = row.podCountsByStatus;
if (!podCountsByStatus) {
return <TanStackTable.Text>-</TanStackTable.Text>;
}
return (
<GroupedStatusCounts items={getPodPhaseStatusItems(podCountsByPhase)} />
);
return <GroupedStatusCounts items={getPodStatusItems(podCountsByStatus)} />;
},
},
{
id: 'replica_status',
id: 'pod_replicas',
header: (): React.ReactNode => (
<ColumnHeader docPath="/infrastructure-monitoring/kubernetes/deployments#replica-status">
Replica Status
<ColumnHeader docPath="/infrastructure-monitoring/kubernetes/deployments#pod-replicas">
Pod Replicas
</ColumnHeader>
),
accessorFn: (row): number => row.availablePods,

View File

@@ -0,0 +1,32 @@
.chartHeader {
display: inline-flex;
align-items: center;
gap: var(--spacing-2);
}
.infoIcon {
display: inline-flex;
align-items: center;
color: var(--l2-foreground);
cursor: pointer;
&:hover {
color: var(--text-slate-primary);
}
}
.metricsExplorerLink {
display: inline-flex;
align-items: center;
color: var(--l2-foreground);
transition: opacity 0.2s;
&:hover {
color: var(--l3-foreground);
}
}
.chartHeaderLabel {
font-size: var(--periscope-font-size-base);
color: var(--l2-foreground);
}

View File

@@ -0,0 +1,83 @@
import { Link } from 'react-router-dom';
import { Compass, Info } from '@signozhq/icons';
import { Tooltip } from 'antd';
import styles from './ChartHeader.module.scss';
const DOCS_BASE_URL = `${process.env.DOCS_BASE_URL}/docs`;
interface ChartHeaderProps {
title: string;
docPath?: string;
tooltip?: string;
metricsExplorerUrl?: string;
metricsExplorerTestId?: string;
}
function ChartHeader({
title,
docPath,
tooltip,
metricsExplorerUrl,
metricsExplorerTestId = 'open-metrics-explorer',
}: ChartHeaderProps): JSX.Element {
const renderInfoIcon = (): React.ReactNode => {
if (docPath) {
const tooltipTitle = tooltip || 'Not sure what this represents?';
return (
<Tooltip
arrow
title={
<>
{tooltipTitle}{' '}
<a
href={`${DOCS_BASE_URL}${docPath}`}
target="_blank"
rel="noopener"
onClick={(e): void => e.stopPropagation()}
>
Learn more.
</a>
</>
}
>
<span className={styles.infoIcon} data-testid="chart-header-info-icon">
<Info size="md" />
</span>
</Tooltip>
);
}
if (tooltip) {
return (
<Tooltip title={tooltip}>
<span className={styles.infoIcon} data-testid="chart-header-info-icon">
<Info size="md" />
</span>
</Tooltip>
);
}
return null;
};
return (
<div className={styles.chartHeader} data-testid="chart-header">
<span className={styles.chartHeaderLabel}>{title}</span>
{renderInfoIcon()}
{metricsExplorerUrl && (
<Tooltip title="Open in Metrics Explorer">
<Link
to={metricsExplorerUrl}
className={styles.metricsExplorerLink}
data-testid={metricsExplorerTestId}
>
<Compass size={14} />
</Link>
</Tooltip>
)}
</div>
);
}
export default ChartHeader;

View File

@@ -14,28 +14,6 @@
box-sizing: border-box;
}
.entityMetricsTitleContainer {
display: flex;
align-items: center;
gap: 8px;
}
.entityMetricsTitle {
font-size: var(--periscope-font-size-base);
color: var(--l2-foreground);
}
.metricsExplorerLink {
display: flex;
align-items: center;
color: var(--l2-foreground);
transition: opacity 0.2s;
&:hover {
color: var(--l3-foreground);
}
}
.metricsHeader {
display: flex;
justify-content: flex-end;

View File

@@ -1,8 +1,6 @@
import { useCallback, useMemo, useRef } from 'react';
import { UseQueryResult } from 'react-query';
import { Link } from 'react-router-dom';
import { Compass } from '@signozhq/icons';
import { Skeleton, Tooltip } from 'antd';
import { Skeleton } from 'antd';
import cx from 'classnames';
import { PANEL_TYPES } from 'constants/queryBuilder';
import TimeSeries from 'container/DashboardContainer/visualization/charts/TimeSeries/TimeSeries';
@@ -24,6 +22,7 @@ import { MetricRangePayloadProps } from 'types/api/metrics/getQueryRange';
import { getMetricsExplorerUrl } from 'utils/explorerUtils';
import { buildEntityMetricsChartConfig } from './configBuilder';
import ChartHeader from './ChartHeader';
import { useEntityMetrics } from './hooks';
import { isKeyNotFoundError } from '../utils';
@@ -47,6 +46,7 @@ interface EntityMetricsProps<T> {
entityWidgetInfo: {
title: string;
yAxisUnit: string;
docPath?: string;
}[];
getEntityQueryPayload: (
node: T,
@@ -207,31 +207,24 @@ function EntityMetrics<T>({
key={entityWidgetInfo[idx].title}
className={styles.entityMetricsCol}
>
<div className={styles.entityMetricsTitleContainer}>
<span className={styles.entityMetricsTitle}>
{entityWidgetInfo[idx].title}
</span>
{queryPayloads[idx] &&
queryPayloads[idx].graphType !== PANEL_TYPES.TABLE && (
<Tooltip title="Open in Metrics Explorer">
<Link
to={getMetricsExplorerUrl({
query: queryPayloads[idx].query,
...(selectedInterval && selectedInterval !== 'custom'
? { relativeTime: selectedInterval }
: {
startTimeMs: timeRange.startTime * 1000,
endTimeMs: timeRange.endTime * 1000,
}),
})}
className={styles.metricsExplorerLink}
data-testid={`open-metrics-explorer-${idx}`}
>
<Compass size={14} />
</Link>
</Tooltip>
)}
</div>
<ChartHeader
title={entityWidgetInfo[idx].title}
docPath={entityWidgetInfo[idx].docPath}
metricsExplorerUrl={
queryPayloads[idx] && queryPayloads[idx].graphType !== PANEL_TYPES.TABLE
? getMetricsExplorerUrl({
query: queryPayloads[idx].query,
...(selectedInterval && selectedInterval !== 'custom'
? { relativeTime: selectedInterval }
: {
startTimeMs: timeRange.startTime * 1000,
endTimeMs: timeRange.endTime * 1000,
}),
})
: undefined
}
metricsExplorerTestId={`open-metrics-explorer-${idx}`}
/>
<div className={styles.entityMetricsCard} ref={graphRef}>
{renderCardContent(query, idx)}
</div>

View File

@@ -87,7 +87,7 @@ describe('EntityTraces - Table Rendering', () => {
expect(badge).toHaveAttribute('data-variant', 'outline');
});
it('should render N/A when http method is empty', async () => {
it('should render - when http method is empty', async () => {
mockQueryRangeV5WithTracesResponse({
customTraces: [{ httpMethod: '', responseStatusCode: '200' }],
});
@@ -96,7 +96,7 @@ describe('EntityTraces - Table Rendering', () => {
renderEntityTraces();
});
await expect(screen.findByText('N/A')).resolves.toBeInTheDocument();
await expect(screen.findByText('-')).resolves.toBeInTheDocument();
expect(screen.queryByTestId('httpMethod')).not.toBeInTheDocument();
});

View File

@@ -4,4 +4,8 @@
.cellText {
color: var(--l2-foreground);
&[data-novalue='true'] {
opacity: 0.6;
}
}

View File

@@ -89,8 +89,12 @@ export const getTraceListColumns = (
if (value === '') {
return (
<BlockLink to={getTraceLink(itemData)} openInNewTab>
<Typography data-testid={key} className={styles.cellText}>
N/A
<Typography
data-testid={key}
className={styles.cellText}
data-novalue="true"
>
-
</Typography>
</BlockLink>
);
@@ -102,7 +106,9 @@ export const getTraceListColumns = (
if (!httpMethod) {
return (
<BlockLink to={getTraceLink(itemData)} openInNewTab>
<Typography className={styles.cellText}>N/A</Typography>
<Typography className={styles.cellText} data-novalue="true">
-
</Typography>
</BlockLink>
);
}
@@ -129,8 +135,11 @@ export const getTraceListColumns = (
if (!isValidCode) {
return (
<BlockLink to={getTraceLink(itemData)} openInNewTab>
<Typography className={styles.cellText}>
{numericCode === 0 || !statusCode ? 'N/A' : statusCode}
<Typography
className={styles.cellText}
data-novalue={numericCode === 0 || !statusCode}
>
{numericCode === 0 || !statusCode ? '-' : statusCode}
</Typography>
</BlockLink>
);

View File

@@ -0,0 +1,47 @@
import { Container } from '@signozhq/icons';
import { GetQueryResultsProps } from 'lib/dashboard/getQueryResults';
import { CustomTab } from '../Base/K8sBaseDetails';
import {
InfraMonitoringEntity,
podUtilizationByPodWidgetInfo,
VIEW_TYPES,
} from '../constants';
import EntityMetrics from './EntityMetrics';
interface CreatePodMetricsTabParams<T> {
getQueryPayload: (
entity: T,
start: number,
end: number,
dotMetricsEnabled: boolean,
) => GetQueryResultsProps[];
category: InfraMonitoringEntity;
queryKey: string;
}
export function createPodMetricsTab<T>({
getQueryPayload,
category,
queryKey,
}: CreatePodMetricsTabParams<T>): CustomTab<T> {
return {
key: VIEW_TYPES.POD_METRICS,
label: 'Pod Metrics',
icon: <Container size={14} />,
render: ({ entity, timeRange, selectedInterval, handleTimeChange }) => (
<EntityMetrics
entity={entity}
selectedInterval={selectedInterval}
timeRange={timeRange}
handleTimeChange={handleTimeChange}
isModalTimeSelection
entityWidgetInfo={podUtilizationByPodWidgetInfo}
getEntityQueryPayload={getQueryPayload}
category={category}
queryKey={queryKey}
/>
),
};
}

View File

@@ -1,11 +1,15 @@
import { useCallback } from 'react';
import { useCallback, useMemo } from 'react';
import { convertToApiError } from 'api/ErrorResponseHandlerForGeneratedAPIs';
import { listJobs } from 'api/generated/services/inframonitoring';
import { RenderErrorResponseDTO } from 'api/generated/services/sigNoz.schemas';
import { AxiosError } from 'axios';
import {
InframonitoringtypesJobRecordDTO,
InframonitoringtypesResponseTypeDTO,
Querybuildertypesv5OrderDirectionDTO,
} from 'api/generated/services/sigNoz.schemas';
import { InfraMonitoringEvents } from 'constants/events';
import APIError from 'types/api/error';
import K8sBaseDetails, { K8sDetailsFilters } from '../Base/K8sBaseDetails';
import { K8sBaseList } from '../Base/K8sBaseList';
@@ -14,6 +18,7 @@ import { InfraMonitoringEntity } from '../constants';
import { SelectedItemParams } from '../hooks';
import {
getJobMetricsQueryPayload,
getJobPodMetricsQueryPayload,
jobWidgetInfo,
k8sJobDetailsMetadataConfig,
k8sJobGetEntityName,
@@ -26,6 +31,7 @@ import {
getK8sJobRowKey,
k8sJobsColumnsConfig,
} from './table.config';
import { createPodMetricsTab } from 'container/InfraMonitoringK8sV2/EntityDetailsUtils/createPodMetricsTab';
function K8sJobsList({
controlListPrefix,
@@ -68,13 +74,12 @@ function K8sJobsList({
warning: data.warning,
};
} catch (error) {
const errMsg =
error instanceof Error ? error.message : 'Failed to fetch jobs';
return {
type: 'list' as const,
records: [] as InframonitoringtypesJobRecordDTO[],
total: 0,
error: errMsg,
error:
convertToApiError(error as AxiosError<RenderErrorResponseDTO>) ?? null,
};
}
},
@@ -87,7 +92,7 @@ function K8sJobsList({
signal?: AbortSignal,
): Promise<{
data: InframonitoringtypesJobRecordDTO | null;
error?: string | null;
error?: APIError | null;
}> => {
try {
const response = await listJobs(
@@ -105,17 +110,27 @@ function K8sJobsList({
data: response.data.records.length > 0 ? response.data.records[0] : null,
};
} catch (error) {
const errMsg =
error instanceof Error ? error.message : 'Failed to fetch job';
return {
data: null,
error: errMsg,
error:
convertToApiError(error as AxiosError<RenderErrorResponseDTO>) ?? null,
};
}
},
[],
);
const customTabs = useMemo(
() => [
createPodMetricsTab<InframonitoringtypesJobRecordDTO>({
getQueryPayload: getJobPodMetricsQueryPayload,
category: InfraMonitoringEntity.JOBS,
queryKey: 'jobPodMetrics',
}),
],
[],
);
return (
<>
<K8sBaseList<InframonitoringtypesJobRecordDTO, SelectedItemParams>
@@ -140,6 +155,7 @@ function K8sJobsList({
entityWidgetInfo={jobWidgetInfo}
getEntityQueryPayload={getJobMetricsQueryPayload}
queryKeyPrefix="job"
customTabs={customTabs}
/>
</>
);

View File

@@ -7,7 +7,10 @@ import { DataSource, ReduceOperators } from 'types/common/queryBuilder';
import { v4 } from 'uuid';
import { K8sDetailsMetadataConfig } from '../Base/K8sBaseDetails';
import { INFRA_MONITORING_ATTR_KEYS } from '../constants';
import {
getPodUtilizationByPodQueryPayloads,
INFRA_MONITORING_ATTR_KEYS,
} from '../constants';
import { SelectedItemParams } from '../hooks';
import {
buildEventsExpression,
@@ -70,18 +73,22 @@ export const jobWidgetInfo = [
{
title: 'CPU usage',
yAxisUnit: '',
docPath: '/infrastructure-monitoring/kubernetes/jobs/#cpu-usage',
},
{
title: 'Memory Usage',
yAxisUnit: 'bytes',
docPath: '/infrastructure-monitoring/kubernetes/jobs/#memory-usage',
},
{
title: 'Network IO',
yAxisUnit: 'binBps',
docPath: '/infrastructure-monitoring/kubernetes/jobs/#network-io',
},
{
title: 'Network errors count',
yAxisUnit: '',
docPath: '/infrastructure-monitoring/kubernetes/jobs/#network-errors-count',
},
];
@@ -425,3 +432,25 @@ export const getJobMetricsQueryPayload = (
},
];
};
export const getJobPodMetricsQueryPayload = (
job: InframonitoringtypesJobRecordDTO,
start: number,
end: number,
dotMetricsEnabled: boolean,
): GetQueryResultsProps[] => {
const k8sJobNameKey = dotMetricsEnabled ? 'k8s.job.name' : 'k8s_job_name';
return getPodUtilizationByPodQueryPayloads(
{
workloadNameKey: k8sJobNameKey,
workloadNameValue: job.jobName ?? '',
clusterName: job.meta?.[INFRA_MONITORING_ATTR_KEYS.K8S_CLUSTER_NAME] ?? '',
namespaceName:
job.meta?.[INFRA_MONITORING_ATTR_KEYS.K8S_NAMESPACE_NAME] ?? '',
},
start,
end,
dotMetricsEnabled,
);
};

View File

@@ -7,7 +7,7 @@ import ColumnHeader from '../Base/ColumnHeader';
import EntityGroupHeader from '../Base/EntityGroupHeader';
import K8sGroupCell from '../Base/K8sGroupCell';
import { SelectedItemParams } from '../hooks';
import { formatBytes, getPodPhaseStatusItems } from '../commonUtils';
import { formatBytes, getPodStatusItems } from '../commonUtils';
import {
CellValueTooltip,
EntityProgressBar,
@@ -81,11 +81,7 @@ export const k8sJobsColumnsConfig: JobTableColumnConfig[] = [
visibilityBehavior: 'hidden-on-expand',
cell: ({ value }): React.ReactNode => {
const jobName = value as string;
return (
<CellValueTooltip value={jobName}>
<TanStackTable.Text>{jobName}</TanStackTable.Text>
</CellValueTooltip>
);
return <CellValueTooltip value={jobName} />;
},
},
{
@@ -102,40 +98,34 @@ export const k8sJobsColumnsConfig: JobTableColumnConfig[] = [
enableResize: true,
cell: ({ value }): React.ReactNode => {
const namespaceName = value as string;
return (
<CellValueTooltip value={namespaceName}>
<TanStackTable.Text>{namespaceName}</TanStackTable.Text>
</CellValueTooltip>
);
return <CellValueTooltip value={namespaceName} />;
},
},
{
id: 'pod_counts_by_phase',
id: 'pod_counts_by_status',
header: (): React.ReactNode => (
<ColumnHeader docPath="/infrastructure-monitoring/kubernetes/jobs#pod-counts-by-phase">
Pod Phases
<ColumnHeader docPath="/infrastructure-monitoring/kubernetes/jobs#pod-counts-by-status">
Pod Status
</ColumnHeader>
),
accessorFn: (row): InframonitoringtypesJobRecordDTO['podCountsByPhase'] =>
row.podCountsByPhase,
accessorFn: (row): InframonitoringtypesJobRecordDTO['podCountsByStatus'] =>
row.podCountsByStatus,
width: { min: 250 },
enableSort: false,
enableResize: true,
cell: ({ row }): React.ReactNode => {
const podCountsByPhase = row.podCountsByPhase;
if (!podCountsByPhase) {
const podCountsByStatus = row.podCountsByStatus;
if (!podCountsByStatus) {
return <TanStackTable.Text>-</TanStackTable.Text>;
}
return (
<GroupedStatusCounts items={getPodPhaseStatusItems(podCountsByPhase)} />
);
return <GroupedStatusCounts items={getPodStatusItems(podCountsByStatus)} />;
},
},
{
id: 'completion_status',
id: 'completion',
header: (): React.ReactNode => (
<ColumnHeader docPath="/infrastructure-monitoring/kubernetes/jobs#completion-status">
Completion Status
<ColumnHeader docPath="/infrastructure-monitoring/kubernetes/jobs#completion">
Completions
</ColumnHeader>
),
accessorFn: (row): number => row.successfulPods,
@@ -155,7 +145,7 @@ export const k8sJobsColumnsConfig: JobTableColumnConfig[] = [
{
value: row.desiredSuccessfulPods,
label: 'Desired',
color: Color.BG_ROBIN_500,
color: Color.BG_AMBER_500,
},
]}
/>

View File

@@ -1,11 +1,15 @@
import { useCallback } from 'react';
import { useCallback, useMemo } from 'react';
import { convertToApiError } from 'api/ErrorResponseHandlerForGeneratedAPIs';
import { listNamespaces } from 'api/generated/services/inframonitoring';
import { RenderErrorResponseDTO } from 'api/generated/services/sigNoz.schemas';
import { AxiosError } from 'axios';
import {
InframonitoringtypesNamespaceRecordDTO,
InframonitoringtypesResponseTypeDTO,
Querybuildertypesv5OrderDirectionDTO,
} from 'api/generated/services/sigNoz.schemas';
import { InfraMonitoringEvents } from 'constants/events';
import APIError from 'types/api/error';
import K8sBaseDetails, { K8sDetailsFilters } from '../Base/K8sBaseDetails';
import { K8sBaseList } from '../Base/K8sBaseList';
@@ -14,7 +18,10 @@ import { InfraMonitoringEntity } from '../constants';
import { SelectedItemParams } from '../hooks';
import {
getNamespaceMetricsQueryPayload,
getNamespacePodMetricsQueryPayload,
k8sNamespaceDetailsCountsConfig,
k8sNamespaceDetailsMetadataConfig,
k8sNamespaceGetCountsFilterExpression,
k8sNamespaceGetEntityName,
k8sNamespaceGetSelectedItemExpression,
k8sNamespaceInitialEventsExpression,
@@ -26,6 +33,7 @@ import {
getK8sNamespaceRowKey,
k8sNamespacesColumnsConfig,
} from './table.config';
import { createPodMetricsTab } from 'container/InfraMonitoringK8sV2/EntityDetailsUtils/createPodMetricsTab';
function K8sNamespacesList({
controlListPrefix,
@@ -68,13 +76,12 @@ function K8sNamespacesList({
warning: data.warning,
};
} catch (error) {
const errMsg =
error instanceof Error ? error.message : 'Failed to fetch namespaces';
return {
type: 'list' as const,
records: [] as InframonitoringtypesNamespaceRecordDTO[],
total: 0,
error: errMsg,
error:
convertToApiError(error as AxiosError<RenderErrorResponseDTO>) ?? null,
};
}
},
@@ -87,7 +94,7 @@ function K8sNamespacesList({
signal?: AbortSignal,
): Promise<{
data: InframonitoringtypesNamespaceRecordDTO | null;
error?: string | null;
error?: APIError | null;
}> => {
try {
const response = await listNamespaces(
@@ -105,17 +112,27 @@ function K8sNamespacesList({
data: response.data.records.length > 0 ? response.data.records[0] : null,
};
} catch (error) {
const errMsg =
error instanceof Error ? error.message : 'Failed to fetch namespace';
return {
data: null,
error: errMsg,
error:
convertToApiError(error as AxiosError<RenderErrorResponseDTO>) ?? null,
};
}
},
[],
);
const customTabs = useMemo(
() => [
createPodMetricsTab<InframonitoringtypesNamespaceRecordDTO>({
getQueryPayload: getNamespacePodMetricsQueryPayload,
category: InfraMonitoringEntity.NAMESPACES,
queryKey: 'namespacePodMetrics',
}),
],
[],
);
return (
<>
<K8sBaseList<InframonitoringtypesNamespaceRecordDTO, SelectedItemParams>
@@ -137,9 +154,12 @@ function K8sNamespacesList({
getInitialLogTracesExpression={k8sNamespaceInitialLogTracesExpression}
getInitialEventsExpression={k8sNamespaceInitialEventsExpression}
metadataConfig={k8sNamespaceDetailsMetadataConfig}
countsConfig={k8sNamespaceDetailsCountsConfig}
getCountsFilterExpression={k8sNamespaceGetCountsFilterExpression}
entityWidgetInfo={namespaceWidgetInfo}
getEntityQueryPayload={getNamespaceMetricsQueryPayload}
queryKeyPrefix="namespace"
customTabs={customTabs}
/>
</>
);

View File

@@ -6,9 +6,17 @@ import { EQueryType } from 'types/common/dashboard';
import { DataSource, ReduceOperators } from 'types/common/queryBuilder';
import { v4 } from 'uuid';
import { K8sDetailsMetadataConfig } from '../Base/K8sBaseDetails';
import { INFRA_MONITORING_ATTR_KEYS } from '../constants';
import {
K8sDetailsCountConfig,
K8sDetailsMetadataConfig,
} from '../Base/K8sBaseDetails';
import {
getPodUtilizationByPodQueryPayloads,
INFRA_MONITORING_ATTR_KEYS,
InfraMonitoringEntity,
} from '../constants';
import { SelectedItemParams } from '../hooks';
import { formatValueForExpression } from 'components/QueryBuilderV2/utils';
import {
buildEventsExpression,
buildExpressionFromSelectedItemParams,
@@ -33,6 +41,30 @@ export const k8sNamespaceDetailsMetadataConfig: K8sDetailsMetadataConfig<Inframo
},
];
export const k8sNamespaceDetailsCountsConfig: K8sDetailsCountConfig<InframonitoringtypesNamespaceRecordDTO>[] =
[
{
label: 'Deployments',
getValue: (p): number => p.counts?.deployments ?? 0,
targetCategory: InfraMonitoringEntity.DEPLOYMENTS,
},
{
label: 'StatefulSets',
getValue: (p): number => p.counts?.statefulSets ?? 0,
targetCategory: InfraMonitoringEntity.STATEFULSETS,
},
{
label: 'DaemonSets',
getValue: (p): number => p.counts?.daemonSets ?? 0,
targetCategory: InfraMonitoringEntity.DAEMONSETS,
},
{
label: 'Jobs',
getValue: (p): number => p.counts?.jobs ?? 0,
targetCategory: InfraMonitoringEntity.JOBS,
},
];
export const k8sNamespaceInitialEventsExpression = (
item: InframonitoringtypesNamespaceRecordDTO,
): string =>
@@ -55,46 +87,78 @@ export const k8sNamespaceGetEntityName = (
item: InframonitoringtypesNamespaceRecordDTO,
): string => item.namespaceName || '';
export const k8sNamespaceGetCountsFilterExpression = (
item: InframonitoringtypesNamespaceRecordDTO,
): string => {
const clusterName = item.meta?.[INFRA_MONITORING_ATTR_KEYS.K8S_CLUSTER_NAME];
const clauses: string[] = [];
if (clusterName) {
clauses.push(
`${INFRA_MONITORING_ATTR_KEYS.K8S_CLUSTER_NAME} = ${formatValueForExpression(clusterName)}`,
);
}
if (item.namespaceName) {
clauses.push(
`${INFRA_MONITORING_ATTR_KEYS.K8S_NAMESPACE_NAME} = ${formatValueForExpression(item.namespaceName)}`,
);
}
return clauses.join(' AND ');
};
export const namespaceWidgetInfo = [
{
title: 'CPU Usage (cores)',
yAxisUnit: '',
docPath: '/infrastructure-monitoring/kubernetes/namespaces/#cpu-usage-cores',
},
{
title: 'Memory Usage (bytes)',
yAxisUnit: 'bytes',
docPath:
'/infrastructure-monitoring/kubernetes/namespaces/#memory-usage-bytes',
},
{
title: 'Pods CPU (top 10)',
yAxisUnit: '',
docPath: '/infrastructure-monitoring/kubernetes/namespaces/#pods-cpu-top-10',
},
{
title: 'Pods Memory (top 10)',
yAxisUnit: 'bytes',
docPath:
'/infrastructure-monitoring/kubernetes/namespaces/#pods-memory-top-10',
},
{
title: 'Network rate',
yAxisUnit: 'binBps',
docPath: '/infrastructure-monitoring/kubernetes/namespaces/#network-rate',
},
{
title: 'Network errors',
yAxisUnit: '',
docPath: '/infrastructure-monitoring/kubernetes/namespaces/#network-errors',
},
{
title: 'StatefulSets',
title: 'StatefulSets (pods)',
yAxisUnit: '',
docPath: '/infrastructure-monitoring/kubernetes/namespaces/#statefulsets',
},
{
title: 'ReplicaSets',
title: 'ReplicaSets (pods)',
yAxisUnit: '',
docPath: '/infrastructure-monitoring/kubernetes/namespaces/#replicasets',
},
{
title: 'DaemonSets',
title: 'DaemonSets (nodes)',
yAxisUnit: '',
docPath: '/infrastructure-monitoring/kubernetes/namespaces/#daemonsets',
},
{
title: 'Deployments',
title: 'Deployments (pods)',
yAxisUnit: '',
docPath: '/infrastructure-monitoring/kubernetes/namespaces/#deployments',
},
];
@@ -1689,3 +1753,26 @@ export const getNamespaceMetricsQueryPayload = (
},
];
};
export const getNamespacePodMetricsQueryPayload = (
namespace: InframonitoringtypesNamespaceRecordDTO,
start: number,
end: number,
dotMetricsEnabled: boolean,
): GetQueryResultsProps[] => {
const k8sNamespaceNameKey = dotMetricsEnabled
? 'k8s.namespace.name'
: 'k8s_namespace_name';
return getPodUtilizationByPodQueryPayloads(
{
workloadNameKey: k8sNamespaceNameKey,
workloadNameValue: namespace.namespaceName ?? '',
clusterName:
namespace.meta?.[INFRA_MONITORING_ATTR_KEYS.K8S_CLUSTER_NAME] ?? '',
},
start,
end,
dotMetricsEnabled,
);
};

View File

@@ -6,7 +6,7 @@ import { ExpandButtonWrapper } from 'container/InfraMonitoringK8sV2/components';
import ColumnHeader from '../Base/ColumnHeader';
import EntityGroupHeader from '../Base/EntityGroupHeader';
import K8sGroupCell from '../Base/K8sGroupCell';
import { formatBytes, getPodPhaseStatusItems } from '../commonUtils';
import { formatBytes, getPodStatusItems } from '../commonUtils';
import {
CellValueTooltip,
GroupedStatusCounts,
@@ -83,11 +83,7 @@ export const k8sNamespacesColumnsConfig: NamespaceTableColumnConfig[] = [
visibilityBehavior: 'hidden-on-expand',
cell: ({ value }): React.ReactNode => {
const namespaceName = value as string;
return (
<CellValueTooltip value={namespaceName}>
<TanStackTable.Text>{namespaceName}</TanStackTable.Text>
</CellValueTooltip>
);
return <CellValueTooltip value={namespaceName} />;
},
},
{
@@ -106,25 +102,25 @@ export const k8sNamespacesColumnsConfig: NamespaceTableColumnConfig[] = [
),
},
{
id: 'podCountsByPhase',
id: 'podCountsByStatus',
header: (): React.ReactNode => (
<ColumnHeader docPath="/infrastructure-monitoring/kubernetes/namespaces#pod-counts-by-phase">
Pod Phases
<ColumnHeader docPath="/infrastructure-monitoring/kubernetes/namespaces#pod-counts-by-status">
Pod Status
</ColumnHeader>
),
accessorFn: (
row,
): InframonitoringtypesNamespaceRecordDTO['podCountsByPhase'] =>
row.podCountsByPhase,
): InframonitoringtypesNamespaceRecordDTO['podCountsByStatus'] =>
row.podCountsByStatus,
width: { min: 250 },
enableSort: false,
cell: ({ row }): React.ReactNode => {
const podCountsByPhase = row.podCountsByPhase;
if (!podCountsByPhase) {
const podCountsByStatus = row.podCountsByStatus;
if (!podCountsByStatus) {
return <TanStackTable.Text>-</TanStackTable.Text>;
}
return (
<GroupedStatusCounts items={getPodPhaseStatusItems(row.podCountsByPhase)} />
<GroupedStatusCounts items={getPodStatusItems(row.podCountsByStatus)} />
);
},
},

View File

@@ -1,11 +1,15 @@
import { useCallback } from 'react';
import { convertToApiError } from 'api/ErrorResponseHandlerForGeneratedAPIs';
import { listNodes } from 'api/generated/services/inframonitoring';
import { RenderErrorResponseDTO } from 'api/generated/services/sigNoz.schemas';
import { AxiosError } from 'axios';
import {
InframonitoringtypesNodeRecordDTO,
InframonitoringtypesResponseTypeDTO,
Querybuildertypesv5OrderDirectionDTO,
} from 'api/generated/services/sigNoz.schemas';
import { InfraMonitoringEvents } from 'constants/events';
import APIError from 'types/api/error';
import K8sBaseDetails, { K8sDetailsFilters } from '../Base/K8sBaseDetails';
import { K8sBaseList } from '../Base/K8sBaseList';
@@ -67,13 +71,12 @@ function K8sNodesList({
warning: data.warning,
};
} catch (error) {
const errMsg =
error instanceof Error ? error.message : 'Failed to fetch nodes';
return {
type: 'list' as const,
records: [] as InframonitoringtypesNodeRecordDTO[],
total: 0,
error: errMsg,
error:
convertToApiError(error as AxiosError<RenderErrorResponseDTO>) ?? null,
};
}
},
@@ -86,7 +89,7 @@ function K8sNodesList({
signal?: AbortSignal,
): Promise<{
data: InframonitoringtypesNodeRecordDTO | null;
error?: string | null;
error?: APIError | null;
}> => {
try {
const response = await listNodes(
@@ -104,11 +107,10 @@ function K8sNodesList({
data: response.data.records.length > 0 ? response.data.records[0] : null,
};
} catch (error) {
const errMsg =
error instanceof Error ? error.message : 'Failed to fetch node';
return {
data: null,
error: errMsg,
error:
convertToApiError(error as AxiosError<RenderErrorResponseDTO>) ?? null,
};
}
},

View File

@@ -57,42 +57,53 @@ export const nodeWidgetInfo = [
{
title: 'CPU Usage (cores)',
yAxisUnit: '',
docPath: '/infrastructure-monitoring/kubernetes/nodes/#cpu-usage-cores',
},
{
title: 'Memory Usage (bytes)',
yAxisUnit: 'bytes',
docPath: '/infrastructure-monitoring/kubernetes/nodes/#memory-usage-bytes',
},
{
title: 'CPU Usage (%)',
yAxisUnit: 'percentunit',
docPath: '/infrastructure-monitoring/kubernetes/nodes/#cpu-usage-',
},
{
title: 'Memory Usage (%)',
yAxisUnit: 'percentunit',
docPath: '/infrastructure-monitoring/kubernetes/nodes/#memory-usage-',
},
{
title: 'Pods by CPU (top 10)',
yAxisUnit: '',
docPath: '/infrastructure-monitoring/kubernetes/nodes/#pods-by-cpu-top-10',
},
{
title: 'Pods by Memory (top 10)',
yAxisUnit: 'bytes',
docPath: '/infrastructure-monitoring/kubernetes/nodes/#pods-by-memory-top-10',
},
{
title: 'Network error count',
yAxisUnit: '',
docPath: '/infrastructure-monitoring/kubernetes/nodes/#network-error-count',
},
{
title: 'Network IO rate',
yAxisUnit: 'binBps',
docPath: '/infrastructure-monitoring/kubernetes/nodes/#network-io-rate',
},
{
title: 'Filesystem usage (bytes)',
yAxisUnit: 'bytes',
docPath:
'/infrastructure-monitoring/kubernetes/nodes/#filesystem-usage-bytes',
},
{
title: 'Filesystem usage (%)',
yAxisUnit: 'percentunit',
docPath: '/infrastructure-monitoring/kubernetes/nodes/#filesystem-usage-',
},
];

View File

@@ -7,7 +7,7 @@ import { ExpandButtonWrapper } from 'container/InfraMonitoringK8sV2/components';
import ColumnHeader from '../Base/ColumnHeader';
import EntityGroupHeader from '../Base/EntityGroupHeader';
import K8sGroupCell from '../Base/K8sGroupCell';
import { formatBytes, getPodPhaseStatusItems } from '../commonUtils';
import { formatBytes, getPodStatusItems } from '../commonUtils';
import { INFRA_MONITORING_ATTR_KEYS } from '../constants';
import {
CellValueTooltip,
@@ -85,11 +85,7 @@ export const k8sNodesColumnsConfig: NodeTableColumnConfig[] = [
visibilityBehavior: 'hidden-on-expand',
cell: ({ value }): React.ReactNode => {
const nodeName = value as string;
return (
<CellValueTooltip value={nodeName}>
<TanStackTable.Text>{nodeName}</TanStackTable.Text>
</CellValueTooltip>
);
return <CellValueTooltip value={nodeName} />;
},
},
{
@@ -132,23 +128,23 @@ export const k8sNodesColumnsConfig: NodeTableColumnConfig[] = [
},
},
{
id: 'podCountsByPhase',
id: 'podCountsByStatus',
header: (): React.ReactNode => (
<ColumnHeader docPath="/infrastructure-monitoring/kubernetes/nodes#pod-counts-by-phase">
Pod Phases
<ColumnHeader docPath="/infrastructure-monitoring/kubernetes/nodes#pod-counts-by-status">
Pod Status
</ColumnHeader>
),
accessorFn: (row): InframonitoringtypesNodeRecordDTO['podCountsByPhase'] =>
row.podCountsByPhase,
accessorFn: (row): InframonitoringtypesNodeRecordDTO['podCountsByStatus'] =>
row.podCountsByStatus,
width: { min: 250 },
enableSort: false,
cell: ({ row }): React.ReactNode => {
const podCountsByPhase = row.podCountsByPhase;
if (!podCountsByPhase) {
const podCountsByStatus = row.podCountsByStatus;
if (!podCountsByStatus) {
return <TanStackTable.Text>-</TanStackTable.Text>;
}
return (
<GroupedStatusCounts items={getPodPhaseStatusItems(row.podCountsByPhase)} />
<GroupedStatusCounts items={getPodStatusItems(row.podCountsByStatus)} />
);
},
},

View File

@@ -1,11 +1,15 @@
import { useCallback } from 'react';
import { convertToApiError } from 'api/ErrorResponseHandlerForGeneratedAPIs';
import { listPods } from 'api/generated/services/inframonitoring';
import { RenderErrorResponseDTO } from 'api/generated/services/sigNoz.schemas';
import { AxiosError } from 'axios';
import {
InframonitoringtypesPodRecordDTO,
InframonitoringtypesResponseTypeDTO,
Querybuildertypesv5OrderDirectionDTO,
} from 'api/generated/services/sigNoz.schemas';
import { InfraMonitoringEvents } from 'constants/events';
import APIError from 'types/api/error';
import K8sBaseDetails, { K8sDetailsFilters } from '../Base/K8sBaseDetails';
import { K8sBaseList } from '../Base/K8sBaseList';
@@ -67,13 +71,12 @@ function K8sPodsList({
warning: data.warning,
};
} catch (error) {
const errMsg =
error instanceof Error ? error.message : 'Failed to fetch pods';
return {
type: 'list' as const,
records: [] as InframonitoringtypesPodRecordDTO[],
total: 0,
error: errMsg,
error:
convertToApiError(error as AxiosError<RenderErrorResponseDTO>) ?? null,
};
}
},
@@ -86,7 +89,7 @@ function K8sPodsList({
signal?: AbortSignal,
): Promise<{
data: InframonitoringtypesPodRecordDTO | null;
error?: string | null;
error?: APIError | null;
}> => {
try {
const response = await listPods(
@@ -104,11 +107,10 @@ function K8sPodsList({
data: response.data.records.length > 0 ? response.data.records[0] : null,
};
} catch (error) {
const errMsg =
error instanceof Error ? error.message : 'Failed to fetch pod';
return {
data: null,
error: errMsg,
error:
convertToApiError(error as AxiosError<RenderErrorResponseDTO>) ?? null,
};
}
},

View File

@@ -67,54 +67,74 @@ export const podWidgetInfo = [
{
title: 'CPU Usage (cores)',
yAxisUnit: '',
docPath: '/infrastructure-monitoring/kubernetes/pods/#cpu-usage-cores-1',
},
{
title: 'CPU Request, Limit Utilization',
yAxisUnit: 'percentunit',
docPath:
'/infrastructure-monitoring/kubernetes/pods/#cpu-request-limit-utilization',
},
{
title: 'Memory Usage (bytes)',
yAxisUnit: 'bytes',
docPath: '/infrastructure-monitoring/kubernetes/pods/#memory-usage-bytes',
},
{
title: 'Memory Request, Limit Utilization',
yAxisUnit: 'percentunit',
docPath:
'/infrastructure-monitoring/kubernetes/pods/#memory-request-limit-utilization',
},
{
title: 'Memory by State',
yAxisUnit: 'bytes',
docPath: '/infrastructure-monitoring/kubernetes/pods/#memory-by-state',
},
{
title: 'Memory Major Page Faults',
yAxisUnit: '',
docPath:
'/infrastructure-monitoring/kubernetes/pods/#memory-major-page-faults',
},
{
title: 'CPU Usage by Container (cores)',
yAxisUnit: '',
docPath:
'/infrastructure-monitoring/kubernetes/pods/#cpu-usage-by-container-cores',
},
{
title: 'CPU Request, Limit Utilization by Container',
yAxisUnit: 'percentunit',
docPath:
'/infrastructure-monitoring/kubernetes/pods/#cpu-request-limit-utilization-by-container',
},
{
title: 'Memory Usage by Container (bytes)',
yAxisUnit: 'bytes',
docPath:
'/infrastructure-monitoring/kubernetes/pods/#memory-usage-by-container-bytes',
},
{
title: 'Memory Request, Limit Utilization by Container',
yAxisUnit: 'percentunit',
docPath:
'/infrastructure-monitoring/kubernetes/pods/#memory-request-limit-utilization-by-container',
},
{
title: 'Network rate',
yAxisUnit: 'binBps',
docPath: '/infrastructure-monitoring/kubernetes/pods/#network-rate',
},
{
title: 'Network errors',
yAxisUnit: '',
docPath: '/infrastructure-monitoring/kubernetes/pods/#network-errors',
},
{
title: 'File system (bytes)',
yAxisUnit: 'bytes',
docPath: '/infrastructure-monitoring/kubernetes/pods/#file-system-bytes',
},
];

View File

@@ -1,9 +1,9 @@
import { Container } from '@signozhq/icons';
import { Badge, BadgeColor } from '@signozhq/ui/badge';
import { Badge } from '@signozhq/ui/badge';
import { TooltipSimple } from '@signozhq/ui/tooltip';
import {
InframonitoringtypesPodPhaseDTO,
InframonitoringtypesPodRecordDTO,
InframonitoringtypesPodStatusDTO,
} from 'api/generated/services/sigNoz.schemas';
import TanStackTable, { TableColumnDef } from 'components/TanStackTableView';
import { ExpandButtonWrapper } from 'container/InfraMonitoringK8sV2/components';
@@ -11,7 +11,11 @@ import { ExpandButtonWrapper } from 'container/InfraMonitoringK8sV2/components';
import ColumnHeader from '../Base/ColumnHeader';
import EntityGroupHeader from '../Base/EntityGroupHeader';
import K8sGroupCell from '../Base/K8sGroupCell';
import { formatBytes, getPodPhaseStatusItems } from '../commonUtils';
import {
formatBytes,
getPodStatusItems,
POD_STATUS_COLORS,
} from '../commonUtils';
import {
CellValueTooltip,
EntityProgressBar,
@@ -40,15 +44,6 @@ export function getK8sPodItemKey(
return pod.podUID;
}
const POD_PHASE_COLORS: Record<string, BadgeColor> = {
running: 'forest',
pending: 'amber',
succeeded: 'robin',
failed: 'cherry',
unknown: 'vanilla',
no_data: 'vanilla',
};
export type PodTableColumnConfig =
TableColumnDef<InframonitoringtypesPodRecordDTO>;
export const k8sPodColumnsConfig: PodTableColumnConfig[] = [
@@ -93,34 +88,30 @@ export const k8sPodColumnsConfig: PodTableColumnConfig[] = [
visibilityBehavior: 'hidden-on-expand',
cell: ({ value }): React.ReactNode => {
const podName = value as string;
return (
<CellValueTooltip value={podName}>
<TanStackTable.Text>{podName}</TanStackTable.Text>
</CellValueTooltip>
);
return <CellValueTooltip value={podName} />;
},
},
{
id: 'podPhase',
id: 'podStatus',
header: (): React.ReactNode => (
<ColumnHeader docPath="/infrastructure-monitoring/kubernetes/pods#pod-phase">
Phase
<ColumnHeader docPath="/infrastructure-monitoring/kubernetes/pods#pod-status">
Status
</ColumnHeader>
),
accessorFn: (row): string => row.podPhase,
width: { min: 120 },
accessorFn: (row): string => row.podStatus,
width: { min: 160 },
enableSort: false,
visibilityBehavior: 'hidden-on-expand',
cell: ({ row }): React.ReactNode => {
if (!row.podPhase) {
if (!row.podStatus) {
return <></>;
}
const color = POD_PHASE_COLORS[row.podPhase] || POD_PHASE_COLORS.unknown;
const color = POD_STATUS_COLORS[row.podStatus] || POD_STATUS_COLORS.unknown;
const label =
row.podPhase === InframonitoringtypesPodPhaseDTO.no_data
row.podStatus === InframonitoringtypesPodStatusDTO.no_data
? 'No Data'
: row.podPhase.charAt(0).toUpperCase() + row.podPhase.slice(1);
: row.podStatus.charAt(0).toUpperCase() + row.podStatus.slice(1);
return (
<Badge color={color} variant="outline">
{label}
@@ -129,30 +120,34 @@ export const k8sPodColumnsConfig: PodTableColumnConfig[] = [
},
},
{
id: 'podCountsByPhase',
id: 'podCountsByStatus',
header: (): React.ReactNode => (
<ColumnHeader docPath="/infrastructure-monitoring/kubernetes/pods#pod-phase">
Phases
<ColumnHeader docPath="/infrastructure-monitoring/kubernetes/pods#pod-status">
Status
</ColumnHeader>
),
accessorFn: (row): InframonitoringtypesPodRecordDTO['podCountsByPhase'] =>
row.podCountsByPhase,
accessorFn: (row): InframonitoringtypesPodRecordDTO['podCountsByStatus'] =>
row.podCountsByStatus,
width: { min: 250 },
enableSort: false,
visibilityBehavior: 'hidden-on-collapse',
cell: ({ row }): React.ReactNode => {
const podCountsByPhase = row.podCountsByPhase;
if (!podCountsByPhase) {
const podCountsByStatus = row.podCountsByStatus;
if (!podCountsByStatus) {
return <TanStackTable.Text>-</TanStackTable.Text>;
}
return (
<GroupedStatusCounts items={getPodPhaseStatusItems(row.podCountsByPhase)} />
<GroupedStatusCounts items={getPodStatusItems(row.podCountsByStatus)} />
);
},
},
{
id: 'podAge',
header: 'Age',
header: (): React.ReactNode => (
<ColumnHeader docPath="/infrastructure-monitoring/kubernetes/pods#age">
Age
</ColumnHeader>
),
accessorFn: (row): number => row.podAge,
width: { min: 100 },
enableSort: false,
@@ -168,6 +163,28 @@ export const k8sPodColumnsConfig: PodTableColumnConfig[] = [
return <TanStackTable.Text>{formatAge(age)}</TanStackTable.Text>;
},
},
{
id: 'podRestarts',
header: (): React.ReactNode => (
<ColumnHeader docPath="/infrastructure-monitoring/kubernetes/pods#restarts">
Restarts
</ColumnHeader>
),
accessorFn: (row): number => row.podRestarts,
width: { min: 100 },
enableSort: true,
cell: ({ value }): React.ReactNode => {
const restarts = value as number;
if (restarts === -1) {
return (
<TooltipSimple title="No data">
<Typography.Text>-</Typography.Text>
</TooltipSimple>
);
}
return <TanStackTable.Text>{restarts}</TanStackTable.Text>;
},
},
{
id: 'cpu_request',
header: (): React.ReactNode => (
@@ -316,7 +333,11 @@ export const k8sPodColumnsConfig: PodTableColumnConfig[] = [
},
{
id: 'namespace',
header: 'Namespace',
header: (): React.ReactNode => (
<ColumnHeader docPath="/infrastructure-monitoring/kubernetes/pods#additional-columns">
Namespace
</ColumnHeader>
),
accessorFn: (row): string =>
row.meta?.[INFRA_MONITORING_ATTR_KEYS.K8S_NAMESPACE_NAME] || '',
width: { default: 100 },
@@ -328,7 +349,11 @@ export const k8sPodColumnsConfig: PodTableColumnConfig[] = [
},
{
id: 'node',
header: 'Node',
header: (): React.ReactNode => (
<ColumnHeader docPath="/infrastructure-monitoring/kubernetes/pods#additional-columns">
Node
</ColumnHeader>
),
accessorFn: (row): string =>
row.meta?.[INFRA_MONITORING_ATTR_KEYS.K8S_NODE_NAME] || '',
width: { default: 100 },
@@ -340,7 +365,11 @@ export const k8sPodColumnsConfig: PodTableColumnConfig[] = [
},
{
id: 'cluster',
header: 'Cluster',
header: (): React.ReactNode => (
<ColumnHeader docPath="/infrastructure-monitoring/kubernetes/pods#additional-columns">
Cluster
</ColumnHeader>
),
accessorFn: (row): string =>
row.meta?.[INFRA_MONITORING_ATTR_KEYS.K8S_CLUSTER_NAME] || '',
width: { default: 100 },

View File

@@ -1,11 +1,15 @@
import { useCallback } from 'react';
import { useCallback, useMemo } from 'react';
import { convertToApiError } from 'api/ErrorResponseHandlerForGeneratedAPIs';
import { listStatefulSets } from 'api/generated/services/inframonitoring';
import { RenderErrorResponseDTO } from 'api/generated/services/sigNoz.schemas';
import { AxiosError } from 'axios';
import {
InframonitoringtypesResponseTypeDTO,
InframonitoringtypesStatefulSetRecordDTO,
Querybuildertypesv5OrderDirectionDTO,
} from 'api/generated/services/sigNoz.schemas';
import { InfraMonitoringEvents } from 'constants/events';
import APIError from 'types/api/error';
import K8sBaseDetails, { K8sDetailsFilters } from '../Base/K8sBaseDetails';
import { K8sBaseList } from '../Base/K8sBaseList';
@@ -14,6 +18,7 @@ import { InfraMonitoringEntity } from '../constants';
import { SelectedItemParams } from '../hooks';
import {
getStatefulSetMetricsQueryPayload,
getStatefulSetPodMetricsQueryPayload,
k8sStatefulSetDetailsMetadataConfig,
k8sStatefulSetGetEntityName,
k8sStatefulSetGetSelectedItemExpression,
@@ -26,6 +31,7 @@ import {
getK8sStatefulSetRowKey,
k8sStatefulSetsColumnsConfig,
} from './table.config';
import { createPodMetricsTab } from 'container/InfraMonitoringK8sV2/EntityDetailsUtils/createPodMetricsTab';
function K8sStatefulSetsList({
controlListPrefix,
@@ -68,13 +74,12 @@ function K8sStatefulSetsList({
warning: data.warning,
};
} catch (error) {
const errMsg =
error instanceof Error ? error.message : 'Failed to fetch statefulsets';
return {
type: 'list' as const,
records: [] as InframonitoringtypesStatefulSetRecordDTO[],
total: 0,
error: errMsg,
error:
convertToApiError(error as AxiosError<RenderErrorResponseDTO>) ?? null,
};
}
},
@@ -87,7 +92,7 @@ function K8sStatefulSetsList({
signal?: AbortSignal,
): Promise<{
data: InframonitoringtypesStatefulSetRecordDTO | null;
error?: string | null;
error?: APIError | null;
}> => {
try {
const response = await listStatefulSets(
@@ -105,17 +110,27 @@ function K8sStatefulSetsList({
data: response.data.records.length > 0 ? response.data.records[0] : null,
};
} catch (error) {
const errMsg =
error instanceof Error ? error.message : 'Failed to fetch statefulset';
return {
data: null,
error: errMsg,
error:
convertToApiError(error as AxiosError<RenderErrorResponseDTO>) ?? null,
};
}
},
[],
);
const customTabs = useMemo(
() => [
createPodMetricsTab<InframonitoringtypesStatefulSetRecordDTO>({
getQueryPayload: getStatefulSetPodMetricsQueryPayload,
category: InfraMonitoringEntity.STATEFULSETS,
queryKey: 'statefulSetPodMetrics',
}),
],
[],
);
return (
<>
<K8sBaseList<InframonitoringtypesStatefulSetRecordDTO, SelectedItemParams>
@@ -140,6 +155,7 @@ function K8sStatefulSetsList({
entityWidgetInfo={statefulSetWidgetInfo}
getEntityQueryPayload={getStatefulSetMetricsQueryPayload}
queryKeyPrefix="statefulSet"
customTabs={customTabs}
/>
</>
);

View File

@@ -7,7 +7,10 @@ import { DataSource, ReduceOperators } from 'types/common/queryBuilder';
import { v4 } from 'uuid';
import { K8sDetailsMetadataConfig } from '../Base/K8sBaseDetails';
import { INFRA_MONITORING_ATTR_KEYS } from '../constants';
import {
getPodUtilizationByPodQueryPayloads,
INFRA_MONITORING_ATTR_KEYS,
} from '../constants';
import { SelectedItemParams } from '../hooks';
import {
buildEventsExpression,
@@ -72,26 +75,37 @@ export const statefulSetWidgetInfo = [
{
title: 'CPU usage, request, limits',
yAxisUnit: '',
docPath:
'/infrastructure-monitoring/kubernetes/statefulsets/#cpu-usage-request-limits',
},
{
title: 'CPU request, limit util (%)',
yAxisUnit: 'percentunit',
docPath:
'/infrastructure-monitoring/kubernetes/statefulsets/#cpu-request-limit-utilization-',
},
{
title: 'Memory usage, request, limits',
yAxisUnit: 'bytes',
docPath:
'/infrastructure-monitoring/kubernetes/statefulsets/#memory-usage-request-limits',
},
{
title: 'Memory request, limit util (%)',
yAxisUnit: 'percentunit',
docPath:
'/infrastructure-monitoring/kubernetes/statefulsets/#memory-request-limit-utilization-',
},
{
title: 'Network IO',
yAxisUnit: 'binBps',
docPath: '/infrastructure-monitoring/kubernetes/statefulsets/#network-io',
},
{
title: 'Network errors count',
yAxisUnit: '',
docPath:
'/infrastructure-monitoring/kubernetes/statefulsets/#network-errors-count',
},
];
@@ -848,3 +862,29 @@ export const getStatefulSetMetricsQueryPayload = (
},
];
};
export const getStatefulSetPodMetricsQueryPayload = (
statefulSet: InframonitoringtypesStatefulSetRecordDTO,
start: number,
end: number,
dotMetricsEnabled: boolean,
): GetQueryResultsProps[] => {
const k8sStatefulSetNameKey = dotMetricsEnabled
? INFRA_MONITORING_ATTR_KEYS.K8S_STATEFULSET_NAME
: 'k8s_statefulset_name';
return getPodUtilizationByPodQueryPayloads(
{
workloadNameKey: k8sStatefulSetNameKey,
workloadNameValue:
statefulSet.meta?.[INFRA_MONITORING_ATTR_KEYS.K8S_STATEFULSET_NAME] ?? '',
clusterName:
statefulSet.meta?.[INFRA_MONITORING_ATTR_KEYS.K8S_CLUSTER_NAME] ?? '',
namespaceName:
statefulSet.meta?.[INFRA_MONITORING_ATTR_KEYS.K8S_NAMESPACE_NAME] ?? '',
},
start,
end,
dotMetricsEnabled,
);
};

View File

@@ -7,7 +7,7 @@ import ColumnHeader from '../Base/ColumnHeader';
import EntityGroupHeader from '../Base/EntityGroupHeader';
import K8sGroupCell from '../Base/K8sGroupCell';
import { SelectedItemParams } from '../hooks';
import { formatBytes, getPodPhaseStatusItems } from '../commonUtils';
import { formatBytes, getPodStatusItems } from '../commonUtils';
import {
CellValueTooltip,
EntityProgressBar,
@@ -88,11 +88,7 @@ export const k8sStatefulSetsColumnsConfig: TableColumnDef<InframonitoringtypesSt
visibilityBehavior: 'hidden-on-expand',
cell: ({ value }): React.ReactNode => {
const statefulsetName = value as string;
return (
<CellValueTooltip value={statefulsetName}>
<TanStackTable.Text>{statefulsetName}</TanStackTable.Text>
</CellValueTooltip>
);
return <CellValueTooltip value={statefulsetName} />;
},
},
{
@@ -109,42 +105,36 @@ export const k8sStatefulSetsColumnsConfig: TableColumnDef<InframonitoringtypesSt
enableResize: true,
cell: ({ value }): React.ReactNode => {
const namespaceName = value as string;
return (
<CellValueTooltip value={namespaceName}>
<TanStackTable.Text>{namespaceName}</TanStackTable.Text>
</CellValueTooltip>
);
return <CellValueTooltip value={namespaceName} />;
},
},
{
id: 'pod_counts_by_phase',
id: 'pod_counts_by_status',
header: (): React.ReactNode => (
<ColumnHeader docPath="/infrastructure-monitoring/kubernetes/statefulsets#pod-counts-by-phase">
Pod Phases
<ColumnHeader docPath="/infrastructure-monitoring/kubernetes/statefulsets#pod-counts-by-status">
Pod Status
</ColumnHeader>
),
accessorFn: (
row,
): InframonitoringtypesStatefulSetRecordDTO['podCountsByPhase'] =>
row.podCountsByPhase,
): InframonitoringtypesStatefulSetRecordDTO['podCountsByStatus'] =>
row.podCountsByStatus,
width: { min: 250 },
enableSort: false,
enableResize: true,
cell: ({ row }): React.ReactNode => {
const podCountsByPhase = row.podCountsByPhase;
if (!podCountsByPhase) {
const podCountsByStatus = row.podCountsByStatus;
if (!podCountsByStatus) {
return <TanStackTable.Text>-</TanStackTable.Text>;
}
return (
<GroupedStatusCounts items={getPodPhaseStatusItems(podCountsByPhase)} />
);
return <GroupedStatusCounts items={getPodStatusItems(podCountsByStatus)} />;
},
},
{
id: 'pod_status',
id: 'pod_replicas',
header: (): React.ReactNode => (
<ColumnHeader docPath="/infrastructure-monitoring/kubernetes/statefulsets#pod-status">
Pod Status
<ColumnHeader docPath="/infrastructure-monitoring/kubernetes/statefulsets#pod-replicas">
Pod Replicas
</ColumnHeader>
),
accessorFn: (row): number => row.currentPods,

View File

@@ -1,11 +1,15 @@
import { useCallback } from 'react';
import { convertToApiError } from 'api/ErrorResponseHandlerForGeneratedAPIs';
import { listVolumes } from 'api/generated/services/inframonitoring';
import { RenderErrorResponseDTO } from 'api/generated/services/sigNoz.schemas';
import { AxiosError } from 'axios';
import {
InframonitoringtypesResponseTypeDTO,
InframonitoringtypesVolumeRecordDTO,
Querybuildertypesv5OrderDirectionDTO,
} from 'api/generated/services/sigNoz.schemas';
import { InfraMonitoringEvents } from 'constants/events';
import APIError from 'types/api/error';
import K8sBaseDetails, { K8sDetailsFilters } from '../Base/K8sBaseDetails';
import { K8sBaseList } from '../Base/K8sBaseList';
@@ -68,13 +72,12 @@ function K8sVolumesList({
warning: data.warning,
};
} catch (error) {
const errMsg =
error instanceof Error ? error.message : 'Failed to fetch volumes';
return {
type: 'list' as const,
records: [] as InframonitoringtypesVolumeRecordDTO[],
total: 0,
error: errMsg,
error:
convertToApiError(error as AxiosError<RenderErrorResponseDTO>) ?? null,
};
}
},
@@ -87,7 +90,7 @@ function K8sVolumesList({
signal?: AbortSignal,
): Promise<{
data: InframonitoringtypesVolumeRecordDTO | null;
error?: string | null;
error?: APIError | null;
}> => {
try {
const response = await listVolumes(
@@ -105,11 +108,10 @@ function K8sVolumesList({
data: response.data.records.length > 0 ? response.data.records[0] : null,
};
} catch (error) {
const errMsg =
error instanceof Error ? error.message : 'Failed to fetch volume';
return {
data: null,
error: errMsg,
error:
convertToApiError(error as AxiosError<RenderErrorResponseDTO>) ?? null,
};
}
},

View File

@@ -69,22 +69,27 @@ export const volumeWidgetInfo = [
{
title: 'Volume available',
yAxisUnit: 'bytes',
docPath: '/infrastructure-monitoring/kubernetes/volumes/#volume-available',
},
{
title: 'Volume capacity',
yAxisUnit: 'bytes',
docPath: '/infrastructure-monitoring/kubernetes/volumes/#volume-capacity',
},
{
title: 'Volume inodes used',
yAxisUnit: 'short',
docPath: '/infrastructure-monitoring/kubernetes/volumes/#volume-inodes-used',
},
{
title: 'Volume inodes',
yAxisUnit: 'short',
docPath: '/infrastructure-monitoring/kubernetes/volumes/#volume-inodes',
},
{
title: 'Volume inodes free',
yAxisUnit: 'short',
docPath: '/infrastructure-monitoring/kubernetes/volumes/#volume-inodes-free',
},
];

View File

@@ -81,11 +81,7 @@ export const k8sVolumesColumnsConfig: VolumeTableColumnConfig[] = [
visibilityBehavior: 'hidden-on-expand',
cell: ({ value }): React.ReactNode => {
const pvcName = value as string;
return (
<CellValueTooltip value={pvcName}>
<TanStackTable.Text>{pvcName}</TanStackTable.Text>
</CellValueTooltip>
);
return <CellValueTooltip value={pvcName} />;
},
},
{
@@ -101,11 +97,7 @@ export const k8sVolumesColumnsConfig: VolumeTableColumnConfig[] = [
enableSort: false,
cell: ({ value }): React.ReactNode => {
const namespaceName = value as string;
return (
<CellValueTooltip value={namespaceName}>
<TanStackTable.Text>{namespaceName}</TanStackTable.Text>
</CellValueTooltip>
);
return <CellValueTooltip value={namespaceName} />;
},
},
{

View File

@@ -1,5 +1,9 @@
import { Color } from '@signozhq/design-tokens';
import { InframonitoringtypesPodCountsByPhaseDTO } from 'api/generated/services/sigNoz.schemas';
import { BadgeColor } from '@signozhq/ui/badge';
import {
InframonitoringtypesPodCountsByStatusDTO,
InframonitoringtypesPodStatusDTO,
} from 'api/generated/services/sigNoz.schemas';
import { StatusCountItem } from './components/GroupedStatusCounts';
@@ -64,17 +68,106 @@ export function getStrokeColorForLimitUtilization(value: number): string {
return Color.BG_SAKURA_500;
}
/**
* Builds StatusCountItem[] for GroupedStatusCounts from pod phase counts.
*/
export function getPodPhaseStatusItems(
counts: InframonitoringtypesPodCountsByPhaseDTO,
export const POD_STATUS_COLORS: Record<
InframonitoringtypesPodStatusDTO,
BadgeColor
> = {
[InframonitoringtypesPodStatusDTO.running]: 'forest',
[InframonitoringtypesPodStatusDTO.completed]: 'robin',
[InframonitoringtypesPodStatusDTO.pending]: 'amber',
[InframonitoringtypesPodStatusDTO.unknown]: 'vanilla',
[InframonitoringtypesPodStatusDTO.no_data]: 'vanilla',
[InframonitoringtypesPodStatusDTO.failed]: 'cherry',
[InframonitoringtypesPodStatusDTO.crashloopbackoff]: 'cherry',
[InframonitoringtypesPodStatusDTO.imagepullbackoff]: 'cherry',
[InframonitoringtypesPodStatusDTO.errimagepull]: 'cherry',
[InframonitoringtypesPodStatusDTO.createcontainerconfigerror]: 'cherry',
[InframonitoringtypesPodStatusDTO.containercreating]: 'amber',
[InframonitoringtypesPodStatusDTO.oomkilled]: 'cherry',
[InframonitoringtypesPodStatusDTO.error]: 'cherry',
[InframonitoringtypesPodStatusDTO.containercannotrun]: 'cherry',
[InframonitoringtypesPodStatusDTO.evicted]: 'cherry',
[InframonitoringtypesPodStatusDTO.nodeaffinity]: 'cherry',
[InframonitoringtypesPodStatusDTO.nodelost]: 'cherry',
[InframonitoringtypesPodStatusDTO.shutdown]: 'cherry',
[InframonitoringtypesPodStatusDTO.unexpectedadmissionerror]: 'cherry',
};
type PodStatusCategory =
| 'running'
| 'completed'
| 'pending'
| 'unknown'
| 'error';
const POD_STATUS_CATEGORY_MAP: Record<
keyof InframonitoringtypesPodCountsByStatusDTO,
PodStatusCategory
> = {
running: 'running',
completed: 'completed',
pending: 'pending',
unknown: 'unknown',
failed: 'error',
crashLoopBackOff: 'error',
imagePullBackOff: 'error',
errImagePull: 'error',
createContainerConfigError: 'error',
containerCreating: 'error',
oomKilled: 'error',
error: 'error',
containerCannotRun: 'error',
evicted: 'error',
nodeAffinity: 'error',
nodeLost: 'error',
shutdown: 'error',
unexpectedAdmissionError: 'error',
};
type ErrorStatusKey = {
[K in keyof InframonitoringtypesPodCountsByStatusDTO]: (typeof POD_STATUS_CATEGORY_MAP)[K] extends 'error'
? K
: never;
}[keyof InframonitoringtypesPodCountsByStatusDTO];
const ERROR_STATUS_LABELS: Record<ErrorStatusKey, string> = {
failed: 'Failed',
crashLoopBackOff: 'CrashLoopBackOff',
imagePullBackOff: 'ImagePullBackOff',
errImagePull: 'ErrImagePull',
createContainerConfigError: 'CreateContainerConfigError',
containerCreating: 'ContainerCreating',
oomKilled: 'OOMKilled',
error: 'Error',
containerCannotRun: 'ContainerCannotRun',
evicted: 'Evicted',
nodeAffinity: 'NodeAffinity',
nodeLost: 'NodeLost',
shutdown: 'Shutdown',
unexpectedAdmissionError: 'UnexpectedAdmissionError',
};
export function getPodStatusItems(
counts: InframonitoringtypesPodCountsByStatusDTO,
): StatusCountItem[] {
const errorKeys = Object.keys(ERROR_STATUS_LABELS) as ErrorStatusKey[];
const errorTotal = errorKeys.reduce((sum, key) => sum + counts[key], 0);
const errorBreakdown = errorKeys.map((key) => ({
label: ERROR_STATUS_LABELS[key],
value: counts[key],
}));
return [
{ value: counts.running, label: 'Running', color: Color.BG_FOREST_500 },
{ value: counts.completed, label: 'Completed', color: Color.BG_ROBIN_500 },
{ value: counts.pending, label: 'Pending', color: Color.BG_AMBER_500 },
{ value: counts.succeeded, label: 'Succeeded', color: Color.BG_ROBIN_500 },
{ value: counts.failed, label: 'Failed', color: Color.BG_CHERRY_500 },
{ value: counts.unknown, label: 'Unknown', color: Color.BG_SLATE_400 },
{
value: errorTotal,
label: 'Error Status',
color: Color.BG_CHERRY_500,
breakdown: errorBreakdown,
},
];
}

View File

@@ -52,3 +52,7 @@
.divider {
--divider-color: rgba(255, 255, 255, 0.14);
}
.value {
width: fit-content;
}

View File

@@ -1,8 +1,9 @@
import { useCallback, type ReactNode, type MouseEvent } from 'react';
import { useCallback, type MouseEvent } from 'react';
import { TooltipSimple } from '@signozhq/ui/tooltip';
import { toast } from '@signozhq/ui/sonner';
import { Copy, Minus, Plus } from '@signozhq/icons';
import { useCopyToClipboard } from 'react-use';
import TanStackTable from 'components/TanStackTableView';
import { useInfraMonitoringCellActionsStore } from './useInfraMonitoringCellActionsStore';
@@ -11,12 +12,10 @@ import { Divider } from '@signozhq/ui/divider';
export interface CellValueTooltipProps {
value: string;
children: ReactNode;
}
export function CellValueTooltip({
value,
children,
}: CellValueTooltipProps): JSX.Element {
const [, copyToClipboard] = useCopyToClipboard();
const { lineClamp, increaseLineClamp, decreaseLineClamp } =
@@ -94,7 +93,7 @@ export function CellValueTooltip({
className: styles.tooltipContentWrapper,
}}
>
{children}
<TanStackTable.Text className={styles.value}>{value}</TanStackTable.Text>
</TooltipSimple>
);
}

View File

@@ -17,9 +17,40 @@
flex-shrink: 0;
}
.valueWrapper {
min-width: 4ch;
}
.valueWrapperTooltip {
display: block;
width: fit-content;
}
.value {
font-variant-numeric: tabular-nums;
min-width: 4ch;
text-align: left;
cursor: default;
min-width: min-content;
}
.tooltipContent {
display: flex;
flex-direction: column;
gap: 4px;
min-width: 120px;
}
.tooltipHeader {
font-weight: 600;
margin-bottom: 2px;
}
.tooltipRow {
display: flex;
justify-content: space-between;
gap: 12px;
}
.tooltipValue {
font-variant-numeric: tabular-nums;
}

View File

@@ -2,11 +2,18 @@ import { TooltipSimple } from '@signozhq/ui/tooltip';
import styles from './GroupedStatusCounts.module.scss';
import TanStackTable from 'components/TanStackTableView';
import { Typography } from '@signozhq/ui/typography';
export interface StatusBreakdownItem {
label: string;
value: number;
}
export interface StatusCountItem {
value: number;
label: string;
color: string;
breakdown?: StatusBreakdownItem[];
}
interface GroupedStatusCountsProps {
@@ -14,6 +21,45 @@ interface GroupedStatusCountsProps {
showZeroValues?: boolean;
}
function buildTooltipContent(item: StatusCountItem): React.ReactNode {
if (!item.breakdown || item.breakdown.length === 0) {
return (
<Typography.Text>
{item.label}: {item.value}
</Typography.Text>
);
}
const nonZeroBreakdown = item.breakdown.filter((b) => b.value > 0);
if (nonZeroBreakdown.length === 0) {
return (
<div className={styles.tooltipContent}>
<Typography.Text className={styles.tooltipHeader}>
{item.label}
</Typography.Text>
<Typography.Text>No errors</Typography.Text>
</div>
);
}
return (
<div className={styles.tooltipContent}>
<Typography.Text className={styles.tooltipHeader}>
{item.label}
</Typography.Text>
{nonZeroBreakdown.map((b) => (
<div key={b.label} className={styles.tooltipRow}>
<Typography.Text>{b.label}</Typography.Text>
<Typography.Text className={styles.tooltipValue}>
{b.value}
</Typography.Text>
</div>
))}
</div>
);
}
export function GroupedStatusCounts({
items,
showZeroValues = true,
@@ -33,13 +79,15 @@ export function GroupedStatusCounts({
className={styles.separator}
style={{ backgroundColor: item.color }}
/>
<TooltipSimple title={`${item.label}: ${item.value}`}>
<span>
<TanStackTable.Text className={styles.value}>
{item.value || '-'}
</TanStackTable.Text>
</span>
</TooltipSimple>
<div className={styles.valueWrapper}>
<TooltipSimple title={buildTooltipContent(item)} arrow align="start">
<span className={styles.valueWrapperTooltip}>
<TanStackTable.Text className={styles.value}>
{item.value || '-'}
</TanStackTable.Text>
</span>
</TooltipSimple>
</div>
</div>
))}
</div>

View File

@@ -2,8 +2,12 @@ import {
FiltersType,
IQuickFiltersConfig,
} from 'components/QuickFilters/types';
import { PANEL_TYPES } from 'constants/queryBuilder';
import { GetQueryResultsProps } from 'lib/dashboard/getQueryResults';
import { DataTypes } from 'types/api/queryBuilder/queryAutocompleteResponse';
import { DataSource } from 'types/common/queryBuilder';
import { EQueryType } from 'types/common/dashboard';
import { DataSource, ReduceOperators } from 'types/common/queryBuilder';
import { v4 } from 'uuid';
// TODO(backend): Find a way to generate this via openapi
export const INFRA_MONITORING_ATTR_KEYS = {
@@ -130,6 +134,7 @@ export enum VIEWS {
CONTAINERS = 'containers',
PROCESSES = 'processes',
EVENTS = 'events',
POD_METRICS = 'pod_metrics',
}
export const VIEW_TYPES = {
@@ -137,6 +142,7 @@ export const VIEW_TYPES = {
LOGS: VIEWS.LOGS,
TRACES: VIEWS.TRACES,
EVENTS: VIEWS.EVENTS,
POD_METRICS: VIEWS.POD_METRICS,
};
export const K8sCategories = {
@@ -916,3 +922,261 @@ export const METRIC_NAMESPACE_BY_ENTITY: Record<InfraMonitoringEntity, string> =
[InfraMonitoringEntity.JOBS]: 'k8s.',
[InfraMonitoringEntity.VOLUMES]: 'k8s.volume.',
};
export interface WorkloadFilterContext {
workloadNameKey: string;
workloadNameValue: string;
clusterName: string;
namespaceName?: string;
}
export const podUtilizationByPodWidgetInfo = [
{
title: 'CPU Limit Utilization By Pod Name',
yAxisUnit: 'percentunit',
},
{
title: 'CPU Request Utilization By Pod Name',
yAxisUnit: 'percentunit',
},
{
title: 'Memory Limit Utilization By Pod Name',
yAxisUnit: 'percentunit',
},
{
title: 'Memory Request Utilization By Pod Name',
yAxisUnit: 'percentunit',
},
{
title: 'FileSystem Usage Percentage By Pod Name',
yAxisUnit: 'percentunit',
},
];
export function getPodUtilizationByPodQueryPayloads(
context: WorkloadFilterContext,
start: number,
end: number,
dotMetricsEnabled: boolean,
): GetQueryResultsProps[] {
const getKey = (dotKey: string, underscoreKey: string): string =>
dotMetricsEnabled ? dotKey : underscoreKey;
const k8sPodCpuLimitUtilKey = getKey(
'k8s.pod.cpu_limit_utilization',
'k8s_pod_cpu_limit_utilization',
);
const k8sPodCpuRequestUtilKey = getKey(
'k8s.pod.cpu_request_utilization',
'k8s_pod_cpu_request_utilization',
);
const k8sPodMemLimitUtilKey = getKey(
'k8s.pod.memory_limit_utilization',
'k8s_pod_memory_limit_utilization',
);
const k8sPodMemRequestUtilKey = getKey(
'k8s.pod.memory_request_utilization',
'k8s_pod_memory_request_utilization',
);
const k8sPodFsUsageKey = getKey(
'k8s.pod.filesystem.usage',
'k8s_pod_filesystem_usage',
);
const k8sPodFsCapacityKey = getKey(
'k8s.pod.filesystem.capacity',
'k8s_pod_filesystem_capacity',
);
const k8sPodNameKey = getKey('k8s.pod.name', 'k8s_pod_name');
const k8sClusterNameKey = getKey('k8s.cluster.name', 'k8s_cluster_name');
const k8sNamespaceNameKey = getKey('k8s.namespace.name', 'k8s_namespace_name');
const baseFilters = [
{
id: 'workload',
key: {
dataType: DataTypes.String,
id: `${context.workloadNameKey}--string--tag--false`,
key: context.workloadNameKey,
type: 'tag',
},
op: '=',
value: context.workloadNameValue,
},
{
id: 'cluster',
key: {
dataType: DataTypes.String,
id: `${k8sClusterNameKey}--string--tag--false`,
key: k8sClusterNameKey,
type: 'tag',
},
op: '=',
value: context.clusterName,
},
...(context.namespaceName
? [
{
id: 'namespace',
key: {
dataType: DataTypes.String,
id: `${k8sNamespaceNameKey}--string--tag--false`,
key: k8sNamespaceNameKey,
type: 'tag',
},
op: '=',
value: context.namespaceName,
},
]
: []),
];
const podNameGroupBy = [
{
dataType: DataTypes.String,
id: `${k8sPodNameKey}--string--tag--false`,
key: k8sPodNameKey,
type: 'tag',
},
];
const buildSingleMetricQuery = (
metricKey: string,
metricId: string,
): GetQueryResultsProps => ({
selectedTime: 'GLOBAL_TIME',
graphType: PANEL_TYPES.TIME_SERIES,
query: {
builder: {
queryData: [
{
aggregateAttribute: {
dataType: DataTypes.Float64,
id: metricId,
key: metricKey,
type: 'Gauge',
},
aggregateOperator: 'avg',
dataSource: DataSource.METRICS,
disabled: false,
expression: 'A',
filters: {
items: [...baseFilters],
op: 'AND',
},
functions: [],
groupBy: podNameGroupBy,
having: [],
legend: `{{${k8sPodNameKey}}}`,
limit: null,
orderBy: [],
queryName: 'A',
reduceTo: ReduceOperators.AVG,
spaceAggregation: 'sum',
stepInterval: 60,
timeAggregation: 'avg',
},
],
queryFormulas: [],
queryTraceOperator: [],
},
clickhouse_sql: [{ disabled: false, legend: '', name: 'A', query: '' }],
id: v4(),
promql: [{ disabled: false, legend: '', name: 'A', query: '' }],
queryType: EQueryType.QUERY_BUILDER,
},
variables: {},
formatForWeb: false,
start,
end,
});
const filesystemUsagePercentQuery: GetQueryResultsProps = {
selectedTime: 'GLOBAL_TIME',
graphType: PANEL_TYPES.TIME_SERIES,
query: {
builder: {
queryData: [
{
aggregateAttribute: {
dataType: DataTypes.Float64,
id: 'fs_usage',
key: k8sPodFsUsageKey,
type: 'Gauge',
},
aggregateOperator: 'avg',
dataSource: DataSource.METRICS,
disabled: true,
expression: 'A',
filters: {
items: [...baseFilters],
op: 'AND',
},
functions: [],
groupBy: podNameGroupBy,
having: [],
legend: `{{${k8sPodNameKey}}}`,
limit: null,
orderBy: [],
queryName: 'A',
reduceTo: ReduceOperators.AVG,
spaceAggregation: 'sum',
stepInterval: 60,
timeAggregation: 'avg',
},
{
aggregateAttribute: {
dataType: DataTypes.Float64,
id: 'fs_capacity',
key: k8sPodFsCapacityKey,
type: 'Gauge',
},
aggregateOperator: 'avg',
dataSource: DataSource.METRICS,
disabled: true,
expression: 'B',
filters: {
items: [...baseFilters],
op: 'AND',
},
functions: [],
groupBy: podNameGroupBy,
having: [],
legend: `{{${k8sPodNameKey}}}`,
limit: null,
orderBy: [],
queryName: 'B',
reduceTo: ReduceOperators.AVG,
spaceAggregation: 'sum',
stepInterval: 60,
timeAggregation: 'avg',
},
],
queryFormulas: [
{
disabled: false,
expression: 'A/B',
legend: `{{${k8sPodNameKey}}}`,
queryName: 'F1',
},
],
queryTraceOperator: [],
},
clickhouse_sql: [{ disabled: false, legend: '', name: 'A', query: '' }],
id: v4(),
promql: [{ disabled: false, legend: '', name: 'A', query: '' }],
queryType: EQueryType.QUERY_BUILDER,
},
variables: {},
formatForWeb: false,
start,
end,
};
return [
buildSingleMetricQuery(k8sPodCpuLimitUtilKey, 'cpu_limit_util'),
buildSingleMetricQuery(k8sPodCpuRequestUtilKey, 'cpu_request_util'),
buildSingleMetricQuery(k8sPodMemLimitUtilKey, 'mem_limit_util'),
buildSingleMetricQuery(k8sPodMemRequestUtilKey, 'mem_request_util'),
filesystemUsagePercentQuery,
];
}

View File

@@ -2872,17 +2872,72 @@ export const nodeWidgetInfo = [
];
export const hostWidgetInfo = [
{ title: 'CPU Usage', yAxisUnit: 'percentunit' },
{ title: 'Memory Usage', yAxisUnit: 'bytes' },
{ title: 'System Load Average', yAxisUnit: '' },
{ title: 'Network usage (bytes)', yAxisUnit: 'bytes' },
{ title: 'Network usage (packet/s)', yAxisUnit: 'pps' },
{ title: 'Network errors', yAxisUnit: 'short' },
{ title: 'Network drops', yAxisUnit: 'short' },
{ title: 'Network connections', yAxisUnit: 'short' },
{ title: 'System disk io (bytes transferred)', yAxisUnit: 'bytes' },
{ title: 'System disk operations/s', yAxisUnit: 'short' },
{ title: 'Queue size', yAxisUnit: 'short' },
{ title: 'System disk operation time/s', yAxisUnit: 's' },
{ title: 'Disk Usage (%) by mountpoint', yAxisUnit: 'percentunit' },
{
title: 'CPU Usage',
yAxisUnit: 'percentunit',
docPath: '/infrastructure-monitoring/host-monitoring/#cpu-usage',
},
{
title: 'Memory Usage',
yAxisUnit: 'bytes',
docPath: '/infrastructure-monitoring/host-monitoring/#memory-usage',
},
{
title: 'System Load Average',
yAxisUnit: '',
docPath: '/infrastructure-monitoring/host-monitoring/#system-load-average',
},
{
title: 'Network usage (bytes)',
yAxisUnit: 'bytes',
docPath: '/infrastructure-monitoring/host-monitoring/#network-usage-bytes',
},
{
title: 'Network usage (packet/s)',
yAxisUnit: 'pps',
docPath: '/infrastructure-monitoring/host-monitoring/#network-usage-packetss',
},
{
title: 'Network errors',
yAxisUnit: 'short',
docPath: '/infrastructure-monitoring/host-monitoring/#network-errors',
},
{
title: 'Network drops',
yAxisUnit: 'short',
docPath: '/infrastructure-monitoring/host-monitoring/#network-drops',
},
{
title: 'Network connections',
yAxisUnit: 'short',
docPath: '/infrastructure-monitoring/host-monitoring/#network-connections',
},
{
title: 'System disk io (bytes transferred)',
yAxisUnit: 'bytes',
docPath: '/infrastructure-monitoring/host-monitoring/#system-disk-io-bytes',
},
{
title: 'System disk operations/s',
yAxisUnit: 'short',
docPath:
'/infrastructure-monitoring/host-monitoring/#system-disk-operationss',
},
{
title: 'Queue size',
yAxisUnit: 'short',
docPath: '/infrastructure-monitoring/host-monitoring/#queue-size',
},
{
title: 'System disk operation time/s',
yAxisUnit: 's',
docPath:
'/infrastructure-monitoring/host-monitoring/#system-disk-operation-times',
},
{
title: 'Disk Usage (%) by mountpoint',
yAxisUnit: 'percentunit',
docPath:
'/infrastructure-monitoring/host-monitoring/#disk-usage--by-mountpoint',
},
];

View File

@@ -15,8 +15,6 @@ var (
FeatureEnableAIObservability = featuretypes.MustNewName("enable_ai_observability")
FeatureEnableMetricsReduction = featuretypes.MustNewName("enable_metrics_reduction")
FeatureUseInfraMonitoringV2 = featuretypes.MustNewName("use_infra_monitoring_v2")
FeatureUsePrometheusClickhouseV2 = featuretypes.MustNewName("use_prometheus_clickhouse_v2")
)
func MustNewRegistry() featuretypes.Registry {
@@ -117,14 +115,6 @@ 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(),
},
)
if err != nil {
panic(err)

View File

@@ -33,7 +33,13 @@ func (handler *handler) GetFieldsKeys(rw http.ResponseWriter, req *http.Request)
fieldKeySelector := telemetrytypes.NewFieldKeySelectorFromPostableFieldKeysParams(params)
keys, complete, err := handler.telemetryMetadataStore.GetKeys(ctx, fieldKeySelector)
claims, err := authtypes.ClaimsFromContext(ctx)
if err != nil {
render.Error(rw, err)
return
}
keys, complete, err := handler.telemetryMetadataStore.GetKeys(ctx, valuer.MustNewUUID(claims.OrgID), fieldKeySelector)
if err != nil {
render.Error(rw, err)
return
@@ -68,7 +74,7 @@ func (handler *handler) GetFieldsValues(rw http.ResponseWriter, req *http.Reques
return
}
relatedValues, relatedComplete, err := handler.telemetryMetadataStore.GetRelatedValues(ctx, fieldValueSelector)
relatedValues, relatedComplete, err := handler.telemetryMetadataStore.GetRelatedValues(ctx, valuer.MustNewUUID(claims.OrgID), fieldValueSelector)
if err != nil {
// we don't want to return error if we fail to get related values for some reason
relatedValues = []string{}

View File

@@ -208,6 +208,7 @@ func (m *module) getContainersTableMetadata(ctx context.Context, orgID valuer.UU
// runs the query. The returned counts map is empty (never nil) when gated off.
func (m *module) getPerGroupContainerStatusCountsWithReqMetricChecks(
ctx context.Context,
orgID valuer.UUID,
start, end int64,
filter *qbtypes.Filter,
groupBy []qbtypes.GroupByKey,
@@ -237,7 +238,7 @@ func (m *module) getPerGroupContainerStatusCountsWithReqMetricChecks(
return map[string]containerStatusCounts{}, warning, nil
}
counts, err := m.getPerGroupContainerStatusCounts(ctx, start, end, filter, groupBy, pageGroups)
counts, err := m.getPerGroupContainerStatusCounts(ctx, orgID, start, end, filter, groupBy, pageGroups)
if err != nil {
return nil, nil, err
}
@@ -263,6 +264,7 @@ func (m *module) getPerGroupContainerStatusCountsWithReqMetricChecks(
// Groups absent from the result map have implicit zero counts (caller default).
func (m *module) getPerGroupContainerStatusCounts(
ctx context.Context,
orgID valuer.UUID,
start, end int64,
filter *qbtypes.Filter,
groupBy []qbtypes.GroupByKey,
@@ -288,7 +290,7 @@ func (m *module) getPerGroupContainerStatusCounts(
err error
)
if mergedFilterExpr != "" {
filterClause, err = m.buildFilterClause(ctx, &qbtypes.Filter{Expression: mergedFilterExpr}, start, end)
filterClause, err = m.buildFilterClause(ctx, orgID, &qbtypes.Filter{Expression: mergedFilterExpr}, start, end)
if err != nil {
return nil, err
}
@@ -527,6 +529,7 @@ func (m *module) getPerGroupContainerStatusCounts(
// Groups absent from the result map have no data (caller default).
func (m *module) getPerGroupContainerRestartCounts(
ctx context.Context,
orgID valuer.UUID,
start, end int64,
filter *qbtypes.Filter,
groupBy []qbtypes.GroupByKey,
@@ -550,7 +553,7 @@ func (m *module) getPerGroupContainerRestartCounts(
err error
)
if mergedFilterExpr != "" {
filterClause, err = m.buildFilterClause(ctx, &qbtypes.Filter{Expression: mergedFilterExpr}, start, end)
filterClause, err = m.buildFilterClause(ctx, orgID, &qbtypes.Filter{Expression: mergedFilterExpr}, start, end)
if err != nil {
return nil, err
}
@@ -670,6 +673,7 @@ func (m *module) getPerGroupContainerRestartCounts(
// Groups absent from the result map have no data (caller default).
func (m *module) getPerGroupContainerReadyCounts(
ctx context.Context,
orgID valuer.UUID,
start, end int64,
filter *qbtypes.Filter,
groupBy []qbtypes.GroupByKey,
@@ -693,7 +697,7 @@ func (m *module) getPerGroupContainerReadyCounts(
err error
)
if mergedFilterExpr != "" {
filterClause, err = m.buildFilterClause(ctx, &qbtypes.Filter{Expression: mergedFilterExpr}, start, end)
filterClause, err = m.buildFilterClause(ctx, orgID, &qbtypes.Filter{Expression: mergedFilterExpr}, start, end)
if err != nil {
return nil, err
}

View File

@@ -398,7 +398,7 @@ func (m *module) buildReducedSamplesTblFingerprintSubQuery(metricNames []string,
return fpSB
}
func (m *module) buildFilterClause(ctx context.Context, filter *qbtypes.Filter, startMillis, endMillis int64) (*sqlbuilder.WhereClause, error) {
func (m *module) buildFilterClause(ctx context.Context, orgID valuer.UUID, filter *qbtypes.Filter, startMillis, endMillis int64) (*sqlbuilder.WhereClause, error) {
expression := ""
if filter != nil {
expression = strings.TrimSpace(filter.Expression)
@@ -413,7 +413,7 @@ func (m *module) buildFilterClause(ctx context.Context, filter *qbtypes.Filter,
whereClauseSelectors[idx].SelectorMatchType = telemetrytypes.FieldSelectorMatchTypeExact
}
keys, _, err := m.telemetryMetadataStore.GetKeysMulti(ctx, whereClauseSelectors)
keys, _, err := m.telemetryMetadataStore.GetKeysMulti(ctx, orgID, whereClauseSelectors)
if err != nil {
return nil, err
}
@@ -646,7 +646,7 @@ func (m *module) getMetadata(
var filterClause *sqlbuilder.WhereClause
if filter != nil && strings.TrimSpace(filter.Expression) != "" {
var err error
filterClause, err = m.buildFilterClause(ctx, filter, startMs, endMs)
filterClause, err = m.buildFilterClause(ctx, orgID, filter, startMs, endMs)
if err != nil {
return nil, err
}
@@ -692,7 +692,7 @@ func (m *module) getMetadata(
)
if filter != nil && strings.TrimSpace(filter.Expression) != "" {
filterClause, err := m.buildFilterClause(ctx, filter, startMs, endMs)
filterClause, err := m.buildFilterClause(ctx, orgID, filter, startMs, endMs)
if err != nil {
return nil, err
}
@@ -860,7 +860,7 @@ func (m *module) getPerGroupDistinctCounts(
var filterClause *sqlbuilder.WhereClause
if mergedFilterExpr != "" {
var err error
filterClause, err = m.buildFilterClause(ctx, &qbtypes.Filter{Expression: mergedFilterExpr}, start, end)
filterClause, err = m.buildFilterClause(ctx, orgID, &qbtypes.Filter{Expression: mergedFilterExpr}, start, end)
if err != nil {
return nil, err
}
@@ -904,7 +904,7 @@ func (m *module) getPerGroupDistinctCounts(
fmt.Sprintf("fingerprint IN (%s)", sb.Var(fpSB)),
)
if mergedFilterExpr != "" {
filterClause, err := m.buildFilterClause(ctx, &qbtypes.Filter{Expression: mergedFilterExpr}, start, end)
filterClause, err := m.buildFilterClause(ctx, orgID, &qbtypes.Filter{Expression: mergedFilterExpr}, start, end)
if err != nil {
return nil, err
}

View File

@@ -64,7 +64,7 @@ func (m *module) getPerGroupHostStatusCounts(
var filterClause *sqlbuilder.WhereClause
if filterExpr != "" {
var err error
filterClause, err = m.buildFilterClause(ctx, &qbtypes.Filter{Expression: filterExpr}, req.Start, req.End)
filterClause, err = m.buildFilterClause(ctx, orgID, &qbtypes.Filter{Expression: filterExpr}, req.Start, req.End)
if err != nil {
return nil, err
}
@@ -110,7 +110,7 @@ func (m *module) getPerGroupHostStatusCounts(
)
if filterExpr != "" {
filterClause, err := m.buildFilterClause(ctx, &qbtypes.Filter{Expression: filterExpr}, req.Start, req.End)
filterClause, err := m.buildFilterClause(ctx, orgID, &qbtypes.Filter{Expression: filterExpr}, req.Start, req.End)
if err != nil {
return nil, err
}

View File

@@ -332,17 +332,17 @@ func (m *module) ListPods(ctx context.Context, orgID valuer.UUID, req *inframoni
})
g.Go(func() error {
var err error
phaseCounts, err = m.getPerGroupPodPhaseCounts(gCtx, req.Start, req.End, req.Filter, req.GroupBy, pageGroups)
phaseCounts, err = m.getPerGroupPodPhaseCounts(gCtx, orgID, req.Start, req.End, req.Filter, req.GroupBy, pageGroups)
return err
})
g.Go(func() error {
var err error
statusCounts, statusWarning, err = m.getPerGroupPodStatusCountsWithReqMetricChecks(gCtx, req.Start, req.End, req.Filter, req.GroupBy, pageGroups)
statusCounts, statusWarning, err = m.getPerGroupPodStatusCountsWithReqMetricChecks(gCtx, orgID, req.Start, req.End, req.Filter, req.GroupBy, pageGroups)
return err
})
g.Go(func() error {
var err error
restartCounts, err = m.getPerGroupPodRestartCounts(gCtx, req.Start, req.End, req.Filter, req.GroupBy, pageGroups)
restartCounts, err = m.getPerGroupPodRestartCounts(gCtx, orgID, req.Start, req.End, req.Filter, req.GroupBy, pageGroups)
return err
})
@@ -436,17 +436,17 @@ func (m *module) ListContainers(ctx context.Context, orgID valuer.UUID, req *inf
})
g.Go(func() error {
var err error
statusCounts, statusWarning, err = m.getPerGroupContainerStatusCountsWithReqMetricChecks(gCtx, req.Start, req.End, req.Filter, req.GroupBy, pageGroups)
statusCounts, statusWarning, err = m.getPerGroupContainerStatusCountsWithReqMetricChecks(gCtx, orgID, req.Start, req.End, req.Filter, req.GroupBy, pageGroups)
return err
})
g.Go(func() error {
var err error
restartCounts, err = m.getPerGroupContainerRestartCounts(gCtx, req.Start, req.End, req.Filter, req.GroupBy, pageGroups)
restartCounts, err = m.getPerGroupContainerRestartCounts(gCtx, orgID, req.Start, req.End, req.Filter, req.GroupBy, pageGroups)
return err
})
g.Go(func() error {
var err error
readyCounts, err = m.getPerGroupContainerReadyCounts(gCtx, req.Start, req.End, req.Filter, req.GroupBy, pageGroups)
readyCounts, err = m.getPerGroupContainerReadyCounts(gCtx, orgID, req.Start, req.End, req.Filter, req.GroupBy, pageGroups)
return err
})
@@ -540,17 +540,17 @@ func (m *module) ListNodes(ctx context.Context, orgID valuer.UUID, req *inframon
})
g.Go(func() error {
var err error
nodeConditionCounts, err = m.getPerGroupNodeConditionCounts(gCtx, req.Start, req.End, req.Filter, req.GroupBy, pageGroups)
nodeConditionCounts, err = m.getPerGroupNodeConditionCounts(gCtx, orgID, req.Start, req.End, req.Filter, req.GroupBy, pageGroups)
return err
})
g.Go(func() error {
var err error
podPhaseCounts, err = m.getPerGroupPodPhaseCounts(gCtx, req.Start, req.End, req.Filter, req.GroupBy, pageGroups)
podPhaseCounts, err = m.getPerGroupPodPhaseCounts(gCtx, orgID, req.Start, req.End, req.Filter, req.GroupBy, pageGroups)
return err
})
g.Go(func() error {
var err error
podStatusCounts, podStatusWarning, err = m.getPerGroupPodStatusCountsWithReqMetricChecks(gCtx, req.Start, req.End, req.Filter, req.GroupBy, pageGroups)
podStatusCounts, podStatusWarning, err = m.getPerGroupPodStatusCountsWithReqMetricChecks(gCtx, orgID, req.Start, req.End, req.Filter, req.GroupBy, pageGroups)
return err
})
@@ -644,12 +644,12 @@ func (m *module) ListNamespaces(ctx context.Context, orgID valuer.UUID, req *inf
})
g.Go(func() error {
var err error
phaseCounts, err = m.getPerGroupPodPhaseCounts(gCtx, req.Start, req.End, req.Filter, req.GroupBy, pageGroups)
phaseCounts, err = m.getPerGroupPodPhaseCounts(gCtx, orgID, req.Start, req.End, req.Filter, req.GroupBy, pageGroups)
return err
})
g.Go(func() error {
var err error
podStatusCounts, podStatusWarning, err = m.getPerGroupPodStatusCountsWithReqMetricChecks(gCtx, req.Start, req.End, req.Filter, req.GroupBy, pageGroups)
podStatusCounts, podStatusWarning, err = m.getPerGroupPodStatusCountsWithReqMetricChecks(gCtx, orgID, req.Start, req.End, req.Filter, req.GroupBy, pageGroups)
return err
})
g.Go(func() error {
@@ -750,17 +750,17 @@ func (m *module) ListClusters(ctx context.Context, orgID valuer.UUID, req *infra
})
g.Go(func() error {
var err error
nodeConditionCountsMap, err = m.getPerGroupNodeConditionCounts(gCtx, req.Start, req.End, req.Filter, req.GroupBy, pageGroups)
nodeConditionCountsMap, err = m.getPerGroupNodeConditionCounts(gCtx, orgID, req.Start, req.End, req.Filter, req.GroupBy, pageGroups)
return err
})
g.Go(func() error {
var err error
podPhaseCountsMap, err = m.getPerGroupPodPhaseCounts(gCtx, req.Start, req.End, req.Filter, req.GroupBy, pageGroups)
podPhaseCountsMap, err = m.getPerGroupPodPhaseCounts(gCtx, orgID, req.Start, req.End, req.Filter, req.GroupBy, pageGroups)
return err
})
g.Go(func() error {
var err error
podStatusCounts, podStatusWarning, err = m.getPerGroupPodStatusCountsWithReqMetricChecks(gCtx, req.Start, req.End, req.Filter, req.GroupBy, pageGroups)
podStatusCounts, podStatusWarning, err = m.getPerGroupPodStatusCountsWithReqMetricChecks(gCtx, orgID, req.Start, req.End, req.Filter, req.GroupBy, pageGroups)
return err
})
g.Go(func() error {
@@ -941,12 +941,12 @@ func (m *module) ListDeployments(ctx context.Context, orgID valuer.UUID, req *in
})
g.Go(func() error {
var err error
phaseCounts, err = m.getPerGroupPodPhaseCounts(gCtx, req.Start, req.End, req.Filter, req.GroupBy, pageGroups)
phaseCounts, err = m.getPerGroupPodPhaseCounts(gCtx, orgID, req.Start, req.End, req.Filter, req.GroupBy, pageGroups)
return err
})
g.Go(func() error {
var err error
podStatusCounts, podStatusWarning, err = m.getPerGroupPodStatusCountsWithReqMetricChecks(gCtx, req.Start, req.End, req.Filter, req.GroupBy, pageGroups)
podStatusCounts, podStatusWarning, err = m.getPerGroupPodStatusCountsWithReqMetricChecks(gCtx, orgID, req.Start, req.End, req.Filter, req.GroupBy, pageGroups)
return err
})
@@ -1046,12 +1046,12 @@ func (m *module) ListStatefulSets(ctx context.Context, orgID valuer.UUID, req *i
})
g.Go(func() error {
var err error
phaseCounts, err = m.getPerGroupPodPhaseCounts(gCtx, req.Start, req.End, req.Filter, req.GroupBy, pageGroups)
phaseCounts, err = m.getPerGroupPodPhaseCounts(gCtx, orgID, req.Start, req.End, req.Filter, req.GroupBy, pageGroups)
return err
})
g.Go(func() error {
var err error
podStatusCounts, podStatusWarning, err = m.getPerGroupPodStatusCountsWithReqMetricChecks(gCtx, req.Start, req.End, req.Filter, req.GroupBy, pageGroups)
podStatusCounts, podStatusWarning, err = m.getPerGroupPodStatusCountsWithReqMetricChecks(gCtx, orgID, req.Start, req.End, req.Filter, req.GroupBy, pageGroups)
return err
})
@@ -1151,12 +1151,12 @@ func (m *module) ListJobs(ctx context.Context, orgID valuer.UUID, req *inframoni
})
g.Go(func() error {
var err error
phaseCounts, err = m.getPerGroupPodPhaseCounts(gCtx, req.Start, req.End, req.Filter, req.GroupBy, pageGroups)
phaseCounts, err = m.getPerGroupPodPhaseCounts(gCtx, orgID, req.Start, req.End, req.Filter, req.GroupBy, pageGroups)
return err
})
g.Go(func() error {
var err error
podStatusCounts, podStatusWarning, err = m.getPerGroupPodStatusCountsWithReqMetricChecks(gCtx, req.Start, req.End, req.Filter, req.GroupBy, pageGroups)
podStatusCounts, podStatusWarning, err = m.getPerGroupPodStatusCountsWithReqMetricChecks(gCtx, orgID, req.Start, req.End, req.Filter, req.GroupBy, pageGroups)
return err
})
@@ -1256,12 +1256,12 @@ func (m *module) ListDaemonSets(ctx context.Context, orgID valuer.UUID, req *inf
})
g.Go(func() error {
var err error
phaseCounts, err = m.getPerGroupPodPhaseCounts(gCtx, req.Start, req.End, req.Filter, req.GroupBy, pageGroups)
phaseCounts, err = m.getPerGroupPodPhaseCounts(gCtx, orgID, req.Start, req.End, req.Filter, req.GroupBy, pageGroups)
return err
})
g.Go(func() error {
var err error
podStatusCounts, podStatusWarning, err = m.getPerGroupPodStatusCountsWithReqMetricChecks(gCtx, req.Start, req.End, req.Filter, req.GroupBy, pageGroups)
podStatusCounts, podStatusWarning, err = m.getPerGroupPodStatusCountsWithReqMetricChecks(gCtx, orgID, req.Start, req.End, req.Filter, req.GroupBy, pageGroups)
return err
})

View File

@@ -177,6 +177,7 @@ func (m *module) getNodesTableMetadata(ctx context.Context, orgID valuer.UUID, r
// Groups absent from the result map have implicit zero counts (caller default).
func (m *module) getPerGroupNodeConditionCounts(
ctx context.Context,
orgID valuer.UUID,
start, end int64,
filter *qbtypes.Filter,
groupBy []qbtypes.GroupByKey,
@@ -217,7 +218,7 @@ func (m *module) getPerGroupNodeConditionCounts(
timeSeriesFPs.LE("unix_milli", flooredEndMs),
)
if mergedFilterExpr != "" {
filterClause, err := m.buildFilterClause(ctx, &qbtypes.Filter{Expression: mergedFilterExpr}, start, end)
filterClause, err := m.buildFilterClause(ctx, orgID, &qbtypes.Filter{Expression: mergedFilterExpr}, start, end)
if err != nil {
return nil, err
}

View File

@@ -248,6 +248,7 @@ func (m *module) getPodsTableMetadata(ctx context.Context, orgID valuer.UUID, re
// Groups absent from the result map have implicit zero counts (caller default).
func (m *module) getPerGroupPodPhaseCounts(
ctx context.Context,
orgID valuer.UUID,
start, end int64,
filter *qbtypes.Filter,
groupBy []qbtypes.GroupByKey,
@@ -288,7 +289,7 @@ func (m *module) getPerGroupPodPhaseCounts(
timeSeriesFPs.LE("unix_milli", flooredEndMs),
)
if mergedFilterExpr != "" {
filterClause, err := m.buildFilterClause(ctx, &qbtypes.Filter{Expression: mergedFilterExpr}, start, end)
filterClause, err := m.buildFilterClause(ctx, orgID, &qbtypes.Filter{Expression: mergedFilterExpr}, start, end)
if err != nil {
return nil, err
}
@@ -397,6 +398,7 @@ func (m *module) getPerGroupPodPhaseCounts(
// runs the query. The returned counts map is empty (never nil) when gated off.
func (m *module) getPerGroupPodStatusCountsWithReqMetricChecks(
ctx context.Context,
orgID valuer.UUID,
start, end int64,
filter *qbtypes.Filter,
groupBy []qbtypes.GroupByKey,
@@ -426,7 +428,7 @@ func (m *module) getPerGroupPodStatusCountsWithReqMetricChecks(
return map[string]podStatusCounts{}, warning, nil
}
counts, err := m.getPerGroupPodStatusCounts(ctx, start, end, filter, groupBy, pageGroups)
counts, err := m.getPerGroupPodStatusCounts(ctx, orgID, start, end, filter, groupBy, pageGroups)
if err != nil {
return nil, nil, err
}
@@ -448,6 +450,7 @@ func (m *module) getPerGroupPodStatusCountsWithReqMetricChecks(
// Groups absent from the result map have implicit zero counts (caller default).
func (m *module) getPerGroupPodStatusCounts(
ctx context.Context,
orgID valuer.UUID,
start, end int64,
filter *qbtypes.Filter,
groupBy []qbtypes.GroupByKey,
@@ -476,7 +479,7 @@ func (m *module) getPerGroupPodStatusCounts(
err error
)
if mergedFilterExpr != "" {
filterClause, err = m.buildFilterClause(ctx, &qbtypes.Filter{Expression: mergedFilterExpr}, start, end)
filterClause, err = m.buildFilterClause(ctx, orgID, &qbtypes.Filter{Expression: mergedFilterExpr}, start, end)
if err != nil {
return nil, err
}
@@ -774,6 +777,7 @@ func (m *module) getPerGroupPodStatusCounts(
// Groups absent from the result map have no data (caller default).
func (m *module) getPerGroupPodRestartCounts(
ctx context.Context,
orgID valuer.UUID,
start, end int64,
filter *qbtypes.Filter,
groupBy []qbtypes.GroupByKey,
@@ -798,7 +802,7 @@ func (m *module) getPerGroupPodRestartCounts(
err error
)
if mergedFilterExpr != "" {
filterClause, err = m.buildFilterClause(ctx, &qbtypes.Filter{Expression: mergedFilterExpr}, start, end)
filterClause, err = m.buildFilterClause(ctx, orgID, &qbtypes.Filter{Expression: mergedFilterExpr}, start, end)
if err != nil {
return nil, err
}

View File

@@ -213,18 +213,18 @@ func (module *module) discoverModels(ctx context.Context, orgID valuer.UUID) ([]
Spec: qbtypes.QueryBuilderQuery[qbtypes.TraceAggregation]{
Name: "A",
Signal: telemetrytypes.SignalTraces,
Filter: &qbtypes.Filter{Expression: fmt.Sprintf("%s EXISTS", llmpricingruletypes.GenAIRequestModel)},
Filter: &qbtypes.Filter{Expression: fmt.Sprintf("%s EXISTS", telemetrytypes.GenAIRequestModel)},
Aggregations: []qbtypes.TraceAggregation{
{Expression: "count()", Alias: "spanCount"},
},
GroupBy: []qbtypes.GroupByKey{
{TelemetryFieldKey: telemetrytypes.TelemetryFieldKey{
Name: llmpricingruletypes.GenAIRequestModel,
Name: telemetrytypes.GenAIRequestModel,
FieldContext: telemetrytypes.FieldContextSpan,
FieldDataType: telemetrytypes.FieldDataTypeString,
}},
{TelemetryFieldKey: telemetrytypes.TelemetryFieldKey{
Name: llmpricingruletypes.GenAIProviderName,
Name: telemetrytypes.GenAIProviderName,
FieldContext: telemetrytypes.FieldContextSpan,
FieldDataType: telemetrytypes.FieldDataTypeString,
}},
@@ -254,9 +254,9 @@ func (module *module) discoverModels(ctx context.Context, orgID valuer.UUID) ([]
switch c.Type {
case qbtypes.ColumnTypeGroup:
switch c.Name {
case llmpricingruletypes.GenAIRequestModel:
case telemetrytypes.GenAIRequestModel:
modelIdx = i
case llmpricingruletypes.GenAIProviderName:
case telemetrytypes.GenAIProviderName:
providerIdx = i
}
case qbtypes.ColumnTypeAggregation:

View File

@@ -565,7 +565,7 @@ func (m *module) InspectMetrics(
start := uint64(req.Start)
end := uint64(req.End)
filterWhereClause, err := m.buildFilterClause(ctx, req.Filter, req.Start, req.End)
filterWhereClause, err := m.buildFilterClause(ctx, orgID, req.Filter, req.Start, req.End)
if err != nil {
return nil, err
}
@@ -950,7 +950,7 @@ func (m *module) insertMetricsMetadata(ctx context.Context, orgID valuer.UUID, r
return nil
}
func (m *module) buildFilterClause(ctx context.Context, filter *qbtypes.Filter, startMillis, endMillis int64) (*sqlbuilder.WhereClause, error) {
func (m *module) buildFilterClause(ctx context.Context, orgID valuer.UUID, filter *qbtypes.Filter, startMillis, endMillis int64) (*sqlbuilder.WhereClause, error) {
expression := ""
if filter != nil {
expression = strings.TrimSpace(filter.Expression)
@@ -969,7 +969,7 @@ func (m *module) buildFilterClause(ctx context.Context, filter *qbtypes.Filter,
// whereClauseSelectors[idx].Source = query.Source
}
keys, _, err := m.telemetryMetadataStore.GetKeysMulti(ctx, whereClauseSelectors)
keys, _, err := m.telemetryMetadataStore.GetKeysMulti(ctx, orgID, whereClauseSelectors)
if err != nil {
return nil, err
}
@@ -1010,7 +1010,7 @@ func (m *module) fetchMetricsStatsWithSamples(
var filterWhereClause *sqlbuilder.WhereClause
if hasFilter {
var err error
filterWhereClause, err = m.buildFilterClause(ctx, req.Filter, req.Start, req.End)
filterWhereClause, err = m.buildFilterClause(ctx, orgID, req.Filter, req.Start, req.End)
if err != nil {
return nil, 0, err
}
@@ -1214,7 +1214,7 @@ func (m *module) computeTimeseriesTreemap(ctx context.Context, orgID valuer.UUID
var filterWhereClause *sqlbuilder.WhereClause
if hasFilter {
var err error
filterWhereClause, err = m.buildFilterClause(ctx, req.Filter, req.Start, req.End)
filterWhereClause, err = m.buildFilterClause(ctx, orgID, req.Filter, req.Start, req.End)
if err != nil {
return nil, err
}
@@ -1332,7 +1332,7 @@ func (m *module) computeSamplesTreemap(ctx context.Context, orgID valuer.UUID, r
var filterWhereClause *sqlbuilder.WhereClause
if hasFilter {
var err error
filterWhereClause, err = m.buildFilterClause(ctx, req.Filter, req.Start, req.End)
filterWhereClause, err = m.buildFilterClause(ctx, orgID, req.Filter, req.Start, req.End)
if err != nil {
return nil, err
}

View File

@@ -9,6 +9,7 @@ import (
"github.com/SigNoz/signoz/pkg/querybuilder"
qbtypes "github.com/SigNoz/signoz/pkg/types/querybuildertypes/querybuildertypesv5"
"github.com/SigNoz/signoz/pkg/types/telemetrytypes"
"github.com/SigNoz/signoz/pkg/valuer"
"github.com/huandu/go-sqlbuilder"
)
@@ -22,6 +23,7 @@ func newConditionBuilder(fm qbtypes.FieldMapper) qbtypes.ConditionBuilder {
func (c *conditionBuilder) ConditionFor(
ctx context.Context,
orgID valuer.UUID,
startNs uint64,
endNs uint64,
key *telemetrytypes.TelemetryFieldKey,
@@ -47,7 +49,7 @@ func (c *conditionBuilder) ConditionFor(
conds := make([]string, 0, len(keys))
for _, k := range keys {
cond, err := c.conditionForKey(ctx, startNs, endNs, k, operator, value, sb)
cond, err := c.conditionForKey(ctx, orgID, startNs, endNs, k, operator, value, sb)
if err != nil {
return nil, nil, err
}
@@ -58,6 +60,7 @@ func (c *conditionBuilder) ConditionFor(
func (c *conditionBuilder) conditionForKey(
ctx context.Context,
orgID valuer.UUID,
startNs uint64,
endNs uint64,
key *telemetrytypes.TelemetryFieldKey,
@@ -69,7 +72,7 @@ func (c *conditionBuilder) conditionForKey(
value = querybuilder.FormatValueForContains(value)
}
fieldName, err := c.fm.FieldFor(ctx, startNs, endNs, key)
fieldName, err := c.fm.FieldFor(ctx, orgID, startNs, endNs, key)
if err != nil {
return "", err
}

View File

@@ -8,6 +8,7 @@ import (
schema "github.com/SigNoz/signoz-otel-collector/cmd/signozschemamigrator/schema_migrator"
qbtypes "github.com/SigNoz/signoz/pkg/types/querybuildertypes/querybuildertypesv5"
"github.com/SigNoz/signoz/pkg/types/telemetrytypes"
"github.com/SigNoz/signoz/pkg/valuer"
"github.com/huandu/go-sqlbuilder"
)
@@ -30,6 +31,12 @@ func newFieldMapper() qbtypes.FieldMapper {
return &fieldMapper{}
}
// CandidateKeys returns nil: rule-state history has no attribute-map fallback, so a
// context-missing key stays unresolved and the caller errors.
func (m *fieldMapper) CandidateKeys(_ context.Context, _ valuer.UUID, _ *telemetrytypes.TelemetryFieldKey, _ any, _ map[string][]*telemetrytypes.TelemetryFieldKey) []*telemetrytypes.TelemetryFieldKey {
return nil
}
func (m *fieldMapper) getColumn(_ context.Context, key *telemetrytypes.TelemetryFieldKey) (*schema.Column, error) { //nolint:unparam
name := strings.TrimSpace(key.Name)
if col, ok := ruleStateHistoryColumns[name]; ok {
@@ -38,7 +45,7 @@ func (m *fieldMapper) getColumn(_ context.Context, key *telemetrytypes.Telemetry
return ruleStateHistoryColumns["labels"], nil
}
func (m *fieldMapper) FieldFor(ctx context.Context, _, _ uint64, key *telemetrytypes.TelemetryFieldKey) (string, error) {
func (m *fieldMapper) FieldFor(ctx context.Context, _ valuer.UUID, _, _ uint64, key *telemetrytypes.TelemetryFieldKey) (string, error) {
col, err := m.getColumn(ctx, key)
if err != nil {
return "", err
@@ -49,7 +56,7 @@ func (m *fieldMapper) FieldFor(ctx context.Context, _, _ uint64, key *telemetryt
return col.Name, nil
}
func (m *fieldMapper) ColumnFor(ctx context.Context, _, _ uint64, key *telemetrytypes.TelemetryFieldKey) ([]*schema.Column, error) {
func (m *fieldMapper) ColumnFor(ctx context.Context, _ valuer.UUID, _, _ uint64, key *telemetrytypes.TelemetryFieldKey) ([]*schema.Column, error) {
col, err := m.getColumn(ctx, key)
if err != nil {
return nil, err
@@ -57,8 +64,8 @@ func (m *fieldMapper) ColumnFor(ctx context.Context, _, _ uint64, key *telemetry
return []*schema.Column{col}, nil
}
func (m *fieldMapper) ColumnExpressionFor(ctx context.Context, tsStart, tsEnd uint64, field *telemetrytypes.TelemetryFieldKey, _ map[string][]*telemetrytypes.TelemetryFieldKey) (string, error) {
colName, err := m.FieldFor(ctx, tsStart, tsEnd, field)
func (m *fieldMapper) ColumnExpressionFor(ctx context.Context, orgID valuer.UUID, tsStart, tsEnd uint64, field *telemetrytypes.TelemetryFieldKey, _ map[string][]*telemetrytypes.TelemetryFieldKey) (string, error) {
colName, err := m.FieldFor(ctx, orgID, tsStart, tsEnd, field)
if err != nil {
return "", err
}

View File

@@ -10,9 +10,11 @@ import (
"github.com/SigNoz/signoz/pkg/http/binding"
"github.com/SigNoz/signoz/pkg/http/render"
"github.com/SigNoz/signoz/pkg/modules/rulestatehistory"
"github.com/SigNoz/signoz/pkg/types/authtypes"
qbtypes "github.com/SigNoz/signoz/pkg/types/querybuildertypes/querybuildertypesv5"
"github.com/SigNoz/signoz/pkg/types/rulestatehistorytypes"
"github.com/SigNoz/signoz/pkg/types/telemetrytypes"
"github.com/SigNoz/signoz/pkg/valuer"
"github.com/gorilla/mux"
)
@@ -85,7 +87,13 @@ func (h *handler) GetRuleHistoryTimeline(w http.ResponseWriter, r *http.Request)
req.Query.Limit = 50
}
timelineItems, timelineTotal, err := h.module.GetHistoryTimeline(r.Context(), ruleID, req.Query)
claims, err := authtypes.ClaimsFromContext(r.Context())
if err != nil {
render.Error(w, err)
return
}
timelineItems, timelineTotal, err := h.module.GetHistoryTimeline(r.Context(), valuer.MustNewUUID(claims.OrgID), ruleID, req.Query)
if err != nil {
render.Error(w, err)
return
@@ -127,7 +135,13 @@ func (h *handler) GetRuleHistoryContributors(w http.ResponseWriter, r *http.Requ
return
}
res, err := h.module.GetHistoryContributors(r.Context(), ruleID, query)
claims, err := authtypes.ClaimsFromContext(r.Context())
if err != nil {
render.Error(w, err)
return
}
res, err := h.module.GetHistoryContributors(r.Context(), valuer.MustNewUUID(claims.OrgID), ruleID, query)
if err != nil {
render.Error(w, err)
return
@@ -152,7 +166,13 @@ func (h *handler) GetRuleHistoryFilterKeys(w http.ResponseWriter, r *http.Reques
return
}
res, err := h.module.GetHistoryFilterKeys(r.Context(), ruleID, query, search, limit)
claims, err := authtypes.ClaimsFromContext(r.Context())
if err != nil {
render.Error(w, err)
return
}
res, err := h.module.GetHistoryFilterKeys(r.Context(), valuer.MustNewUUID(claims.OrgID), ruleID, query, search, limit)
if err != nil {
render.Error(w, err)
return
@@ -167,7 +187,13 @@ func (h *handler) GetRuleHistoryFilterValues(w http.ResponseWriter, r *http.Requ
return
}
res, err := h.module.GetHistoryFilterValues(r.Context(), ruleID, key, query, search, limit)
claims, err := authtypes.ClaimsFromContext(r.Context())
if err != nil {
render.Error(w, err)
return
}
res, err := h.module.GetHistoryFilterValues(r.Context(), valuer.MustNewUUID(claims.OrgID), ruleID, key, query, search, limit)
if err != nil {
render.Error(w, err)
return

View File

@@ -9,6 +9,7 @@ import (
"github.com/SigNoz/signoz/pkg/types/rulestatehistorytypes"
"github.com/SigNoz/signoz/pkg/types/ruletypes"
"github.com/SigNoz/signoz/pkg/types/telemetrytypes"
"github.com/SigNoz/signoz/pkg/valuer"
)
type module struct {
@@ -23,20 +24,20 @@ func (m *module) GetLastSavedRuleStateHistory(ctx context.Context, ruleID string
return m.store.GetLastSavedRuleStateHistory(ctx, ruleID)
}
func (m *module) GetHistoryTimeline(ctx context.Context, ruleID string, query rulestatehistorytypes.Query) ([]rulestatehistorytypes.RuleStateHistory, uint64, error) {
return m.store.ReadRuleStateHistoryByRuleID(ctx, ruleID, &query)
func (m *module) GetHistoryTimeline(ctx context.Context, orgID valuer.UUID, ruleID string, query rulestatehistorytypes.Query) ([]rulestatehistorytypes.RuleStateHistory, uint64, error) {
return m.store.ReadRuleStateHistoryByRuleID(ctx, orgID, ruleID, &query)
}
func (m *module) GetHistoryFilterKeys(ctx context.Context, ruleID string, query rulestatehistorytypes.Query, search string, limit int64) (*telemetrytypes.GettableFieldKeys, error) {
return m.store.ReadRuleStateHistoryFilterKeysByRuleID(ctx, ruleID, &query, search, limit)
func (m *module) GetHistoryFilterKeys(ctx context.Context, orgID valuer.UUID, ruleID string, query rulestatehistorytypes.Query, search string, limit int64) (*telemetrytypes.GettableFieldKeys, error) {
return m.store.ReadRuleStateHistoryFilterKeysByRuleID(ctx, orgID, ruleID, &query, search, limit)
}
func (m *module) GetHistoryFilterValues(ctx context.Context, ruleID string, key string, query rulestatehistorytypes.Query, search string, limit int64) (*telemetrytypes.GettableFieldValues, error) {
return m.store.ReadRuleStateHistoryFilterValuesByRuleID(ctx, ruleID, key, &query, search, limit)
func (m *module) GetHistoryFilterValues(ctx context.Context, orgID valuer.UUID, ruleID string, key string, query rulestatehistorytypes.Query, search string, limit int64) (*telemetrytypes.GettableFieldValues, error) {
return m.store.ReadRuleStateHistoryFilterValuesByRuleID(ctx, orgID, ruleID, key, &query, search, limit)
}
func (m *module) GetHistoryContributors(ctx context.Context, ruleID string, query rulestatehistorytypes.Query) ([]rulestatehistorytypes.RuleStateHistoryContributor, error) {
return m.store.ReadRuleStateHistoryTopContributorsByRuleID(ctx, ruleID, &query)
func (m *module) GetHistoryContributors(ctx context.Context, orgID valuer.UUID, ruleID string, query rulestatehistorytypes.Query) ([]rulestatehistorytypes.RuleStateHistoryContributor, error) {
return m.store.ReadRuleStateHistoryTopContributorsByRuleID(ctx, orgID, ruleID, &query)
}
func (m *module) GetHistoryOverallStatus(ctx context.Context, ruleID string, query rulestatehistorytypes.Query) ([]rulestatehistorytypes.GettableRuleStateWindow, error) {

View File

@@ -13,6 +13,7 @@ import (
"github.com/SigNoz/signoz/pkg/types/rulestatehistorytypes"
"github.com/SigNoz/signoz/pkg/types/ruletypes"
"github.com/SigNoz/signoz/pkg/types/telemetrytypes"
"github.com/SigNoz/signoz/pkg/valuer"
sqlbuilder "github.com/huandu/go-sqlbuilder"
)
@@ -102,7 +103,7 @@ func (s *store) GetLastSavedRuleStateHistory(ctx context.Context, ruleID string)
return history, nil
}
func (s *store) ReadRuleStateHistoryByRuleID(ctx context.Context, ruleID string, query *rulestatehistorytypes.Query) ([]rulestatehistorytypes.RuleStateHistory, uint64, error) {
func (s *store) ReadRuleStateHistoryByRuleID(ctx context.Context, orgID valuer.UUID, ruleID string, query *rulestatehistorytypes.Query) ([]rulestatehistorytypes.RuleStateHistory, uint64, error) {
sb := sqlbuilder.NewSelectBuilder()
sb.Select(
"rule_id",
@@ -119,7 +120,7 @@ func (s *store) ReadRuleStateHistoryByRuleID(ctx context.Context, ruleID string,
sb.From(historyTable())
s.applyBaseHistoryFilters(sb, ruleID, query)
whereClause, err := s.buildFilterClause(ctx, query.FilterExpression, query.Start, query.End)
whereClause, err := s.buildFilterClause(ctx, orgID, query.FilterExpression, query.Start, query.End)
if err != nil {
return nil, 0, err
}
@@ -155,7 +156,7 @@ func (s *store) ReadRuleStateHistoryByRuleID(ctx context.Context, ruleID string,
return history, total, nil
}
func (s *store) ReadRuleStateHistoryFilterKeysByRuleID(ctx context.Context, ruleID string, query *rulestatehistorytypes.Query, search string, limit int64) (*telemetrytypes.GettableFieldKeys, error) {
func (s *store) ReadRuleStateHistoryFilterKeysByRuleID(ctx context.Context, orgID valuer.UUID, ruleID string, query *rulestatehistorytypes.Query, search string, limit int64) (*telemetrytypes.GettableFieldKeys, error) {
if limit <= 0 {
limit = 50
}
@@ -172,7 +173,7 @@ func (s *store) ReadRuleStateHistoryFilterKeysByRuleID(ctx context.Context, rule
sb.Where(fmt.Sprintf("positionCaseInsensitiveUTF8(%s, %s) > 0", keyExpr, sb.Var(search)))
}
whereClause, err := s.buildFilterClause(ctx, query.FilterExpression, query.Start, query.End)
whereClause, err := s.buildFilterClause(ctx, orgID, query.FilterExpression, query.Start, query.End)
if err != nil {
return nil, err
}
@@ -226,7 +227,7 @@ func (s *store) ReadRuleStateHistoryFilterKeysByRuleID(ctx context.Context, rule
}, nil
}
func (s *store) ReadRuleStateHistoryFilterValuesByRuleID(ctx context.Context, ruleID string, key string, query *rulestatehistorytypes.Query, search string, limit int64) (*telemetrytypes.GettableFieldValues, error) {
func (s *store) ReadRuleStateHistoryFilterValuesByRuleID(ctx context.Context, orgID valuer.UUID, ruleID string, key string, query *rulestatehistorytypes.Query, search string, limit int64) (*telemetrytypes.GettableFieldValues, error) {
if limit <= 0 {
limit = 50
}
@@ -244,7 +245,7 @@ func (s *store) ReadRuleStateHistoryFilterValuesByRuleID(ctx context.Context, ru
sb.Where(fmt.Sprintf("positionCaseInsensitiveUTF8(%s, %s) > 0", valExpr, sb.Var(search)))
}
whereClause, err := s.buildFilterClause(ctx, query.FilterExpression, query.Start, query.End)
whereClause, err := s.buildFilterClause(ctx, orgID, query.FilterExpression, query.Start, query.End)
if err != nil {
return nil, err
}
@@ -291,7 +292,7 @@ func (s *store) ReadRuleStateHistoryFilterValuesByRuleID(ctx context.Context, ru
}, nil
}
func (s *store) ReadRuleStateHistoryTopContributorsByRuleID(ctx context.Context, ruleID string, query *rulestatehistorytypes.Query) ([]rulestatehistorytypes.RuleStateHistoryContributor, error) {
func (s *store) ReadRuleStateHistoryTopContributorsByRuleID(ctx context.Context, orgID valuer.UUID, ruleID string, query *rulestatehistorytypes.Query) ([]rulestatehistorytypes.RuleStateHistoryContributor, error) {
sb := sqlbuilder.NewSelectBuilder()
sb.Select(
"fingerprint",
@@ -305,7 +306,7 @@ func (s *store) ReadRuleStateHistoryTopContributorsByRuleID(ctx context.Context,
sb.Where(sb.GE("unix_milli", query.Start))
sb.Where(sb.LT("unix_milli", query.End))
whereClause, err := s.buildFilterClause(ctx, query.FilterExpression, query.Start, query.End)
whereClause, err := s.buildFilterClause(ctx, orgID, query.FilterExpression, query.Start, query.End)
if err != nil {
return nil, err
}
@@ -472,7 +473,7 @@ func (s *store) querySeries(ctx context.Context, selectQuery string, args ...any
return series, nil
}
func (s *store) buildFilterClause(ctx context.Context, filter qbtypes.Filter, startMillis, endMillis int64) (*sqlbuilder.WhereClause, error) {
func (s *store) buildFilterClause(ctx context.Context, orgID valuer.UUID, filter qbtypes.Filter, startMillis, endMillis int64) (*sqlbuilder.WhereClause, error) {
expression := strings.TrimSpace(filter.Expression)
if expression == "" {
return nil, nil //nolint:nilnil
@@ -483,7 +484,7 @@ func (s *store) buildFilterClause(ctx context.Context, filter qbtypes.Filter, st
selectors[i].SelectorMatchType = telemetrytypes.FieldSelectorMatchTypeExact
}
fieldKeys, _, err := s.telemetryMetadataStore.GetKeysMulti(ctx, selectors)
fieldKeys, _, err := s.telemetryMetadataStore.GetKeysMulti(ctx, orgID, selectors)
if err != nil || len(fieldKeys) == 0 {
fieldKeys = map[string][]*telemetrytypes.TelemetryFieldKey{}
for _, sel := range selectors {

View File

@@ -6,6 +6,7 @@ import (
"github.com/SigNoz/signoz/pkg/types/rulestatehistorytypes"
"github.com/SigNoz/signoz/pkg/types/telemetrytypes"
"github.com/SigNoz/signoz/pkg/valuer"
)
// Module defines the core operations for managing rule state history.
@@ -23,16 +24,16 @@ type Module interface {
// GetHistoryTimeline returns a time-ordered list of rule state history entries and a total count
// for the given query, suitable for paginated timeline views.
GetHistoryTimeline(context.Context, string, rulestatehistorytypes.Query) ([]rulestatehistorytypes.RuleStateHistory, uint64, error)
GetHistoryTimeline(context.Context, valuer.UUID, string, rulestatehistorytypes.Query) ([]rulestatehistorytypes.RuleStateHistory, uint64, error)
// GetHistoryFilterKeys returns the available filter keys for rule state history queries.
GetHistoryFilterKeys(context.Context, string, rulestatehistorytypes.Query, string, int64) (*telemetrytypes.GettableFieldKeys, error)
GetHistoryFilterKeys(context.Context, valuer.UUID, string, rulestatehistorytypes.Query, string, int64) (*telemetrytypes.GettableFieldKeys, error)
// GetHistoryFilterValues returns the available values for a specific filter key in rule state history.
GetHistoryFilterValues(context.Context, string, string, rulestatehistorytypes.Query, string, int64) (*telemetrytypes.GettableFieldValues, error)
GetHistoryFilterValues(context.Context, valuer.UUID, string, string, rulestatehistorytypes.Query, string, int64) (*telemetrytypes.GettableFieldValues, error)
// GetHistoryContributors returns the top contributors to trigger alert, for the given query.
GetHistoryContributors(context.Context, string, rulestatehistorytypes.Query) ([]rulestatehistorytypes.RuleStateHistoryContributor, error)
GetHistoryContributors(context.Context, valuer.UUID, string, rulestatehistorytypes.Query) ([]rulestatehistorytypes.RuleStateHistoryContributor, error)
// GetHistoryOverallStatus returns the overall status windows for rule state history,
// providing an aggregated view of rule health over time.

View File

@@ -10,7 +10,6 @@ import (
"github.com/SigNoz/signoz/pkg/errors"
"github.com/SigNoz/signoz/pkg/factory"
"github.com/SigNoz/signoz/pkg/query-service/constants"
"github.com/SigNoz/signoz/pkg/telemetrystore"
"github.com/SigNoz/signoz/pkg/types/ctxtypes"
"github.com/SigNoz/signoz/pkg/types/instrumentationtypes"
@@ -143,10 +142,6 @@ func (client *client) queryToClickhouseQuery(_ context.Context, query *prompb.Qu
conditions = append(conditions, "temporality IN ['Cumulative', 'Unspecified']")
conditions = append(conditions, fmt.Sprintf("unix_milli >= %d AND unix_milli < %d", start, end))
normalized := !constants.IsDotMetricsEnabled
conditions = append(conditions, fmt.Sprintf("__normalized = %v", normalized))
args = append(args, metricName)
for _, m := range query.Matchers {
switch m.Type {

View File

@@ -1,89 +0,0 @@
package clickhouseprometheusv2
import (
"context"
"sync"
"github.com/SigNoz/signoz/pkg/prometheus"
"github.com/prometheus/prometheus/model/labels"
"github.com/prometheus/prometheus/storage"
"github.com/prometheus/prometheus/util/annotations"
)
// 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
}
type captureQueryable struct {
client *client
recorder *statementRecorder
}
func (c *captureQueryable) Querier(mint, maxt int64) (storage.Querier, error) {
return &captureQuerier{
querier: querier{mint: mint, maxt: maxt, client: c.client},
recorder: c.recorder,
}, nil
}
// captureQuerier builds the same SQL as the live querier but records it and
// returns no data. The fingerprint filter always takes the subquery form:
// without executing the series lookup, the inline literal set is unknown.
type captureQuerier struct {
querier
recorder *statementRecorder
}
func (c *captureQuerier) Select(ctx context.Context, _ bool, hints *storage.SelectHints, matchers ...*labels.Matcher) storage.SeriesSet {
if rawQuery, ok := rawSQLQuery(matchers); ok {
c.recorder.record(rawQuery, nil)
return storage.EmptySeriesSet()
}
start, end := c.window(hints)
samplesQuery, args, err := buildSamplesQuery(start, end, metricNamesFromMatchers(matchers), nil, matchers, c.lastSamplePerStepFor(ctx, hints))
if err != nil {
return storage.ErrSeriesSet(err)
}
c.recorder.record(samplesQuery, args)
return storage.EmptySeriesSet()
}
func (c *captureQuerier) LabelValues(context.Context, string, *storage.LabelHints, ...*labels.Matcher) ([]string, annotations.Annotations, error) {
return nil, nil, nil
}
func (c *captureQuerier) LabelNames(context.Context, *storage.LabelHints, ...*labels.Matcher) ([]string, annotations.Annotations, error) {
return nil, nil, nil
}
// metricNamesFromMatchers extracts the statically known metric name, if any.
// The live path derives names from the matched series; the capture path has
// no execution results, so only a __name__ equality contributes.
func metricNamesFromMatchers(matchers []*labels.Matcher) []string {
for _, m := range matchers {
if m.Name == metricNameLabel && m.Type == labels.MatchEqual && m.Value != "" {
return []string{m.Value}
}
}
return nil
}

View File

@@ -1,282 +0,0 @@
package clickhouseprometheusv2
import (
"context"
"database/sql"
"encoding/json"
"fmt"
"log/slog"
"math"
"slices"
"github.com/SigNoz/signoz/pkg/errors"
"github.com/SigNoz/signoz/pkg/factory"
"github.com/SigNoz/signoz/pkg/prometheus"
"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/prometheus/prometheus/model/labels"
promValue "github.com/prometheus/prometheus/model/value"
)
// seriesLookup is a series-lookup result: matched fingerprints with their
// labels, and the distinct metric names seen on them.
type seriesLookup struct {
fingerprints map[uint64]labels.Labels
metricNames []string
}
// client executes the series, samples and raw queries against ClickHouse.
type client struct {
settings factory.ScopedProviderSettings
telemetryStore telemetrystore.TelemetryStore
cfg prometheus.ClickhouseV2Config
lookbackMs int64
}
func newClient(settings factory.ScopedProviderSettings, telemetryStore telemetrystore.TelemetryStore, cfg prometheus.Config) *client {
lookback := cfg.LookbackDelta
if lookback <= 0 {
// Mirror the engine: promql defaults an unset lookback to 5m.
lookback = defaultLookbackDelta
}
return &client{
settings: settings,
telemetryStore: telemetryStore,
cfg: cfg.ClickhouseV2,
lookbackMs: lookback.Milliseconds(),
}
}
func (c *client) withContext(ctx context.Context, functionName string) context.Context {
return ctxtypes.NewContextWithCommentVals(ctx, map[string]string{
instrumentationtypes.TelemetrySignal: telemetrytypes.SignalMetrics.StringValue(),
instrumentationtypes.CodeNamespace: "clickhouse-prometheus-v2",
instrumentationtypes.CodeFunctionName: functionName,
})
}
// selectSeries runs the series lookup for the given matchers and window.
func (c *client) selectSeries(ctx context.Context, query string, args []any) (*seriesLookup, error) {
ctx = c.withContext(ctx, "selectSeries")
rows, err := c.telemetryStore.ClickhouseDB().Query(ctx, query, args...)
if err != nil {
return nil, err
}
defer rows.Close()
lookup := &seriesLookup{fingerprints: make(map[uint64]labels.Labels)}
names := make(map[string]struct{})
var fingerprint uint64
var labelsJSON string
for rows.Next() {
if err := rows.Scan(&fingerprint, &labelsJSON); err != nil {
return nil, err
}
lset, err := unmarshalLabels(labelsJSON)
if err != nil {
return nil, err
}
lookup.fingerprints[fingerprint] = lset
if name := lset.Get(metricNameLabel); name != "" {
names[name] = struct{}{}
}
if c.cfg.MaxFetchedSeries > 0 && len(lookup.fingerprints) > c.cfg.MaxFetchedSeries {
return nil, errors.NewInvalidInputf(
errors.CodeInvalidInput,
"promql selector matched more than %d series; narrow the label matchers or raise prometheus::clickhousev2::max_fetched_series",
c.cfg.MaxFetchedSeries,
)
}
}
if err := rows.Err(); err != nil {
return nil, err
}
for name := range names {
lookup.metricNames = append(lookup.metricNames, name)
}
slices.Sort(lookup.metricNames)
return lookup, nil
}
// unmarshalLabels parses the labels JSON column. Unlike v1, the fingerprint
// is not injected as a synthetic label (it would take part in `without (...)`
// grouping and vector matching) and empty-valued labels are dropped: an empty
// label value means "label absent" in Prometheus, and upstream never produces
// such labels, but stored attribute JSON can carry them.
func unmarshalLabels(s string) (labels.Labels, error) {
m := make(map[string]string)
if err := json.Unmarshal([]byte(s), &m); err != nil {
return labels.EmptyLabels(), err
}
builder := labels.NewScratchBuilder(len(m))
for k, v := range m {
if v == "" {
continue
}
builder.Add(k, v)
}
builder.Sort()
return builder.Labels(), nil
}
// selectSamples executes a samples query (raw or last-sample-per-step; both
// produce the same column shape) and assembles the per-series sample slices.
// Rows arrive ordered by (fingerprint, unix_milli). Rows whose fingerprint
// is missing from the lookup are skipped (possible in the subquery filter
// mode, where the fingerprint filter re-runs after the lookup and can see
// series born in between). Stale flags map to the engine's StaleNaN.
// Duplicate timestamps pass through as stored: upstream Prometheus cannot
// produce them (its TSDB rejects them at ingest), our ingest can under
// at-least-once retries, and v1 feeds them to the engine as-is —
// deduplicating here would make this provider silently disagree with both
// v1 and the transpiled statements over the same dirty data. Uniqueness
// belongs to the ingest layer.
func (c *client) selectSamples(ctx context.Context, query string, args []any, lookup *seriesLookup) ([]*series, error) {
ctx = c.withContext(ctx, "selectSamples")
rows, err := c.telemetryStore.ClickhouseDB().Query(ctx, query, args...)
if err != nil {
return nil, err
}
defer rows.Close()
var (
result []*series
current *series
fingerprint uint64
prevFp uint64
timestampMs int64
val float64
flags uint32
first = true
haveCurrent bool
staleMarker = math.Float64frombits(promValue.StaleNaN)
maxSamples = c.cfg.MaxFetchedSamples
fetched int64
unknownCount int
)
for rows.Next() {
if err := rows.Scan(&fingerprint, &timestampMs, &val, &flags); err != nil {
return nil, err
}
fetched++
if maxSamples > 0 && fetched > maxSamples {
return nil, errors.NewInvalidInputf(
errors.CodeInvalidInput,
"promql query would fetch more than %d samples; narrow the selector or time range, or raise prometheus::clickhousev2::max_fetched_samples",
maxSamples,
)
}
if first || fingerprint != prevFp {
first = false
prevFp = fingerprint
lset, ok := lookup.fingerprints[fingerprint]
if !ok {
unknownCount++
haveCurrent = false
continue
}
current = &series{lset: lset}
result = append(result, current)
haveCurrent = true
}
if !haveCurrent {
// Remaining rows of a fingerprint missing from the lookup.
continue
}
if flags&1 == 1 {
val = staleMarker
}
current.ts = append(current.ts, timestampMs)
current.vs = append(current.vs, val)
}
if err := rows.Err(); err != nil {
return nil, err
}
if unknownCount > 0 {
c.settings.Logger().DebugContext(ctx, "skipped samples of fingerprints missing from series lookup",
slog.Int("unknown_fingerprints", unknownCount))
}
return result, nil
}
// queryRaw supports the {job="rawsql", query="..."} escape hatch: the value of
// the query matcher runs as-is, each row becoming a single-sample series
// stamped at the query end. Column "value" is the sample value; every other
// column is a label.
func (c *client) queryRaw(ctx context.Context, query string, ts int64) ([]*series, error) {
ctx = c.withContext(ctx, "queryRaw")
rows, err := c.telemetryStore.ClickhouseDB().Query(ctx, query)
if err != nil {
return nil, err
}
defer rows.Close()
columns := rows.Columns()
targets := make([]any, len(columns))
for i := range targets {
targets[i] = new(scanner)
}
var result []*series
for rows.Next() {
if err := rows.Scan(targets...); err != nil {
return nil, err
}
builder := labels.NewScratchBuilder(len(columns))
var val float64
for i, col := range columns {
v := targets[i].(*scanner)
if col == "value" {
val = v.f
continue
}
builder.Add(col, v.s)
}
builder.Sort()
result = append(result, &series{
lset: builder.Labels(),
ts: []int64{ts},
vs: []float64{val},
})
}
if err := rows.Err(); err != nil {
return nil, err
}
return result, nil
}
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

@@ -1,334 +0,0 @@
// Package clickhouseprometheusv2 is the second-generation ClickHouse-backed
// Prometheus provider. It exists because the v1 provider fetches every raw
// sample of a query's union window through the remote-read protobuf layer
// and hands it to the engine — the cost is a function of ingested data, not
// of the question asked, which is how a dashboard of PromQL panels takes an
// instance down.
//
// Every query runs in one of two ways, decided per query:
//
// - Transpiled: the query is evaluated entirely inside ClickHouse and only
// final (or near-final) per-group grid arrays come back, built on the
// timeSeries*ToGrid aggregate functions (the supported ClickHouse floor
// is >= 25.6, so they are assumed available).
// - Engine: the stock promql engine evaluates over this package's native
// storage.Querier. This is the path for everything not transpilable.
//
// Correctness is the constraint that shaped both paths: a PromQL result that
// differs from upstream Prometheus is a lost user, so anything that cannot
// reproduce engine semantics exactly falls back rather than approximate.
// The rest of this comment is the PromQL -> SQL story, because that mapping
// is where correctness is won or lost.
//
// # The evaluation model the SQL must reproduce
//
// A PromQL range query is an instant query evaluated at every grid point
// t_i = start + i*step, i = 0..(end-start)/step. At each t_i:
//
// - an instant selector resolves to the latest sample in the left-open
// lookback window (t_i - lookback, t_i], and to nothing when that latest
// sample is a stale marker — even if older real samples sit inside the
// window;
// - a range selector [r] collects every sample in (t_i - r, t_i], stale
// markers excluded;
// - offset d shifts both windows to (t_i - d - w, t_i - d].
//
// The transpilation invariant follows from this: every transpiled construct
// produces, per output series, one array with exactly one slot per grid
// point — slot i holds the value at t_i, NULL means absent. This is what
// makes composition correct, not just convenient: the engine evaluates
// these operators independently per t_i, so any representation that gets
// every slot right gets the whole query right, and spatial aggregation over
// arrays is sound because it combines values that belong to the same t_i by
// construction. Slot index i maps back to t_i = start + i*step at scan time
// (toMatrix). Everything below is about filling those slots with exactly
// the numbers the engine would compute — and each equivalence was validated
// against the vendored engine on live data before its shape entered the
// allowlist; anything unproven stays on the engine path.
//
// # Classification: finding what a statement can answer
//
// classify walks the parsed AST looking for "core units" — maximal subtrees
// of the shape
//
// [agg by/without (...)] [fn(] selector[range] [offset d] [)] [op scalar]...
//
// classifyCore peels that chain from the outside in: an optional
// sum/min/max/avg/count aggregation, then one of the allowlisted functions
// or a bare instant selector, then the selector with its offset; on the way
// out it accumulates number-literal arithmetic, comparisons (including
// bool) and unary minus into a scalar-op pipeline. A node qualifies only if
// its type, arguments and children are in the proven set — an allowlist, so
// an overlooked construct becomes a fallback instead of a wrong number.
//
// Three unit kinds come out of this, each with its own SQL form:
// unitRange (rate, irate, increase, delta, idelta over a range selector),
// unitInstant (instant vector selection, bare or comparison-filtered) and
// unitOverTime (avg/min/max/sum/count/last _over_time).
//
// If the entire tree is one unit, the plan is "full": the statement's rows
// are the query result. Otherwise every maximal unit is cut out and replaced
// in the expression with a synthetic selector __signoz_transpiled_N__, and
// the rewritten expression runs in the engine over the units' materialized
// results ("hybrid") — histogram_quantile, topk, or/and/unless and vector
// matching keep exact engine semantics while their expensive inputs were
// aggregated server-side.
//
// Classification refuses when exact semantics cannot be guaranteed
// server-side: the @ modifier anywhere and default-resolution subqueries
// (their resolution is a server runtime setting the transpiler cannot see);
// steps or ranges that are not whole seconds (the grid functions take
// whole-second parameters); grouping by or matching on __name__ in hybrid
// plans (the synthetic name would leak into results); name-keeping units —
// bare/comparison instant selectors and last_over_time keep their real
// __name__ (keepsName), which substitution would replace, so they transpile
// only as full plans; and every function outside the allowlist (changes,
// resets, quantile_over_time, absent, native-histogram functions, ...).
//
// Units inside a fixed-resolution subquery evaluate on the subquery's own
// grid instead of the query grid: epoch-aligned multiples of the resolution
// strictly after outerStart - offset - range, ending at outer end - offset —
// the exact derivation the engine uses, because a grid shifted by one step
// changes which samples every window sees.
//
// # From one unit to one statement
//
// buildUnitSQL renders each unit as a single statement. For
// sum by (pod) (rate(m{job="api"}[5m])) the skeleton is:
//
// SELECT gkey, sumForEach(grid) AS grid FROM (
// SELECT series.gkey AS gkey,
// timeSeriesRateToGrid(<start>, <end>, <step>, <range>)(fromUnixTimestamp64Milli(unix_milli), value) AS grid
// FROM signoz_metrics.distributed_samples_v4 AS points
// INNER JOIN (
// SELECT fingerprint, <group key expr> AS gkey
// FROM signoz_metrics.time_series_v4
// WHERE <series predicates>
// GROUP BY fingerprint, gkey
// ) AS series ON points.fingerprint = series.fingerprint
// WHERE metric_name = ? AND temporality IN ['Cumulative', 'Unspecified']
// AND points.fingerprint IN (<matched fingerprints>)
// AND unix_milli > <start - range> AND unix_milli <= <end>
// AND bitAnd(flags, 1) = 0
// GROUP BY points.fingerprint, series.gkey
// ) GROUP BY gkey
// SETTINGS allow_experimental_ts_to_grid_aggregate_function = 1
//
// Reading it inside out:
//
// The time window is the selector's semantics verbatim: strict > on the
// lower bound and <= on the upper is the left-open (t - w, t] rule, with the
// whole window shifted by the offset. bitAnd(flags, 1) = 0 drops stale
// markers, which PromQL excludes from range vectors.
//
// The inner GROUP BY computes one grid array per series.
// timeSeriesRateToGrid(start, end, step, range) is a parametric aggregate:
// fed (timestamp, value) pairs it produces Array(Nullable(Float64)) with one
// slot per grid point. Correct because it implements the engine's
// extrapolatedRate decision for decision — counter resets, the zero-point
// clamp, the extrapolation thresholds, the >= 2 samples rule, the left-open
// window — verified by feeding identical samples to both and comparing
// slot for slot: the only difference ever observed is the last bit
// (ClickHouse's C++ and Go round the same formula differently), which is
// the floating-point floor, not a semantic gap. irate/delta/idelta map to
// their own timeSeries*ToGrid functions with the same verification;
// increase has no function of its own and is emitted as
// arrayMap(x -> x * <range seconds>, <rate expr>), exact by definition —
// extrapolatedRate computes the same extrapolated delta for both and
// divides by the range only when isRate, so multiplying it back is the
// identity, not an approximation. The grid parameters are rendered as
// literals, not bound args — they are aggregate-function parameters — and
// the experimental gate rides as a SETTINGS clause on the statement itself
// so telemetrystore hooks cannot clobber it.
//
// The join annotates each series with its group key: toJSONString of the
// sorted [label, value] pairs the unit projects, extracted from the stored
// labels JSON. by keeps the listed labels, without excludes them plus
// __name__, no aggregation keeps everything minus __name__ unless the unit
// keeps its name — the engine's name-dropping rules. Correct as a grouping
// key because the pairs are sorted and empty values are filtered: key
// equality is then exactly label-set equality on the projection —
// Prometheus treats an empty label value as the label being absent, and
// stored attribute JSON can carry empties that must not split groups — and
// the same canonical string parses back into the output label set
// (labelsFromGroupKey).
//
// The outer GROUP BY is the spatial aggregation: sum/min/max/avg/count
// by/without become the -ForEach combinators. Element-wise aggregation over
// grid arrays is the engine's per-t_i aggregation, because slot i of every
// input array refers to the same t_i; the combinators skip NULLs, which is
// the engine aggregating only the series present at t_i, and an index where
// every series is absent stays NULL. Two edges need explicit handling:
// countForEach wraps in a mapping of 0 back to NULL, because a count over
// an all-absent index is an absent point, not 0; and a unit without
// aggregation still passes through maxForEach — the identity for the common
// one-fingerprint group, and a deterministic NULL-skipping merge when a
// regex __name__ selector collapses distinct metrics onto one projected
// label set. One caveat is inherent: summation order over series differs
// from the engine's, so spatial aggregates can differ in the last ULP —
// float addition is not associative; no ordering reproduces the engine's
// bit-exactly from inside a GROUP BY.
//
// # Instant selectors: staleness needs two aggregates
//
// unitInstant uses window = lookback and must reproduce the shadowing rule:
// the point is absent when the latest in-window sample is a stale marker.
// timeSeriesLastToGrid alone cannot express that — skipping stale rows in
// WHERE would resurrect the older real sample the marker was written to
// bury. So stale rows stay in the scan for this kind only, and the grid
// expression compares three aggregates per slot:
//
// arrayMap((tall, tok, vok) -> if(tall IS NULL OR tok IS NULL OR tall != tok, NULL, vok),
// timeSeriesLastToGrid(...)(ts, toFloat64(unix_milli)), -- last sample overall
// timeSeriesLastToGridIf(...)(ts, toFloat64(unix_milli), bitAnd(flags, 1) = 0), -- last non-stale, its timestamp
// timeSeriesLastToGridIf(...)(ts, value, bitAnd(flags, 1) = 0)) -- last non-stale, its value
//
// Correct by cases on a slot's window. No samples at all: both timestamp
// aggregates are NULL, the slot is NULL — absent, as the engine says. Latest
// sample non-stale: it is the latest overall and the latest non-stale, the
// timestamps agree, the slot takes its value — the engine's pick. Latest
// sample stale: the last-overall timestamp is the marker's, the
// last-non-stale timestamp is older (or NULL when only markers are in
// window), they disagree, the slot is NULL — the marker shadows, exactly
// the engine's rule. Timestamps are unique per series (ingest dedups), so
// timestamp equality identifies "the same sample" without ambiguity. The
// -If combinator's applicability to these experimental aggregates was
// probed before being trusted, not assumed.
//
// # Windowed *_over_time: fan-out instead of a grid function
//
// avg/min/max/sum/count _over_time aggregate every raw sample in the window,
// and no timeSeries*ToGrid function computes them. (last_over_time is the
// exception: the last sample of a range vector — stale markers excluded from
// range vectors by PromQL, excluded here in WHERE — is exactly
// timeSeriesLastToGrid.) Instead, each sample is fanned out to every grid
// index whose window contains it:
//
// ARRAY JOIN range(toUInt64(greatest(0, intDiv(unix_milli - <start> + <step> - 1, <step>))),
// toUInt64(least(<lastIdx>, intDiv(unix_milli + <range> - 1 - <start>, <step>)) + 1)) AS k
//
// Correct because the bounds solve the window condition for k. A sample at
// ts contributes to slot k iff t_k - range < ts <= t_k. The right side
// gives t_k >= ts, so the first index is ceil((ts - start)/step) — a sample
// at exactly t_k belongs to k, the window is right-closed. The left side
// gives t_k < ts + range, and with millisecond-integer timestamps that is
// t_k <= ts + range - 1, so the last index is
// floor((ts + range - 1 - start)/step) — a sample at exactly t_k - range is
// excluded, the window is left-open. Clamped to the grid, the fan-out
// therefore lands each sample in exactly the slots whose windows contain
// it, and GROUP BY (fingerprint, k) with the plain aggregate (avg(value),
// min(value), ...) computes per slot over precisely the engine's sample
// multiset — the same numbers, since avg/min/max/sum/count are
// order-insensitive on a given multiset (sum/avg up to summation order, the
// float caveat above). A second level assembles the positional array with
// groupArray + indexOf, mapping missing indices to NULL — groupArrayInsertAt
// would coerce NULL defaults to 0, which is a value, not absence. The
// group-key join happens at the initiator here, over rows already reduced
// to per-(series, index); see the sharding section for why that costs
// nothing.
//
// # Scalar ops, full plans, hybrid plans
//
// The scalar-op pipeline applies in Go to the returned arrays
// (applyScalarOps), slot by slot: arithmetic operators compute, comparisons
// filter (the slot keeps the vector-side value or becomes NULL) or return
// 0/1 under bool. Correct trivially: it is the same float64 operation the
// engine would apply to the same slot value, in the same operator order the
// AST dictates — running it in Go instead of another SQL layer changes
// where, not what.
//
// A full plan's arrays map straight to the result matrix. A hybrid plan
// materializes each unit's arrays as synthetic series under its
// __signoz_transpiled_N__ name and evaluates the rewritten expression over
// a storage that serves synthetic names from memory and everything else
// live. Substitution is sound because a unit's output is a plain instant
// vector to the engine — same values at same timestamps under a different
// name, and the name cannot matter: plans that group by or match on
// __name__ were refused at classification, and name-keeping units are never
// substituted. One subtlety makes it exact: stale markers are written at
// absent grid points, because the engine's lookback would otherwise
// resurrect a point from up to lookback earlier — the marker encodes
// "absent here" the way the engine itself encodes it. Units evaluate
// concurrently; each is one series lookup plus one grid statement. A step
// of 0 is an instant query: a single evaluation at end.
//
// # Series lookup
//
// Both paths resolve matchers the same way, once per selector
// (selectSeries): __name__ matchers translate to the metric_name column —
// all four matcher types; the v1 client silently returned nothing for regex
// metric names — and every other matcher to a JSONExtractString condition on
// the labels column (applySeriesConditions). Regexes are anchored before
// they reach match(): PromQL matchers match the whole value, ClickHouse
// match() searches for a substring, and without anchoring =~"api" would
// also select "x-api-y". An equality matcher against "" matches series
// without the label, mirroring PromQL, because JSONExtractString returns ""
// for missing keys. The series tables hold one row per (fingerprint, bucket)
// at 1h/6h/1d/1w granularities; timeSeriesTableFor picks the table whose
// bucket fits the window and rounds the window start down to the bucket
// boundary. The resulting label sets drop what v1 leaked into results: the
// synthetic fingerprint label (it would take part in without() grouping and
// vector matching) and empty-valued labels. MaxFetchedSeries fails the
// lookup with a typed invalid-input error past the ceiling — v1's behavior
// for an oversized selector was to buffer everything and OOM, and a 4xx the
// user can narrow beats a dead process serving nobody.
//
// # The engine path
//
// Queries that do not transpile run in the stock engine over this package's
// storage.Querier, which is still not the v1 path. Samples are fetched per
// selector using the engine's per-selector hints, not the query-wide union
// window, so foo / foo offset 1d reads two narrow windows instead of the
// widest one twice. Instant selectors of subquery-free queries fetch only
// the last sample per step bucket (lastSamplePerStep): buckets anchor at the
// selector's first evaluation timestamp — recovered from the hints as
// hints.Start + lookback - 1ms, the inverse of how the engine derives
// hints.Start — so bucket boundaries coincide with evaluation timestamps and
// a non-final sample of a bucket can never be the latest sample in
// (t - lookback, t] for any grid t. Real timestamps are preserved, so the
// engine's own lookback and staleness handling stay exact. Range selectors
// always fetch raw — every sample feeds the range function — and the
// subquery-free proof travels in the context as prometheus.QueryTraits,
// because subquery selectors evaluate at the subquery's step while the
// hints carry the top-level step. Row assembly counts rows against
// MaxFetchedSamples while scanning, keeps the first of consecutive equal
// timestamps, maps stale flags to the engine's StaleNaN, and merges series
// with identical label sets (sortAndMerge) — the engine assumes storages
// never emit duplicates. A {job="rawsql", query="..."} selector bypasses all
// of this and runs the query matcher's value verbatim.
//
// # Sharding
//
// samples_v4 and time_series_v4 (and all their rollups) shard on the same
// key — cityHash64(env, temporality, metric_name, fingerprint) — so a
// series' samples and catalog rows live on the same shard. The transpiled
// statement above exploits that: the distributed samples table at the
// top-level FROM makes ClickHouse rewrite the whole inner query per shard,
// where the join against the shard-local series table and the per-series
// grid aggregation run next to the data; the initiator only merges
// aggregate states and applies the spatial -ForEach step. Same layout as
// the telemetrymetrics statement builder. Fingerprint filters follow suit:
// matched sets inline as sorted literals up to inlineFingerprintsLimit
// (literals engage the samples primary key; sorting keeps statements
// deterministic), beyond it the group-key join alone restricts — a
// semi-join on the same predicates would only rescan the series table —
// except the windowed *_over_time fan-out, which has no join and keeps a
// shard-local IN subquery rather than expand every series of the metric.
// The engine path's over-limit filter is the same shard-local subquery, 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 — that engages the leading samples
// primary-key column. Delta-temporality series stay invisible to PromQL
// here exactly as they are in v1: the rollout gate is parity with v1, and
// making 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
//
// Every statement carries a log_comment with
// code.namespace=clickhouse-prometheus-v2 and code.function.name naming the
// call site (selectSeries, selectSamples, transpiledUnit, LabelValues,
// LabelNames), so this provider's work is attributable in system.query_log
// without guessing from query text.
package clickhouseprometheusv2

View File

@@ -1,191 +0,0 @@
package clickhouseprometheusv2
import (
"fmt"
"math/rand"
"sort"
"testing"
"github.com/stretchr/testify/require"
)
// The lastSamplePerStep correctness argument, executed: for instant selectors, keeping
// only the last sample of every step bucket (bucket 0 = (start, firstEval],
// bucket i = (firstEval+(i-1)·step, firstEval+i·step]) yields exactly the
// same instant-vector selections as the raw samples, for every evaluation
// timestamp on the grid. The engine picks the latest sample in
// (t-lookback, t] per evaluation timestamp t and treats a stale marker as
// absent; both behaviors are emulated here directly.
type tsample struct {
ts int64
value float64
stale bool
}
// engineSelect emulates the engine's instant-selector resolution at
// evaluation timestamp t over samples ordered by timestamp: the latest sample
// in (t-lookback, t], absent when none or when it is a stale marker.
func engineSelect(samples []tsample, t, lookbackMs int64) (tsample, bool) {
var picked tsample
found := false
for _, s := range samples {
if s.ts > t-lookbackMs && s.ts <= t {
picked = s
found = true
}
}
if !found || picked.stale {
return tsample{}, false
}
return picked, true
}
// lastPerStep emulates the last-sample-per-step samples query: group samples into buckets and
// keep only the last sample of each (ties keep either; ClickHouse argMax over
// equal keys is unspecified, so generated timestamps are unique).
func lastPerStep(samples []tsample, firstEvalMs, stepMs int64) []tsample {
last := make(map[int64]tsample)
for _, s := range samples {
var bucket int64
if stepMs > 0 && s.ts > firstEvalMs {
bucket = (s.ts-firstEvalMs-1)/stepMs + 1
}
if cur, ok := last[bucket]; !ok || s.ts > cur.ts {
last[bucket] = s
}
}
out := make([]tsample, 0, len(last))
for _, s := range last {
out = append(out, s)
}
sort.Slice(out, func(i, j int) bool { return out[i].ts < out[j].ts })
return out
}
func TestLastSamplePerStepEquivalence(t *testing.T) {
rng := rand.New(rand.NewSource(42))
for caseIdx := 0; caseIdx < 2000; caseIdx++ {
// Random query shape. Units are milliseconds but kept small so bucket
// boundaries are hit often.
stepMs := []int64{1, 2, 5, 7, 30, 60}[rng.Intn(6)]
lookbackMs := []int64{1, 3, 5, 10, 45}[rng.Intn(5)]
queryStart := int64(1000)
numSteps := rng.Int63n(20)
queryEnd := queryStart + numSteps*stepMs + rng.Int63n(stepMs) // grid may not divide the range
// Engine-derived selector window for instant selectors:
// hints.Start = firstEval - (lookback - 1), hints.End = queryEnd.
hintsStart := queryStart - (lookbackMs - 1)
hintsEnd := queryEnd
firstEval := hintsStart + lookbackMs - 1
require.Equal(t, queryStart, firstEval)
// Random samples inside the fetch window [hints.Start, hints.End],
// with unique timestamps and occasional stale markers. The sample
// count is capped by the window size: timestamps are unique.
windowSize := hintsEnd - hintsStart + 1
numSamples := rng.Int63n(40)
if numSamples > windowSize {
numSamples = windowSize
}
seen := make(map[int64]bool)
var samples []tsample
for int64(len(samples)) < numSamples {
ts := hintsStart + rng.Int63n(windowSize)
if seen[ts] {
continue
}
seen[ts] = true
samples = append(samples, tsample{ts: ts, value: rng.Float64(), stale: rng.Intn(8) == 0})
}
sort.Slice(samples, func(i, j int) bool { return samples[i].ts < samples[j].ts })
reduced := lastPerStep(samples, firstEval, stepMs)
desc := fmt.Sprintf("case=%d step=%d lookback=%d start=%d end=%d samples=%d",
caseIdx, stepMs, lookbackMs, queryStart, queryEnd, len(samples))
for evalTs := queryStart; evalTs <= queryEnd; evalTs += stepMs {
rawPick, rawOK := engineSelect(samples, evalTs, lookbackMs)
reducedPick, reducedOK := engineSelect(reduced, evalTs, lookbackMs)
require.Equal(t, rawOK, reducedOK, "%s eval=%d presence mismatch", desc, evalTs)
if rawOK {
require.Equal(t, rawPick, reducedPick, "%s eval=%d sample mismatch", desc, evalTs)
}
}
}
}
// Instant queries (step 0) evaluate once at firstEval == hints.End; lastSamplePerStep
// collapses to a single bucket over the whole window.
func TestLastSamplePerStepEquivalenceInstantQuery(t *testing.T) {
rng := rand.New(rand.NewSource(7))
for caseIdx := 0; caseIdx < 500; caseIdx++ {
lookbackMs := []int64{1, 3, 5, 10, 45}[rng.Intn(5)]
evalTs := int64(1000)
hintsStart := evalTs - (lookbackMs - 1)
hintsEnd := evalTs
firstEval := hintsStart + lookbackMs - 1
require.Equal(t, evalTs, firstEval)
windowSize := hintsEnd - hintsStart + 1
numSamples := rng.Int63n(10)
if numSamples > windowSize {
numSamples = windowSize
}
seen := make(map[int64]bool)
var samples []tsample
for int64(len(samples)) < numSamples {
ts := hintsStart + rng.Int63n(windowSize)
if seen[ts] {
continue
}
seen[ts] = true
samples = append(samples, tsample{ts: ts, value: rng.Float64(), stale: rng.Intn(4) == 0})
}
sort.Slice(samples, func(i, j int) bool { return samples[i].ts < samples[j].ts })
reduced := lastPerStep(samples, firstEval, 0)
require.LessOrEqual(t, len(reduced), 1, "instant reduction must keep at most one sample")
rawPick, rawOK := engineSelect(samples, evalTs, lookbackMs)
reducedPick, reducedOK := engineSelect(reduced, evalTs, lookbackMs)
require.Equal(t, rawOK, reducedOK, "case=%d presence mismatch", caseIdx)
if rawOK {
require.Equal(t, rawPick, reducedPick, "case=%d sample mismatch", caseIdx)
}
}
}
// A stale marker that is the latest sample of its bucket must shadow older
// samples: the engine sees the marker and reports the series absent, exactly
// as with raw samples. Pre-filtering stale rows would instead resurrect the
// older sample.
func TestLastSamplePerStepKeepsStaleShadowing(t *testing.T) {
lookbackMs := int64(10)
stepMs := int64(5)
queryStart := int64(1000)
samples := []tsample{
{ts: 998, value: 1.0}, // bucket 0
{ts: 999, stale: true}, // bucket 0: marker shadows 998
{ts: 1003, value: 2.0}, // bucket 1
{ts: 1004, stale: true}, // bucket 1: marker shadows 1003
{ts: 1008, value: 3.0, stale: false}, // bucket 2
}
firstEval := queryStart
reduced := lastPerStep(samples, firstEval, stepMs)
for evalTs := queryStart; evalTs <= queryStart+2*stepMs; evalTs += stepMs {
rawPick, rawOK := engineSelect(samples, evalTs, lookbackMs)
reducedPick, reducedOK := engineSelect(reduced, evalTs, lookbackMs)
require.Equal(t, rawOK, reducedOK, "eval=%d", evalTs)
if rawOK {
require.Equal(t, rawPick, reducedPick, "eval=%d", evalTs)
}
}
}

View File

@@ -1,84 +0,0 @@
package clickhouseprometheusv2
import (
"context"
"time"
"github.com/SigNoz/signoz/pkg/factory"
"github.com/SigNoz/signoz/pkg/prometheus"
"github.com/SigNoz/signoz/pkg/telemetrystore"
"github.com/prometheus/prometheus/promql"
"github.com/prometheus/prometheus/storage"
)
// Provider ties the package together: its own engine and parser, the
// ClickHouse client behind the native storage.Querier, and the transpiler
// executor. See the package documentation for what runs where and why. It is
// exported as a concrete type — pkg/querier holds it directly for shadow
// comparison and pinned serving, and an interface with a single
// implementation would only hide that dependency.
type Provider struct {
settings factory.ScopedProviderSettings
engine *prometheus.Engine
parser prometheus.Parser
client *client
executor *executor
}
var (
_ prometheus.Prometheus = (*Provider)(nil)
_ prometheus.StatementCapturer = (*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) {
return New(ctx, providerSettings, config, telemetryStore)
})
}
func New(_ context.Context, providerSettings factory.ProviderSettings, config prometheus.Config, telemetryStore telemetrystore.TelemetryStore) (*Provider, error) {
settings := factory.NewScopedProviderSettings(providerSettings, "github.com/SigNoz/signoz/pkg/prometheus/clickhouseprometheusv2")
engine := prometheus.NewEngine(settings.Logger(), config)
parser := prometheus.NewParser()
client := newClient(settings, telemetryStore, config)
return &Provider{
settings: settings,
engine: engine,
parser: parser,
client: client,
executor: &executor{client: client, engine: engine, parser: parser},
}, nil
}
// TryExecuteRange evaluates transpilable query shapes directly in ClickHouse
// (see transpiler.go). ok=false means the shape is not transpilable and the
// caller should evaluate through Engine over Storage instead.
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) Engine() *prometheus.Engine {
return p.engine
}
func (p *Provider) Parser() prometheus.Parser {
return p.parser
}
func (p *Provider) Storage() storage.Queryable {
return p
}
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

@@ -1,233 +0,0 @@
package clickhouseprometheusv2
import (
"context"
"fmt"
"slices"
"sort"
"time"
"github.com/SigNoz/signoz/pkg/prometheus"
"github.com/huandu/go-sqlbuilder"
"github.com/prometheus/prometheus/model/labels"
"github.com/prometheus/prometheus/storage"
"github.com/prometheus/prometheus/util/annotations"
)
// defaultLookbackDelta mirrors promql's default when the config leaves the
// lookback unset; the engine and the storage must agree on it for
// last-sample-per-step bucket anchoring.
const defaultLookbackDelta = 5 * time.Minute
// querier is a native storage.Querier over ClickHouse. Unlike v1 it does not
// round-trip through the remote-read protobuf machinery: Select builds SQL
// directly from the matchers and hints, and the result set is assembled once
// into compact series.
type querier struct {
mint, maxt int64
client *client
}
var _ storage.Querier = (*querier)(nil)
func (q *querier) Select(ctx context.Context, sortSeries bool, hints *storage.SelectHints, matchers ...*labels.Matcher) storage.SeriesSet {
if rawQuery, ok := rawSQLQuery(matchers); ok {
_, end := q.window(hints)
list, err := q.client.queryRaw(ctx, rawQuery, end)
if err != nil {
return storage.ErrSeriesSet(err)
}
if sortSeries {
sort.Slice(list, func(i, j int) bool { return labels.Compare(list[i].lset, list[j].lset) < 0 })
}
return newSeriesSet(list)
}
start, end := q.window(hints)
seriesQuery, seriesArgs, err := buildSeriesQuery(start, end, matchers)
if err != nil {
return storage.ErrSeriesSet(err)
}
lookup, err := q.client.selectSeries(ctx, seriesQuery, seriesArgs)
if err != nil {
return storage.ErrSeriesSet(err)
}
if len(lookup.fingerprints) == 0 {
return storage.EmptySeriesSet()
}
list, err := q.fetchSamples(ctx, start, end, matchers, lookup, q.lastSamplePerStepFor(ctx, hints))
if err != nil {
return storage.ErrSeriesSet(err)
}
// Sorting doubles as duplicate-label-set detection, which the engine
// depends on storages never emitting; the cost is on series count, not
// samples.
list = sortAndMerge(list)
return newSeriesSet(list)
}
// LabelValues returns the values of a label across series matching the
// matchers within the querier window.
func (q *querier) LabelValues(ctx context.Context, name string, hints *storage.LabelHints, matchers ...*labels.Matcher) ([]string, annotations.Annotations, error) {
sb := sqlbuilder.NewSelectBuilder()
if name == metricNameLabel {
sb.Select("DISTINCT metric_name AS value")
} else {
sb.Select(fmt.Sprintf("DISTINCT JSONExtractString(labels, %s) AS value", sb.Var(name)))
}
adjustedStart, table := timeSeriesTableFor(q.mint, q.maxt)
sb.From(fmt.Sprintf("%s.%s", databaseName, table))
if err := applySeriesConditions(sb, adjustedStart, q.maxt, matchers); err != nil {
return nil, nil, err
}
sb.Where("value != ''")
if hints != nil && hints.Limit > 0 {
sb.Limit(hints.Limit)
}
query, args := sb.BuildWithFlavor(sqlbuilder.ClickHouse)
values, err := q.selectStrings(ctx, "LabelValues", query, args)
if err != nil {
return nil, nil, err
}
slices.Sort(values)
return values, nil, nil
}
// LabelNames returns the label names present on series matching the matchers
// within the querier window.
func (q *querier) LabelNames(ctx context.Context, hints *storage.LabelHints, matchers ...*labels.Matcher) ([]string, annotations.Annotations, error) {
sb := sqlbuilder.NewSelectBuilder()
sb.Select("DISTINCT arrayJoin(JSONExtractKeys(labels)) AS name")
adjustedStart, table := timeSeriesTableFor(q.mint, q.maxt)
sb.From(fmt.Sprintf("%s.%s", databaseName, table))
if err := applySeriesConditions(sb, adjustedStart, q.maxt, matchers); err != nil {
return nil, nil, err
}
if hints != nil && hints.Limit > 0 {
sb.Limit(hints.Limit)
}
query, args := sb.BuildWithFlavor(sqlbuilder.ClickHouse)
names, err := q.selectStrings(ctx, "LabelNames", query, args)
if err != nil {
return nil, nil, err
}
slices.Sort(names)
return names, nil, nil
}
func (q *querier) Close() error {
return nil
}
// window returns the per-selector fetch window. The engine sends per-selector
// bounds in the hints (already adjusted for offset, @, range and lookback);
// they are always at least as tight as the querier-level mint/maxt, which
// span the union of all selectors in the query.
func (q *querier) window(hints *storage.SelectHints) (int64, int64) {
if hints != nil && hints.Start != 0 && hints.End != 0 && hints.Start <= hints.End {
return hints.Start, hints.End
}
return q.mint, q.maxt
}
// lastSamplePerStepFor decides whether the fetch can keep only the last
// sample per step bucket, and computes the bucket parameters. Requirements:
// - the call site attached QueryTraits proving the query has no subquery
// (subquery selectors evaluate at the subquery's own step, but hints
// carry the top-level step);
// - the selector is an instant selector (hints.Range == 0); range selectors
// need every raw sample in the window;
// - per-selector hints are present.
//
// The engine derives hints.Start for instant selectors as
// firstEval - (lookback - 1ms), so the first evaluation timestamp is
// recovered as hints.Start + lookback - 1ms. Bucket boundaries then coincide
// with evaluation timestamps, which is what makes keeping only the last
// sample per bucket lossless.
func (q *querier) lastSamplePerStepFor(ctx context.Context, hints *storage.SelectHints) *lastSamplePerStep {
if hints == nil || hints.Range != 0 || hints.Start <= 0 {
return nil
}
traits, ok := prometheus.QueryTraitsFromContext(ctx)
if !ok || !traits.SubqueryFree {
return nil
}
firstEval := hints.Start + q.client.lookbackMs - 1
if firstEval > hints.End {
// Defensive: never anchor a bucket past the window.
firstEval = hints.End
}
return &lastSamplePerStep{firstEvalMs: firstEval, stepMs: hints.Step}
}
// fetchSamples runs the samples query for the matched series. Small sets
// inline the fingerprints as sorted uint64 literals — literals engage the
// samples primary key, and sorting keeps the statement deterministic for
// logging and tests. Larger sets re-run the series predicates as a
// shard-local IN subquery instead: inlining hundreds of thousands of
// literals makes the statement itself the bottleneck, while the subquery is
// a cheap primary-key scan on each shard's own series table (see
// localTimeSeriesTable for why that is complete).
func (q *querier) fetchSamples(ctx context.Context, start, end int64, matchers []*labels.Matcher, lookup *seriesLookup, lastPerStep *lastSamplePerStep) ([]*series, error) {
var fingerprints []uint64
if len(lookup.fingerprints) <= inlineFingerprintsLimit {
fingerprints = make([]uint64, 0, len(lookup.fingerprints))
for fp := range lookup.fingerprints {
fingerprints = append(fingerprints, fp)
}
slices.Sort(fingerprints)
}
query, args, err := buildSamplesQuery(start, end, lookup.metricNames, fingerprints, matchers, lastPerStep)
if err != nil {
return nil, err
}
return q.client.selectSamples(ctx, query, args, lookup)
}
func (q *querier) selectStrings(ctx context.Context, fn, query string, args []any) ([]string, error) {
ctx = q.client.withContext(ctx, fn)
rows, err := q.client.telemetryStore.ClickhouseDB().Query(ctx, query, args...)
if err != nil {
return nil, err
}
defer rows.Close()
var out []string
var v string
for rows.Next() {
if err := rows.Scan(&v); err != nil {
return nil, err
}
out = append(out, v)
}
if err := rows.Err(); err != nil {
return nil, err
}
return out, nil
}
// rawSQLQuery detects the {job="rawsql", query="..."} escape hatch.
func rawSQLQuery(matchers []*labels.Matcher) (string, bool) {
if len(matchers) != 2 {
return "", false
}
var hasJob bool
var query string
for _, m := range matchers {
if m.Type == labels.MatchEqual && m.Name == "job" && m.Value == "rawsql" {
hasJob = true
}
if m.Type == labels.MatchEqual && m.Name == "query" {
query = m.Value
}
}
if hasJob && query != "" {
return query, true
}
return "", false
}

View File

@@ -1,221 +0,0 @@
package clickhouseprometheusv2
import (
"context"
"fmt"
"testing"
"github.com/DATA-DOG/go-sqlmock"
cmock "github.com/SigNoz/clickhouse-go-mock"
"github.com/stretchr/testify/assert"
"github.com/stretchr/testify/require"
"github.com/SigNoz/signoz/pkg/errors"
"github.com/SigNoz/signoz/pkg/factory"
"github.com/SigNoz/signoz/pkg/instrumentation/instrumentationtest"
"github.com/SigNoz/signoz/pkg/prometheus"
"github.com/SigNoz/signoz/pkg/telemetrystore"
"github.com/SigNoz/signoz/pkg/telemetrystore/telemetrystoretest"
"github.com/prometheus/prometheus/model/labels"
"github.com/prometheus/prometheus/storage"
)
var (
seriesCols = []cmock.ColumnType{
{Name: "fingerprint", Type: "UInt64"},
{Name: "labels", Type: "String"},
}
samplesCols = []cmock.ColumnType{
{Name: "fingerprint", Type: "UInt64"},
{Name: "unix_milli", Type: "Int64"},
{Name: "value", Type: "Float64"},
{Name: "flags", Type: "UInt32"},
}
)
func newTestClient(t *testing.T, cfg prometheus.ClickhouseV2Config) (*client, *telemetrystoretest.Provider) {
t.Helper()
store := telemetrystoretest.New(telemetrystore.Config{Provider: "clickhouse"}, sqlmock.QueryMatcherRegexp)
settings := factory.NewScopedProviderSettings(instrumentationtest.New().ToProviderSettings(), "clickhouseprometheusv2_test")
promCfg := prometheus.Config{ClickhouseV2: cfg}
return newClient(settings, store, promCfg), store
}
func testMatchers(t *testing.T) []*labels.Matcher {
t.Helper()
return []*labels.Matcher{
mustMatcher(t, labels.MatchEqual, "__name__", "cpu_usage"),
mustMatcher(t, labels.MatchEqual, "job", "api"),
}
}
func TestQuerierSelectRawPath(t *testing.T) {
c, store := newTestClient(t, prometheus.ClickhouseV2Config{})
q := &querier{mint: 1000, maxt: 2000, client: c}
store.Mock().ExpectQuery("SELECT fingerprint, any\\(labels\\)").WithArgs("cpu_usage", int64(0), int64(2000), "job", "api").WillReturnRows(cmock.NewRows(seriesCols, [][]any{
{uint64(42), `{"__name__":"cpu_usage","job":"api","instance":"a"}`},
{uint64(7), `{"__name__":"cpu_usage","job":"api","instance":"b"}`},
}))
// Inline fingerprints (sorted), raw samples: no traits in ctx -> no
// last-sample-per-step reduction.
store.Mock().ExpectQuery("SELECT fingerprint, unix_milli, value, flags FROM signoz_metrics.distributed_samples_v4 WHERE metric_name = \\? AND temporality IN \\['Cumulative', 'Unspecified'\\] AND fingerprint IN \\(7, 42\\)").
WithArgs("cpu_usage", int64(1000), int64(2000)).
WillReturnRows(cmock.NewRows(samplesCols, [][]any{
{uint64(7), int64(1100), 1.5, uint32(0)},
{uint64(7), int64(1200), 2.5, uint32(0)},
{uint64(42), int64(1100), 3.5, uint32(1)}, // stale marker
}))
hints := &storage.SelectHints{Start: 1000, End: 2000, Step: 60_000}
set := q.Select(context.Background(), false, hints, testMatchers(t)...)
var got []*series
for set.Next() {
got = append(got, set.At().(*series))
}
require.NoError(t, set.Err())
require.Len(t, got, 2)
// Sorted by labels: instance=a (fp 42) before instance=b (fp 7).
assert.Equal(t, "a", got[0].lset.Get("instance"))
require.Len(t, got[0].ts, 1)
assert.True(t, got[0].vs[0] != got[0].vs[0], "stale marker must be NaN") //nolint:testifylint
assert.Equal(t, "b", got[1].lset.Get("instance"))
assert.Equal(t, []int64{1100, 1200}, got[1].ts)
assert.Equal(t, []float64{1.5, 2.5}, got[1].vs)
// No fingerprint label injected.
assert.Empty(t, got[0].lset.Get("fingerprint"))
}
// Wrong gating silently corrupts range functions (a rate over reduced
// samples loses points), so the decision logic is pinned here even though
// the helper is unexported: the integration suite would catch it too, but
// with far worse failure locality.
func TestLastSamplePerStepFor(t *testing.T) {
c, _ := newTestClient(t, prometheus.ClickhouseV2Config{})
q := &querier{mint: 0, maxt: 2000, client: c}
traitsCtx := prometheus.NewContextWithQueryTraits(context.Background(), prometheus.QueryTraits{SubqueryFree: true})
tests := []struct {
name string
ctx context.Context
hints *storage.SelectHints
want *lastSamplePerStep
}{
{"no traits in context stays raw", context.Background(), &storage.SelectHints{Start: 1000, End: 2000, Step: 60_000}, nil},
{"subquery in the query stays raw", prometheus.NewContextWithQueryTraits(context.Background(), prometheus.QueryTraits{SubqueryFree: false}), &storage.SelectHints{Start: 1000, End: 2000, Step: 60_000}, nil},
{"range selector stays raw", traitsCtx, &storage.SelectHints{Start: 1000, End: 2000, Step: 60_000, Range: 300_000}, nil},
{"instant selector reduces, anchored at first eval", traitsCtx, &storage.SelectHints{Start: 1000, End: 2_000_000, Step: 60_000}, &lastSamplePerStep{firstEvalMs: 1000 + c.lookbackMs - 1, stepMs: 60_000}},
{"anchor never passes the window end", traitsCtx, &storage.SelectHints{Start: 1000, End: 2000, Step: 60_000}, &lastSamplePerStep{firstEvalMs: 2000, stepMs: 60_000}},
}
for _, tt := range tests {
t.Run(tt.name, func(t *testing.T) {
assert.Equal(t, tt.want, q.lastSamplePerStepFor(tt.ctx, tt.hints))
})
}
}
func TestQuerierSelectSeriesBudget(t *testing.T) {
c, store := newTestClient(t, prometheus.ClickhouseV2Config{MaxFetchedSeries: 1})
q := &querier{mint: 1000, maxt: 2000, client: c}
store.Mock().ExpectQuery("SELECT fingerprint, any\\(labels\\)").WithArgs("cpu_usage", int64(0), int64(2000), "job", "api").WillReturnRows(cmock.NewRows(seriesCols, [][]any{
{uint64(1), `{"__name__":"cpu_usage","instance":"a"}`},
{uint64(2), `{"__name__":"cpu_usage","instance":"b"}`},
}))
set := q.Select(context.Background(), false, &storage.SelectHints{Start: 1000, End: 2000}, testMatchers(t)...)
assert.False(t, set.Next())
require.Error(t, set.Err())
assert.True(t, errors.Ast(set.Err(), errors.TypeInvalidInput), "budget error must be typed invalid input, got %v", set.Err())
}
func TestQuerierSelectSamplesBudget(t *testing.T) {
c, store := newTestClient(t, prometheus.ClickhouseV2Config{MaxFetchedSamples: 2})
q := &querier{mint: 1000, maxt: 2000, client: c}
store.Mock().ExpectQuery("SELECT fingerprint, any\\(labels\\)").WithArgs("cpu_usage", int64(0), int64(2000)).WillReturnRows(cmock.NewRows(seriesCols, [][]any{
{uint64(7), `{"__name__":"cpu_usage"}`},
}))
store.Mock().ExpectQuery("SELECT fingerprint, unix_milli, value, flags").
WithArgs("cpu_usage", int64(1000), int64(2000)).
WillReturnRows(cmock.NewRows(samplesCols, [][]any{
{uint64(7), int64(1100), 1.0, uint32(0)},
{uint64(7), int64(1200), 2.0, uint32(0)},
{uint64(7), int64(1300), 3.0, uint32(0)},
}))
set := q.Select(context.Background(), false, &storage.SelectHints{Start: 1000, End: 2000},
mustMatcher(t, labels.MatchEqual, "__name__", "cpu_usage"))
assert.False(t, set.Next())
require.Error(t, set.Err())
assert.True(t, errors.Ast(set.Err(), errors.TypeInvalidInput))
}
func TestQuerierSelectSubqueryFilterOverInlineLimit(t *testing.T) {
c, store := newTestClient(t, prometheus.ClickhouseV2Config{})
q := &querier{mint: 1000, maxt: 2000, client: c}
seriesRows := make([][]any, inlineFingerprintsLimit+1)
for i := range seriesRows {
seriesRows[i] = []any{uint64(i + 1), fmt.Sprintf(`{"__name__":"cpu_usage","instance":"i%d"}`, i)}
}
store.Mock().ExpectQuery("SELECT fingerprint, any\\(labels\\)").WithArgs("cpu_usage", int64(0), int64(2000), "job", "api").WillReturnRows(cmock.NewRows(seriesCols, seriesRows))
// The over-limit samples query embeds the semi-join against the
// shard-local series table (fingerprint co-locality), not a GLOBAL
// broadcast; args follow placeholder order — samples metric name, then
// the semi-join's series predicates, then the samples window bounds.
store.Mock().ExpectQuery("fingerprint IN \\(SELECT fingerprint FROM signoz_metrics\\.time_series_v4").
WithArgs("cpu_usage", "cpu_usage", int64(0), int64(2000), "job", "api", int64(1000), int64(2000)).
WillReturnRows(cmock.NewRows(samplesCols, [][]any{}))
set := q.Select(context.Background(), false, &storage.SelectHints{Start: 1000, End: 2000}, testMatchers(t)...)
assert.False(t, set.Next())
require.NoError(t, set.Err())
}
func TestQuerierSelectRawSQLPassthrough(t *testing.T) {
c, store := newTestClient(t, prometheus.ClickhouseV2Config{})
q := &querier{mint: 1000, maxt: 2000, client: c}
rawCols := []cmock.ColumnType{
{Name: "le", Type: "String"},
{Name: "value", Type: "Float64"},
}
store.Mock().ExpectQuery("SELECT le, avg\\(v\\) AS value FROM t").WillReturnRows(cmock.NewRows(rawCols, [][]any{
{"0.5", 12.5},
}))
set := q.Select(context.Background(), false, &storage.SelectHints{Start: 1000, End: 2000},
mustMatcher(t, labels.MatchEqual, "job", "rawsql"),
mustMatcher(t, labels.MatchEqual, "query", "SELECT le, avg(v) AS value FROM t"),
)
require.True(t, set.Next())
s := set.At()
assert.Equal(t, "0.5", s.Labels().Get("le"))
it := s.Iterator(nil)
require.NotNil(t, it)
_, v := func() (int64, float64) { it.Next(); return it.At() }()
assert.Equal(t, 12.5, v)
assert.False(t, set.Next())
}
func TestCaptureQuerierRecordsWithoutExecuting(t *testing.T) {
c, _ := newTestClient(t, prometheus.ClickhouseV2Config{})
recorder := &statementRecorder{}
cq := &captureQuerier{querier: querier{mint: 1000, maxt: 2000, client: c}, recorder: recorder}
ctx := prometheus.NewContextWithQueryTraits(context.Background(), prometheus.QueryTraits{SubqueryFree: true})
set := cq.Select(ctx, false, &storage.SelectHints{Start: 1000, End: 2000, Step: 60_000}, testMatchers(t)...)
assert.False(t, set.Next())
require.NoError(t, set.Err())
statements := recorder.Statements()
require.Len(t, statements, 1)
assert.Contains(t, statements[0].Query, "IN (SELECT fingerprint FROM signoz_metrics.time_series_v4")
assert.Contains(t, statements[0].Query, "argMax(value, unix_milli)")
}

View File

@@ -1,184 +0,0 @@
package clickhouseprometheusv2
import (
"sort"
"github.com/prometheus/prometheus/model/histogram"
"github.com/prometheus/prometheus/model/labels"
"github.com/prometheus/prometheus/storage"
"github.com/prometheus/prometheus/tsdb/chunkenc"
"github.com/prometheus/prometheus/util/annotations"
)
// series is one time series with samples stored as parallel slices, ordered
// by timestamp. The compact layout avoids per-sample allocations and keeps
// iteration cache friendly.
type series struct {
lset labels.Labels
ts []int64
vs []float64
}
var _ storage.Series = (*series)(nil)
func (s *series) Labels() labels.Labels {
return s.lset
}
func (s *series) Iterator(it chunkenc.Iterator) chunkenc.Iterator {
if fit, ok := it.(*floatIterator); ok {
fit.reset(s)
return fit
}
fit := &floatIterator{}
fit.reset(s)
return fit
}
// floatIterator implements chunkenc.Iterator over a series' sample slices.
type floatIterator struct {
s *series
i int
}
var _ chunkenc.Iterator = (*floatIterator)(nil)
func (it *floatIterator) reset(s *series) {
it.s = s
it.i = -1
}
func (it *floatIterator) Next() chunkenc.ValueType {
it.i++
if it.i >= len(it.s.ts) {
return chunkenc.ValNone
}
return chunkenc.ValFloat
}
func (it *floatIterator) Seek(t int64) chunkenc.ValueType { //nolint:govet // stdmethods flags io.Seeker; this is chunkenc.Iterator's Seek
if it.i < 0 {
it.i = 0
}
if it.i >= len(it.s.ts) {
return chunkenc.ValNone
}
// The current position, once valid, must not move backwards.
if it.s.ts[it.i] >= t {
return chunkenc.ValFloat
}
it.i += sort.Search(len(it.s.ts)-it.i, func(j int) bool {
return it.s.ts[it.i+j] >= t
})
if it.i >= len(it.s.ts) {
return chunkenc.ValNone
}
return chunkenc.ValFloat
}
func (it *floatIterator) At() (int64, float64) {
return it.s.ts[it.i], it.s.vs[it.i]
}
func (it *floatIterator) AtHistogram(*histogram.Histogram) (int64, *histogram.Histogram) {
return 0, nil
}
func (it *floatIterator) AtFloatHistogram(*histogram.FloatHistogram) (int64, *histogram.FloatHistogram) {
return 0, nil
}
func (it *floatIterator) AtT() int64 {
return it.s.ts[it.i]
}
// AtST returns the current start timestamp; not tracked by this storage.
func (it *floatIterator) AtST() int64 {
return 0
}
func (it *floatIterator) Err() error {
return nil
}
// seriesSet iterates a fully materialized, label-sorted list of series.
type seriesSet struct {
series []*series
i int
}
var _ storage.SeriesSet = (*seriesSet)(nil)
func newSeriesSet(list []*series) *seriesSet {
return &seriesSet{series: list, i: -1}
}
func (s *seriesSet) Next() bool {
s.i++
return s.i < len(s.series)
}
func (s *seriesSet) At() storage.Series {
return s.series[s.i]
}
func (s *seriesSet) Err() error {
return nil
}
func (s *seriesSet) Warnings() annotations.Annotations {
return nil
}
// sortAndMerge orders series by label set and merges series whose label sets
// are identical. Distinct fingerprints can carry identical label sets (e.g.
// series differing only in a non-label dimension); Prometheus storages never
// expose duplicate label sets to the engine, so merge their samples by
// timestamp, keeping the first sample on ties.
func sortAndMerge(list []*series) []*series {
if len(list) < 2 {
return list
}
sort.Slice(list, func(i, j int) bool {
return labels.Compare(list[i].lset, list[j].lset) < 0
})
out := list[:1]
for _, s := range list[1:] {
last := out[len(out)-1]
if labels.Compare(last.lset, s.lset) != 0 {
out = append(out, s)
continue
}
merged := mergeSamples(last, s)
out[len(out)-1] = merged
}
return out
}
func mergeSamples(a, b *series) *series {
ts := make([]int64, 0, len(a.ts)+len(b.ts))
vs := make([]float64, 0, len(a.ts)+len(b.ts))
i, j := 0, 0
for i < len(a.ts) && j < len(b.ts) {
switch {
case a.ts[i] < b.ts[j]:
ts = append(ts, a.ts[i])
vs = append(vs, a.vs[i])
i++
case a.ts[i] > b.ts[j]:
ts = append(ts, b.ts[j])
vs = append(vs, b.vs[j])
j++
default:
ts = append(ts, a.ts[i])
vs = append(vs, a.vs[i])
i++
j++
}
}
ts = append(ts, a.ts[i:]...)
vs = append(vs, a.vs[i:]...)
ts = append(ts, b.ts[j:]...)
vs = append(vs, b.vs[j:]...)
return &series{lset: a.lset, ts: ts, vs: vs}
}

View File

@@ -1,199 +0,0 @@
package clickhouseprometheusv2
import (
"fmt"
"strconv"
"strings"
"github.com/SigNoz/signoz/pkg/errors"
"github.com/SigNoz/signoz/pkg/query-service/constants"
"github.com/huandu/go-sqlbuilder"
"github.com/prometheus/prometheus/model/labels"
)
// inlineFingerprintsLimit is the largest matched-series count inlined into
// the samples query as literals. Literals engage the samples primary key and
// avoid a second series-table scan; past a few thousand the statement itself
// becomes the cost, and the shard-local subquery filter wins. Not
// configurable: the crossover depends on statement parsing, not on any
// property of a deployment an operator could know better.
const inlineFingerprintsLimit = 5_000
// buildSeriesQuery renders the series lookup: one row per matched fingerprint
// with its labels.
func buildSeriesQuery(start, end int64, matchers []*labels.Matcher) (string, []any, error) {
adjustedStart, table := timeSeriesTableFor(start, end)
sb := sqlbuilder.NewSelectBuilder()
sb.Select("fingerprint", "any(labels)")
sb.From(fmt.Sprintf("%s.%s", databaseName, table))
if err := applySeriesConditions(sb, adjustedStart, end, matchers); err != nil {
return "", nil, err
}
sb.GroupBy("fingerprint")
query, args := sb.BuildWithFlavor(sqlbuilder.ClickHouse)
return query, args, nil
}
// buildSamplesQuery renders the samples fetch for the series selected by the
// series lookup. Small matched sets pass inlineFingerprints — sorted uint64
// literals that engage the samples primary key; nil means the set exceeded
// the inline limit, and the filter becomes a semi-join re-running the series
// predicates against the shard-local series table (complete by fingerprint
// co-locality, see localTimeSeriesTable; a GLOBAL broadcast of the matched
// set would ship it to every shard instead). metricNames narrows the
// primary-key scan; when the selector had no __name__ equality, the names
// observed on the matched series are used. A non-nil lastPerStep groups to
// one (the last) sample per step bucket.
func buildSamplesQuery(start, end int64, metricNames []string, inlineFingerprints []uint64, matchers []*labels.Matcher, lastPerStep *lastSamplePerStep) (string, []any, error) {
sb := sqlbuilder.NewSelectBuilder()
if lastPerStep != nil {
// Aliases must not shadow source columns: ClickHouse resolves aliases
// in WHERE too, and "max(unix_milli) AS unix_milli" would put an
// aggregate into the WHERE clause (error 184).
sb.Select("fingerprint", "max(unix_milli) AS ts", "argMax(value, unix_milli) AS val", "argMax(flags, unix_milli) AS fl")
} else {
sb.Select("fingerprint", "unix_milli", "value", "flags")
}
sb.From(fmt.Sprintf("%s.%s", databaseName, distributedSamplesV4))
switch len(metricNames) {
case 0:
// No name constraint derivable; correct but unable to use the
// metric_name primary-key prefix.
case 1:
sb.Where(sb.EQ("metric_name", metricNames[0]))
default:
sb.Where(sb.In("metric_name", sqlbuilder.List(metricNames)))
}
// temporality precedes metric_name in the samples primary key; the
// fingerprints already come from these temporalities, so this only helps
// granule pruning.
sb.Where("temporality IN ['Cumulative', 'Unspecified']")
if inlineFingerprints != nil {
sb.Where("fingerprint " + inlineFingerprintFilter(inlineFingerprints))
} else {
sub := sqlbuilder.NewSelectBuilder()
sub.Select("fingerprint")
adjustedStart, table := timeSeriesTableFor(start, end)
sub.From(fmt.Sprintf("%s.%s", databaseName, localTimeSeriesTable(table)))
if err := applySeriesConditions(sub, adjustedStart, end, matchers); err != nil {
return "", nil, err
}
sb.Where(sb.In("fingerprint", sub))
}
sb.Where(sb.GTE("unix_milli", start), sb.LTE("unix_milli", end))
if lastPerStep != nil {
sb.GroupBy("fingerprint")
if expr := lastPerStep.bucketExpr(); expr != "" {
sb.GroupBy(expr)
}
sb.OrderBy("fingerprint", "ts")
} else {
sb.OrderBy("fingerprint", "unix_milli")
}
query, args := sb.BuildWithFlavor(sqlbuilder.ClickHouse)
return query, args, nil
}
// applySeriesConditions adds the WHERE conditions of a series table scan for
// the given matchers and window. __name__ matchers translate to the
// metric_name column (all four matcher types — the v1 client silently
// returned nothing for regex metric names); every other matcher translates
// to a JSONExtractString condition on the labels column. An equality matcher
// against "" matches series without the label, mirroring PromQL, because
// JSONExtractString returns "" for missing keys. Regexes are anchored:
// PromQL matchers match the whole value, while ClickHouse match() searches
// for a partial match — without anchoring, =~"api" would also select
// "x-api-y".
func applySeriesConditions(sb *sqlbuilder.SelectBuilder, start, end int64, matchers []*labels.Matcher) error {
for _, m := range matchers {
if m.Name != metricNameLabel {
continue
}
switch m.Type {
case labels.MatchEqual:
sb.Where(sb.EQ("metric_name", m.Value))
case labels.MatchNotEqual:
sb.Where(sb.NE("metric_name", m.Value))
case labels.MatchRegexp:
sb.Where(fmt.Sprintf("match(metric_name, %s)", sb.Var(anchorRegex(m.Value))))
case labels.MatchNotRegexp:
sb.Where(fmt.Sprintf("NOT match(metric_name, %s)", sb.Var(anchorRegex(m.Value))))
default:
return errors.NewInvalidInputf(errors.CodeInvalidInput, "unsupported matcher type %q for __name__", m.Type)
}
}
sb.Where("temporality IN ['Cumulative', 'Unspecified']")
sb.Where(fmt.Sprintf("__normalized = %v", !constants.IsDotMetricsEnabled))
sb.Where(sb.GTE("unix_milli", start), sb.LT("unix_milli", end))
for _, m := range matchers {
if m.Name == metricNameLabel {
continue
}
switch m.Type {
case labels.MatchEqual:
sb.Where(fmt.Sprintf("JSONExtractString(labels, %s) = %s", sb.Var(m.Name), sb.Var(m.Value)))
case labels.MatchNotEqual:
sb.Where(fmt.Sprintf("JSONExtractString(labels, %s) != %s", sb.Var(m.Name), sb.Var(m.Value)))
case labels.MatchRegexp:
sb.Where(fmt.Sprintf("match(JSONExtractString(labels, %s), %s)", sb.Var(m.Name), sb.Var(anchorRegex(m.Value))))
case labels.MatchNotRegexp:
sb.Where(fmt.Sprintf("NOT match(JSONExtractString(labels, %s), %s)", sb.Var(m.Name), sb.Var(anchorRegex(m.Value))))
default:
return errors.NewInvalidInputf(errors.CodeInvalidInput, "unsupported matcher type %q", m.Type)
}
}
return nil
}
// anchorRegex turns a PromQL regex into its fully-anchored form (see
// applySeriesConditions).
func anchorRegex(v string) string {
return "^(?:" + v + ")$"
}
// inlineFingerprintFilter renders "IN (fp1, fp2, ...)" with literal uint64s.
func inlineFingerprintFilter(fingerprints []uint64) string {
var b strings.Builder
b.Grow(len(fingerprints)*21 + 8)
b.WriteString("IN (")
for i, fp := range fingerprints {
if i > 0 {
b.WriteString(", ")
}
b.WriteString(strconv.FormatUint(fp, 10))
}
b.WriteString(")")
return b.String()
}
// lastSamplePerStep reduces an instant-selector fetch to the last sample of
// each step bucket. Buckets are anchored at the selector's first evaluation
// timestamp so that every bucket boundary coincides with an evaluation
// timestamp: bucket 0 is (start, firstEval] (the initial lookback window)
// and bucket i is (firstEval+(i-1)·step, firstEval+i·step]. Keeping only the
// last sample per bucket is lossless: the engine resolves each evaluation
// timestamp t to the latest sample in (t-lookback, t], and a non-final
// sample of a bucket can never be that latest sample for any t on the
// evaluation grid. Real timestamps are preserved, so the engine's own
// lookback and staleness handling remain exact.
type lastSamplePerStep struct {
firstEvalMs int64
stepMs int64
}
func (t *lastSamplePerStep) bucketExpr() string {
if t.stepMs <= 0 {
// Instant query: a single evaluation at firstEval; one bucket.
return ""
}
return fmt.Sprintf(
"if(unix_milli <= %d, 0, intDiv(unix_milli - %d - 1, %d) + 1)",
t.firstEvalMs, t.firstEvalMs, t.stepMs,
)
}

View File

@@ -1,148 +0,0 @@
package clickhouseprometheusv2
import (
"testing"
"time"
"github.com/prometheus/prometheus/model/labels"
"github.com/stretchr/testify/assert"
"github.com/stretchr/testify/require"
)
func mustMatcher(t *testing.T, mt labels.MatchType, name, value string) *labels.Matcher {
t.Helper()
m, err := labels.NewMatcher(mt, name, value)
require.NoError(t, err)
return m
}
func TestTimeSeriesTableFor(t *testing.T) {
base := time.Date(2026, 7, 10, 3, 27, 0, 0, time.UTC).UnixMilli()
tests := []struct {
name string
span time.Duration
wantTable string
roundTo time.Duration
}{
{"under 6h uses hourly table", 2 * time.Hour, distributedTimeSeriesV4, time.Hour},
{"under 1d uses 6h table", 12 * time.Hour, distributedTimeSeriesV46hrs, 6 * time.Hour},
{"under 1w uses 1d table", 3 * 24 * time.Hour, distributedTimeSeriesV41day, 24 * time.Hour},
{"over 1w uses 1w table", 10 * 24 * time.Hour, distributedTimeSeriesV41week, 7 * 24 * time.Hour},
}
for _, tt := range tests {
t.Run(tt.name, func(t *testing.T) {
start, table := timeSeriesTableFor(base, base+tt.span.Milliseconds())
assert.Equal(t, tt.wantTable, table)
assert.Zero(t, start%tt.roundTo.Milliseconds())
assert.LessOrEqual(t, start, base)
})
}
}
func TestBuildSeriesQuery(t *testing.T) {
start := int64(1_700_000_000_000)
end := start + time.Hour.Milliseconds()
// The series table window rounds down to the table's bucket boundary.
adjustedStart := start - (start % time.Hour.Milliseconds())
t.Run("equality name and label matchers", func(t *testing.T) {
query, args, err := buildSeriesQuery(start, end, []*labels.Matcher{
mustMatcher(t, labels.MatchEqual, "__name__", "http_requests_total"),
mustMatcher(t, labels.MatchEqual, "job", "api"),
})
require.NoError(t, err)
assert.Equal(t,
"SELECT fingerprint, any(labels) FROM signoz_metrics.distributed_time_series_v4 WHERE metric_name = ? AND temporality IN ['Cumulative', 'Unspecified'] AND __normalized = false AND unix_milli >= ? AND unix_milli < ? AND JSONExtractString(labels, ?) = ? GROUP BY fingerprint",
query,
)
assert.Equal(t, []any{"http_requests_total", adjustedStart, end, "job", "api"}, args)
})
t.Run("regex matchers are anchored", func(t *testing.T) {
_, args, err := buildSeriesQuery(start, end, []*labels.Matcher{
mustMatcher(t, labels.MatchEqual, "__name__", "up"),
mustMatcher(t, labels.MatchRegexp, "instance", "prod.*"),
mustMatcher(t, labels.MatchNotRegexp, "env", "dev|test"),
})
require.NoError(t, err)
assert.Equal(t, []any{"up", adjustedStart, end, "instance", "^(?:prod.*)$", "env", "^(?:dev|test)$"}, args)
})
t.Run("regex name matcher uses metric_name column", func(t *testing.T) {
query, args, err := buildSeriesQuery(start, end, []*labels.Matcher{
mustMatcher(t, labels.MatchRegexp, "__name__", "node_cpu.*|node_memory.*"),
})
require.NoError(t, err)
assert.Contains(t, query, "match(metric_name, ?)")
assert.NotContains(t, query, "JSONExtractString")
assert.Equal(t, []any{"^(?:node_cpu.*|node_memory.*)$", adjustedStart, end}, args)
})
t.Run("no name matcher omits metric_name condition", func(t *testing.T) {
query, _, err := buildSeriesQuery(start, end, []*labels.Matcher{
mustMatcher(t, labels.MatchEqual, "job", "api"),
})
require.NoError(t, err)
assert.NotContains(t, query, "metric_name")
})
}
func TestBuildSamplesQuery(t *testing.T) {
start := int64(1_700_000_000_000)
end := start + time.Hour.Milliseconds()
adjustedStart := start - (start % time.Hour.Milliseconds())
matchers := []*labels.Matcher{
mustMatcher(t, labels.MatchEqual, "__name__", "up"),
mustMatcher(t, labels.MatchEqual, "job", "api"),
}
t.Run("raw with inline fingerprints", func(t *testing.T) {
query, args, err := buildSamplesQuery(start, end, []string{"up"}, []uint64{7, 42}, matchers, nil)
require.NoError(t, err)
assert.Equal(t,
"SELECT fingerprint, unix_milli, value, flags FROM signoz_metrics.distributed_samples_v4 WHERE metric_name = ? AND temporality IN ['Cumulative', 'Unspecified'] AND fingerprint IN (7, 42) AND unix_milli >= ? AND unix_milli <= ? ORDER BY fingerprint, unix_milli",
query,
)
assert.Equal(t, []any{"up", start, end}, args)
})
t.Run("last-sample-per-step groups by step bucket anchored at first eval", func(t *testing.T) {
lastPerStep := &lastSamplePerStep{firstEvalMs: start + 299_999, stepMs: 60_000}
query, _, err := buildSamplesQuery(start, end, []string{"up"}, []uint64{7}, matchers, lastPerStep)
require.NoError(t, err)
assert.Contains(t, query, "argMax(value, unix_milli) AS val")
assert.Contains(t, query, "argMax(flags, unix_milli) AS fl")
assert.Contains(t, query, "GROUP BY fingerprint, if(unix_milli <= 1700000299999, 0, intDiv(unix_milli - 1700000299999 - 1, 60000) + 1)")
assert.Contains(t, query, "ORDER BY fingerprint, ts")
// Aliases must not shadow the source columns referenced in WHERE.
assert.NotContains(t, query, "AS unix_milli")
assert.NotContains(t, query, "AS value")
assert.NotContains(t, query, "AS flags")
})
t.Run("instant query keeps one bucket", func(t *testing.T) {
lastPerStep := &lastSamplePerStep{firstEvalMs: end, stepMs: 0}
query, _, err := buildSamplesQuery(start, end, []string{"up"}, []uint64{7}, matchers, lastPerStep)
require.NoError(t, err)
assert.Contains(t, query, "GROUP BY fingerprint ORDER BY fingerprint, ts")
assert.NotContains(t, query, "intDiv")
})
t.Run("over-limit set becomes a shard-local semi-join", func(t *testing.T) {
query, args, err := buildSamplesQuery(start, end, []string{"up"}, nil, matchers, nil)
require.NoError(t, err)
assert.Contains(t, query, "fingerprint IN (SELECT fingerprint FROM signoz_metrics.time_series_v4 WHERE ")
assert.NotContains(t, query, "GLOBAL IN")
// Args follow placeholder order: samples metric name, the semi-join's
// series predicates, then the samples window bounds.
assert.Equal(t, []any{"up", "up", adjustedStart, end, "job", "api", start, end}, args)
})
t.Run("multiple metric names from regex selector", func(t *testing.T) {
query, args, err := buildSamplesQuery(start, end, []string{"node_cpu", "node_memory"}, []uint64{7}, matchers, nil)
require.NoError(t, err)
assert.Contains(t, query, "metric_name IN (?, ?)")
assert.Equal(t, []any{"node_cpu", "node_memory", start, end}, args)
})
}

View File

@@ -1,65 +0,0 @@
package clickhouseprometheusv2
import "time"
const (
// metricNameLabel is the reserved PromQL label holding the metric name.
metricNameLabel string = "__name__"
databaseName string = "signoz_metrics"
distributedTimeSeriesV4 string = "distributed_time_series_v4"
distributedTimeSeriesV46hrs string = "distributed_time_series_v4_6hrs"
distributedTimeSeriesV41day string = "distributed_time_series_v4_1day"
distributedTimeSeriesV41week string = "distributed_time_series_v4_1week"
distributedSamplesV4 string = "distributed_samples_v4"
localTimeSeriesV4 string = "time_series_v4"
localTimeSeriesV46hrs string = "time_series_v4_6hrs"
localTimeSeriesV41day string = "time_series_v4_1day"
localTimeSeriesV41week string = "time_series_v4_1week"
)
// localTimeSeriesTable maps a distributed time series table to its shard-local
// table. Samples and time series shard on the same key
// (cityHash64(env, temporality, metric_name, fingerprint)), so a query whose
// top-level FROM is the distributed samples table can join or semi-join the
// local time series table inside each shard: the shard rewrite runs the
// subquery against the shard's own series rows, which are exactly the series
// of the shard's samples. No broadcast, no initiator-side join.
func localTimeSeriesTable(distributed string) string {
switch distributed {
case distributedTimeSeriesV46hrs:
return localTimeSeriesV46hrs
case distributedTimeSeriesV41day:
return localTimeSeriesV41day
case distributedTimeSeriesV41week:
return localTimeSeriesV41week
default:
return localTimeSeriesV4
}
}
var (
oneHourInMilliseconds = time.Hour.Milliseconds()
sixHoursInMilliseconds = time.Hour.Milliseconds() * 6
oneDayInMilliseconds = time.Hour.Milliseconds() * 24
oneWeekInMilliseconds = time.Hour.Milliseconds() * 24 * 7
)
// timeSeriesTableFor returns the adjusted start and the time series table for
// the window. Time series tables hold one row per (fingerprint, bucket), with
// bucket granularities of 1h, 6h, 1d and 1w; the start is rounded down to the
// bucket boundary so a window beginning mid-bucket still matches the bucket's
// row.
func timeSeriesTableFor(start, end int64) (int64, string) {
switch {
case end-start < sixHoursInMilliseconds:
return start - (start % oneHourInMilliseconds), distributedTimeSeriesV4
case end-start < oneDayInMilliseconds:
return start - (start % sixHoursInMilliseconds), distributedTimeSeriesV46hrs
case end-start < oneWeekInMilliseconds:
return start - (start % oneDayInMilliseconds), distributedTimeSeriesV41day
default:
return start - (start % oneWeekInMilliseconds), distributedTimeSeriesV41week
}
}

View File

@@ -1,485 +0,0 @@
package clickhouseprometheusv2
import (
"fmt"
"strings"
"github.com/prometheus/prometheus/model/labels"
"github.com/prometheus/prometheus/promql/parser"
)
// The compiler turns PromQL subtrees into single ClickHouse queries built on
// the timeSeries*ToGrid aggregate functions (CH >= 25.6), whose semantics
// were verified against this repo's vendored engine: exact extrapolatedRate
// behavior including counter resets, the counter zero-point clamp, the
// 1.1x-average extrapolation threshold, left-open windows, the >= 2 samples
// rule, stale-marker shadowing, and millisecond grid starts. Sample rows
// never leave ClickHouse: one row per output series comes back, holding the
// whole grid as an array.
//
// Scope (the allowlist): an optional sum/min/max/avg/count by/without
// aggregation over a core unit — a rate/increase/delta/irate/idelta range
// selection, an instant vector selection, or an avg/min/max/sum/count/last
// _over_time window — plus number-literal arithmetic/comparisons and unary
// minus on top. Units inside fixed-resolution subqueries evaluate on the
// subquery's own grid. Everything else either falls back to the engine over
// this package's querier, or — when a transpilable subtree sits under a
// non-transpilable node — runs hybrid: the subtree's grids are computed in
// ClickHouse and substituted into the engine as synthetic series (see
// compiler_exec.go). See doc.go for the fallback list and the reasons behind
// each entry.
// rangeFn is a transpilable range-vector function.
type rangeFn string
const (
fnRate rangeFn = "rate"
fnIncrease rangeFn = "increase"
fnDelta rangeFn = "delta"
fnIRate rangeFn = "irate"
fnIDelta rangeFn = "idelta"
)
var gridFunction = map[rangeFn]string{
fnRate: "timeSeriesRateToGrid",
fnIncrease: "timeSeriesRateToGrid", // increase == rate * range seconds, exactly (same factor algebra)
fnDelta: "timeSeriesDeltaToGrid",
fnIRate: "timeSeriesInstantRateToGrid",
fnIDelta: "timeSeriesInstantDeltaToGrid",
}
// scalarOp is one number-literal arithmetic or comparison applied to a
// compiled vector, evaluated in Go during assembly with the same float64
// operations the engine uses.
type scalarOp struct {
op parser.ItemType
scalar float64
scalarOnLeft bool
returnBool bool
}
// isComparison reports whether the op is a filtering/bool comparison, which
// preserves the metric name (arithmetic drops it).
func (o scalarOp) isComparison() bool {
return o.op.IsComparisonOperator()
}
// unitKind is the selector shape at the bottom of a core unit.
type unitKind int
const (
// unitRange: rate/increase/delta/irate/idelta over a matrix selector.
unitRange unitKind = iota
// unitInstant: a plain vector selector resolved per grid point with
// lookback and stale-marker shadowing.
unitInstant
// unitOverTime: avg/min/max/sum/count/last_over_time over a matrix
// selector (aggregation over the window's samples, stale rows excluded).
unitOverTime
)
// coreUnit is one transpilable subtree: selector [-> range function] ->
// optional aggregation -> scalar op pipeline.
type coreUnit struct {
kind unitKind
matchers []*labels.Matcher
offsetMs int64
fn rangeFn // unitRange
overFn string // unitOverTime: avg|min|max|sum|count|last
rangeMs int64 // unitRange/unitOverTime window
hasAgg bool
aggOp parser.ItemType // SUM MIN MAX AVG COUNT
by bool
grouping []string
ops []scalarOp
}
// keepsName reports whether the unit's output series keep their real
// __name__: bare/comparison-filtered instant selectors and last_over_time do
// (it returns the raw sample, name included); range functions, the other
// *_over_time functions, aggregations, arithmetic and bool comparisons all
// drop it — a bool comparison returns 0/1, not the sample, so the engine
// drops the name there too. Units that keep the name cannot be substituted
// as synthetic series in hybrid plans — the synthetic name would replace
// the real one — but transpile fine as full plans, where assembly emits the
// real names.
func (u *coreUnit) keepsName() bool {
nameKeepingSelector := u.kind == unitInstant || (u.kind == unitOverTime && u.overFn == "last")
if !nameKeepingSelector || u.hasAgg {
return false
}
for _, op := range u.ops {
if !op.isComparison() || op.returnBool {
return false
}
}
return true
}
// gridContext is the evaluation grid a unit computes on. The query grid for
// top-level units; for units inside subqueries, the subquery's own grid:
// epoch-aligned multiples of its resolution covering the subquery window,
// exactly as the engine derives it (engine.go, *parser.SubqueryExpr case).
type gridContext struct {
startMs int64
endMs int64
stepMs int64
}
// subqueryGrid derives the inner grid for a subquery evaluated on outer:
// interval S, end = outer end offset, start = first multiple of S strictly
// greater than outer start offset range.
func subqueryGrid(outer gridContext, rangeMs, stepMs, offsetMs int64) gridContext {
lower := outer.startMs - offsetMs - rangeMs
start := stepMs * (lower / stepMs)
if start <= lower {
start += stepMs
}
return gridContext{startMs: start, endMs: outer.endMs - offsetMs, stepMs: stepMs}
}
// transpiledUnit is a coreUnit scheduled for execution, named for hybrid
// substitution, carrying the grid it evaluates on.
type transpiledUnit struct {
core coreUnit
name string // __signoz_transpiled_<n>__
grid gridContext
}
// transpilePlan is the outcome of classifying a query.
type transpilePlan struct {
units []*transpiledUnit
grid gridContext // the query's top-level grid
// full is set when the entire query is units[0]; otherwise rewritten
// holds the query with each unit replaced by a synthetic selector, to be
// evaluated by the engine over a hybrid storage.
full bool
rewritten string
}
const syntheticNamePrefix = "__signoz_transpiled_"
func syntheticName(i int) string {
return fmt.Sprintf("%s%d__", syntheticNamePrefix, i)
}
// classifyCore matches a subtree against the transpilable core shape.
// stepMs gates second-granularity: the grid functions take whole-second step
// and window parameters (grid *starts* are millisecond-precise).
func classifyCore(node parser.Expr, stepMs int64) (*coreUnit, bool) {
unit := &coreUnit{}
expr := node
// Peel scalar ops and parens off the top, outermost first; ops apply in
// evaluation order, so prepend while peeling.
for {
switch n := expr.(type) {
case *parser.ParenExpr:
expr = n.Expr
continue
case *parser.UnaryExpr:
if n.Op != parser.SUB {
expr = n.Expr // unary '+' is a no-op
continue
}
// -x == -1 * x for every float64 (incl. NaN and signed zero).
unit.ops = append([]scalarOp{{op: parser.MUL, scalar: -1}}, unit.ops...)
expr = n.Expr
continue
case *parser.StepInvariantExpr:
// @-pinned expressions evaluate on a different grid.
return nil, false
case *parser.BinaryExpr:
lit, litOnLeft, ok := numberLiteralSide(n)
if !ok {
return nil, false
}
if !n.Op.IsOperator() && !n.Op.IsComparisonOperator() {
return nil, false
}
if n.Op == parser.ATAN2 {
// atan2 is arithmetic in PromQL but rarely used; keep the
// allowlist tight.
return nil, false
}
returnBool := n.ReturnBool
unit.ops = append([]scalarOp{{op: n.Op, scalar: lit, scalarOnLeft: litOnLeft, returnBool: returnBool}}, unit.ops...)
if litOnLeft {
expr = n.RHS
} else {
expr = n.LHS
}
continue
}
break
}
// Optional aggregation.
if agg, ok := expr.(*parser.AggregateExpr); ok {
switch agg.Op {
case parser.SUM, parser.MIN, parser.MAX, parser.AVG, parser.COUNT:
default:
return nil, false
}
for _, g := range agg.Grouping {
if g == metricNameLabel {
// by(__name__)/without(__name__) over synthetic or compiled
// output needs name bookkeeping the compiler doesn't do.
return nil, false
}
}
unit.hasAgg = true
unit.aggOp = agg.Op
unit.by = !agg.Without
unit.grouping = agg.Grouping
expr = agg.Expr
for {
if p, ok := expr.(*parser.ParenExpr); ok {
expr = p.Expr
continue
}
break
}
}
// The grid functions take whole-second steps; stepMs == 0 is an instant
// query (single-point grid).
if stepMs < 0 || stepMs%1000 != 0 {
return nil, false
}
// Bare instant selector: resolved per grid point with lookback and
// stale-marker shadowing (see compiler_sql.go).
if vs, ok := expr.(*parser.VectorSelector); ok {
if vs.Timestamp != nil || vs.StartOrEnd != 0 || vs.Anchored || vs.Smoothed {
return nil, false
}
offsetMs := vs.OriginalOffset.Milliseconds()
if offsetMs < 0 {
return nil, false
}
unit.kind = unitInstant
unit.offsetMs = offsetMs
unit.matchers = vs.LabelMatchers
return unit, true
}
// Range or *_over_time function over a plain matrix selector.
call, ok := expr.(*parser.Call)
if !ok {
return nil, false
}
var fn rangeFn
var overFn string
switch call.Func.Name {
case "rate":
fn = fnRate
case "increase":
fn = fnIncrease
case "delta":
fn = fnDelta
case "irate":
fn = fnIRate
case "idelta":
fn = fnIDelta
case "avg_over_time", "min_over_time", "max_over_time", "sum_over_time", "count_over_time", "last_over_time":
overFn = strings.TrimSuffix(call.Func.Name, "_over_time")
default:
return nil, false
}
if len(call.Args) != 1 {
return nil, false
}
ms, ok := call.Args[0].(*parser.MatrixSelector)
if !ok {
return nil, false
}
vs, ok := ms.VectorSelector.(*parser.VectorSelector)
if !ok {
return nil, false
}
if vs.Timestamp != nil || vs.StartOrEnd != 0 || vs.Anchored || vs.Smoothed {
return nil, false
}
rangeMs := ms.Range.Milliseconds()
offsetMs := vs.OriginalOffset.Milliseconds()
if rangeMs <= 0 || rangeMs%1000 != 0 || offsetMs < 0 {
return nil, false
}
if overFn != "" {
unit.kind = unitOverTime
unit.overFn = overFn
} else {
unit.kind = unitRange
unit.fn = fn
}
unit.rangeMs = rangeMs
unit.offsetMs = offsetMs
unit.matchers = vs.LabelMatchers
return unit, true
}
// numberLiteralSide returns the number literal on one side of a binary
// expression (peeling parens and unary minus), and which side it is on.
func numberLiteralSide(b *parser.BinaryExpr) (float64, bool, bool) {
if v, ok := literalValue(b.LHS); ok {
return v, true, true
}
if v, ok := literalValue(b.RHS); ok {
return v, false, true
}
return 0, false, false
}
func literalValue(e parser.Expr) (float64, bool) {
neg := false
for {
switch n := e.(type) {
case *parser.ParenExpr:
e = n.Expr
continue
case *parser.StepInvariantExpr:
e = n.Expr
continue
case *parser.UnaryExpr:
if n.Op == parser.SUB {
neg = !neg
}
e = n.Expr
continue
case *parser.NumberLiteral:
if neg {
return -n.Val, true
}
return n.Val, true
default:
return 0, false
}
}
}
// classify builds the compile plan for a query: full when the root is a core
// unit, hybrid when core units sit strictly below the root (including inside
// fixed-resolution subqueries, computed on the subquery grid), none
// otherwise.
func classify(root parser.Expr, grid gridContext) (*transpilePlan, bool) {
if unit, ok := classifyCore(root, grid.stepMs); ok {
return &transpilePlan{
units: []*transpiledUnit{{core: *unit, name: syntheticName(0), grid: grid}},
grid: grid,
full: true,
}, true
}
plan := &transpilePlan{grid: grid}
rewritten := rewrite(root, grid, plan, false)
if len(plan.units) == 0 {
return nil, false
}
plan.rewritten = rewritten.String()
return plan, true
}
// rewrite walks top-down replacing maximal transpilable subtrees with synthetic
// vector selectors. nameSensitive marks scopes where an ancestor's semantics
// depend on __name__ (grouping or vector matching on it): synthetic series
// carry a synthetic __name__, so substitution there would change results.
// Fixed-resolution subqueries recurse with the subquery's own grid; scopes
// whose evaluation grid is unknowable (@-pinned, default-resolution
// subqueries) are not entered.
func rewrite(node parser.Expr, grid gridContext, plan *transpilePlan, nameSensitive bool) parser.Expr {
if node == nil {
return nil
}
if !nameSensitive {
// Units whose output keeps the real __name__ (bare instant selectors)
// cannot be substituted: the synthetic name would replace it in the
// engine's output. They still compile as full plans.
if unit, ok := classifyCore(node, grid.stepMs); ok && !unit.keepsName() {
cu := &transpiledUnit{core: *unit, name: syntheticName(len(plan.units)), grid: grid}
plan.units = append(plan.units, cu)
return &parser.VectorSelector{
Name: cu.name,
LabelMatchers: []*labels.Matcher{
labels.MustNewMatcher(labels.MatchEqual, metricNameLabel, cu.name),
},
PosRange: node.PositionRange(),
}
}
}
switch n := node.(type) {
case *parser.ParenExpr:
n.Expr = rewrite(n.Expr, grid, plan, nameSensitive)
case *parser.UnaryExpr:
n.Expr = rewrite(n.Expr, grid, plan, nameSensitive)
case *parser.AggregateExpr:
sensitive := nameSensitive || groupingUsesName(n.Grouping)
n.Expr = rewrite(n.Expr, grid, plan, sensitive)
// n.Param is a scalar/string; nothing transpilable inside for our core.
case *parser.Call:
for i, arg := range n.Args {
n.Args[i] = rewrite(arg, grid, plan, nameSensitive)
}
case *parser.BinaryExpr:
sensitive := nameSensitive || vectorMatchingUsesName(n.VectorMatching)
n.LHS = rewrite(n.LHS, grid, plan, sensitive)
n.RHS = rewrite(n.RHS, grid, plan, sensitive)
case *parser.SubqueryExpr:
// The alert-smoothing idiom fn_over_time((expr)[R:S]) dominates real
// rule fleets; inner units evaluate on the subquery grid, and the
// engine does the smoothing over the synthetic series. Requires an
// explicit whole-second resolution (S == 0 needs the engine's
// default-interval function) and no @ pinning.
stepMs := n.Step.Milliseconds()
rangeMs := n.Range.Milliseconds()
offsetMs := n.OriginalOffset.Milliseconds()
if n.Timestamp == nil && n.StartOrEnd == 0 &&
stepMs > 0 && stepMs%1000 == 0 && rangeMs%1000 == 0 && offsetMs >= 0 {
inner := subqueryGrid(grid, rangeMs, stepMs, offsetMs)
n.Expr = rewrite(n.Expr, inner, plan, nameSensitive)
}
case *parser.StepInvariantExpr, *parser.MatrixSelector,
*parser.VectorSelector, *parser.NumberLiteral, *parser.StringLiteral:
// Leaves, or scopes substitution must not enter.
}
return node
}
func groupingUsesName(grouping []string) bool {
for _, g := range grouping {
if g == metricNameLabel {
return true
}
}
return false
}
func vectorMatchingUsesName(vm *parser.VectorMatching) bool {
if vm == nil {
return false
}
for _, l := range append(append([]string{}, vm.MatchingLabels...), vm.Include...) {
if l == metricNameLabel {
return true
}
}
// Default (all-labels) matching ignores __name__, and by()/ignoring()
// lists were checked above.
return false
}
// isSyntheticSelector reports whether matchers target a compiled unit.
func isSyntheticSelector(matchers []*labels.Matcher) (string, bool) {
for _, m := range matchers {
if m.Name == metricNameLabel && m.Type == labels.MatchEqual && strings.HasPrefix(m.Value, syntheticNamePrefix) {
return m.Value, true
}
}
return "", false
}

View File

@@ -1,150 +0,0 @@
package clickhouseprometheusv2
import (
"bufio"
"encoding/json"
"fmt"
"os"
"regexp"
"sort"
"strings"
"testing"
"github.com/prometheus/prometheus/promql/parser"
"github.com/stretchr/testify/require"
)
// TestClassifyCorpus measures real-workload compiler coverage: it classifies
// every query of a JSON-lines corpus (one JSON-encoded PromQL string per
// line) with the live classifier and reports full / hybrid / fallback
// shares. Skipped unless PROMQL_CORPUS points to one or more files
// (comma-separated). Dashboard template variables are substituted with
// placeholder values before parsing, mirroring the production render step.
//
// PROMQL_CORPUS=corpus-a.jsonl,corpus-b.jsonl go test -run TestClassifyCorpus -v
func TestClassifyCorpus(t *testing.T) {
corpus := os.Getenv("PROMQL_CORPUS")
if corpus == "" {
t.Skip("PROMQL_CORPUS not set")
}
varRe := regexp.MustCompile(`\{\{\s*\.?[\w.]+\s*\}\}|\[\[\s*[\w.]+\s*\]\]|\$[\w.]+`)
promParser := parser.NewParser(parser.Options{})
for _, path := range strings.Split(corpus, ",") {
f, err := os.Open(path)
require.NoError(t, err)
var full, hybrid, fallbackInstant, fallbackOther, parseErrs int
fallbackReasons := map[string]int{}
scanner := bufio.NewScanner(f)
scanner.Buffer(make([]byte, 1024*1024), 1024*1024)
for scanner.Scan() {
var query string
require.NoError(t, json.Unmarshal(scanner.Bytes(), &query))
query = varRe.ReplaceAllString(query, "placeholder")
expr, err := promParser.ParseExpr(query)
if err != nil {
parseErrs++
continue
}
plan, ok := classify(expr, gridContext{startMs: 1_700_000_000_000, endMs: 1_700_007_200_000, stepMs: 60_000})
switch {
case ok && plan.full:
full++
case ok:
hybrid++
default:
reason := fallbackShape(expr)
fallbackReasons[reason]++
if reason == "instant-selector shape (last-sample-per-step engine path)" {
fallbackInstant++
} else {
fallbackOther++
}
}
}
require.NoError(t, scanner.Err())
_ = f.Close()
total := full + hybrid + fallbackInstant + fallbackOther
if total == 0 {
t.Logf("%s: no parseable queries (%d parse errors)", path, parseErrs)
continue
}
t.Logf("%s: %d queries — full=%d (%.0f%%) hybrid=%d (%.0f%%) fallback=%d (%.0f%%; instant-shape=%d) parse_errors=%d",
path, total,
full, 100*float64(full)/float64(total),
hybrid, 100*float64(hybrid)/float64(total),
fallbackInstant+fallbackOther, 100*float64(fallbackInstant+fallbackOther)/float64(total),
fallbackInstant, parseErrs)
reasons := make([]string, 0, len(fallbackReasons))
for r := range fallbackReasons {
reasons = append(reasons, r)
}
sort.Slice(reasons, func(i, j int) bool { return fallbackReasons[reasons[i]] > fallbackReasons[reasons[j]] })
for _, r := range reasons {
t.Logf(" fallback %4d %s", fallbackReasons[r], r)
}
}
}
// fallbackShape buckets a non-transpilable query by why it stays on the engine
// path, to separate "already served well" (instant selectors on the last-sample-per-step
// path) from genuine compiler gaps.
func fallbackShape(expr parser.Expr) string {
var hasMatrix, hasSubquery, hasAt, overTime bool
rangeFns := map[string]bool{"rate": true, "increase": true, "delta": true, "irate": true, "idelta": true}
var unsupportedFns []string
parser.Inspect(expr, func(node parser.Node, _ []parser.Node) error {
switch n := node.(type) {
case *parser.MatrixSelector:
hasMatrix = true
case *parser.SubqueryExpr:
hasSubquery = true
case *parser.VectorSelector:
if n.Timestamp != nil || n.StartOrEnd != 0 {
hasAt = true
}
case *parser.Call:
if strings.HasSuffix(n.Func.Name, "_over_time") {
overTime = true
} else if !rangeFns[n.Func.Name] {
unsupportedFns = append(unsupportedFns, n.Func.Name)
}
}
return nil
})
switch {
case hasSubquery:
return "subquery"
case hasAt:
return "@ modifier"
case overTime:
return "*_over_time range function"
case !hasMatrix:
return "instant-selector shape (last-sample-per-step engine path)"
case len(unsupportedFns) > 0:
return fmt.Sprintf("range shape with unsupported function(s): %s", strings.Join(dedupe(unsupportedFns), ",")) //nolint:makezero
default:
return "other range shape"
}
}
func dedupe(in []string) []string {
seen := map[string]bool{}
var out []string
for _, s := range in {
if !seen[s] {
seen[s] = true
out = append(out, s)
}
}
sort.Strings(out)
return out
}

View File

@@ -1,463 +0,0 @@
package clickhouseprometheusv2
import (
"context"
"encoding/json"
"math"
"sort"
"sync/atomic"
"time"
"github.com/SigNoz/signoz/pkg/errors"
"github.com/SigNoz/signoz/pkg/prometheus"
"github.com/prometheus/prometheus/model/labels"
promValue "github.com/prometheus/prometheus/model/value"
"github.com/prometheus/prometheus/promql"
"github.com/prometheus/prometheus/promql/parser"
"github.com/prometheus/prometheus/storage"
"golang.org/x/sync/errgroup"
)
// executor evaluates transpilable PromQL directly in ClickHouse, falling
// back (ok=false) whenever the query shape or the step doesn't qualify. The
// timeSeries*ToGrid functions it builds on are assumed available: the
// supported ClickHouse floor is >= 25.6.
type executor struct {
client *client
engine *prometheus.Engine
parser prometheus.Parser
}
// TryExecuteRange transpiles and runs the query in ClickHouse when its shape
// is in the allowlist. ok=false means "not transpilable" and carries no
// error; the caller runs the engine path.
func (e *executor) TryExecuteRange(ctx context.Context, qs string, start, end time.Time, step time.Duration) (promql.Matrix, bool, error) {
expr, err := e.parser.ParseExpr(qs)
if err != nil {
// Let the engine path produce the (enhanced) parse error.
return nil, false, nil
}
plan, ok := classify(expr, queryGrid(start, end, step))
if !ok {
return nil, false, nil
}
// timeSeriesLastToGrid widens its window to max(window, step) — probed: a
// sample aged (window, step] still fills the slot — while the rate/delta
// family enforces the window strictly. The Last-style kinds therefore
// transpile only when their window covers the step; otherwise the engine
// path serves them exactly.
for _, unit := range plan.units {
lastStyle := unit.core.kind == unitInstant || (unit.core.kind == unitOverTime && unit.core.overFn == "last")
if !lastStyle {
continue
}
windowMs := unit.core.rangeMs
if unit.core.kind == unitInstant {
windowMs = e.client.lookbackMs
}
if windowMs < unit.grid.stepMs {
return nil, false, nil
}
}
// Evaluate every unit concurrently on its own grid (the query grid, or a
// subquery grid); each is one series lookup plus one grid query. The
// units share one grid-cell budget: transpiled results never pass
// through the engine's sample limiter, so without this a large
// series-count x grid-width query would buffer unbounded arrays — the
// OOM this provider exists to prevent.
results := make([][]transpiledSeries, len(plan.units))
var gridCells atomic.Int64
eg, egCtx := errgroup.WithContext(ctx)
for i, unit := range plan.units {
eg.Go(func() error {
res, err := e.executeUnit(egCtx, &unit.core, unit.grid, &gridCells)
if err != nil {
return err
}
results[i] = res
return nil
})
}
if err := eg.Wait(); err != nil {
return nil, true, err
}
if plan.full {
g := plan.units[0].grid
return toMatrix(results[0], g.startMs, g.stepMs), true, nil
}
matrix, err := e.executeHybrid(ctx, plan, results)
if err != nil {
return nil, true, err
}
return matrix, true, nil
}
// queryGrid derives the top-level evaluation grid; step 0 is an instant
// query: a single evaluation at end, whatever start was.
func queryGrid(start, end time.Time, step time.Duration) gridContext {
startMs, endMs, stepMs := start.UnixMilli(), end.UnixMilli(), step.Milliseconds()
if stepMs == 0 {
startMs = endMs
}
return gridContext{startMs: startMs, endMs: endMs, stepMs: stepMs}
}
// transpiledSeries is one output series of a unit: projected labels and one
// value pointer per grid point (nil = absent).
type transpiledSeries struct {
lset labels.Labels
values []*float64
}
// executeUnit runs one core unit on its grid: series lookup (budgets,
// fingerprints, metric names), then the single grid query, then the
// scalar-op pipeline.
func (e *executor) executeUnit(ctx context.Context, unit *coreUnit, grid gridContext, gridCells *atomic.Int64) ([]transpiledSeries, error) {
startMs, endMs, stepMs := grid.startMs, grid.endMs, grid.stepMs
windowMs := unit.rangeMs
if unit.kind == unitInstant {
windowMs = e.client.lookbackMs
}
dataStart := startMs - unit.offsetMs - windowMs
dataEnd := endMs - unit.offsetMs
seriesQuery, seriesArgs, err := buildSeriesQuery(dataStart, dataEnd, unit.matchers)
if err != nil {
return nil, err
}
lookup, err := e.client.selectSeries(ctx, seriesQuery, seriesArgs)
if err != nil {
return nil, err
}
if len(lookup.fingerprints) == 0 {
return nil, nil
}
// The result buffers one grid array per series; series count times grid
// width is the transpiled equivalent of fetched samples, counted before
// the arrays exist rather than after the memory is spent.
gridLen := int64(1)
if stepMs > 0 {
gridLen = (endMs-startMs)/stepMs + 1
}
if maxSamples := e.client.cfg.MaxFetchedSamples; maxSamples > 0 && gridCells.Add(int64(len(lookup.fingerprints))*gridLen) > maxSamples {
return nil, errors.NewInvalidInputf(
errors.CodeInvalidInput,
"promql query would buffer more than %d output points; narrow the selector or time range, or raise prometheus::clickhousev2::max_fetched_samples",
maxSamples,
)
}
query, args, err := buildUnitSQL(unit, lookup.metricNames, transpiledFingerprintFilter(lookup), dataStart, dataEnd, startMs, endMs, stepMs, e.client.lookbackMs)
if err != nil {
return nil, err
}
rows, err := e.client.telemetryStore.ClickhouseDB().Query(e.client.withContext(ctx, "transpiledUnit"), query, args...)
if err != nil {
return nil, err
}
defer rows.Close()
// Name-dropping units keep __name__ in the SQL group key so distinct
// metrics never merge server-side; the name comes off here, and a
// post-strip collision is the engine's duplicate-labelset error — v1
// would have errored, so silently inventing a merged series would be a
// divergence.
stripName := !unit.hasAgg && !unit.keepsName()
seen := make(map[uint64]string)
var out []transpiledSeries
var gkey string
var gridValues []*float64
for rows.Next() {
if err := rows.Scan(&gkey, &gridValues); err != nil {
return nil, err
}
lset, err := labelsFromGroupKey(gkey)
if err != nil {
return nil, err
}
if stripName {
name := lset.Get(metricNameLabel)
lset = labels.NewBuilder(lset).Del(metricNameLabel).Labels()
if prev, ok := seen[lset.Hash()]; ok && prev != name {
return nil, errors.NewInvalidInputf(errors.CodeInvalidInput, "vector cannot contain metrics with the same labelset")
}
seen[lset.Hash()] = name
}
values := make([]*float64, len(gridValues))
copy(values, gridValues)
applyScalarOps(unit.ops, values)
out = append(out, transpiledSeries{lset: lset, values: values})
}
if err := rows.Err(); err != nil {
return nil, err
}
sort.Slice(out, func(i, j int) bool { return labels.Compare(out[i].lset, out[j].lset) < 0 })
return out, nil
}
// transpiledFingerprintFilter returns the matched fingerprints as a sorted
// slice when they fit the inline limit — literals engage the samples primary
// key, and sorting keeps the statement deterministic for logging and tests.
// Over the limit it returns nil: the unit query's INNER JOIN against the
// local series subquery restricts to exactly the matched fingerprints
// already, and a semi-join on the same predicates would only rescan the
// series table.
func transpiledFingerprintFilter(lookup *seriesLookup) []uint64 {
if len(lookup.fingerprints) > inlineFingerprintsLimit {
return nil
}
fingerprints := make([]uint64, 0, len(lookup.fingerprints))
for fp := range lookup.fingerprints {
fingerprints = append(fingerprints, fp)
}
sort.Slice(fingerprints, func(i, j int) bool { return fingerprints[i] < fingerprints[j] })
return fingerprints
}
// labelsFromGroupKey parses the toJSONString'd sorted [key, value] pairs.
func labelsFromGroupKey(gkey string) (labels.Labels, error) {
var pairs [][]string
if err := json.Unmarshal([]byte(gkey), &pairs); err != nil {
return labels.EmptyLabels(), errors.WrapInternalf(err, errors.CodeInternal, "malformed compiled group key %q", gkey)
}
builder := labels.NewScratchBuilder(len(pairs))
for _, p := range pairs {
if len(p) != 2 {
return labels.EmptyLabels(), errors.NewInternalf(errors.CodeInternal, "malformed compiled group key pair %q", gkey)
}
builder.Add(p[0], p[1])
}
builder.Sort()
return builder.Labels(), nil
}
// applyScalarOps applies the number-literal op pipeline in place, with the
// same float64 arithmetic and comparison-filter semantics as the engine.
func applyScalarOps(ops []scalarOp, values []*float64) {
for _, op := range ops {
for i, v := range values {
if v == nil {
continue
}
lhs, rhs := *v, op.scalar
if op.scalarOnLeft {
lhs, rhs = op.scalar, *v
}
switch op.op {
case parser.ADD:
res := lhs + rhs
values[i] = &res
case parser.SUB:
res := lhs - rhs
values[i] = &res
case parser.MUL:
res := lhs * rhs
values[i] = &res
case parser.DIV:
res := lhs / rhs
values[i] = &res
case parser.MOD:
res := math.Mod(lhs, rhs)
values[i] = &res
case parser.POW:
res := math.Pow(lhs, rhs)
values[i] = &res
default:
keep := compare(op.op, lhs, rhs)
switch {
case op.returnBool:
res := 0.0
if keep {
res = 1.0
}
values[i] = &res
case keep:
// Filter comparisons keep the vector-side value.
vec := *v
values[i] = &vec
default:
values[i] = nil
}
}
}
}
}
func compare(op parser.ItemType, lhs, rhs float64) bool {
switch op {
case parser.EQLC:
return lhs == rhs
case parser.NEQ:
return lhs != rhs
case parser.GTR:
return lhs > rhs
case parser.LSS:
return lhs < rhs
case parser.GTE:
return lhs >= rhs
case parser.LTE:
return lhs <= rhs
}
return false
}
// toMatrix converts a unit result to a promql matrix on the query grid.
func toMatrix(series []transpiledSeries, startMs, stepMs int64) promql.Matrix {
matrix := make(promql.Matrix, 0, len(series))
for _, s := range series {
var floats []promql.FPoint
for i, v := range s.values {
if v == nil {
continue
}
floats = append(floats, promql.FPoint{T: startMs + int64(i)*stepMs, F: *v})
}
if len(floats) == 0 {
continue
}
matrix = append(matrix, promql.Series{Metric: s.lset, Floats: floats})
}
return matrix
}
// executeHybrid substitutes each unit's grids into the engine as synthetic
// series and evaluates the rewritten query over a storage that serves
// synthetic selectors from memory and everything else from the live querier.
// Absent grid points become stale markers so the engine's lookback cannot
// resurrect the previous grid point. Each unit's synthetic samples sit on its
// own grid (query grid, or subquery grid for units inside subqueries).
func (e *executor) executeHybrid(ctx context.Context, plan *transpilePlan, results [][]transpiledSeries) (promql.Matrix, error) {
synthetic := make(map[string][]*series, len(plan.units))
staleMarker := math.Float64frombits(promValue.StaleNaN)
queryGrid := plan.grid
for i, unit := range plan.units {
g := unit.grid
gridLen := 1
if g.stepMs > 0 {
gridLen = int((g.endMs-g.startMs)/g.stepMs) + 1
}
list := make([]*series, 0, len(results[i]))
for _, cs := range results[i] {
builder := labels.NewBuilder(cs.lset)
builder.Set(metricNameLabel, unit.name)
s := &series{lset: builder.Labels()}
s.ts = make([]int64, 0, gridLen)
s.vs = make([]float64, 0, gridLen)
for idx := 0; idx < gridLen; idx++ {
t := g.startMs + int64(idx)*g.stepMs
var v float64
if idx < len(cs.values) && cs.values[idx] != nil {
v = *cs.values[idx]
} else {
v = staleMarker
}
s.ts = append(s.ts, t)
s.vs = append(s.vs, v)
}
list = append(list, s)
}
synthetic[unit.name] = list
}
hybrid := &hybridQueryable{client: e.client, synthetic: synthetic}
var qry promql.Query
var err error
if queryGrid.stepMs == 0 {
qry, err = e.engine.NewInstantQuery(ctx, hybrid, nil, plan.rewritten, time.UnixMilli(queryGrid.endMs))
} else {
qry, err = e.engine.NewRangeQuery(ctx, hybrid, nil, plan.rewritten, time.UnixMilli(queryGrid.startMs), time.UnixMilli(queryGrid.endMs), time.Duration(queryGrid.stepMs)*time.Millisecond)
}
if err != nil {
return nil, err
}
defer qry.Close()
res := qry.Exec(ctx)
if res.Err != nil {
return nil, res.Err
}
matrix, err := resultToMatrix(res)
if err != nil {
return nil, err
}
// Deep-copy before Close returns the result's slices to the engine pool,
// and drop the synthetic __name__ that filter comparisons preserve.
out := make(promql.Matrix, 0, len(matrix))
for _, s := range matrix {
lset := s.Metric
if name := lset.Get(metricNameLabel); len(name) >= len(syntheticNamePrefix) && name[:len(syntheticNamePrefix)] == syntheticNamePrefix {
builder := labels.NewBuilder(lset)
builder.Del(metricNameLabel)
lset = builder.Labels()
}
floats := make([]promql.FPoint, len(s.Floats))
copy(floats, s.Floats)
out = append(out, promql.Series{Metric: lset.Copy(), Floats: floats})
}
sort.Slice(out, func(i, j int) bool { return labels.Compare(out[i].Metric, out[j].Metric) < 0 })
return out, nil
}
func resultToMatrix(res *promql.Result) (promql.Matrix, error) {
switch v := res.Value.(type) {
case promql.Matrix:
return v, nil
case promql.Vector:
matrix := make(promql.Matrix, 0, len(v))
for _, s := range v {
matrix = append(matrix, promql.Series{Metric: s.Metric, Floats: []promql.FPoint{{T: s.T, F: s.F}}})
}
return matrix, nil
case promql.Scalar:
return promql.Matrix{{Metric: labels.EmptyLabels(), Floats: []promql.FPoint{{T: v.T, F: v.V}}}}, nil
default:
return nil, errors.NewInternalf(errors.CodeInternal, "unexpected hybrid result type %T", res.Value)
}
}
// hybridQueryable serves synthetic (compiled) selectors from memory and
// everything else from the live storage.
type hybridQueryable struct {
client *client
synthetic map[string][]*series
}
func (h *hybridQueryable) Querier(mint, maxt int64) (storage.Querier, error) {
return &hybridQuerier{
querier: querier{mint: mint, maxt: maxt, client: h.client},
synthetic: h.synthetic,
}, nil
}
type hybridQuerier struct {
querier
synthetic map[string][]*series
}
func (h *hybridQuerier) Select(ctx context.Context, sortSeries bool, hints *storage.SelectHints, matchers ...*labels.Matcher) storage.SeriesSet {
if name, ok := isSyntheticSelector(matchers); ok {
list := h.synthetic[name]
if sortSeries {
sorted := make([]*series, len(list))
copy(sorted, list)
sort.Slice(sorted, func(i, j int) bool { return labels.Compare(sorted[i].lset, sorted[j].lset) < 0 })
list = sorted
}
return newSeriesSet(list)
}
return h.querier.Select(ctx, sortSeries, hints, matchers...)
}

View File

@@ -1,303 +0,0 @@
package clickhouseprometheusv2
import (
"fmt"
"strings"
"github.com/huandu/go-sqlbuilder"
)
// experimental gate for the timeSeries*ToGrid aggregate functions; attached
// as a SETTINGS clause so telemetrystore hooks cannot clobber it.
const gridFunctionsSetting = "SETTINGS allow_experimental_ts_to_grid_aggregate_function = 1"
var aggForEach = map[string]string{
"sum": "sumForEach",
"min": "minForEach",
"max": "maxForEach",
"avg": "avgForEach",
"count": "countForEach",
}
// buildUnitSQL renders the single ClickHouse query evaluating a core unit
// over the [startMs, endMs] / stepMs evaluation grid: per-series grids via a
// timeSeries*ToGrid aggregate (or a windowed aggregation for *_over_time),
// then spatial aggregation with -ForEach combinators grouped by a canonical
// JSON key of the projected label pairs.
//
// The heavy level is shaped to run on the shards: the top-level FROM is the
// distributed samples table and the group-key join partner is a subquery on
// the shard-local time series table, so the shard rewrite executes the join
// and the per-(fingerprint, gkey) grid aggregation next to the data —
// complete by fingerprint co-locality (see localTimeSeriesTable) — and the
// initiator only merges per-series grid states and applies the spatial
// -ForEach step. Same layout as the telemetrymetrics statement builder. The
// windowed *_over_time form is the exception: its ARRAY JOIN level
// aggregates on the shards the same way, but the group-key join happens at
// the initiator over the already-reduced per-(series, index) rows — pushing
// it down would not move any data off the initiator (the reduced rows arrive
// there either way), so the combined ARRAY JOIN + JOIN form buys nothing.
//
// inlineFingerprints carries the matched set when it fits the inline limit;
// nil means over the limit, where the group-key join restricts on its own
// (the windowed form, whose fan-out query has no join, falls back to a
// shard-local semi-join so it does not expand every series of the metric).
//
// The selector's data window is offset-shifted; the resulting grid indices
// map 1:1 onto the query grid (output ts = startMs + i*stepMs). Grid
// parameters are rendered as literals — they are aggregate-function
// parameters, not bindable values.
//
// Statements nest builder-rendered SQL as text, so the returned args must be
// ordered by where each fragment lands in the final statement: ClickHouse
// binds ? placeholders by position. A JOIN renders before WHERE, so a joined
// subquery's args precede the outer query's own condition args.
//
// Row shape: (gkey String, grid Array(Nullable(Float64))). gkey is
// toJSONString of the sorted projected [key, value] pairs; NULL grid points
// are absent points (the engine's "no value here"), which the -ForEach
// combinators preserve: an index where every series is NULL aggregates to
// NULL, and countForEach's 0 is mapped back to NULL.
func buildUnitSQL(unit *coreUnit, metricNames []string, inlineFingerprints []uint64, dataStart, dataEnd int64, startMs, endMs, stepMs, lookbackMs int64) (string, []any, error) {
selStart := startMs - unit.offsetMs
selEnd := endMs - unit.offsetMs
stepSec := stepMs / 1000
if stepSec == 0 {
// Instant query: start == end, so the grid has one point for any
// positive step.
stepSec = 1
}
windowMs := unit.rangeMs
if unit.kind == unitInstant {
windowMs = lookbackMs
}
windowSec := windowMs / 1000
adjustedTsStart, tsTable := timeSeriesTableFor(dataStart, dataEnd)
// seriesSub computes fingerprint -> group key. It reads the local series
// table when it rides inside the shard-rewritten samples query, and the
// distributed one when it joins at the initiator (windowed form).
seriesSub := func(table string) (string, []any, error) {
sub := sqlbuilder.NewSelectBuilder()
sub.Select("fingerprint", groupKeyExpr(unit)+" AS gkey")
sub.From(fmt.Sprintf("%s.%s", databaseName, table))
if err := applySeriesConditions(sub, adjustedTsStart, dataEnd, unit.matchers); err != nil {
return "", nil, err
}
sub.GroupBy("fingerprint", "gkey")
q, args := sub.BuildWithFlavor(sqlbuilder.ClickHouse)
return q, args, nil
}
// samplesConditions adds the samples-side WHERE. The samples table is
// aliased "points" in every kind: under the group-key join both sides
// carry a fingerprint column, so the filter must qualify it. A nil
// inline set adds no fingerprint condition — the join restricts.
samplesConditions := func(sb *sqlbuilder.SelectBuilder, excludeStale bool) {
switch len(metricNames) {
case 0:
// No name constraint derivable; correct but unable to use the
// metric_name primary-key prefix.
case 1:
sb.Where(sb.EQ("metric_name", metricNames[0]))
default:
sb.Where(sb.In("metric_name", sqlbuilder.List(metricNames)))
}
// temporality precedes metric_name in the samples primary key; the
// fingerprints already come from these temporalities, so this only
// helps granule pruning.
sb.Where("temporality IN ['Cumulative', 'Unspecified']")
if inlineFingerprints != nil {
sb.Where("points.fingerprint " + inlineFingerprintFilter(inlineFingerprints))
}
// Left-open window: a sample exactly at the window's lower boundary
// is never used (range selectors and lookback are both left-open).
sb.Where(sb.GT("unix_milli", selStart-windowMs), sb.LTE("unix_milli", selEnd))
if excludeStale {
// PromQL excludes stale markers from range vectors. Instant
// selectors need the stale rows for shadowing instead.
sb.Where("bitAnd(flags, 1) = 0")
}
}
// joinedInner builds the shard-side SELECT for the single-pass kinds:
// grid expression per (fingerprint, gkey), group-key join against the
// local series table.
joinedInner := func(gridExpr string, excludeStale bool) (string, []any, error) {
seriesSQL, seriesArgs, err := seriesSub(localTimeSeriesTable(tsTable))
if err != nil {
return "", nil, err
}
sb := sqlbuilder.NewSelectBuilder()
sb.Select("series.gkey AS gkey", gridExpr+" AS grid")
sb.From(fmt.Sprintf("%s.%s AS points", databaseName, distributedSamplesV4))
sb.JoinWithOption(sqlbuilder.InnerJoin, fmt.Sprintf("(%s) AS series", seriesSQL), "points.fingerprint = series.fingerprint")
samplesConditions(sb, excludeStale)
sb.GroupBy("points.fingerprint", "series.gkey")
q, args := sb.BuildWithFlavor(sqlbuilder.ClickHouse)
// The join text renders before WHERE: its args come first.
return q, append(seriesArgs, args...), nil
}
var inner string
var innerArgs []any
var err error
switch unit.kind {
case unitInstant:
// Instant selection with stale shadowing: the grid value is the last
// non-stale sample in (t-lookback, t], absent when the overall last
// sample in that window is a stale marker (verified semantics: the
// -If combinator applies to the grid aggregates, and NULL comparisons
// make a stale-latest point absent).
gridParams := fmt.Sprintf("(fromUnixTimestamp64Milli(%d), fromUnixTimestamp64Milli(%d), %d, %d)", selStart, selEnd, stepSec, windowSec)
gridExpr := fmt.Sprintf(
"arrayMap((tall, tok, vok) -> if(tall IS NULL OR tok IS NULL OR tall != tok, NULL, vok), timeSeriesLastToGrid%s(fromUnixTimestamp64Milli(unix_milli), toFloat64(unix_milli)), timeSeriesLastToGridIf%s(fromUnixTimestamp64Milli(unix_milli), toFloat64(unix_milli), bitAnd(flags, 1) = 0), timeSeriesLastToGridIf%s(fromUnixTimestamp64Milli(unix_milli), value, bitAnd(flags, 1) = 0))",
gridParams, gridParams, gridParams,
)
inner, innerArgs, err = joinedInner(gridExpr, false)
case unitOverTime:
if unit.overFn == "last" {
// last_over_time == last non-stale sample in the window: the
// stale rows are already excluded in WHERE.
gridExpr := fmt.Sprintf(
"timeSeriesLastToGrid(fromUnixTimestamp64Milli(%d), fromUnixTimestamp64Milli(%d), %d, %d)(fromUnixTimestamp64Milli(unix_milli), value)",
selStart, selEnd, stepSec, windowSec,
)
inner, innerArgs, err = joinedInner(gridExpr, true)
break
}
inner, innerArgs, err = windowedInner(unit, samplesConditions, seriesSub, inlineFingerprints == nil, adjustedTsStart, dataEnd, tsTable, selStart, selEnd, stepMs, windowMs)
default: // unitRange
gridExpr := fmt.Sprintf(
"%s(fromUnixTimestamp64Milli(%d), fromUnixTimestamp64Milli(%d), %d, %d)(fromUnixTimestamp64Milli(unix_milli), value)",
gridFunction[unit.fn], selStart, selEnd, stepSec, windowSec,
)
if unit.fn == fnIncrease {
// increase == rate * range-seconds, exactly: extrapolatedRate
// divides by the range only when isRate.
gridExpr = fmt.Sprintf("arrayMap(x -> x * %d, %s)", windowSec, gridExpr)
}
inner, innerArgs, err = joinedInner(gridExpr, true)
}
if err != nil {
return "", nil, err
}
spatial := "maxForEach(grid)"
switch {
case !unit.hasAgg:
// Per-series output: one row per (labels-minus-__name__) group.
// Distinct fingerprints can collapse onto the same projected label
// set only via a regex __name__ selector over metrics with identical
// other labels; maxForEach is a deterministic NULL-skipping merge and
// the identity for the overwhelmingly common one-fingerprint group.
case unit.aggOp.String() == "count":
// count over an all-absent index is an absent point, not 0.
spatial = "arrayMap(c -> if(c = 0, NULL, toFloat64(c)), countForEach(grid))"
default:
spatial = fmt.Sprintf("%s(grid)", aggForEach[unit.aggOp.String()])
}
query := fmt.Sprintf("SELECT gkey, %s AS grid FROM (%s) GROUP BY gkey %s", spatial, inner, gridFunctionsSetting)
return query, innerArgs, nil
}
// windowedInner builds the avg/min/max/sum/count _over_time form: each
// sample fans out to every grid index k whose window (t_k - range, t_k]
// contains it (ARRAY JOIN), aggregates per (fingerprint, k) — shard-side
// partials over the distributed table — then assembles the positional grid
// and joins the group key at the initiator over the reduced rows. The
// group-key subquery reads the distributed series table here because it does
// not ride inside a shard-rewritten query.
//
// This is the one form whose samples query has no series join, so an
// over-the-limit fingerprint set (semiJoin) must fall back to the
// shard-local semi-join: without it the fan-out would expand every series of
// the metric and discard the unmatched ones only at the group-key join.
func windowedInner(unit *coreUnit, samplesConditions func(*sqlbuilder.SelectBuilder, bool), seriesSub func(string) (string, []any, error), semiJoin bool, adjustedTsStart, dataEnd int64, tsTable string, selStart, selEnd, stepMs, windowMs int64) (string, []any, error) {
aggExpr := map[string]string{
"avg": "avg(value)",
"min": "min(value)",
"max": "max(value)",
"sum": "sum(value)",
"count": "toFloat64(count(value))",
}[unit.overFn]
effStepMs := stepMs
if effStepMs == 0 {
effStepMs = 1000
}
lastIdx := (selEnd - selStart) / effStepMs
perWindow := sqlbuilder.NewSelectBuilder()
perWindow.Select("fingerprint", "k", aggExpr+" AS v")
perWindow.From(fmt.Sprintf(
"%s.%s AS points ARRAY JOIN range(toUInt64(greatest(0, intDiv(unix_milli - %d + %d - 1, %d))), toUInt64(least(%d, intDiv(unix_milli + %d - 1 - %d, %d)) + 1)) AS k",
databaseName, distributedSamplesV4,
selStart, effStepMs, effStepMs,
lastIdx, windowMs, selStart, effStepMs,
))
samplesConditions(perWindow, true)
if semiJoin {
sub := sqlbuilder.NewSelectBuilder()
sub.Select("fingerprint")
sub.From(fmt.Sprintf("%s.%s", databaseName, localTimeSeriesTable(tsTable)))
if err := applySeriesConditions(sub, adjustedTsStart, dataEnd, unit.matchers); err != nil {
return "", nil, err
}
perWindow.Where(perWindow.In("points.fingerprint", sub))
}
perWindow.GroupBy("fingerprint", "k")
perWindowSQL, perWindowArgs := perWindow.BuildWithFlavor(sqlbuilder.ClickHouse)
grids := fmt.Sprintf(
"SELECT fingerprint, arrayMap(i -> if(indexOf(ks, i) = 0, NULL, vs[indexOf(ks, i)]), range(toUInt64(%d))) AS grid FROM (SELECT fingerprint, groupArray(k) AS ks, groupArray(v) AS vs FROM (%s) GROUP BY fingerprint)",
lastIdx+1, perWindowSQL,
)
seriesSQL, seriesArgs, err := seriesSub(tsTable)
if err != nil {
return "", nil, err
}
inner := fmt.Sprintf(
"SELECT series.gkey AS gkey, points.grid AS grid FROM (%s) AS points INNER JOIN (%s) AS series ON points.fingerprint = series.fingerprint",
grids, seriesSQL,
)
return inner, append(perWindowArgs, seriesArgs...), nil
}
// groupKeyExpr renders the canonical group key for a unit: the sorted
// [key, value] pairs of the projected labels, JSON-encoded.
// - by (a, b): keep only the listed labels (absent labels stay absent,
// matching PromQL's by() over missing labels);
// - without (a, b): keep everything except the listed labels and __name__;
// - no aggregation: keep everything including __name__ — even when the
// unit drops the name from its OUTPUT, the key must keep it so distinct
// metrics never merge in SQL; executeUnit strips the name afterwards and
// turns a post-strip collision into the engine's duplicate-labelset
// error instead of a silently invented merge.
func groupKeyExpr(unit *coreUnit) string {
// An empty label value means "label absent" in Prometheus; the stored
// labels JSON can carry empty attribute values, which must not become
// output labels or group keys.
pairs := "arraySort(JSONExtractKeysAndValues(labels, 'String'))"
if !unit.hasAgg {
return fmt.Sprintf("toJSONString(arrayFilter(p -> p.2 != '', %s))", pairs)
}
if unit.by {
if len(unit.grouping) == 0 {
return "'[]'"
}
return fmt.Sprintf("toJSONString(arrayFilter(p -> p.2 != '' AND p.1 IN (%s), %s))", quotedList(unit.grouping), pairs)
}
excluded := append([]string{metricNameLabel}, unit.grouping...)
return fmt.Sprintf("toJSONString(arrayFilter(p -> p.2 != '' AND p.1 NOT IN (%s), %s))", quotedList(excluded), pairs)
}
func quotedList(items []string) string {
quoted := make([]string, len(items))
for i, s := range items {
quoted[i] = "'" + strings.ReplaceAll(s, "'", "\\'") + "'"
}
return strings.Join(quoted, ", ")
}

View File

@@ -1,517 +0,0 @@
package clickhouseprometheusv2
import (
"context"
"sync/atomic"
"testing"
"time"
cmock "github.com/SigNoz/clickhouse-go-mock"
"github.com/SigNoz/signoz/pkg/errors"
"github.com/SigNoz/signoz/pkg/prometheus"
"github.com/prometheus/prometheus/model/labels"
"github.com/prometheus/prometheus/promql/parser"
"github.com/stretchr/testify/assert"
"github.com/stretchr/testify/require"
)
func parse(t *testing.T, q string) parser.Expr {
t.Helper()
expr, err := parser.NewParser(parser.Options{}).ParseExpr(q)
require.NoError(t, err)
return expr
}
func TestClassifyFullShapes(t *testing.T) {
tests := []struct {
name string
query string
check func(t *testing.T, u *coreUnit)
}{
{
name: "sum by rate",
query: `sum by (pod) (rate(http_requests_total{job="api"}[5m]))`,
check: func(t *testing.T, u *coreUnit) {
assert.Equal(t, fnRate, u.fn)
assert.Equal(t, int64(300_000), u.rangeMs)
assert.True(t, u.hasAgg)
assert.True(t, u.by)
assert.Equal(t, []string{"pod"}, u.grouping)
},
},
{
name: "bare increase with offset",
query: `increase(errors_total[10m] offset 30m)`,
check: func(t *testing.T, u *coreUnit) {
assert.Equal(t, fnIncrease, u.fn)
assert.Equal(t, int64(1_800_000), u.offsetMs)
assert.False(t, u.hasAgg)
},
},
{
name: "avg without over delta",
query: `avg without (instance) (delta(gauge_metric[15m]))`,
check: func(t *testing.T, u *coreUnit) {
assert.Equal(t, fnDelta, u.fn)
assert.True(t, u.hasAgg)
assert.False(t, u.by)
},
},
{
name: "scalar pipeline with comparison",
query: `sum(rate(x[5m])) * 100 > 5`,
check: func(t *testing.T, u *coreUnit) {
require.Len(t, u.ops, 2)
assert.Equal(t, parser.ItemType(parser.MUL), u.ops[0].op)
assert.Equal(t, 100.0, u.ops[0].scalar)
assert.Equal(t, parser.ItemType(parser.GTR), u.ops[1].op)
},
},
{
name: "scalar on left with unary minus",
query: `-1 * sum(rate(x[5m]))`,
check: func(t *testing.T, u *coreUnit) {
require.Len(t, u.ops, 1)
assert.True(t, u.ops[0].scalarOnLeft)
assert.Equal(t, -1.0, u.ops[0].scalar)
},
},
{
name: "bool comparison",
query: `sum(rate(x[5m])) >= bool 0.5`,
check: func(t *testing.T, u *coreUnit) {
require.Len(t, u.ops, 1)
assert.True(t, u.ops[0].returnBool)
},
},
{
name: "irate utf8 name",
query: `sum by ("k8s.pod.name") (irate({"k8s.container.cpu.time"}[2m]))`,
check: func(t *testing.T, u *coreUnit) {
assert.Equal(t, fnIRate, u.fn)
assert.Equal(t, []string{"k8s.pod.name"}, u.grouping)
},
},
{
name: "bare instant selector keeps name",
query: `up{job="api"}`,
check: func(t *testing.T, u *coreUnit) {
assert.Equal(t, unitInstant, u.kind)
assert.True(t, u.keepsName())
},
},
{
name: "gauge aggregation",
query: `sum by (pod) (container_memory offset 5m)`,
check: func(t *testing.T, u *coreUnit) {
assert.Equal(t, unitInstant, u.kind)
assert.Equal(t, int64(300_000), u.offsetMs)
assert.True(t, u.hasAgg)
assert.False(t, u.keepsName())
},
},
{
name: "gauge comparison keeps name",
query: `container_memory > 100`,
check: func(t *testing.T, u *coreUnit) {
assert.Equal(t, unitInstant, u.kind)
assert.True(t, u.keepsName())
},
},
{
name: "gauge arithmetic drops name",
query: `container_memory / 1024`,
check: func(t *testing.T, u *coreUnit) {
assert.Equal(t, unitInstant, u.kind)
assert.False(t, u.keepsName())
},
},
{
name: "avg_over_time",
query: `max by (node) (avg_over_time(load1[10m]))`,
check: func(t *testing.T, u *coreUnit) {
assert.Equal(t, unitOverTime, u.kind)
assert.Equal(t, "avg", u.overFn)
assert.Equal(t, int64(600_000), u.rangeMs)
},
},
{
name: "last_over_time keeps name",
query: `last_over_time(load1[10m])`,
check: func(t *testing.T, u *coreUnit) {
assert.Equal(t, unitOverTime, u.kind)
assert.Equal(t, "last", u.overFn)
assert.True(t, u.keepsName())
},
},
}
for _, tt := range tests {
t.Run(tt.name, func(t *testing.T) {
plan, ok := classify(parse(t, tt.query), testGrid(60_000))
require.True(t, ok, "expected transpilable")
require.True(t, plan.full, "expected full compilation")
require.Len(t, plan.units, 1)
tt.check(t, &plan.units[0].core)
})
}
}
func TestClassifyFallbackShapes(t *testing.T) {
queries := []struct {
name string
query string
step int64
}{
{"default-resolution subquery", `max_over_time(rate(x[5m])[30m:])`, 60_000},
{"at modifier", `sum(rate(x[5m] @ 1609746000))`, 60_000},
{"at modifier on gauge", `sum(container_memory @ 1609746000)`, 60_000},
{"sub-second step", `sum(rate(x[5m]))`, 500},
{"sub-second range", `sum(rate(x[1500ms]))`, 60_000},
{"by __name__ full", `sum by (__name__) (rate({__name__=~"a|b"}[5m]))`, 60_000},
{"quantile_over_time unsupported", `quantile_over_time(0.9, load1[10m])`, 60_000},
}
for _, tt := range queries {
t.Run(tt.name, func(t *testing.T) {
_, ok := classify(parse(t, tt.query), testGrid(tt.step))
assert.False(t, ok, "expected fallback for %s", tt.query)
})
}
}
func TestClassifyHybridShapes(t *testing.T) {
tests := []struct {
name string
query string
wantUnits int
wantRewritten string
}{
{
name: "histogram quantile",
query: `histogram_quantile(0.95, sum by (le) (rate(http_bucket[5m])))`,
wantUnits: 1,
wantRewritten: `histogram_quantile(0.95, __signoz_transpiled_0__)`,
},
{
name: "topk over compiled",
query: `topk(5, sum by (pod) (rate(x[5m])))`,
wantUnits: 1,
wantRewritten: `topk(5, __signoz_transpiled_0__)`,
},
{
name: "ratio of compiled units",
query: `sum(rate(a[5m])) / sum(rate(b[5m]))`,
wantUnits: 2,
wantRewritten: `__signoz_transpiled_0__ / __signoz_transpiled_1__`,
},
{
name: "or vector zero",
query: `sum(rate(a[5m])) or vector(0)`,
wantUnits: 1,
wantRewritten: `__signoz_transpiled_0__ or vector(0)`,
},
{
name: "quantile agg over compiled rate",
query: `quantile(0.9, rate(x[5m]))`,
wantUnits: 1,
wantRewritten: `quantile(0.9, __signoz_transpiled_0__)`,
},
{
name: "non-literal scalar side stays engine-side",
query: `sum(rate(x[5m])) * scalar(y)`,
wantUnits: 1,
wantRewritten: `__signoz_transpiled_0__ * scalar(y)`,
},
{
name: "compiled mixed with raw selector",
query: `sum by (pod) (rate(a[5m])) / on (pod) group_left () b`,
wantUnits: 1,
wantRewritten: `__signoz_transpiled_0__ / on (pod) group_left () b`,
},
}
for _, tt := range tests {
t.Run(tt.name, func(t *testing.T) {
plan, ok := classify(parse(t, tt.query), testGrid(60_000))
require.True(t, ok)
assert.False(t, plan.full)
assert.Len(t, plan.units, tt.wantUnits)
assert.Equal(t, tt.wantRewritten, plan.rewritten)
})
}
}
func TestClassifyHybridGuards(t *testing.T) {
t.Run("no substitution under on(__name__)", func(t *testing.T) {
plan, ok := classify(parse(t, `sum(rate(a[5m])) * on (__name__) b`), testGrid(60_000))
_ = plan
assert.False(t, ok, "matching on __name__ must not see synthetic names")
})
t.Run("no substitution inside @-pinned subquery", func(t *testing.T) {
_, ok := classify(parse(t, `max_over_time(rate(x[5m])[30m:1m] @ 1609746000)`), testGrid(60_000))
assert.False(t, ok)
})
}
// The alert-smoothing idiom: units inside a fixed-resolution subquery
// evaluate on the subquery grid — epoch-aligned multiples of the resolution,
// starting strictly after (outer start - range), exactly as the engine
// derives it.
func TestClassifySubqueryUnits(t *testing.T) {
grid := gridContext{startMs: 1_700_000_030_000, endMs: 1_700_007_200_000, stepMs: 60_000}
plan, ok := classify(parse(t, `min_over_time((sum by (ns) (increase(x[5m])))[10m:5m]) > 0`), grid)
require.True(t, ok)
require.False(t, plan.full)
require.Len(t, plan.units, 1)
assert.Equal(t, `min_over_time(__signoz_transpiled_0__[10m:5m]) > 0`, plan.rewritten)
unit := plan.units[0]
// lower bound = outer start - range = 1_699_999_430_000; first multiple
// of 300_000 strictly greater is 1_699_999_500_000.
assert.Equal(t, int64(1_699_999_500_000), unit.grid.startMs)
assert.Equal(t, grid.endMs, unit.grid.endMs)
assert.Equal(t, int64(300_000), unit.grid.stepMs)
assert.Equal(t, fnIncrease, unit.core.fn)
t.Run("subquery offset shifts the grid", func(t *testing.T) {
plan, ok := classify(parse(t, `max_over_time((sum(rate(x[5m])))[10m:5m] offset 30m)`), grid)
require.True(t, ok)
require.Len(t, plan.units, 1)
// lower = start - offset - range = 1_699_997_630_000 -> first
// multiple of 300_000 above = 1_699_997_700_000; end shifts too.
assert.Equal(t, int64(1_699_997_700_000), plan.units[0].grid.startMs)
assert.Equal(t, grid.endMs-1_800_000, plan.units[0].grid.endMs)
})
t.Run("mollusk ratio-inside-subquery idiom", func(t *testing.T) {
q := `min_over_time(((sum by (a) (rate(m1[5m]))) / (avg by (a) (m2)))[5m:1m])`
plan, ok := classify(parse(t, q), grid)
require.True(t, ok)
// Both sides compile on the subquery grid: the rate side and the
// gauge aggregation side; the engine joins them and smooths.
require.Len(t, plan.units, 2)
assert.Equal(t, int64(60_000), plan.units[0].grid.stepMs)
assert.Equal(t, unitInstant, plan.units[1].core.kind)
assert.Contains(t, plan.rewritten, `__signoz_transpiled_0__ / __signoz_transpiled_1__`)
})
}
func TestBuildUnitSQL(t *testing.T) {
unit := &coreUnit{
fn: fnRate,
rangeMs: 300_000,
hasAgg: true,
aggOp: parser.SUM,
by: true,
grouping: []string{"pod"},
matchers: []*labels.Matcher{mustMatcher(t, labels.MatchEqual, "__name__", "http_requests_total")},
}
sql, args, err := buildUnitSQL(unit, []string{"http_requests_total"}, []uint64{7, 42}, 1_699_999_700_000, 1_700_003_600_000, 1_700_000_000_000, 1_700_003_600_000, 60_000, 300_000)
require.NoError(t, err)
assert.Contains(t, sql, "timeSeriesRateToGrid(fromUnixTimestamp64Milli(1700000000000), fromUnixTimestamp64Milli(1700003600000), 60, 300)(fromUnixTimestamp64Milli(unix_milli), value)")
assert.Contains(t, sql, "unix_milli > ? AND unix_milli <= ?")
assert.Contains(t, sql, "bitAnd(flags, 1) = 0")
assert.Contains(t, sql, "sumForEach(grid)")
// The group-key join rides inside the shard query: distributed samples
// at the top level, the local series table in the join subquery, the
// grid aggregation grouped per (fingerprint, gkey) shard-side.
assert.Contains(t, sql, "FROM signoz_metrics.distributed_samples_v4 AS points INNER JOIN (SELECT fingerprint,")
assert.Contains(t, sql, "FROM signoz_metrics.time_series_v4 WHERE")
assert.Contains(t, sql, "GROUP BY points.fingerprint, series.gkey")
assert.Contains(t, sql, "points.fingerprint IN (7, 42)")
assert.Contains(t, sql, `toJSONString(arrayFilter(p -> p.2 != '' AND p.1 IN ('pod'),`)
assert.Contains(t, sql, "SETTINGS allow_experimental_ts_to_grid_aggregate_function = 1")
// Args follow placeholder order: the joined series subquery renders
// before the samples WHERE.
assert.Equal(t, []any{"http_requests_total", int64(1_699_999_200_000), int64(1_700_003_600_000), "http_requests_total", int64(1_699_999_700_000), int64(1_700_003_600_000)}, args)
}
func TestBuildUnitSQLIncreaseAndOffset(t *testing.T) {
unit := &coreUnit{
fn: fnIncrease,
rangeMs: 600_000,
offsetMs: 1_800_000,
matchers: []*labels.Matcher{mustMatcher(t, labels.MatchEqual, "__name__", "errors_total")},
}
sql, _, err := buildUnitSQL(unit, nil, []uint64{7}, 1_699_997_600_000, 1_700_001_800_000, 1_700_000_000_000, 1_700_003_600_000, 60_000, 300_000)
require.NoError(t, err)
// Grid and window shift by the offset; increase multiplies rate by the
// range in seconds.
assert.Contains(t, sql, "fromUnixTimestamp64Milli(1699998200000), fromUnixTimestamp64Milli(1700001800000)")
assert.Contains(t, sql, "arrayMap(x -> x * 600, timeSeriesRateToGrid")
assert.Contains(t, sql, "maxForEach(grid)")
}
func TestBuildUnitSQLOverLimitJoinOnly(t *testing.T) {
// Past the inline limit no fingerprint filter is rendered: the series
// join restricts to the matched fingerprints on its own.
unit := &coreUnit{
fn: fnRate,
rangeMs: 300_000,
hasAgg: true,
aggOp: parser.SUM,
by: true,
matchers: []*labels.Matcher{mustMatcher(t, labels.MatchEqual, "__name__", "http_requests_total")},
}
sql, _, err := buildUnitSQL(unit, []string{"http_requests_total"}, nil, 1_699_999_700_000, 1_700_003_600_000, 1_700_000_000_000, 1_700_003_600_000, 60_000, 300_000)
require.NoError(t, err)
assert.NotContains(t, sql, "points.fingerprint IN")
assert.Contains(t, sql, "INNER JOIN (SELECT fingerprint,")
assert.Contains(t, sql, "FROM signoz_metrics.time_series_v4 WHERE")
}
func TestBuildUnitSQLOverLimitWindowedSemiJoin(t *testing.T) {
// The windowed *_over_time fan-out has no series join, so the over-limit
// regime falls back to the shard-local semi-join instead of expanding
// every series of the metric.
unit := &coreUnit{
kind: unitOverTime,
overFn: "avg",
rangeMs: 600_000,
matchers: []*labels.Matcher{mustMatcher(t, labels.MatchEqual, "__name__", "node_load1")},
}
sql, _, err := buildUnitSQL(unit, []string{"node_load1"}, nil, 1_699_999_400_000, 1_700_003_600_000, 1_700_000_000_000, 1_700_003_600_000, 60_000, 300_000)
require.NoError(t, err)
assert.Contains(t, sql, "points.fingerprint IN (SELECT fingerprint FROM signoz_metrics.time_series_v4 WHERE ")
assert.Contains(t, sql, "ARRAY JOIN range(")
}
func TestApplyScalarOps(t *testing.T) {
f := func(v float64) *float64 { return &v }
t.Run("arithmetic chain", func(t *testing.T) {
values := []*float64{f(2), nil, f(4)}
applyScalarOps([]scalarOp{{op: parser.MUL, scalar: 100}, {op: parser.ADD, scalar: 1}}, values)
require.NotNil(t, values[0])
assert.Equal(t, 201.0, *values[0])
assert.Nil(t, values[1])
assert.Equal(t, 401.0, *values[2])
})
t.Run("comparison filters points", func(t *testing.T) {
values := []*float64{f(1), f(10)}
applyScalarOps([]scalarOp{{op: parser.GTR, scalar: 5}}, values)
assert.Nil(t, values[0])
require.NotNil(t, values[1])
assert.Equal(t, 10.0, *values[1], "filter comparisons keep the original value")
})
t.Run("bool comparison emits 0/1", func(t *testing.T) {
values := []*float64{f(1), f(10)}
applyScalarOps([]scalarOp{{op: parser.GTR, scalar: 5, returnBool: true}}, values)
assert.Equal(t, 0.0, *values[0])
assert.Equal(t, 1.0, *values[1])
})
t.Run("scalar on left division", func(t *testing.T) {
values := []*float64{f(4)}
applyScalarOps([]scalarOp{{op: parser.DIV, scalar: 100, scalarOnLeft: true}}, values)
assert.Equal(t, 25.0, *values[0])
})
}
func TestLabelsFromGroupKey(t *testing.T) {
lset, err := labelsFromGroupKey(`[["pod","api-0"],["ns","prod"]]`)
require.NoError(t, err)
assert.Equal(t, "api-0", lset.Get("pod"))
assert.Equal(t, "prod", lset.Get("ns"))
empty, err := labelsFromGroupKey(`[]`)
require.NoError(t, err)
assert.True(t, empty.IsEmpty())
}
// testGrid is a 2h query grid ending on a round timestamp.
func testGrid(stepMs int64) gridContext {
return gridContext{startMs: 1_700_000_000_000, endMs: 1_700_007_200_000, stepMs: stepMs}
}
// A bool comparison returns 0/1, not the sample, so the engine drops
// __name__; keeping it would change downstream vector matching.
func TestKeepsName_BoolComparisonDropsName(t *testing.T) {
plan, ok := classify(parse(t, `up > bool 0`), testGrid(60_000))
require.True(t, ok)
assert.False(t, plan.units[0].core.keepsName())
plan, ok = classify(parse(t, `up > 0`), testGrid(60_000))
require.True(t, ok)
assert.True(t, plan.units[0].core.keepsName())
}
// timeSeriesLastToGrid widens its window to max(window, step) — probed on
// 25.12 — so Last-style units at window < step must fall back or they would
// resurrect samples the engine's lookback already dropped.
func TestTryExecuteRange_LastStyleWindowBelowStepFallsBack(t *testing.T) {
c, _ := newTestClient(t, prometheus.ClickhouseV2Config{})
e := &executor{client: c, parser: prometheus.NewParser()}
start := time.UnixMilli(1_700_000_000_000)
end := time.UnixMilli(1_700_003_600_000)
_, ok, err := e.TryExecuteRange(context.Background(), `sum by (pod) (up)`, start, end, time.Hour)
require.NoError(t, err)
assert.False(t, ok, "instant selection at step > lookback must not transpile")
_, ok, err = e.TryExecuteRange(context.Background(), `last_over_time(up[10m])`, start, end, time.Hour)
require.NoError(t, err)
assert.False(t, ok, "last_over_time at range < step must not transpile")
}
// Transpiled results never pass the engine's sample limiter, so the grid
// cells (series x grid width) must be budgeted before the arrays exist —
// otherwise a wide query rebuilds the OOM this provider exists to prevent.
func TestExecuteUnit_GridCellBudget(t *testing.T) {
c, store := newTestClient(t, prometheus.ClickhouseV2Config{MaxFetchedSamples: 100})
e := &executor{client: c, parser: prometheus.NewParser()}
store.Mock().ExpectQuery("SELECT fingerprint, any\\(labels\\)").WithArgs("up", int64(1_699_999_200_000), int64(1_700_003_600_000)).WillReturnRows(cmock.NewRows(seriesCols, [][]any{
{uint64(1), `{"__name__":"up","instance":"a"}`},
{uint64(2), `{"__name__":"up","instance":"b"}`},
}))
plan, ok := classify(parse(t, `sum(rate(up[5m]))`), gridContext{startMs: 1_700_000_000_000, endMs: 1_700_003_600_000, stepMs: 60_000})
require.True(t, ok)
var cells atomic.Int64
// 2 series x 61 grid points = 122 cells > 100.
_, err := e.executeUnit(context.Background(), &plan.units[0].core, plan.units[0].grid, &cells)
require.Error(t, err)
assert.True(t, errors.Ast(err, errors.TypeInvalidInput), "budget refusal must be typed invalid input, got %v", err)
}
// Two metrics collapsing onto one labelset after the name drop is the
// engine's duplicate-labelset error; silently merging them would invent a
// series no engine would produce.
func TestExecuteUnit_NameCollisionErrors(t *testing.T) {
c, store := newTestClient(t, prometheus.ClickhouseV2Config{})
e := &executor{client: c, parser: prometheus.NewParser()}
store.Mock().ExpectQuery("SELECT fingerprint, any\\(labels\\)").WithArgs("^(?:a|b)$", int64(1_699_999_200_000), int64(1_700_003_600_000)).WillReturnRows(cmock.NewRows(seriesCols, [][]any{
{uint64(1), `{"__name__":"a","job":"x"}`},
{uint64(2), `{"__name__":"b","job":"x"}`},
}))
store.Mock().ExpectQuery("SELECT gkey").
WithArgs("^(?:a|b)$", int64(1_699_999_200_000), int64(1_700_003_600_000), "a", "b", int64(1_699_999_700_000), int64(1_700_003_600_000)).
WillReturnRows(cmock.NewRows(gkeyCols, [][]any{
{`[["__name__","a"],["job","x"]]`, []*float64{f64(1)}},
{`[["__name__","b"],["job","x"]]`, []*float64{f64(2)}},
}))
plan, ok := classify(parse(t, `rate({__name__=~"a|b"}[5m])`), gridContext{startMs: 1_700_000_000_000, endMs: 1_700_003_600_000, stepMs: 60_000})
require.True(t, ok)
var cells atomic.Int64
_, err := e.executeUnit(context.Background(), &plan.units[0].core, plan.units[0].grid, &cells)
require.Error(t, err)
assert.Contains(t, err.Error(), "vector cannot contain metrics with the same labelset")
}
var gkeyCols = []cmock.ColumnType{
{Name: "gkey", Type: "String"},
{Name: "grid", Type: "Array(Nullable(Float64))"},
}
func f64(v float64) *float64 { return &v }

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