chore: change tests to reflect non-normalised support for scope

For scope name and version fields

.github/CODEOWNERS

@@ -109,25 +109,6 @@ go.mod @therealpandey
 /pkg/modules/role/ @therealpandey
 /pkg/types/coretypes/ @therealpandey @vikrantgupta25
 
-/frontend/src/hooks/useAuthZ/ @H4ad
-/frontend/src/components/GuardAuthZ/ @H4ad
-/frontend/src/components/AuthZTooltip/ @H4ad
-/frontend/src/components/createGuardedRoute/ @H4ad
-/frontend/src/container/RolesSettings/ @H4ad
-/frontend/src/components/RolesSelect/ @H4ad
-/frontend/src/pages/MembersSettings/ @H4ad
-/frontend/src/container/MembersSettings/ @H4ad
-/frontend/src/components/MembersTable/ @H4ad
-/frontend/src/components/EditMemberDrawer/ @H4ad
-/frontend/src/components/InviteMembersModal/ @H4ad
-/frontend/src/hooks/member/ @H4ad
-/frontend/src/pages/ServiceAccountsSettings/ @H4ad
-/frontend/src/container/ServiceAccountsSettings/ @H4ad
-/frontend/src/components/ServiceAccountsTable/ @H4ad
-/frontend/src/components/ServiceAccountDrawer/ @H4ad
-/frontend/src/components/CreateServiceAccountModal/ @H4ad
-/frontend/src/hooks/serviceAccount/ @H4ad
-
 # IdentN Owners
 
 /pkg/identn/ @therealpandey
@@ -137,9 +118,6 @@ go.mod @therealpandey
 
 /tests/integration/ @therealpandey
 
-# e2e tests
-/tests/e2e/ @AshwinBhatkal
-
 # Flagger Owners
 
 /pkg/flagger/ @therealpandey
@@ -184,106 +162,3 @@ go.mod @therealpandey
 /frontend/src/lib/dashboard/ @SigNoz/pulse-frontend
 /frontend/src/lib/dashboardVariables/ @SigNoz/pulse-frontend
 /frontend/src/components/NewSelect/ @SigNoz/pulse-frontend
-
-## Dashboard V2
-/frontend/src/pages/DashboardPageV2/ @SigNoz/pulse-frontend
-/frontend/src/pages/DashboardsListPageV2/ @SigNoz/pulse-frontend
-
-## Infrastructure Monitoring
-/frontend/src/pages/InfrastructureMonitoring/ @SigNoz/pulse-frontend
-/frontend/src/container/InfraMonitoringHosts/ @SigNoz/pulse-frontend
-/frontend/src/container/InfraMonitoringK8s/ @SigNoz/pulse-frontend
-
-## Alerts
-/frontend/src/pages/AlertList/ @SigNoz/pulse-frontend
-/frontend/src/pages/AlertDetails/ @SigNoz/pulse-frontend
-/frontend/src/pages/CreateAlert/ @SigNoz/pulse-frontend
-/frontend/src/pages/EditRules/ @SigNoz/pulse-frontend
-/frontend/src/container/AlertHistory/ @SigNoz/pulse-frontend
-/frontend/src/container/CreateAlertRule/ @SigNoz/pulse-frontend
-/frontend/src/container/CreateAlertV2/ @SigNoz/pulse-frontend
-/frontend/src/container/EditAlertV2/ @SigNoz/pulse-frontend
-/frontend/src/container/FormAlertRules/ @SigNoz/pulse-frontend
-/frontend/src/container/ListAlertRules/ @SigNoz/pulse-frontend
-/frontend/src/container/TriggeredAlerts/ @SigNoz/pulse-frontend
-/frontend/src/container/AnomalyAlertEvaluationView/ @SigNoz/pulse-frontend
-
-## Notification Channels
-/frontend/src/pages/ChannelsEdit/ @SigNoz/pulse-frontend
-/frontend/src/pages/ChannelsNew/ @SigNoz/pulse-frontend
-/frontend/src/container/AllAlertChannels/ @SigNoz/pulse-frontend
-/frontend/src/container/CreateAlertChannels/ @SigNoz/pulse-frontend
-/frontend/src/container/EditAlertChannels/ @SigNoz/pulse-frontend
-
-## OpenAPI Schema - Generated
-/frontend/src/api/generated/services/ @therealpandey @vikrantgupta25 @srikanthccv
-/docs/api/openapi.yml @therealpandey @vikrantgupta25 @srikanthccv
-
-## Logs
-/frontend/src/pages/Logs/ @SigNoz/events-frontend
-/frontend/src/pages/LogsExplorer/ @SigNoz/events-frontend
-/frontend/src/pages/LogsModulePage/ @SigNoz/events-frontend
-/frontend/src/pages/LogsSettings/ @SigNoz/events-frontend
-/frontend/src/pages/LiveLogs/ @SigNoz/events-frontend
-/frontend/src/container/LogsExplorerChart/ @SigNoz/events-frontend
-/frontend/src/container/LogsExplorerContext/ @SigNoz/events-frontend
-/frontend/src/container/LogsExplorerList/ @SigNoz/events-frontend
-/frontend/src/container/LogsExplorerTable/ @SigNoz/events-frontend
-/frontend/src/container/LogsExplorerViews/ @SigNoz/events-frontend
-/frontend/src/container/LogsFilters/ @SigNoz/events-frontend
-/frontend/src/container/LogsSearchFilter/ @SigNoz/events-frontend
-/frontend/src/container/LogsTable/ @SigNoz/events-frontend
-/frontend/src/container/LogsAggregate/ @SigNoz/events-frontend
-/frontend/src/container/LogsContextList/ @SigNoz/events-frontend
-/frontend/src/container/LogsIndexToFields/ @SigNoz/events-frontend
-/frontend/src/container/LogsLoading/ @SigNoz/events-frontend
-/frontend/src/container/LogsPanelTable/ @SigNoz/events-frontend
-/frontend/src/container/LogControls/ @SigNoz/events-frontend
-/frontend/src/container/LogDetailedView/ @SigNoz/events-frontend
-/frontend/src/container/LogExplorerQuerySection/ @SigNoz/events-frontend
-/frontend/src/container/LogLiveTail/ @SigNoz/events-frontend
-/frontend/src/container/LiveLogs/ @SigNoz/events-frontend
-/frontend/src/container/EmptyLogsSearch/ @SigNoz/events-frontend
-/frontend/src/container/NoLogs/ @SigNoz/events-frontend
-/frontend/src/components/Logs/ @SigNoz/events-frontend
-/frontend/src/components/LogDetail/ @SigNoz/events-frontend
-/frontend/src/components/LogsFormatOptionsMenu/ @SigNoz/events-frontend
-/frontend/src/hooks/logs/ @SigNoz/events-frontend
-
-## Logs Pipelines
-/frontend/src/pages/Pipelines/ @SigNoz/events-frontend
-/frontend/src/container/PipelinePage/ @SigNoz/events-frontend
-
-## Traces / Trace Explorer
-/frontend/src/pages/Trace/ @SigNoz/events-frontend
-/frontend/src/pages/TracesExplorer/ @SigNoz/events-frontend
-/frontend/src/pages/TracesModulePage/ @SigNoz/events-frontend
-/frontend/src/container/Trace/ @SigNoz/events-frontend
-/frontend/src/container/TracesExplorer/ @SigNoz/events-frontend
-/frontend/src/container/TracesTableComponent/ @SigNoz/events-frontend
-
-## Trace Funnels
-/frontend/src/pages/TracesFunnels/ @SigNoz/events-frontend
-/frontend/src/pages/TracesFunnelDetails/ @SigNoz/events-frontend
-/frontend/src/hooks/TracesFunnels/ @SigNoz/events-frontend
-
-## Trace Details
-/frontend/src/pages/TraceDetailsV3/ @SigNoz/events-frontend
-/frontend/src/pages/TraceDetailOldRedirect/ @SigNoz/events-frontend
-/frontend/src/hooks/trace/ @SigNoz/events-frontend
-
-## Exceptions
-/frontend/src/pages/AllErrors/ @SigNoz/events-frontend
-/frontend/src/pages/ErrorDetails/ @SigNoz/events-frontend
-/frontend/src/container/AllError/ @SigNoz/events-frontend
-/frontend/src/container/ErrorDetails/ @SigNoz/events-frontend
-
-## External APIs
-/frontend/src/pages/ApiMonitoring/ @SigNoz/events-frontend
-/frontend/src/container/ApiMonitoring/ @SigNoz/events-frontend
-
-## Messaging Queues
-/frontend/src/pages/MessagingQueues/ @SigNoz/events-frontend
-/frontend/src/components/MessagingQueues/ @SigNoz/events-frontend
-/frontend/src/components/MessagingQueueHealthCheck/ @SigNoz/events-frontend
-/frontend/src/hooks/messagingQueue/ @SigNoz/events-frontend

.github/workflows/build-enterprise.yaml

@@ -58,6 +58,8 @@ jobs:
         run: |
           mkdir -p frontend
           echo 'CI=1' > frontend/.env
+          echo 'VITE_INTERCOM_APP_ID="${{ secrets.INTERCOM_APP_ID }}"' >> frontend/.env
+          echo 'VITE_SEGMENT_ID="${{ secrets.SEGMENT_ID }}"' >> frontend/.env
           echo 'VITE_SENTRY_AUTH_TOKEN="${{ secrets.SENTRY_AUTH_TOKEN }}"' >> frontend/.env
           echo 'VITE_SENTRY_ORG="${{ secrets.SENTRY_ORG }}"' >> frontend/.env
           echo 'VITE_SENTRY_PROJECT_ID="${{ secrets.SENTRY_PROJECT_ID }}"' >> frontend/.env
@@ -69,8 +71,6 @@ jobs:
           echo 'VITE_APPCUES_APP_ID="${{ secrets.APPCUES_APP_ID }}"' >> frontend/.env
           echo 'VITE_PYLON_IDENTITY_SECRET="${{ secrets.PYLON_IDENTITY_SECRET }}"' >> frontend/.env
           echo 'VITE_DOCS_BASE_URL="https://signoz.io"' >> frontend/.env
-          echo 'VITE_ENVIRONMENT="production"' >> frontend/.env
-          echo 'VITE_VERSION="${{ steps.build-info.outputs.version }}"' >> frontend/.env
       - name: cache-dotenv
         uses: actions/cache@v4
         with:

.github/workflows/build-staging.yaml

@@ -64,18 +64,12 @@ jobs:
         run: |
           mkdir -p frontend
           echo 'CI=1' > frontend/.env
-          echo 'VITE_SENTRY_AUTH_TOKEN="${{ secrets.SENTRY_AUTH_TOKEN }}"' >> frontend/.env
-          echo 'VITE_SENTRY_ORG="${{ secrets.SENTRY_ORG }}"' >> frontend/.env
-          echo 'VITE_SENTRY_PROJECT_ID="${{ secrets.SENTRY_PROJECT_ID }}"' >> frontend/.env
-          echo 'VITE_SENTRY_DSN="${{ secrets.SENTRY_DSN }}"' >> frontend/.env
           echo 'VITE_TUNNEL_URL="${{ secrets.NP_TUNNEL_URL }}"' >> frontend/.env
           echo 'VITE_TUNNEL_DOMAIN="${{ secrets.NP_TUNNEL_DOMAIN }}"' >> frontend/.env
           echo 'VITE_PYLON_APP_ID="${{ secrets.NP_PYLON_APP_ID }}"' >> frontend/.env
           echo 'VITE_APPCUES_APP_ID="${{ secrets.NP_APPCUES_APP_ID }}"' >> frontend/.env
           echo 'VITE_PYLON_IDENTITY_SECRET="${{ secrets.NP_PYLON_IDENTITY_SECRET }}"' >> frontend/.env
           echo 'VITE_DOCS_BASE_URL="https://staging.signoz.io"' >> frontend/.env
-          echo 'VITE_ENVIRONMENT="staging"' >> frontend/.env
-          echo 'VITE_VERSION="${{ steps.build-info.outputs.version }}"' >> frontend/.env
       - name: cache-dotenv
         uses: actions/cache@v4
         with:

.github/workflows/e2eci.yaml

@@ -70,11 +70,7 @@ jobs:
           cd tests/e2e && pnpm install --frozen-lockfile
       - name: playwright-browsers
         run: |
-          docker create --name pw mcr.microsoft.com/playwright:v1.57.0-noble
-          docker cp pw:/ms-playwright "$RUNNER_TEMP/ms-playwright"
-          docker rm pw
-          echo "PLAYWRIGHT_BROWSERS_PATH=$RUNNER_TEMP/ms-playwright" >> "$GITHUB_ENV"
-          cd tests/e2e && pnpm playwright install-deps ${{ matrix.project }}
+          cd tests/e2e && pnpm playwright install --with-deps ${{ matrix.project }}
       - name: bring-up-stack
         run: |
           cd tests && \

.github/workflows/goci.yaml

@@ -123,37 +123,3 @@ jobs:
         run: |
           go run cmd/enterprise/*.go generate authz
           git diff --compact-summary --exit-code || (echo; echo "Unexpected difference in authz permissions. Run go run cmd/enterprise/*.go generate authz locally and commit."; exit 1)
-  web-settings:
-    if: |
-      github.event_name == 'merge_group' ||
-      (github.event_name == 'pull_request' && ! github.event.pull_request.head.repo.fork && github.event.pull_request.user.login != 'dependabot[bot]' && ! contains(github.event.pull_request.labels.*.name, 'safe-to-test')) ||
-      (github.event_name == 'pull_request_target' && contains(github.event.pull_request.labels.*.name, 'safe-to-test'))
-    runs-on: ubuntu-latest
-    steps:
-      - name: self-checkout
-        uses: actions/checkout@v4
-      - name: go-install
-        uses: actions/setup-go@v5
-        with:
-          go-version: "1.24"
-      - name: generate-web-settings
-        run: |
-          go run cmd/enterprise/*.go generate config web-settings
-          git diff --compact-summary --exit-code || (echo; echo "Unexpected difference in web settings schema. Run go run cmd/enterprise/*.go generate config web-settings locally and commit."; exit 1)
-  transaction-groups:
-    if: |
-      github.event_name == 'merge_group' ||
-      (github.event_name == 'pull_request' && ! github.event.pull_request.head.repo.fork && github.event.pull_request.user.login != 'dependabot[bot]' && ! contains(github.event.pull_request.labels.*.name, 'safe-to-test')) ||
-      (github.event_name == 'pull_request_target' && contains(github.event.pull_request.labels.*.name, 'safe-to-test'))
-    runs-on: ubuntu-latest
-    steps:
-      - name: self-checkout
-        uses: actions/checkout@v4
-      - name: go-install
-        uses: actions/setup-go@v5
-        with:
-          go-version: "1.24"
-      - name: generate-transaction-groups
-        run: |
-          go run cmd/enterprise/*.go generate config transaction-groups
-          git diff --compact-summary --exit-code || (echo; echo "Unexpected difference in transaction groups schema. Run go run cmd/enterprise/*.go generate config transaction-groups locally and commit."; exit 1)

.github/workflows/gor-signoz.yaml

@@ -24,6 +24,8 @@ jobs:
       - name: dotenv-frontend
         working-directory: frontend
         run: |
+          echo 'VITE_INTERCOM_APP_ID="${{ secrets.INTERCOM_APP_ID }}"' > .env
+          echo 'VITE_SEGMENT_ID="${{ secrets.SEGMENT_ID }}"' >> .env
           echo 'VITE_SENTRY_AUTH_TOKEN="${{ secrets.SENTRY_AUTH_TOKEN }}"' >> .env
           echo 'VITE_SENTRY_ORG="${{ secrets.SENTRY_ORG }}"' >> .env
           echo 'VITE_SENTRY_PROJECT_ID="${{ secrets.SENTRY_PROJECT_ID }}"' >> .env
@@ -35,8 +37,6 @@ jobs:
           echo 'VITE_APPCUES_APP_ID="${{ secrets.APPCUES_APP_ID }}"' >> .env
           echo 'VITE_PYLON_IDENTITY_SECRET="${{ secrets.PYLON_IDENTITY_SECRET }}"' >> .env
           echo 'VITE_DOCS_BASE_URL="https://signoz.io"' >> .env
-          echo 'VITE_ENVIRONMENT="production"' >> .env
-          echo 'VITE_VERSION="${{ github.ref_name }}"' >> .env
       - name: node-setup
         uses: actions/setup-node@v5
         with:

.github/workflows/integrationci.yaml

@@ -39,12 +39,10 @@ jobs:
       matrix:
         suite:
           - alerts
-          - basepath
           - callbackauthn
           - cloudintegrations
           - dashboard
           - ingestionkeys
-          - inframonitoring
           - logspipelines
           - passwordauthn
           - preference
@@ -54,7 +52,6 @@ jobs:
           - rootuser
           - serviceaccount
           - querier_json_body
-          - querier_skip_resource_fingerprint
           - ttl
         sqlstore-provider:
           - postgres
@@ -85,7 +82,7 @@ jobs:
         run: |
           cd tests && uv sync
       - name: webdriver
-        if: matrix.suite == 'callbackauthn' || matrix.suite == 'basepath'
+        if: matrix.suite == 'callbackauthn'
         run: |
           wget -q -O - https://dl-ssl.google.com/linux/linux_signing_key.pub | sudo apt-key add -
           echo "deb http://dl.google.com/linux/chrome/deb/ stable main" | sudo tee -a /etc/apt/sources.list.d/google-chrome.list

.github/workflows/jsci.yaml

@@ -56,6 +56,17 @@ jobs:
       PRIMUS_REF: main
       JS_SRC: frontend
       JS_PKG_MANAGER: pnpm
+  languages:
+    if: |
+      github.event_name == 'merge_group' ||
+      (github.event_name == 'pull_request' && ! github.event.pull_request.head.repo.fork && github.event.pull_request.user.login != 'dependabot[bot]' && ! contains(github.event.pull_request.labels.*.name, 'safe-to-test')) ||
+      (github.event_name == 'pull_request_target' && contains(github.event.pull_request.labels.*.name, 'safe-to-test'))
+    runs-on: ubuntu-latest
+    steps:
+      - name: self-checkout
+        uses: actions/checkout@v4
+      - name: run
+        run: bash frontend/scripts/validate-md-languages.sh
   openapi:
     if: |
       github.event_name == 'merge_group' ||
@@ -79,26 +90,3 @@ jobs:
         run: |
           cd frontend && pnpm generate:api
           git diff --compact-summary --exit-code || (echo; echo "Unexpected difference in generated api clients. Run pnpm generate:api in frontend/ locally and commit."; exit 1)
-  web-settings:
-    if: |
-      github.event_name == 'merge_group' ||
-      (github.event_name == 'pull_request' && ! github.event.pull_request.head.repo.fork && github.event.pull_request.user.login != 'dependabot[bot]' && ! contains(github.event.pull_request.labels.*.name, 'safe-to-test')) ||
-      (github.event_name == 'pull_request_target' && contains(github.event.pull_request.labels.*.name, 'safe-to-test'))
-    runs-on: ubuntu-latest
-    steps:
-      - name: self-checkout
-        uses: actions/checkout@v4
-      - name: node-install
-        uses: actions/setup-node@v5
-        with:
-          node-version: "22"
-      - name: install-pnpm
-        uses: pnpm/action-setup@v6
-        with:
-          version: 10
-      - name: install-frontend
-        run: cd frontend && pnpm install
-      - name: generate-web-settings
-        run: |
-          cd frontend && pnpm generate:config:web-settings
-          git diff --compact-summary --exit-code || (echo; echo "Unexpected difference in generated web settings types. Run pnpm generate:config:web-settings in frontend/ locally and commit."; exit 1)

.gitignore

@@ -231,4 +231,5 @@ cython_debug/
 # LSP config files
 pyrightconfig.json
 
-
+# agents
+*settings.local.json

.mockery.yml

@@ -8,14 +8,6 @@ packages:
       filename: "alertmanager.go"
       structname: 'Mock{{.InterfaceName}}'
       pkgname: '{{.SrcPackageName}}test'
-  github.com/SigNoz/signoz/pkg/types/alertmanagertypes:
-    interfaces:
-      MaintenanceStore:
-    config:
-      dir: '{{.InterfaceDir}}/alertmanagertypestest'
-      filename: "maintenance.go"
-      structname: 'Mock{{.InterfaceName}}'
-      pkgname: '{{.SrcPackageName}}test'
   github.com/SigNoz/signoz/pkg/tokenizer:
     config:
       all: true

.vscode/settings.json

@@ -19,8 +19,5 @@
     "editor.defaultFormatter": "vscode.html-language-features"
   },
   "python-envs.defaultEnvManager": "ms-python.python:system",
-  "python-envs.pythonProjects": [],
-  "[json]": {
-    "editor.defaultFormatter": "vscode.json-language-features"
-  }
+  "python-envs.pythonProjects": []
 }

README.de-de.md

@@ -1,190 +1,197 @@
 <p align="center">
-  <picture>
-    <source media="(prefers-color-scheme: dark)" srcset="docs/readme-assets/signoz-hero-dark.png" width="900">
-    <source media="(prefers-color-scheme: light)" srcset="docs/readme-assets/signoz-hero-light.png" width="900">
-    <img alt="SigNoz - Observability nach deinen Bedingungen, basierend auf offenen Standards." src="docs/readme-assets/signoz-hero-light.png" width="900">
-  </picture>
+  <img src="https://res.cloudinary.com/dcv3epinx/image/upload/v1618904450/signoz-images/LogoGithub_sigfbu.svg" alt="SigNoz-logo" width="240" />
+
+  <p align="center">Überwache deine Anwendungen und behebe Probleme in deinen bereitgestellten Anwendungen. SigNoz ist eine Open Source Alternative zu DataDog, New Relic, etc.</p>
 </p>
 
 <p align="center">
-  <a href="README.md">English</a> ·
-  <a href="README.zh-cn.md">中文</a> ·
-  <a href="README.pt-br.md">Português</a>
+    <img alt="Downloads" src="https://img.shields.io/docker/pulls/signoz/query-service?label=Downloads"> </a>
+    <img alt="GitHub issues" src="https://img.shields.io/github/issues/signoz/signoz"> </a>
+    <a href="https://twitter.com/intent/tweet?text=Monitor%20your%20applications%20and%20troubleshoot%20problems%20with%20SigNoz,%20an%20open-source%20alternative%20to%20DataDog,%20NewRelic.&url=https://signoz.io/&via=SigNozHQ&hashtags=opensource,signoz,observability">
+        <img alt="tweet" src="https://img.shields.io/twitter/url/http/shields.io.svg?style=social"> </a>
 </p>
 
-<p align="center">
-  <a href="https://github.com/SigNoz/signoz/issues"><img alt="GitHub issues" src="https://img.shields.io/github/issues/SigNoz/signoz"></a>
-  <a href="https://github.com/SigNoz/signoz/releases"><img alt="GitHub release" src="https://img.shields.io/github/v/release/SigNoz/signoz?label=release"></a>
-  <a href="https://signoz.io/slack"><img alt="Slack community" src="https://img.shields.io/badge/slack-community-4A154B?logo=slack&logoColor=white"></a>
-  <a href="https://www.linkedin.com/company/signozio/"><img alt="LinkedIn" src="https://img.shields.io/badge/linkedin-SigNoz-0A66C2?logo=linkedin&logoColor=white"></a>
-  <a href="https://twitter.com/intent/tweet?text=Monitor%20your%20applications%20and%20troubleshoot%20problems%20with%20SigNoz,%20an%20open-source%20alternative%20to%20DataDog,%20NewRelic.&url=https://signoz.io/&via=SigNozHQ&hashtags=opensource,signoz,observability"><img alt="Tweet" src="https://img.shields.io/twitter/url/http/shields.io.svg?style=social"></a>
-</p>
+<h3 align="center">
+  <a href="https://signoz.io/docs"><b>Dokumentation</b></a> &bull;
+  <a href="https://github.com/SigNoz/signoz/blob/main/README.md"><b>Readme auf Englisch </b></a> &bull;
+  <a href="https://github.com/SigNoz/signoz/blob/main/README.zh-cn.md"><b>ReadMe auf Chinesisch</b></a> &bull;
+  <a href="https://github.com/SigNoz/signoz/blob/main/README.pt-br.md"><b>ReadMe auf Portugiesisch</b></a> &bull;
+  <a href="https://signoz.io/slack"><b>Slack Community</b></a> &bull;
+  <a href="https://twitter.com/SigNozHq"><b>Twitter</b></a>
+</h3>
 
-SigNoz ist eine Open-Source-Observability-Plattform auf Basis von OpenTelemetry. Wir bauen eine Enterprise-taugliche Alternative zu fragmentierten Monitoring-Stacks, mit Logs, Metriken, Traces, Alerts und Dashboards an einem Ort.
+##
 
-### Wähle, wie du SigNoz betreibst
+SigNoz hilft Entwicklern, Anwendungen zu überwachen und Probleme in ihren bereitgestellten Anwendungen zu beheben. Mit SigNoz können Sie Folgendes tun:
 
-#### SigNoz Cloud (empfohlen)
+👉 Visualisieren Sie Metriken, Traces und Logs in einer einzigen Oberfläche.
 
-Vollständig verwaltetes SigNoz mit 30 Tagen kostenloser Testphase, ohne Kreditkarte, nutzungsbasierter Preisgestaltung ab 49 USD und regionalem Datenhosting.
+👉 Sie können Metriken wie die p99-Latenz, Fehlerquoten für Ihre Dienste, externe API-Aufrufe und individuelle Endpunkte anzeigen.
 
-[**Kostenlos starten →**](https://signoz.io/teams/)
+👉 Sie können die Ursache des Problems ermitteln, indem Sie zu den genauen Traces gehen, die das Problem verursachen, und detaillierte Flammenbilder einzelner Anfragetraces anzeigen.
 
-#### Enterprise
+👉 Führen Sie Aggregationen auf Trace-Daten durch, um geschäftsrelevante Metriken zu erhalten.
 
-Enterprise Cloud, BYOC oder Enterprise Self-Hosted mit Compliance, Support, benutzerdefinierter Aufbewahrung, RBAC, Ingestion Controls, Datenresidenz und Regionsauswahl.
+👉 Filtern und Abfragen von Logs, Erstellen von Dashboards und Benachrichtigungen basierend auf Attributen in den Logs.
 
-[**Enterprise entdecken →**](https://signoz.io/enterprise/)
+👉 Automatische Aufzeichnung von Ausnahmen in Python, Java, Ruby und Javascript.
 
-#### Community
+👉 Einfache Einrichtung von Benachrichtigungen mit dem selbst erstellbaren Abfrage-Builder.
 
-Kostenloses Open-Source-SigNoz, das in deiner eigenen Infrastruktur läuft. Deployment mit Docker, Kubernetes oder Linux, während du die volle Kontrolle über deine Datenebene behältst.
+##
 
-[**SigNoz installieren →**](https://signoz.io/docs/install/self-host/)
+### Anwendung Metriken
 
-### Was kannst du überwachen?
+![application_metrics](https://user-images.githubusercontent.com/83692067/226637410-900dbc5e-6705-4b11-a10c-bd0faeb2a92f.png)
 
-SigNoz hilft Teams, Produktionsprobleme schneller zu debuggen, indem Logs, Metriken, Traces, Alerts, Dashboards, Exceptions und agent-native Workflows an einem Ort verbunden werden.
+### Verteiltes Tracing
 
-#### APM-Überblick
+<img width="2068" alt="distributed_tracing_2 2" src="https://user-images.githubusercontent.com/83692067/226536447-bae58321-6a22-4ed3-af80-e3e964cb3489.png">
 
-Überwache Service-Latenz, Fehlerrate, Durchsatz, Apdex, wichtige Endpunkte, Datenbankaufrufe und externe Aufrufe.
+<img width="2068" alt="distributed_tracing_1" src="https://user-images.githubusercontent.com/83692067/226536462-939745b6-4f9d-45a6-8016-814837e7f7b4.png">
 
-<p align="center">
-  <img alt="SigNoz APM-Dashboard mit Latenz, Durchsatz, Apdex und wichtigen Operationen" src="docs/readme-assets/monitor/apm.png" width="900">
-</p>
+### Log Verwaltung
 
-Mehr erfahren: [APM-Dokumentation](https://signoz.io/docs/instrumentation/overview/)
+<img width="2068" alt="logs_management" src="https://user-images.githubusercontent.com/83692067/226536482-b8a5c4af-b69c-43d5-969c-338bd5eaf1a5.png">
 
-#### Log-Management
+### Infrastruktur Überwachung
 
-Erfasse, suche, aggregiere und korreliere Logs mit Traces und Metriken über einen visuellen Query Builder.
+<img width="2068" alt="infrastructure_monitoring" src="https://user-images.githubusercontent.com/83692067/226536496-f38c4dbf-e03c-4158-8be0-32d4a61158c7.png">
 
-<p align="center">
-  <img alt="SigNoz Logs Explorer mit Filtern, Frequenzdiagramm und Log-Zeilen" src="docs/readme-assets/monitor/log-management.svg" width="900">
-</p>
+### Exceptions Monitoring
 
-Mehr erfahren: [Log-Management-Dokumentation](https://signoz.io/docs/logs-management/overview/)
+![exceptions_light](https://user-images.githubusercontent.com/83692067/226637967-4188d024-3ac9-4799-be95-f5ea9c45436f.png)
 
-#### Metriken und Dashboards
+### Alarme
 
-Erstelle Dashboards für Anwendungs-, Infrastruktur- und benutzerdefinierte Metriken mit Query Builder, PromQL oder ClickHouse SQL.
+<img width="2068" alt="alerts_management" src="https://user-images.githubusercontent.com/83692067/226536548-2c81e2e8-c12d-47e8-bad7-c6be79055def.png">
 
-<p align="center">
-  <img alt="SigNoz Host-Metrics-Dashboard mit Systemlast- und Netzwerkdiagrammen" src="docs/readme-assets/monitor/metrics.png" width="900">
-</p>
+<br /><br />
 
-Mehr erfahren: [Metriken-Dokumentation](https://signoz.io/docs/metrics-management/overview/)
+## Werde Teil unserer Slack Community
 
-#### Infrastruktur-Monitoring
+Sag Hi zu uns auf [Slack](https://signoz.io/slack) 👋
 
-Überwache Kubernetes-Cluster, Pods, Nodes, Workloads sowie Host-CPU, Arbeitsspeicher, Festplatten, Netzwerk, Logs und Traces.
+<br /><br />
 
-<p align="center">
-  <img alt="SigNoz Kubernetes-Infrastruktur-Dashboard mit Pod- und Node-Metriken" src="docs/readme-assets/monitor/infrastructure.png" width="900">
-</p>
+## Funktionen:
 
-Mehr erfahren: [Infrastruktur-Monitoring-Dokumentation](https://signoz.io/docs/infrastructure-monitoring/overview/)
+- Einheitliche Benutzeroberfläche für Metriken, Traces und Logs. Keine Notwendigkeit, zwischen Prometheus und Jaeger zu wechseln, um Probleme zu debuggen oder ein separates Log-Tool wie Elastic neben Ihrer Metriken- und Traces-Stack zu verwenden.
+- Überblick über Anwendungsmetriken wie RPS, Latenzzeiten des 50tes/90tes/99tes Perzentils und Fehlerquoten.
+- Langsamste Endpunkte in Ihrer Anwendung.
+- Zeigen Sie genaue Anfragetraces an, um Probleme in nachgelagerten Diensten, langsamen Datenbankabfragen oder Aufrufen von Drittanbieterdiensten wie Zahlungsgateways zu identifizieren.
+- Filtern Sie Traces nach Dienstname, Operation, Latenz, Fehler, Tags/Annotationen.
+- Führen Sie Aggregationen auf Trace-Daten (Ereignisse/Spans) durch, um geschäftsrelevante Metriken zu erhalten. Beispielsweise können Sie die Fehlerquote und die 99tes Perzentillatenz für `customer_type: gold` oder `deployment_version: v2` oder `external_call: paypal` erhalten.
+- Native Unterstützung für OpenTelemetry-Logs, erweiterten Log-Abfrage-Builder und automatische Log-Sammlung aus dem Kubernetes-Cluster.
+- Blitzschnelle Log-Analytik ([Logs Perf. Benchmark](https://signoz.io/blog/logs-performance-benchmark/))
+- End-to-End-Sichtbarkeit der Infrastrukturleistung, Aufnahme von Metriken aus allen Arten von Host-Umgebungen.
+- Einfache Einrichtung von Benachrichtigungen mit dem selbst erstellbaren Abfrage-Builder.
 
-#### LLM- und AI-Observability
+<br /><br />
 
-Verfolge LLM-Apps, RAG-Pipelines, Prompts, Tool Calls, Tokens, Latenz und Kosten zusammen mit Anwendungs- und Infrastruktur-Telemetrie.
+## Wieso SigNoz?
 
-<p align="center">
-  <img alt="SigNoz LLM-Observability-Dashboard für Traces, Token-Nutzung, Latenz und Kosten" src="docs/readme-assets/monitor/llm.png" width="900">
-</p>
+Als Entwickler fanden wir es anstrengend, uns für jede kleine Funktion, die wir haben wollten, auf Closed Source SaaS Anbieter verlassen zu müssen. Closed Source Anbieter überraschen ihre Kunden zum Monatsende oft mit hohen Rechnungen, die keine Transparenz bzgl. der Kostenaufteilung bieten.
 
-Mehr erfahren: [LLM-Observability-Dokumentation](https://signoz.io/docs/llm-observability/)
+Wir wollten eine selbst gehostete, Open Source Variante von Lösungen wie DataDog, NewRelic für Firmen anbieten, die Datenschutz und Sicherheitsbedenken haben, bei der Weitergabe von Kundendaten an Drittanbieter.
 
-#### Agent-Native Observability und MCP
+Open Source gibt dir außerdem die totale Kontrolle über deine Konfiguration, Stichprobenentnahme und Betriebszeit. Du kannst des Weiteren neue Module auf Basis von SigNoz bauen, die erweiterte, geschäftsspezifische Funktionen anbieten.
 
-Nutze den SigNoz MCP-Server, um Telemetrie in Coding Agents zu bringen, oder nutze Noz in SigNoz, um Incidents zu untersuchen, Alerts zu verbessern und Dashboards mit Produktionskontext zu erstellen. [Noz](https://signoz.io/docs/ai/noz/) ist nur in SigNoz Cloud verfügbar.
+### Languages supported:
 
-<p align="center">
-  <img alt="SigNoz Noz-Oberfläche neben einem MCP-gestützten Agent-Workflow" src="docs/readme-assets/monitor/agent-native.png" width="900">
-</p>
+Wir unterstützen [OpenTelemetry](https://opentelemetry.io) als Bibliothek, mit der Sie Ihre Anwendungen instrumentieren können. Daher wird jedes von OpenTelemetry unterstützte Framework und jede Sprache auch von SignNoz unterstützt. Einige der wichtigsten unterstützten Sprachen sind:
 
-Mehr erfahren: [SigNoz MCP-Server-Dokumentation](https://signoz.io/docs/ai/signoz-mcp-server/) · [Agent-Skills-Dokumentation](https://signoz.io/docs/ai/agent-skills/#install-the-plugin)
+- Java
+- Python
+- NodeJS
+- Go
+- PHP
+- .NET
+- Ruby
+- Elixir
+- Rust
 
-#### Distributed Tracing
+Hier findest du die vollständige Liste von unterstützten Programmiersprachen - https://opentelemetry.io/docs/
 
-Verfolge Requests über Services hinweg mit Flamegraphs, Waterfalls, Span Events, Filtern und Trace Analytics.
+<br /><br />
 
-<p align="center">
-  <img alt="SigNoz Distributed-Tracing-Ansicht mit Flamegraph und Waterfall-Spans" src="docs/readme-assets/monitor/distributed-tracing.png" width="900">
-</p>
+## Erste Schritte mit SigNoz
 
-Mehr erfahren: [Distributed-Tracing-Dokumentation](https://signoz.io/docs/instrumentation/)
+### Bereitstellung mit Docker
 
-#### Trace Funnels
+Bitte folge den [hier](https://signoz.io/docs/install/docker/) aufgelisteten Schritten um deine Anwendung mit Docker bereitzustellen.
 
-Erstelle Funnels aus Traces, um Drop-offs im Request-Flow, fehlgeschlagene Übergänge und systemische Workflow-Probleme zu verstehen.
+Die [Anleitungen zur Fehlerbehebung](https://signoz.io/docs/install/troubleshooting/) könnten hilfreich sein, falls du auf irgendwelche Schwierigkeiten stößt.
 
-<p align="center">
-  <img alt="SigNoz Trace Funnels mit Request-Flow-Drop-offs und fehlgeschlagenen Übergängen" src="docs/readme-assets/monitor/trace-funnels.png" width="900">
-</p>
+<p>&nbsp  </p>
 
-Mehr erfahren: [Trace-Funnels-Dokumentation](https://signoz.io/docs/trace-funnels/overview/)
+### Deploy in Kubernetes using Helm
 
-Du kannst außerdem [**Exceptions**](https://signoz.io/docs/userguide/exceptions/), [**Alerts**](https://signoz.io/docs/alerts/), [**externe APIs**](https://signoz.io/docs/external-api-monitoring/overview/) und [**Integrationen**](https://signoz.io/docs/integrations/integrations-list/) für OpenTelemetry, Prometheus, Kubernetes, Cloud-Anbieter, Sprach-SDKs, Application Frameworks, Datenbanken und LLM-Tools überwachen.
+Bitte folge den [hier](https://signoz.io/docs/deployment/helm_chart) aufgelisteten Schritten, um deine Anwendung mit Helm Charts bereitzustellen.
 
-### Warum Teams SigNoz nutzen
+<br /><br />
 
-1. **OpenTelemetry-native**<br>
-   Einmal mit offenen Standards instrumentieren und die Kontrolle über deine Telemetrie behalten.
-2. **Korrelierte Signale**<br>
-   Von Service-Charts zu Traces, Logs, Infrastrukturmetriken und Exceptions wechseln, ohne das Tool zu wechseln.
-3. **Eine einzelne spaltenorientierte Datenbank**<br>
-   Gebaut für hochkardinale Observability-Workloads mit hohem Volumen.
-4. **Vorhersehbare Preise**<br>
-   Keine Preise pro Host, keine Preise pro Nutzerplatz und keine Sonderpreise für Custom Metrics.
-5. **Enterprise-ready**<br>
-   SOC 2 Type II und HIPAA Compliance, RBAC, Ingestion Controls, benutzerdefinierte Aufbewahrung, Support, BYOC und Self-Hosting.
+## Vergleiche mit bekannten Tools
 
-### Erste Schritte
+### SigNoz vs Prometheus
 
-#### Mit Cloud starten
+Prometheus ist gut, falls du dich nur für Metriken interessierst. Wenn du eine nahtlose Integration von Metriken und Einzelschritt-Fehlersuchen haben möchtest, ist die Kombination aus Prometheus und Jaeger nicht das Richtige für dich.
 
-Erstelle einen verwalteten SigNoz-Workspace und erhalte dein erstes Dashboard, ohne Observability-Infrastruktur betreiben zu müssen.
+Unser Ziel ist es, eine integrierte Benutzeroberfläche aus Metriken und Einzelschritt-Fehlersuchen anzubieten, ähnlich wie es SaaS Anbieter wie Datadog tun, mit der Möglichkeit von erweitertem filtern und aggregieren von Fehlersuchen. Etwas, was in Jaeger aktuell fehlt.
 
-[**Kostenlos mit SigNoz Cloud starten**](https://signoz.io/teams/)
+<p>&nbsp  </p>
 
-#### SigNoz selbst hosten
+### SigNoz vs Jaeger
 
-Betreibe SigNoz in deiner eigenen Infrastruktur mit Foundry, Docker, Kubernetes oder Linux.
+Jaeger kümmert sich nur um verteilte Einzelschritt-Fehlersuche. SigNoz erstellt sowohl Metriken als auch Einzelschritt-Fehlersuche, daneben haben wir auch Protokoll Verwaltung auf unserem Plan.
 
-[**Foundry**](https://github.com/SigNoz/foundry) · [**Docker**](https://signoz.io/docs/install/docker/) · [**Kubernetes**](https://signoz.io/docs/install/kubernetes/) · [**Linux**](https://signoz.io/docs/install/linux/)
+Außerdem hat SigNoz noch mehr spezielle Funktionen im Vergleich zu Jaeger:
 
-#### Daten senden
+- Jaeger UI zeigt keine Metriken für Einzelschritt-Fehlersuchen oder für gefilterte Einzelschritt-Fehlersuchen an.
+- Jaeger erstellt keine Aggregate für gefilterte Einzelschritt-Fehlersuchen, z. B. die P99 Latenz von Abfragen mit dem Tag `customer_type=premium`, was hingegen mit SigNoz leicht umsetzbar ist.
 
-Instrumentiere Anwendungen und Infrastruktur mit OpenTelemetry, Prometheus, Sprach-SDKs und Integrationen.
+<p>&nbsp  </p>
 
-[**Instrumentation**](https://signoz.io/docs/instrumentation/) · [**Integrationen**](https://signoz.io/docs/integrations/integrations-list/)
+### SigNoz vs Elastic
 
-### Vergleich mit bekannten Tools
+- Die Verwaltung von SigNoz-Protokollen basiert auf 'ClickHouse', einem spaltenbasierten OLAP-Datenspeicher, der aggregierte Protokollanalyseabfragen wesentlich effizienter macht.
+- 50 % geringerer Ressourcenbedarf im Vergleich zu Elastic während der Aufnahme.
 
-SigNoz wird häufig von Teams eingeführt, die von einzelnen Spezialtools oder kommerziellen Plattformen mit unvorhersehbarer Preisgestaltung wechseln.
+Wir haben Benchmarks veröffentlicht, die Elastic mit SignNoz vergleichen. Schauen Sie es sich [hier](https://signoz.io/blog/logs-performance-benchmark/?utm_source=github-readme&utm_medium=logs-benchmark)
 
-**Prometheus**<br>
-Gut, wenn du nur Metriken brauchst. SigNoz hält Metriken, Logs, Traces, Dashboards und Alerts zusammen, damit Teams mit korreliertem Kontext debuggen können.
+<p>&nbsp  </p>
 
-**Jaeger**<br>
-Jaeger macht ausschließlich Distributed Tracing. SigNoz ergänzt Metriken, Logs, Trace Analytics, Dashboards, Alerts, Exceptions und Trace-to-Log-Workflows.
+### SigNoz vs Loki
 
-**Elastic**<br>
-SigNoz nutzt eine spaltenorientierte Datenbank für effiziente Observability-Analysen und hochkardinale Log-Workloads, mit 50 % geringerem Ressourcenbedarf gegenüber Elastic während der Ingestion. Lies die [detaillierte Studie](https://signoz.io/blog/logs-performance-benchmark/?utm_source=github-readme&utm_medium=logs-benchmark).
+- SigNoz unterstützt Aggregationen von Daten mit hoher Kardinalität über ein großes Volumen, Loki hingegen nicht.
+- SigNoz unterstützt Indizes über Daten mit hoher Kardinalität und hat keine Beschränkungen hinsichtlich der Anzahl der Indizes, während Loki maximale Streams erreicht, wenn ein paar Indizes hinzugefügt werden.
+- Das Durchsuchen großer Datenmengen ist in Loki im Vergleich zu SigNoz schwierig und langsam.
 
-**Loki**<br>
-Im verlinkten Benchmark indexierte SigNoz alle Keys im Test-Setup, während Loki beim Hinzufügen weiterer Labels Max-Stream-Fehler erreichte. Lies die [detaillierte Studie](https://signoz.io/blog/logs-performance-benchmark/?utm_source=github-readme&utm_medium=logs-benchmark).
+Wir haben Benchmarks veröffentlicht, die Loki mit SigNoz vergleichen. Schauen Sie es sich [hier](https://signoz.io/blog/logs-performance-benchmark/?utm_source=github-readme&utm_medium=logs-benchmark)
 
-## Mitwirken
+<br /><br />
 
-Wir freuen uns über große und kleine Beiträge. Lies bitte [CONTRIBUTING.md](CONTRIBUTING.md), um mit Beiträgen zu SigNoz loszulegen.
+## Zum Projekt beitragen
 
-Nicht sicher, wie du anfangen sollst? **Schreib uns einfach im Channel `#contributing` in unserer [Slack Community](https://signoz.io/slack).**
+Wir ❤️ Beiträge zum Projekt, egal ob große oder kleine. Bitte lies dir zuerst die [CONTRIBUTING.md](CONTRIBUTING.md), durch, bevor du anfängst, Beiträge zu SigNoz zu machen.
+Du bist dir nicht sicher, wie du anfangen sollst? Schreib uns einfach auf dem #contributing Kanal in unserer [slack community](https://signoz.io/slack)
 
-Wie immer: Danke an unsere großartigen Contributors!
+<br /><br />
+
+## Dokumentation
+
+Du findest unsere Dokumentation unter https://signoz.io/docs/. Falls etwas unverständlich ist oder fehlt, öffne gerne ein Github Issue mit dem Label `documentation` oder schreib uns über den Community Slack Channel.
+
+<br /><br />
+
+## Gemeinschaft
+
+Werde Teil der [slack community](https://signoz.io/slack) um mehr über verteilte Einzelschritt-Fehlersuche, Messung von Systemzuständen oder SigNoz zu erfahren und sich mit anderen Nutzern und Mitwirkenden in Verbindung zu setzen.
+
+Falls du irgendwelche Ideen, Fragen oder Feedback hast, kannst du sie gerne über unsere [Github Discussions](https://github.com/SigNoz/signoz/discussions) mit uns teilen.
+
+Wie immer, Dank an unsere großartigen Mitwirkenden!
 
 <a href="https://github.com/signoz/signoz/graphs/contributors">
-  <img alt="SigNoz Contributors" src="https://contrib.rocks/image?repo=signoz/signoz" />
+  <img src="https://contrib.rocks/image?repo=signoz/signoz" />
 </a>

README.md

@@ -1,190 +1,244 @@
-<p align="center">
-  <picture>
-    <source media="(prefers-color-scheme: dark)" srcset="docs/readme-assets/signoz-hero-dark.png" width="900">
-    <source media="(prefers-color-scheme: light)" srcset="docs/readme-assets/signoz-hero-light.png" width="900">
-    <img alt="SigNoz - Observability on Your Terms, Powered by Open Standards." src="docs/readme-assets/signoz-hero-light.png" width="900">
-  </picture>
-</p>
+<h1 align="center" style="border-bottom: none">
+    <a href="https://signoz.io" target="_blank">
+        <img alt="SigNoz" src="https://github.com/user-attachments/assets/ef9a33f7-12d7-4c94-8908-0a02b22f0c18" width="100" height="100">
+    </a>
+    <br>SigNoz
+</h1>
+
+<p align="center">All your logs, metrics, and traces in one place. Monitor your application, spot issues before they occur and troubleshoot downtime quickly with rich context. SigNoz is a cost-effective open-source alternative to Datadog and New Relic. Visit <a href="https://signoz.io" target="_blank">signoz.io</a> for the full documentation, tutorials, and guide.</p>
 
 <p align="center">
-  <a href="README.zh-cn.md">中文</a> ·
-  <a href="README.de-de.md">Deutsch</a> ·
-  <a href="README.pt-br.md">Português</a>
+    <img alt="GitHub issues" src="https://img.shields.io/github/issues/signoz/signoz"> </a>
+    <a href="https://twitter.com/intent/tweet?text=Monitor%20your%20applications%20and%20troubleshoot%20problems%20with%20SigNoz,%20an%20open-source%20alternative%20to%20DataDog,%20NewRelic.&url=https://signoz.io/&via=SigNozHQ&hashtags=opensource,signoz,observability"> 
+        <img alt="tweet" src="https://img.shields.io/twitter/url/http/shields.io.svg?style=social"> </a> 
 </p>
+  
+  
+<h3 align="center">
+  <a href="https://signoz.io/docs"><b>Documentation</b></a> &bull;
+  <a href="https://github.com/SigNoz/signoz/blob/main/README.zh-cn.md"><b>ReadMe in Chinese</b></a> &bull;
+  <a href="https://github.com/SigNoz/signoz/blob/main/README.de-de.md"><b>ReadMe in German</b></a> &bull;
+  <a href="https://github.com/SigNoz/signoz/blob/main/README.pt-br.md"><b>ReadMe in Portuguese</b></a> &bull;
+  <a href="https://signoz.io/slack"><b>Slack Community</b></a> &bull;
+  <a href="https://twitter.com/SigNozHq"><b>Twitter</b></a>
+</h3>
 
-<p align="center">
-  <a href="https://github.com/SigNoz/signoz/issues"><img alt="GitHub issues" src="https://img.shields.io/github/issues/SigNoz/signoz"></a>
-  <a href="https://github.com/SigNoz/signoz/releases"><img alt="GitHub release" src="https://img.shields.io/github/v/release/SigNoz/signoz?label=release"></a>
-  <a href="https://signoz.io/slack"><img alt="Slack community" src="https://img.shields.io/badge/slack-community-4A154B?logo=slack&logoColor=white"></a>
-  <a href="https://www.linkedin.com/company/signozio/"><img alt="LinkedIn" src="https://img.shields.io/badge/linkedin-SigNoz-0A66C2?logo=linkedin&logoColor=white"></a>
-  <a href="https://twitter.com/intent/tweet?text=Monitor%20your%20applications%20and%20troubleshoot%20problems%20with%20SigNoz,%20an%20open-source%20alternative%20to%20DataDog,%20NewRelic.&url=https://signoz.io/&via=SigNozHQ&hashtags=opensource,signoz,observability"><img alt="Tweet" src="https://img.shields.io/twitter/url/http/shields.io.svg?style=social"></a>
-</p>
+## Features
 
-SigNoz is an open-source observability platform built on OpenTelemetry. We’re building an enterprise-grade alternative to fragmented monitoring stacks, with logs, metrics, traces, alerts, and dashboards in one place.
 
-### Choose how to run SigNoz
+### Application Performance Monitoring
 
-#### SigNoz Cloud (Recommended)
+Use SigNoz APM to monitor your applications and services. It comes with out-of-box charts for key application metrics like p99 latency, error rate, Apdex and operations per second. You can also monitor the database and external calls made from your application. Read [more](https://signoz.io/application-performance-monitoring/).
 
-Fully managed SigNoz with a 30-day free trial, no credit card required, usage-based pricing that starts at $49, and regional data hosting.
+You can [instrument](https://signoz.io/docs/instrumentation/) your application with OpenTelemetry to get started.
 
-[**Start free →**](https://signoz.io/teams/)
+![apm-cover](https://github.com/user-attachments/assets/fa5c0396-0854-4c8b-b972-9b62fd2a70d2)
 
-#### Enterprise
 
-Enterprise Cloud, BYOC, or Enterprise Self-Hosted with compliance, support, custom retention, RBAC, ingestion controls, data residency, and region selection.
+### Logs Management
 
-[**Explore Enterprise →**](https://signoz.io/enterprise/)
+SigNoz can be used as a centralized log management solution. We use ClickHouse (used by likes of Uber & Cloudflare) as a datastore, ⎯ an extremely fast and highly optimized storage for logs data. Instantly search through all your logs using quick filters and a powerful query builder.
 
-#### Community
+You can also create charts on your logs and monitor them with customized dashboards. Read [more](https://signoz.io/log-management/).
 
-Free open-source SigNoz that runs in your own infrastructure. Deploy with Docker, Kubernetes, or Linux and keep full control of your data plane.
+![logs-management-cover](https://github.com/user-attachments/assets/343588ee-98fb-4310-b3d2-c5bacf9c7384)
 
-[**Install SigNoz →**](https://signoz.io/docs/install/self-host/)
 
-### What can you monitor?
+### Distributed Tracing
 
-SigNoz helps teams debug production issues faster by connecting logs, metrics, traces, alerts, dashboards, exceptions, and agent-native workflows in one place.
+Distributed Tracing is essential to troubleshoot issues in microservices applications. Powered by OpenTelemetry, distributed tracing in SigNoz can help you track user requests across services to help you identify performance bottlenecks. 
 
-#### APM Overview
+See user requests in a detailed breakdown with the help of Flamegraphs and Gantt Charts. Click on any span to see the entire trace represented beautifully, which will help you make sense of where issues actually occurred in the flow of requests.
 
-Monitor service latency, error rate, throughput, Apdex, top endpoints, database calls, and external calls.
+Read [more](https://signoz.io/distributed-tracing/).
 
-<p align="center">
-  <img alt="SigNoz APM dashboard showing latency, throughput, Apdex, and key operations" src="docs/readme-assets/monitor/apm.png" width="900">
-</p>
+![distributed-tracing-cover](https://github.com/user-attachments/assets/9bfe060a-0c40-4922-9b55-8a97e1a4076c)
 
-Learn more: [APM documentation](https://signoz.io/docs/instrumentation/overview/)
 
-#### Log Management
 
-Ingest, search, aggregate, and correlate logs with traces and metrics using a visual query builder.
+### Metrics and Dashboards
 
-<p align="center">
-  <img alt="SigNoz logs explorer with filters, frequency chart, and log lines" src="docs/readme-assets/monitor/log-management.svg" width="900">
-</p>
+Ingest metrics from your infrastructure or applications and create customized dashboards to monitor them. Create visualization that suits your needs with a variety of panel types like pie chart, time-series, bar chart, etc.
 
-Learn more: [Log management documentation](https://signoz.io/docs/logs-management/overview/)
+Create queries on your metrics data quickly with an easy-to-use metrics query builder. Add multiple queries and combine those queries with formulae to create really complex queries quickly.
 
-#### Metrics and Dashboards
+Read [more](https://signoz.io/metrics-and-dashboards/).
 
-Build dashboards for application, infrastructure, and custom metrics using Query Builder, PromQL, or ClickHouse SQL.
+![metrics-n-dashboards-cover](https://github.com/user-attachments/assets/a536fd71-1d2c-4681-aa7e-516d754c47a5)
 
-<p align="center">
-  <img alt="SigNoz host metrics dashboard with system load and network charts" src="docs/readme-assets/monitor/metrics.png" width="900">
-</p>
+### LLM Observability
 
-Learn more: [Metrics documentation](https://signoz.io/docs/metrics-management/overview/)
+Monitor and debug your LLM applications with comprehensive observability. Track LLM calls, analyze token usage, monitor performance, and gain insights into your AI application's behavior in production.
 
-#### Infrastructure Monitoring
+SigNoz LLM observability helps you understand how your language models are performing, identify issues with prompts and responses, track token usage and costs, and optimize your AI applications for better performance and reliability.
 
-Monitor Kubernetes clusters, pods, nodes, workloads, and host-level CPU, memory, disk, network, logs, and traces.
+[Get started with LLM Observability →](https://signoz.io/docs/llm-observability/)
 
-<p align="center">
-  <img alt="SigNoz Kubernetes infrastructure dashboard with pod and node metrics" src="docs/readme-assets/monitor/infrastructure.png" width="900">
-</p>
+![llm-observability-cover](https://github.com/user-attachments/assets/a6cc0ca3-59df-48f9-9c16-7c843fccff96)
 
-Learn more: [Infrastructure monitoring documentation](https://signoz.io/docs/infrastructure-monitoring/overview/)
 
-#### LLM and AI Observability
+### Alerts
 
-Trace LLM apps, RAG pipelines, prompts, tool calls, tokens, latency, and costs alongside application and infrastructure telemetry.
+Use alerts in SigNoz to get notified when anything unusual happens in your application. You can set alerts on any type of telemetry signal (logs, metrics, traces), create thresholds and set up a notification channel to get notified. Advanced features like alert history and anomaly detection can help you create smarter alerts.
 
-<p align="center">
-  <img alt="SigNoz LLM observability dashboard for traces, token usage, latency, and costs" src="docs/readme-assets/monitor/llm.png" width="900">
-</p>
+Alerts in SigNoz help you identify issues proactively so that you can address them before they reach your customers.
 
-Learn more: [LLM observability documentation](https://signoz.io/docs/llm-observability/)
+Read [more](https://signoz.io/alerts-management/).
 
-#### Agent-Native Observability and MCP
+![alerts-cover](https://github.com/user-attachments/assets/03873bb8-1b62-4adf-8f56-28bb7b1750ea)
 
-Use the SigNoz MCP server to bring telemetry into coding agents, or use Noz inside SigNoz to investigate incidents, tune alerts, and build dashboards with production context. [Noz](https://signoz.io/docs/ai/noz/) is available only on SigNoz Cloud.
+### Exceptions Monitoring
 
-<p align="center">
-  <img alt="SigNoz Noz interface alongside MCP-powered agent workflow" src="docs/readme-assets/monitor/agent-native.png" width="900">
-</p>
+Monitor exceptions automatically in Python, Java, Ruby, and Javascript. For other languages, just drop in a few lines of code and start monitoring exceptions.
 
-Learn more: [SigNoz MCP server docs](https://signoz.io/docs/ai/signoz-mcp-server/) · [Agent skills docs](https://signoz.io/docs/ai/agent-skills/#install-the-plugin)
+See the detailed stack trace for all exceptions caught in your application. You can also log in custom attributes to add more context to your exceptions. For example, you can add attributes to identify users for which exceptions occurred.
 
-#### Distributed Tracing
+Read [more](https://signoz.io/exceptions-monitoring/).
 
-Follow requests across services with flamegraphs, waterfalls, span events, filters, and trace analytics.
 
-<p align="center">
-  <img alt="SigNoz distributed trace view with flamegraph and waterfall spans" src="docs/readme-assets/monitor/distributed-tracing.png" width="900">
-</p>
+![exceptions-cover](https://github.com/user-attachments/assets/4be37864-59f2-4e8a-8d6e-e29ad04298c5)
 
-Learn more: [Distributed tracing documentation](https://signoz.io/docs/instrumentation/)
 
-#### Trace Funnels
+<br /><br />
 
-Create funnels from traces to understand request-flow drop-offs, failed transitions, and systemic workflow issues.
+## Why SigNoz?
 
-<p align="center">
-  <img alt="SigNoz trace funnels showing request-flow drop-offs and failed transitions" src="docs/readme-assets/monitor/trace-funnels.png" width="900">
-</p>
+SigNoz is a single tool for all your monitoring and observability needs. Here are a few reasons why you should choose SigNoz:
 
-Learn more: [Trace funnels documentation](https://signoz.io/docs/trace-funnels/overview/)
+- Single tool for observability(logs, metrics, and traces)
 
-Also monitor: [**exceptions**](https://signoz.io/docs/userguide/exceptions/), [**alerts**](https://signoz.io/docs/alerts/), [**external APIs**](https://signoz.io/docs/external-api-monitoring/overview/), and [**integrations**](https://signoz.io/docs/integrations/integrations-list/) for OpenTelemetry, Prometheus, Kubernetes, cloud providers, language SDKs, application frameworks, databases, and LLM tools.
+- Built on top of [OpenTelemetry](https://opentelemetry.io/), the open-source standard which frees you from any type of vendor lock-in
 
-### Why teams use SigNoz
+- Correlated logs, metrics and traces for much richer context while debugging
 
-1. **OpenTelemetry-native**<br>
-   Instrument once with open standards and keep ownership of your telemetry.
-2. **Correlated signals**<br>
-   Move from service charts to traces, logs, infra metrics, and exceptions without switching tools.
-3. **Single columnar database**<br>
-   Built for high-cardinality, high-volume observability workloads.
-4. **Predictable pricing**<br>
-   No per-host pricing, no user-seat pricing, and no special pricing for custom metrics.
-5. **Enterprise ready**<br>
-   SOC 2 Type II and HIPAA compliance, RBAC, ingestion controls, custom retention, support, BYOC, and self-hosting.
+- Uses ClickHouse (used by likes of Uber & Cloudflare) as datastore - an extremely fast and highly optimized storage for observability data
 
-### Getting started
+- DIY Query builder, PromQL, and ClickHouse queries to fulfill all your use-cases around querying observability data
 
-#### Start on Cloud
+- Open-Source - you can use open-source, our [cloud service](https://signoz.io/teams/) or a mix of both based on your use case
 
-Create a managed SigNoz workspace and get your first dashboard without running observability infrastructure.
 
-[**Start free on SigNoz Cloud**](https://signoz.io/teams/)
+## Getting Started
 
-#### Self-host SigNoz
+### Create a SigNoz Cloud Account
 
-Run SigNoz in your own infrastructure with Foundry, Docker, Kubernetes, or Linux.
+SigNoz cloud is the easiest way to get started with SigNoz. Our cloud service is for those users who want to spend more time in getting insights for their application performance without worrying about maintenance. 
 
-[**Foundry**](https://github.com/SigNoz/foundry) · [**Docker**](https://signoz.io/docs/install/docker/) · [**Kubernetes**](https://signoz.io/docs/install/kubernetes/) · [**Linux**](https://signoz.io/docs/install/linux/)
+[Get started for free](https://signoz.io/teams/)
 
-#### Send data
+### Deploy using Docker(self-hosted)
 
-Instrument applications and infrastructure with OpenTelemetry, Prometheus, language SDKs, and integrations.
+Please follow the steps listed [here](https://signoz.io/docs/install/docker/) to install using docker
 
-[**Instrumentation**](https://signoz.io/docs/instrumentation/) · [**Integrations**](https://signoz.io/docs/integrations/integrations-list/)
+The [troubleshooting instructions](https://signoz.io/docs/install/troubleshooting/) may be helpful if you face any issues.
 
-### Comparisons to familiar tools
+<p>&nbsp  </p>
+  
+  
+### Deploy in Kubernetes using Helm(self-hosted)
 
-SigNoz is often adopted by teams moving from a stack of single-purpose tools or commercial platforms with unpredictable pricing.
+Please follow the steps listed [here](https://signoz.io/docs/deployment/helm_chart) to install using helm charts
 
-**Prometheus**<br>
-Good if you just need metrics. SigNoz keeps metrics, logs, traces, dashboards, and alerts together so teams can debug with correlated context.
+<br /><br />
 
-**Jaeger**<br>
-Jaeger only does distributed tracing. SigNoz adds metrics, logs, trace analytics, dashboards, alerts, exceptions, and trace-to-log workflows.
+We also offer managed services in your infra. Check our [pricing plans](https://signoz.io/pricing/) for all details.
 
-**Elastic**<br>
-SigNoz uses columnar database for efficient observability analytics and high-cardinality log workloads, with 50% lower resource requirement compared to Elastic during ingestion. Check the [detailed study](https://signoz.io/blog/logs-performance-benchmark/?utm_source=github-readme&utm_medium=logs-benchmark).
 
-**Loki**<br>
-In the linked benchmark, SigNoz indexed all keys in the test setup, while Loki hit max stream errors when more labels were added. Check the [detailed study](https://signoz.io/blog/logs-performance-benchmark/?utm_source=github-readme&utm_medium=logs-benchmark).
+## Join our Slack community
+
+Come say Hi to us on [Slack](https://signoz.io/slack) 👋
+
+<br /><br />
+
+
+### Languages supported:
+
+SigNoz supports all major programming languages for monitoring. Any framework and language supported by OpenTelemetry is supported by SigNoz. Find instructions for instrumenting different languages below:
+
+- [Java](https://signoz.io/docs/instrumentation/java/)
+- [Python](https://signoz.io/docs/instrumentation/python/)
+- [Node.js or Javascript](https://signoz.io/docs/instrumentation/javascript/)
+- [Go](https://signoz.io/docs/instrumentation/golang/)
+- [PHP](https://signoz.io/docs/instrumentation/php/)
+- [.NET](https://signoz.io/docs/instrumentation/dotnet/)
+- [Ruby](https://signoz.io/docs/instrumentation/ruby-on-rails/)
+- [Elixir](https://signoz.io/docs/instrumentation/elixir/)
+- [Rust](https://signoz.io/docs/instrumentation/rust/)
+- [Swift](https://signoz.io/docs/instrumentation/swift/)
+
+You can find our entire documentation [here](https://signoz.io/docs/introduction/).
+
+<br /><br />
+
+
+## Comparisons to Familiar Tools
+
+### SigNoz vs Prometheus
+
+Prometheus is good if you want to do just metrics. But if you want to have a seamless experience between metrics, logs and traces, then current experience of stitching together Prometheus & other tools is not great.
+
+SigNoz is a one-stop solution for metrics and other telemetry signals. And because you will use the same standard(OpenTelemetry) to collect all telemetry signals, you can also correlate these signals to troubleshoot quickly.
+
+For example, if you see that there are issues with infrastructure metrics of your k8s cluster at a timestamp, you can jump to other signals like logs and traces to understand the issue quickly.
+
+<p>&nbsp  </p>
+
+### SigNoz vs Jaeger
+
+Jaeger only does distributed tracing. SigNoz supports metrics, traces and logs - all the 3 pillars of observability.
+
+Moreover, SigNoz has few more advanced features wrt Jaeger:
+
+- Jaegar UI doesn’t show any metrics on traces or on filtered traces
+- Jaeger can’t get aggregates on filtered traces. For example, p99 latency of requests which have tag - customer_type='premium'. This can be done easily on SigNoz
+- You can also go from traces to logs easily in SigNoz
+
+<p>&nbsp  </p>
+
+### SigNoz vs Elastic 
+
+- SigNoz Logs management are based on ClickHouse, a columnar OLAP datastore which makes aggregate log analytics queries much more efficient
+- 50% lower resource requirement compared to Elastic during ingestion
+
+We have published benchmarks comparing Elastic with SigNoz. Check it out [here](https://signoz.io/blog/logs-performance-benchmark/?utm_source=github-readme&utm_medium=logs-benchmark)
+
+<p>&nbsp  </p>
+
+### SigNoz vs Loki
+
+- SigNoz supports aggregations on high-cardinality data over a huge volume while loki doesn’t.
+- SigNoz supports indexes over high cardinality data and has no limitations on the number of indexes, while Loki reaches max streams with a few indexes added to it.
+- Searching over a huge volume of data is difficult and slow in Loki compared to SigNoz
+
+We have published benchmarks comparing Loki with SigNoz. Check it out [here](https://signoz.io/blog/logs-performance-benchmark/?utm_source=github-readme&utm_medium=logs-benchmark)
+
+<br /><br />
+
 
 ## Contributing
 
 We ❤️ contributions big or small. Please read [CONTRIBUTING.md](CONTRIBUTING.md) to get started with making contributions to SigNoz.
 
-Not sure how to get started? **Just ping us on `#contributing` in our [slack community](https://signoz.io/slack).**
+Not sure how to get started? Just ping us on `#contributing` in our [slack community](https://signoz.io/slack)
+
+<br /><br />
+
+
+## Documentation
+
+You can find docs at https://signoz.io/docs/. If you need any clarification or find something missing, feel free to raise a GitHub issue with the label `documentation` or reach out to us at the community slack channel.
+
+<br /><br />
+
+
+## Community
+
+Join the [slack community](https://signoz.io/slack) to know more about distributed tracing, observability, or SigNoz and to connect with other users and contributors.
+
+If you have any ideas, questions, or any feedback, please share on our [Github Discussions](https://github.com/SigNoz/signoz/discussions)
 
 As always, thanks to our amazing contributors!
 
 <a href="https://github.com/signoz/signoz/graphs/contributors">
-  <img alt="SigNoz contributors" src="https://contrib.rocks/image?repo=signoz/signoz" />
+  <img src="https://contrib.rocks/image?repo=signoz/signoz" />
 </a>

README.pt-br.md

@@ -1,190 +1,158 @@
 <p align="center">
-  <picture>
-    <source media="(prefers-color-scheme: dark)" srcset="docs/readme-assets/signoz-hero-dark.png" width="900">
-    <source media="(prefers-color-scheme: light)" srcset="docs/readme-assets/signoz-hero-light.png" width="900">
-    <img alt="SigNoz - Observabilidade nos seus termos, baseada em padrões abertos." src="docs/readme-assets/signoz-hero-light.png" width="900">
-  </picture>
+  <img src="https://res.cloudinary.com/dcv3epinx/image/upload/v1618904450/signoz-images/LogoGithub_sigfbu.svg" alt="SigNoz-logo" width="240" />
+
+  <p align="center">Monitore seus aplicativos e solucione problemas em seus aplicativos implantados, uma alternativa de código aberto para soluções como DataDog, New Relic, entre outras.</p>
 </p>
 
 <p align="center">
-  <a href="README.md">English</a> ·
-  <a href="README.zh-cn.md">中文</a> ·
-  <a href="README.de-de.md">Deutsch</a>
+    <img alt="Downloads" src="https://img.shields.io/docker/pulls/signoz/frontend?label=Downloads"> </a>
+    <img alt="GitHub issues" src="https://img.shields.io/github/issues/signoz/signoz"> </a>
+    <a href="https://twitter.com/intent/tweet?text=Monitor%20your%20applications%20and%20troubleshoot%20problems%20with%20SigNoz,%20an%20open-source%20alternative%20to%20DataDog,%20NewRelic.&url=https://signoz.io/&via=SigNozHQ&hashtags=opensource,signoz,observability"> 
+        <img alt="tweet" src="https://img.shields.io/twitter/url/http/shields.io.svg?style=social"> </a> 
 </p>
+  
+  
+<h3 align="center">
+  <a href="https://signoz.io/docs"><b>Documentação</b></a> &bull;
+  <a href="https://signoz.io/slack"><b>Comunidade no Slack</b></a> &bull;
+  <a href="https://twitter.com/SigNozHq"><b>Twitter</b></a>
+</h3>
 
-<p align="center">
-  <a href="https://github.com/SigNoz/signoz/issues"><img alt="GitHub issues" src="https://img.shields.io/github/issues/SigNoz/signoz"></a>
-  <a href="https://github.com/SigNoz/signoz/releases"><img alt="GitHub release" src="https://img.shields.io/github/v/release/SigNoz/signoz?label=release"></a>
-  <a href="https://signoz.io/slack"><img alt="Slack community" src="https://img.shields.io/badge/slack-community-4A154B?logo=slack&logoColor=white"></a>
-  <a href="https://www.linkedin.com/company/signozio/"><img alt="LinkedIn" src="https://img.shields.io/badge/linkedin-SigNoz-0A66C2?logo=linkedin&logoColor=white"></a>
-  <a href="https://twitter.com/intent/tweet?text=Monitor%20your%20applications%20and%20troubleshoot%20problems%20with%20SigNoz,%20an%20open-source%20alternative%20to%20DataDog,%20NewRelic.&url=https://signoz.io/&via=SigNozHQ&hashtags=opensource,signoz,observability"><img alt="Tweet" src="https://img.shields.io/twitter/url/http/shields.io.svg?style=social"></a>
-</p>
+##
 
-SigNoz é uma plataforma de observabilidade open-source construída sobre OpenTelemetry. Estamos criando uma alternativa de nível empresarial a stacks de monitoramento fragmentadas, com logs, métricas, traces, alertas e dashboards em um só lugar.
+SigNoz auxilia os desenvolvedores a monitorarem aplicativos e solucionar problemas em seus aplicativos implantados. SigNoz usa rastreamento distribuído para obter visibilidade em sua pilha de software. 
 
-### Escolha como executar o SigNoz
+👉 Você pode verificar métricas como latência p99, taxas de erro em seus serviços, requisições às APIs externas e endpoints individuais.
 
-#### SigNoz Cloud (recomendado)
+👉 Você pode encontrar a causa raiz do problema acessando os rastreamentos exatos que estão causando o problema e verificar os quadros detalhados de cada requisição individual.
 
-SigNoz totalmente gerenciado, com teste gratuito de 30 dias, sem cartão de crédito, preço baseado em uso a partir de US$ 49 e hospedagem de dados por região.
+👉 Execute agregações em dados de rastreamento para obter métricas de negócios relevantes.
 
-[**Comece gratuitamente →**](https://signoz.io/teams/)
 
-#### Enterprise
+![SigNoz Feature](https://signoz-public.s3.us-east-2.amazonaws.com/signoz_hero_github.png)
 
-Enterprise Cloud, BYOC ou Enterprise Self-Hosted com compliance, suporte, retenção personalizada, RBAC, controles de ingestão, residência de dados e seleção de região.
+<br /><br />
 
-[**Conheça o Enterprise →**](https://signoz.io/enterprise/)
+<img align="left" src="https://signoz-public.s3.us-east-2.amazonaws.com/Contributing.svg" width="50px" />
 
-#### Community
+## Junte-se à nossa comunidade no Slack 
 
-SigNoz open-source gratuito, executado na sua própria infraestrutura. Faça o deploy com Docker, Kubernetes ou Linux e mantenha controle total sobre o seu plano de dados.
+Venha dizer oi para nós no [Slack](https://signoz.io/slack) 👋
 
-[**Instale o SigNoz →**](https://signoz.io/docs/install/self-host/)
+<br /><br />
 
-### O que você pode monitorar?
+<img align="left" src="https://signoz-public.s3.us-east-2.amazonaws.com/Features.svg" width="50px" />
 
-O SigNoz ajuda equipes a depurar problemas de produção mais rapidamente ao conectar logs, métricas, traces, alertas, dashboards, exceções e fluxos agent-native em um só lugar.
+## Funções:
 
-#### Visão geral de APM
+- Métricas de visão geral do aplicativo, como RPS, latências de percentual 50/90/99 e taxa de erro
+- Endpoints mais lentos em seu aplicativo
+- Visualize o rastreamento preciso de requisições de rede para descobrir problemas em serviços downstream, consultas lentas de banco de dados, chamadas para serviços de terceiros, como gateways de pagamento, etc. 
+- Filtre os rastreamentos por nome de serviço, operação, latência, erro, tags / anotações.
+- Execute agregações em dados de rastreamento (eventos / extensões) para obter métricas de negócios relevantes, como por exemplo, você pode obter a taxa de erro e a latência do 99º percentil de `customer_type: gold` or `deployment_version: v2` or `external_call: paypal`
+- Interface de Usuário unificada para métricas e rastreios. Não há necessidade de mudar de Prometheus para Jaeger para depurar problemas.
 
-Monitore latência de serviço, taxa de erro, throughput, Apdex, principais endpoints, chamadas ao banco de dados e chamadas externas.
+<br /><br />
 
-<p align="center">
-  <img alt="Dashboard de APM do SigNoz mostrando latência, throughput, Apdex e operações principais" src="docs/readme-assets/monitor/apm.png" width="900">
-</p>
+<img align="left" src="https://signoz-public.s3.us-east-2.amazonaws.com/WhatsCool.svg" width="50px" />
 
-Saiba mais: [documentação de APM](https://signoz.io/docs/instrumentation/overview/)
+## Por que escolher SigNoz?
 
-#### Gerenciamento de logs
+Sendo desenvolvedores, achamos irritante contar com fornecedores de SaaS de código fechado para cada pequeno recurso que queríamos. Fornecedores de código fechado costumam surpreendê-lo com enormes contas no final do mês de uso sem qualquer transparência .
 
-Ingira, pesquise, agregue e correlacione logs com traces e métricas usando um construtor visual de consultas.
+Queríamos fazer uma versão auto-hospedada e de código aberto de ferramentas como DataDog, NewRelic para empresas que têm preocupações com privacidade e segurança em ter dados de clientes indo para serviços de terceiros. 
 
-<p align="center">
-  <img alt="Explorador de logs do SigNoz com filtros, gráfico de frequência e linhas de log" src="docs/readme-assets/monitor/log-management.svg" width="900">
-</p>
+Ser open source também oferece controle completo de sua configuração, amostragem e tempos de atividade. Você também pode construir módulos sobre o SigNoz para estender recursos específicos do negócio.
 
-Saiba mais: [documentação de gerenciamento de logs](https://signoz.io/docs/logs-management/overview/)
+### Linguagens Suportadas:
 
-#### Métricas e dashboards
+Nós apoiamos a biblioteca [OpenTelemetry](https://opentelemetry.io) como a biblioteca que você pode usar para instrumentar seus aplicativos. Em outras palavras, SigNoz oferece suporte a qualquer framework e linguagem que suporte a biblioteca OpenTelemetry. As principais linguagens suportadas incluem: 
 
-Crie dashboards para métricas de aplicação, infraestrutura e métricas personalizadas usando Query Builder, PromQL ou ClickHouse SQL.
+- Java
+- Python
+- NodeJS
+- Go
 
-<p align="center">
-  <img alt="Dashboard de métricas de host do SigNoz com gráficos de carga do sistema e rede" src="docs/readme-assets/monitor/metrics.png" width="900">
-</p>
+Você pode encontrar a lista completa de linguagens aqui - https://opentelemetry.io/docs/
 
-Saiba mais: [documentação de métricas](https://signoz.io/docs/metrics-management/overview/)
+<br /><br />
 
-#### Monitoramento de infraestrutura
+<img align="left" src="https://signoz-public.s3.us-east-2.amazonaws.com/Philosophy.svg" width="50px" />
 
-Monitore clusters Kubernetes, pods, nodes, workloads e CPU, memória, disco, rede, logs e traces em nível de host.
+## Iniciando
+  
+  
+### Implantar usando Docker
 
-<p align="center">
-  <img alt="Dashboard de infraestrutura Kubernetes do SigNoz com métricas de pods e nodes" src="docs/readme-assets/monitor/infrastructure.png" width="900">
-</p>
+Siga as etapas listadas [aqui](https://signoz.io/docs/install/docker/) para instalar usando o Docker.
 
-Saiba mais: [documentação de monitoramento de infraestrutura](https://signoz.io/docs/infrastructure-monitoring/overview/)
+Esse [guia para solução de problemas](https://signoz.io/docs/install/troubleshooting/) pode ser útil se você enfrentar quaisquer problemas. 
 
-#### Observabilidade de LLM e AI
+<p>&nbsp  </p>
+  
+  
+### Implentar no Kubernetes usando Helm
 
-Rastreie apps LLM, pipelines RAG, prompts, chamadas de ferramentas, tokens, latência e custos junto com telemetria de aplicação e infraestrutura.
+Siga as etapas listadas [aqui](https://signoz.io/docs/deployment/helm_chart) para instalar usando helm charts.
+  
 
-<p align="center">
-  <img alt="Dashboard de observabilidade de LLM do SigNoz para traces, uso de tokens, latência e custos" src="docs/readme-assets/monitor/llm.png" width="900">
-</p>
+<br /><br />
 
-Saiba mais: [documentação de observabilidade de LLM](https://signoz.io/docs/llm-observability/)
+<img align="left" src="https://signoz-public.s3.us-east-2.amazonaws.com/UseSigNoz.svg" width="50px" />
 
-#### Observabilidade agent-native e MCP
+## Comparações com ferramentas similares 
 
-Use o servidor MCP do SigNoz para levar telemetria aos agentes de programação, ou use o Noz dentro do SigNoz para investigar incidentes, ajustar alertas e criar dashboards com contexto de produção. O [Noz](https://signoz.io/docs/ai/noz/) está disponível apenas no SigNoz Cloud.
+### SigNoz ou Prometheus
 
-<p align="center">
-  <img alt="Interface Noz do SigNoz ao lado de um fluxo agent via MCP" src="docs/readme-assets/monitor/agent-native.png" width="900">
-</p>
+Prometheus é bom se você quiser apenas fazer métricas. Mas se você quiser ter uma experiência perfeita entre métricas e rastreamentos, a experiência atual de unir Prometheus e Jaeger não é ótima.
 
-Saiba mais: [documentação do servidor MCP do SigNoz](https://signoz.io/docs/ai/signoz-mcp-server/) · [documentação de agent skills](https://signoz.io/docs/ai/agent-skills/#install-the-plugin)
+Nosso objetivo é fornecer uma interface do usuário integrada entre métricas e rastreamentos - semelhante ao que fornecedores de SaaS como o Datadog fornecem - e fornecer filtragem e agregação avançada sobre rastreamentos, algo que a Jaeger atualmente carece. 
 
-#### Tracing distribuído
+<p>&nbsp  </p>
 
-Acompanhe requisições entre serviços com flamegraphs, waterfalls, eventos de span, filtros e análise de traces.
+### SigNoz ou Jaeger
 
-<p align="center">
-  <img alt="Visualização de tracing distribuído do SigNoz com flamegraph e spans em waterfall" src="docs/readme-assets/monitor/distributed-tracing.png" width="900">
-</p>
+Jaeger só faz rastreamento distribuído. SigNoz faz métricas e rastreia, e também temos gerenciamento de log em nossos planos.
 
-Saiba mais: [documentação de tracing distribuído](https://signoz.io/docs/instrumentation/)
+Além disso, SigNoz tem alguns recursos mais avançados do que Jaeger:
 
-#### Trace Funnels
+- A interface de usuário do Jaegar não mostra nenhuma métrica em traces ou em traces filtrados
+- Jaeger não pode obter agregados em rastros filtrados. Por exemplo, latência p99 de solicitações que possuem tag - customer_type='premium'. Isso pode ser feito facilmente com SigNoz.
 
-Crie funis a partir de traces para entender quedas no fluxo de requisições, transições com falha e problemas sistêmicos de workflow.
+<br /><br />
 
-<p align="center">
-  <img alt="Trace Funnels do SigNoz mostrando quedas no fluxo de requisições e transições com falha" src="docs/readme-assets/monitor/trace-funnels.png" width="900">
-</p>
-
-Saiba mais: [documentação de Trace Funnels](https://signoz.io/docs/trace-funnels/overview/)
-
-Também monitore: [**exceções**](https://signoz.io/docs/userguide/exceptions/), [**alertas**](https://signoz.io/docs/alerts/), [**APIs externas**](https://signoz.io/docs/external-api-monitoring/overview/) e [**integrações**](https://signoz.io/docs/integrations/integrations-list/) para OpenTelemetry, Prometheus, Kubernetes, provedores de nuvem, SDKs de linguagem, frameworks de aplicação, bancos de dados e ferramentas de LLM.
-
-### Por que equipes usam o SigNoz
-
-1. **Nativo em OpenTelemetry**<br>
-   Instrumente uma vez com padrões abertos e mantenha a posse da sua telemetria.
-2. **Sinais correlacionados**<br>
-   Vá de gráficos de serviço para traces, logs, métricas de infraestrutura e exceções sem trocar de ferramenta.
-3. **Um único banco de dados colunar**<br>
-   Construído para workloads de observabilidade de alto volume e alta cardinalidade.
-4. **Preço previsível**<br>
-   Sem cobrança por host, sem cobrança por usuário e sem preço especial para métricas personalizadas.
-5. **Pronto para enterprise**<br>
-   Compliance SOC 2 Type II e HIPAA, RBAC, controles de ingestão, retenção personalizada, suporte, BYOC e self-hosting.
-
-### Primeiros passos
-
-#### Comece na Cloud
-
-Crie um workspace gerenciado do SigNoz e obtenha seu primeiro dashboard sem operar infraestrutura de observabilidade.
-
-[**Comece gratuitamente no SigNoz Cloud**](https://signoz.io/teams/)
-
-#### Self-host SigNoz
-
-Execute o SigNoz na sua própria infraestrutura com Foundry, Docker, Kubernetes ou Linux.
-
-[**Foundry**](https://github.com/SigNoz/foundry) · [**Docker**](https://signoz.io/docs/install/docker/) · [**Kubernetes**](https://signoz.io/docs/install/kubernetes/) · [**Linux**](https://signoz.io/docs/install/linux/)
-
-#### Envie dados
-
-Instrumente aplicações e infraestrutura com OpenTelemetry, Prometheus, SDKs de linguagem e integrações.
-
-[**Instrumentação**](https://signoz.io/docs/instrumentation/) · [**Integrações**](https://signoz.io/docs/integrations/integrations-list/)
-
-### Comparações com ferramentas conhecidas
-
-O SigNoz é frequentemente adotado por equipes que estão migrando de ferramentas de propósito único ou plataformas comerciais com preços imprevisíveis.
-
-**Prometheus**<br>
-Bom se você precisa apenas de métricas. O SigNoz mantém métricas, logs, traces, dashboards e alertas juntos para que equipes possam depurar com contexto correlacionado.
-
-**Jaeger**<br>
-Jaeger faz apenas tracing distribuído. O SigNoz adiciona métricas, logs, análise de traces, dashboards, alertas, exceções e fluxos de trace para log.
-
-**Elastic**<br>
-O SigNoz usa banco de dados colunar para análises de observabilidade eficientes e workloads de logs de alta cardinalidade, com 50% menos necessidade de recursos em comparação ao Elastic durante a ingestão. Confira o [estudo detalhado](https://signoz.io/blog/logs-performance-benchmark/?utm_source=github-readme&utm_medium=logs-benchmark).
-
-**Loki**<br>
-No benchmark vinculado, o SigNoz indexou todas as chaves na configuração de teste, enquanto o Loki atingiu erros de max streams ao adicionar mais labels. Confira o [estudo detalhado](https://signoz.io/blog/logs-performance-benchmark/?utm_source=github-readme&utm_medium=logs-benchmark).
+<img align="left" src="https://signoz-public.s3.us-east-2.amazonaws.com/Contributors.svg" width="50px" />
 
 ## Contribuindo
 
-Adoramos contribuições grandes ou pequenas. Leia [CONTRIBUTING.md](CONTRIBUTING.md) para começar a contribuir com o SigNoz.
 
-Não sabe como começar? **Fale conosco no `#contributing` na nossa [comunidade Slack](https://signoz.io/slack).**
+Nós ❤️ contribuições grandes ou pequenas. Leia [CONTRIBUTING.md](CONTRIBUTING.md) para começar a fazer contribuições para o SigNoz. 
 
-Como sempre, obrigado aos nossos incríveis contribuidores!
+Não sabe como começar? Basta enviar um sinal para nós no canal `#contributing` em nossa [comunidade no Slack.](https://signoz.io/slack)
+
+<br /><br />
+
+<img align="left" src="https://signoz-public.s3.us-east-2.amazonaws.com/DevelopingLocally.svg" width="50px" />
+
+## Documentação
+
+Você pode encontrar a documentação em https://signoz.io/docs/. Se você tiver alguma dúvida ou sentir falta de algo, sinta-se à vontade para criar uma issue com a tag `documentation` no GitHub ou entre em contato conosco no canal da comunidade no Slack.
+
+<br /><br />
+
+<img align="left" src="https://signoz-public.s3.us-east-2.amazonaws.com/Contributing.svg" width="50px" />
+
+## Comunidade
+
+Junte-se a [comunidade no Slack](https://signoz.io/slack) para saber mais sobre rastreamento distribuído, observabilidade ou SigNoz e para se conectar com outros usuários e colaboradores. 
+
+Se você tiver alguma ideia, pergunta ou feedback, compartilhe em nosso [Github Discussões](https://github.com/SigNoz/signoz/discussions)
+
+Como sempre, obrigado aos nossos incríveis colaboradores! 
 
 <a href="https://github.com/signoz/signoz/graphs/contributors">
-  <img alt="Contribuidores do SigNoz" src="https://contrib.rocks/image?repo=signoz/signoz" />
+  <img src="https://contrib.rocks/image?repo=signoz/signoz" />
 </a>
+
+
+

README.zh-cn.md

@@ -1,190 +1,208 @@
-<p align="center">
-  <picture>
-    <source media="(prefers-color-scheme: dark)" srcset="docs/readme-assets/signoz-hero-dark.png" width="900">
-    <source media="(prefers-color-scheme: light)" srcset="docs/readme-assets/signoz-hero-light.png" width="900">
-    <img alt="SigNoz - 按你的方式运行的可观测性，由开放标准驱动。" src="docs/readme-assets/signoz-hero-light.png" width="900">
-  </picture>
+<img src="https://res.cloudinary.com/dcv3epinx/image/upload/v1618904450/signoz-images/LogoGithub_sigfbu.svg" alt="SigNoz-logo" width="240" />
+
+<p align="center">监控你的应用，并且可排查已部署应用的问题，这是一个可替代 DataDog、NewRelic 的开源方案</p>
 </p>
 
 <p align="center">
-  <a href="README.md">English</a> ·
-  <a href="README.de-de.md">Deutsch</a> ·
-  <a href="README.pt-br.md">Português</a>
+    <img alt="Downloads" src="https://img.shields.io/docker/pulls/signoz/query-service?label=Docker Downloads"> </a>
+    <img alt="GitHub issues" src="https://img.shields.io/github/issues/signoz/signoz"> </a>
+    <a href="https://twitter.com/intent/tweet?text=Monitor%20your%20applications%20and%20troubleshoot%20problems%20with%20SigNoz,%20an%20open-source%20alternative%20to%20DataDog,%20NewRelic.&url=https://signoz.io/&via=SigNozHQ&hashtags=opensource,signoz,observability"> 
+        <img alt="tweet" src="https://img.shields.io/twitter/url/http/shields.io.svg?style=social"> </a> 
 </p>
 
-<p align="center">
-  <a href="https://github.com/SigNoz/signoz/issues"><img alt="GitHub issues" src="https://img.shields.io/github/issues/SigNoz/signoz"></a>
-  <a href="https://github.com/SigNoz/signoz/releases"><img alt="GitHub release" src="https://img.shields.io/github/v/release/SigNoz/signoz?label=release"></a>
-  <a href="https://signoz.io/slack"><img alt="Slack community" src="https://img.shields.io/badge/slack-community-4A154B?logo=slack&logoColor=white"></a>
-  <a href="https://www.linkedin.com/company/signozio/"><img alt="LinkedIn" src="https://img.shields.io/badge/linkedin-SigNoz-0A66C2?logo=linkedin&logoColor=white"></a>
-  <a href="https://twitter.com/intent/tweet?text=Monitor%20your%20applications%20and%20troubleshoot%20problems%20with%20SigNoz,%20an%20open-source%20alternative%20to%20DataDog,%20NewRelic.&url=https://signoz.io/&via=SigNozHQ&hashtags=opensource,signoz,observability"><img alt="Tweet" src="https://img.shields.io/twitter/url/http/shields.io.svg?style=social"></a>
-</p>
+<h3 align="center">
+  <a href="https://signoz.io/docs"><b>文档</b></a> •
+  <a href="https://github.com/SigNoz/signoz/blob/main/README.zh-cn.md"><b>中文ReadMe</b></a> •
+  <a href="https://github.com/SigNoz/signoz/blob/main/README.de-de.md"><b>德文ReadMe</b></a> •
+  <a href="https://github.com/SigNoz/signoz/blob/main/README.pt-br.md"><b>葡萄牙语ReadMe</b></a> •
+  <a href="https://signoz.io/slack"><b>Slack 社区</b></a> •
+  <a href="https://twitter.com/SigNozHq"><b>Twitter</b></a>
+</h3>
 
-SigNoz 是一个基于 OpenTelemetry 构建的开源可观测性平台。我们正在构建一个企业级替代方案，用来替代分散的监控工具栈，把日志、指标、链路追踪、告警和仪表盘放在同一个地方。
+##
 
-### 选择 SigNoz 的运行方式
+SigNoz 帮助开发人员监控应用并排查已部署应用的问题。你可以使用 SigNoz 实现如下能力:
 
-#### SigNoz Cloud（推荐）
+👉 在同一块面板上，可视化 Metrics, Traces 和 Logs 内容。
 
-完全托管的 SigNoz，提供 30 天免费试用，无需信用卡，按用量计费，起价为 49 美元，并支持区域化数据托管。
+👉 你可以关注服务的 p99 延迟和错误率， 包括外部 API 调用和个别的端点。
 
-[**免费开始 →**](https://signoz.io/teams/)
+👉 你可以找到问题的根因，通过提取相关问题的 traces 日志、单独查看请求 traces 的火焰图详情。
 
-#### 企业版
+👉 执行 trace 数据聚合，以获取业务相关的 metrics
 
-Enterprise Cloud、BYOC 或 Enterprise Self-Hosted，提供合规、支持、自定义保留期、RBAC、摄取控制、数据驻留和区域选择。
+👉 对日志过滤和查询，通过日志的属性建立看板和告警
 
-[**了解企业版 →**](https://signoz.io/enterprise/)
+👉 通过 Python，java，Ruby 和 Javascript 自动记录异常
 
-#### 社区版
+👉 轻松的自定义查询和设置告警
 
-免费的开源 SigNoz，可运行在你自己的基础设施中。使用 Docker、Kubernetes 或 Linux 部署，并完全掌控你的数据平面。
+### 应用 Metrics 展示
 
-[**安装 SigNoz →**](https://signoz.io/docs/install/self-host/)
+![application_metrics](https://user-images.githubusercontent.com/83692067/226637410-900dbc5e-6705-4b11-a10c-bd0faeb2a92f.png)
 
-### 你可以监控什么？
+### 分布式追踪
 
-SigNoz 将日志、指标、链路追踪、告警、仪表盘、异常和面向 Agent 的工作流连接在一起，帮助团队更快地调试生产问题。
+<img width="2068" alt="distributed_tracing_2 2" src="https://user-images.githubusercontent.com/83692067/226536447-bae58321-6a22-4ed3-af80-e3e964cb3489.png">
 
-#### APM 概览
+<img width="2068" alt="distributed_tracing_1" src="https://user-images.githubusercontent.com/83692067/226536462-939745b6-4f9d-45a6-8016-814837e7f7b4.png">
 
-监控服务延迟、错误率、吞吐量、Apdex、核心端点、数据库调用和外部调用。
+### 日志管理
 
-<p align="center">
-  <img alt="SigNoz APM 仪表盘，展示延迟、吞吐量、Apdex 和关键操作" src="docs/readme-assets/monitor/apm.png" width="900">
-</p>
+<img width="2068" alt="logs_management" src="https://user-images.githubusercontent.com/83692067/226536482-b8a5c4af-b69c-43d5-969c-338bd5eaf1a5.png">
 
-了解更多：[APM 文档](https://signoz.io/docs/instrumentation/overview/)
+### 基础设施监控
 
-#### 日志管理
+<img width="2068" alt="infrastructure_monitoring" src="https://user-images.githubusercontent.com/83692067/226536496-f38c4dbf-e03c-4158-8be0-32d4a61158c7.png">
 
-摄取、搜索、聚合日志，并通过可视化查询构建器将日志与链路追踪和指标关联起来。
+### 异常监控
 
-<p align="center">
-  <img alt="SigNoz 日志浏览器，包含过滤器、频率图和日志行" src="docs/readme-assets/monitor/log-management.svg" width="900">
-</p>
+![exceptions_light](https://user-images.githubusercontent.com/83692067/226637967-4188d024-3ac9-4799-be95-f5ea9c45436f.png)
 
-了解更多：[日志管理文档](https://signoz.io/docs/logs-management/overview/)
+### 告警
 
-#### 指标和仪表盘
+<img width="2068" alt="alerts_management" src="https://user-images.githubusercontent.com/83692067/226536548-2c81e2e8-c12d-47e8-bad7-c6be79055def.png">
 
-使用 Query Builder、PromQL 或 ClickHouse SQL 为应用、基础设施和自定义指标构建仪表盘。
+<br /><br />
 
-<p align="center">
-  <img alt="SigNoz 主机指标仪表盘，展示系统负载和网络图表" src="docs/readme-assets/monitor/metrics.png" width="900">
-</p>
+## 加入我们 Slack 社区
 
-了解更多：[指标文档](https://signoz.io/docs/metrics-management/overview/)
+来 [Slack](https://signoz.io/slack) 和我们打招呼吧 👋
 
-#### 基础设施监控
+<br /><br />
 
-监控 Kubernetes 集群、Pod、节点、工作负载，以及主机级 CPU、内存、磁盘、网络、日志和链路追踪。
+## 特性:
 
-<p align="center">
-  <img alt="SigNoz Kubernetes 基础设施仪表盘，展示 Pod 和节点指标" src="docs/readme-assets/monitor/infrastructure.png" width="900">
-</p>
+- 为 metrics, traces and logs 制定统一的 UI。 无需切换 Prometheus 到 Jaeger 去查找问题，也无需使用想 Elastic 这样的日志工具分开你的 metrics 和 traces
 
-了解更多：[基础设施监控文档](https://signoz.io/docs/infrastructure-monitoring/overview/)
+- 默认统计应用的 metrics 数据，像 RPS (每秒请求数)， 50th/90th/99th 的分位数延迟数据，还有相关的错误率
 
-#### LLM 和 AI 可观测性
+- 找到应用中最慢的端点
 
-追踪 LLM 应用、RAG 流水线、Prompt、工具调用、Token、延迟和成本，并与应用和基础设施遥测数据放在一起分析。
+- 查看准确的请求跟踪数据，找到下游服务的问题了，比如 DB 慢查询，或者调用第三方的支付网关等
 
-<p align="center">
-  <img alt="SigNoz LLM 可观测性仪表盘，展示链路追踪、Token 使用、延迟和成本" src="docs/readme-assets/monitor/llm.png" width="900">
-</p>
+- 通过 服务名、操作方式、延迟、错误、标签/注释 过滤 traces 数据
 
-了解更多：[LLM 可观测性文档](https://signoz.io/docs/llm-observability/)
+- 通过聚合 trace 数据而获得业务相关的 metrics。 比如你可以通过 `customer_type: gold` 或者 `deployment_version: v2` 或者 `external_call: paypal` 获取错误率和 P99 延迟数据
 
-#### Agent 原生可观测性和 MCP
+- 原生支持 OpenTelemetry 日志，高级日志查询，自动收集 k8s 相关日志
 
-使用 SigNoz MCP server 将遥测数据带入编程 Agent，或在 SigNoz 中使用 Noz，基于生产上下文调查事故、优化告警并构建仪表盘。[Noz](https://signoz.io/docs/ai/noz/) 仅适用于 SigNoz Cloud。
+- 快如闪电的日志分析 ([Logs Perf. Benchmark](https://signoz.io/blog/logs-performance-benchmark/))
 
-<p align="center">
-  <img alt="SigNoz Noz 界面与基于 MCP 的 Agent 工作流" src="docs/readme-assets/monitor/agent-native.png" width="900">
-</p>
+- 可视化点到点的基础设施性能，提取有所有类型机器的 metrics 数据
 
-了解更多：[SigNoz MCP server 文档](https://signoz.io/docs/ai/signoz-mcp-server/) · [Agent skills 文档](https://signoz.io/docs/ai/agent-skills/#install-the-plugin)
+- 轻易自定义告警查询
 
-#### 分布式链路追踪
+<br /><br />
 
-通过火焰图、瀑布图、Span 事件、过滤器和 Trace 分析，跟踪请求在各个服务之间的流转。
+## 为什么使用 SigNoz?
 
-<p align="center">
-  <img alt="SigNoz 分布式链路追踪视图，包含火焰图和瀑布图 Span" src="docs/readme-assets/monitor/distributed-tracing.png" width="900">
-</p>
+作为开发者, 我们发现 SaaS 厂商对一些大家想要的小功能都是闭源的，这种行为真的让人有点恼火。 闭源厂商还会在月底给你一张没有明细的巨额账单。
 
-了解更多：[分布式链路追踪文档](https://signoz.io/docs/instrumentation/)
+我们想做一个自托管并且可开源的工具，像 DataDog 和 NewRelic 那样， 为那些担心数据隐私和安全的公司提供第三方服务。
 
-#### Trace Funnels
+作为开源的项目，你完全可以自己掌控你的配置、样本和更新。你同样可以基于 SigNoz 拓展特定的业务模块。
 
-基于链路追踪创建漏斗，用于理解请求流中的掉点、失败转换和系统性工作流问题。
+### 支持的编程语言:
 
-<p align="center">
-  <img alt="SigNoz Trace Funnels，展示请求流掉点和失败转换" src="docs/readme-assets/monitor/trace-funnels.png" width="900">
-</p>
+我们支持 [OpenTelemetry](https://opentelemetry.io)。作为一个观测你应用的库文件。所以任何 OpenTelemetry 支持的框架和语言，对于 SigNoz 也同样支持。 一些主要支持的语言如下：
 
-了解更多：[Trace Funnels 文档](https://signoz.io/docs/trace-funnels/overview/)
+- Java
+- Python
+- NodeJS
+- Go
+- PHP
+- .NET
+- Ruby
+- Elixir
+- Rust
 
-你还可以监控：[**异常**](https://signoz.io/docs/userguide/exceptions/)、[**告警**](https://signoz.io/docs/alerts/)、[**外部 API**](https://signoz.io/docs/external-api-monitoring/overview/)，以及面向 OpenTelemetry、Prometheus、Kubernetes、云服务商、语言 SDK、应用框架、数据库和 LLM 工具的[**集成**](https://signoz.io/docs/integrations/integrations-list/)。
+你可以在这里找到全部支持的语言列表 - https://opentelemetry.io/docs/
 
-### 为什么团队选择 SigNoz
+<br /><br />
 
-1. **OpenTelemetry 原生**<br>
-   用开放标准完成一次接入，并保持对遥测数据的所有权。
-2. **信号关联**<br>
-   在服务图表、链路追踪、日志、基础设施指标和异常之间切换时，不需要更换工具。
-3. **单一列式数据库**<br>
-   为高基数、高吞吐量的可观测性工作负载而构建。
-4. **可预测的定价**<br>
-   不按主机收费，不按用户席位收费，也不对自定义指标设置特殊价格。
-5. **企业就绪**<br>
-   SOC 2 Type II 和 HIPAA 合规、RBAC、摄取控制、自定义保留期、支持、BYOC 和自托管。
+## 让我们开始吧
 
-### 快速开始
+### 使用 Docker 部署
 
-#### 从 Cloud 开始
+请一步步跟随 [这里](https://signoz.io/docs/install/docker/) 通过 docker 来安装。
 
-创建一个托管的 SigNoz 工作区，无需运行可观测性基础设施，即可获得第一个仪表盘。
+这个 [排障说明书](https://signoz.io/docs/install/troubleshooting/) 可以帮助你解决碰到的问题。
 
-[**免费开始使用 SigNoz Cloud**](https://signoz.io/teams/)
+<p>&nbsp  </p>
 
-#### 自托管 SigNoz
+### 使用 Helm 在 Kubernetes 部署
 
-在你自己的基础设施中通过 Foundry、Docker、Kubernetes 或 Linux 运行 SigNoz。
+请一步步跟随 [这里](https://signoz.io/docs/deployment/helm_chart) 通过 helm 来安装
 
-[**Foundry**](https://github.com/SigNoz/foundry) · [**Docker**](https://signoz.io/docs/install/docker/) · [**Kubernetes**](https://signoz.io/docs/install/kubernetes/) · [**Linux**](https://signoz.io/docs/install/linux/)
+<br /><br />
 
-#### 发送数据
+## 比较相似的工具
 
-使用 OpenTelemetry、Prometheus、语言 SDK 和集成来接入应用与基础设施。
+### SigNoz vs Prometheus
 
-[**接入文档**](https://signoz.io/docs/instrumentation/) · [**集成列表**](https://signoz.io/docs/integrations/integrations-list/)
+Prometheus 是一个针对 metrics 监控的强大工具。但是如果你想无缝的切换 metrics 和 traces 查询，你当前大概率需要在 Prometheus 和 Jaeger 之间切换。
 
-### 与常见工具的对比
+我们的目标是提供一个客户观测 metrics 和 traces 整合的 UI。就像 SaaS 供应商 DataDog，它提供很多 jaeger 缺失的功能，比如针对 traces 过滤功能和聚合功能。
 
-许多团队在从单一用途工具或价格不可预测的商业平台迁移时，会选择 SigNoz。
+<p>&nbsp  </p>
 
-**Prometheus**<br>
-如果你只需要指标，Prometheus 很合适。SigNoz 将指标、日志、链路追踪、仪表盘和告警放在一起，让团队可以通过关联上下文进行调试。
+### SigNoz vs Jaeger
 
-**Jaeger**<br>
-Jaeger 只做分布式链路追踪。SigNoz 增加了指标、日志、Trace 分析、仪表盘、告警、异常和 Trace 到日志的工作流。
+Jaeger 仅仅是一个分布式追踪系统。 但是 SigNoz 可以提供 metrics, traces 和 logs 所有的观测。
 
-**Elastic**<br>
-SigNoz 使用列式数据库来高效处理可观测性分析和高基数日志工作负载。在摄取阶段，相比 Elastic 可降低 50% 的资源需求。查看[详细评测](https://signoz.io/blog/logs-performance-benchmark/?utm_source=github-readme&utm_medium=logs-benchmark)。
+而且, SigNoz 相较于 Jaeger 拥有更对的高级功能:
 
-**Loki**<br>
-在链接的评测中，SigNoz 在测试设置中索引了所有键，而 Loki 在增加更多标签时遇到了 max stream 错误。查看[详细评测](https://signoz.io/blog/logs-performance-benchmark/?utm_source=github-readme&utm_medium=logs-benchmark)。
+- Jaegar UI 不能提供任何基于 traces 的 metrics 查询和过滤。
+
+- Jaeger 不能针对过滤的 traces 做聚合。 比如， p99 延迟的请求有个标签是 customer_type='premium'。 而这些在 SigNoz 可以轻松做到。
+
+<p>&nbsp  </p>
+
+### SigNoz vs Elastic
+
+- SigNoz 的日志管理是基于 ClickHouse 实现的，可以使日志的聚合更加高效，因为它是基于 OLAP 的数据仓储。
+
+- 与 Elastic 相比，可以节省 50% 的资源成本
+
+我们已经公布了 Elastic 和 SigNoz 的性能对比。 请点击 [这里](https://signoz.io/blog/logs-performance-benchmark/?utm_source=github-readme&utm_medium=logs-benchmark)
+
+<p>&nbsp  </p>
+
+### SigNoz vs Loki
+
+- SigNoz 支持大容量高基数的聚合，但是 loki 是不支持的。
+
+- SigNoz 支持索引的高基数查询，并且对索引没有数量限制，而 Loki 会在添加部分索引后到达最大上限。
+
+- 相较于 SigNoz，Loki 在搜索大量数据下既困难又缓慢。
+
+我们已经发布了基准测试对比 Loki 和 SigNoz 性能。请点击 [这里](https://signoz.io/blog/logs-performance-benchmark/?utm_source=github-readme&utm_medium=logs-benchmark)
+
+<br /><br />
 
 ## 贡献
 
-无论贡献大小，我们都非常欢迎。请阅读 [CONTRIBUTING.md](CONTRIBUTING.md)，开始为 SigNoz 做贡献。
+我们 ❤️ 你的贡献，无论大小。 请先阅读 [CONTRIBUTING.md](CONTRIBUTING.md) 再开始给 SigNoz 做贡献。
 
-不确定如何开始？**可以在我们的 [Slack 社区](https://signoz.io/slack)中通过 `#contributing` 联系我们。**
+如果你不知道如何开始？ 只需要在 [slack 社区](https://signoz.io/slack) 通过 `#contributing` 频道联系我们。
 
-一如既往，感谢所有出色的贡献者！
+<br /><br />
+
+## 文档
+
+你可以通过 https://signoz.io/docs/ 找到相关文档。如果你需要阐述问题或者发现一些确实的事件， 通过标签为 `documentation` 提交 Github 问题。或者通过 slack 社区频道。
+
+<br /><br />
+
+## 社区
+
+加入 [slack 社区](https://signoz.io/slack) 去了解更多关于分布式追踪、可观测性系统 。或者与 SigNoz 其他用户和贡献者交流。
+
+如果你有任何想法、问题、或者任何反馈， 请通过 [Github Discussions](https://github.com/SigNoz/signoz/discussions) 分享。
+
+不管怎么样，感谢这个项目的所有贡献者!
 
 <a href="https://github.com/signoz/signoz/graphs/contributors">
-  <img alt="SigNoz 贡献者" src="https://contrib.rocks/image?repo=signoz/signoz" />
+  <img src="https://contrib.rocks/image?repo=signoz/signoz" />
 </a>

cmd/authz.go

@@ -5,7 +5,6 @@ import (
 	"context"
 	"os"
 	"sort"
-	"strings"
 	"text/template"
 
 	"github.com/SigNoz/signoz/pkg/types/coretypes"
@@ -24,7 +23,6 @@ export default {
 			{
 				kind: '{{ .Kind }}',
 				type: '{{ .Type }}',
-{{ .FormattedAllowedVerbs }}
 			},
 {{- end }}
 		],
@@ -43,9 +41,8 @@ type permissionsTypeRelation struct {
 }
 
 type permissionsTypeResource struct {
-	Kind                  string
-	Type                  string
-	FormattedAllowedVerbs string
+	Kind string
+	Type string
 }
 
 type permissionsTypeData struct {
@@ -53,30 +50,6 @@ type permissionsTypeData struct {
 	Relations []permissionsTypeRelation
 }
 
-// formatAllowedVerbs returns a prettier-compatible formatted allowedVerbs line.
-// indentLevel is the number of tabs for the property (matching kind/type indent).
-// printWidth is prettier's printWidth; tabWidth is assumed to be 1 (each \t = 1 char).
-func formatAllowedVerbs(verbs []string, indentLevel int, printWidth int) string {
-	quoted := make([]string, len(verbs))
-	for i, v := range verbs {
-		quoted[i] = "'" + v + "'"
-	}
-	indent := strings.Repeat("\t", indentLevel)
-
-	oneLine := indent + "allowedVerbs: [" + strings.Join(quoted, ", ") + "],"
-	if len(oneLine) <= printWidth {
-		return oneLine
-	}
-
-	var b strings.Builder
-	b.WriteString(indent + "allowedVerbs: [\n")
-	for _, q := range quoted {
-		b.WriteString(indent + "\t" + q + ",\n")
-	}
-	b.WriteString(indent + "],")
-	return b.String()
-}
-
 func registerGenerateAuthz(parentCmd *cobra.Command) {
 	authzCmd := &cobra.Command{
 		Use:   "authz",
@@ -93,9 +66,10 @@ func runGenerateAuthz(_ context.Context) error {
 	registry := coretypes.NewRegistry()
 
 	allowedResources := map[string]bool{
-		coretypes.NewResourceRef(coretypes.ResourceServiceAccount).String():           true,
-		coretypes.NewResourceRef(coretypes.ResourceRole).String():                     true,
-		coretypes.NewResourceRef(coretypes.ResourceMetaResourceFactorAPIKey).String(): true,
+		coretypes.NewResourceRef(coretypes.ResourceServiceAccount).String():              true,
+		coretypes.NewResourceRef(coretypes.ResourceMetaResourcesServiceAccount).String(): true,
+		coretypes.NewResourceRef(coretypes.ResourceRole).String():                        true,
+		coretypes.NewResourceRef(coretypes.ResourceMetaResourcesRole).String():           true,
 	}
 
 	allowedTypes := map[string]bool{}
@@ -107,23 +81,9 @@ func runGenerateAuthz(_ context.Context) error {
 			continue
 		}
 		allowedTypes[ref.Type.StringValue()] = true
-
-		resource, err := coretypes.NewResourceFromTypeAndKind(ref.Type, ref.Kind)
-		if err != nil {
-			return err
-		}
-
-		verbs := resource.AllowedVerbs()
-		allowedVerbStrings := make([]string, 0, len(verbs))
-		for _, verb := range verbs {
-			allowedVerbStrings = append(allowedVerbStrings, verb.StringValue())
-		}
-		sort.Strings(allowedVerbStrings)
-
 		resources = append(resources, permissionsTypeResource{
-			Kind:                  ref.Kind.String(),
-			Type:                  ref.Type.StringValue(),
-			FormattedAllowedVerbs: formatAllowedVerbs(allowedVerbStrings, 4, 80),
+			Kind: ref.Kind.String(),
+			Type: ref.Type.StringValue(),
 		})
 	}
 

cmd/community/Dockerfile

@@ -11,7 +11,7 @@ RUN apk update && \
 
 
 COPY ./target/${OS}-${TARGETARCH}/signoz-community /root/signoz
-COPY ./templates /root/templates
+COPY ./templates/email /root/templates
 COPY frontend/build/ /etc/signoz/web/
 
 RUN chmod 755 /root /root/signoz

cmd/community/Dockerfile.multi-arch

@@ -12,7 +12,7 @@ RUN apk update && \
     rm -rf /var/cache/apk/*
 
 COPY ./target/${OS}-${ARCH}/signoz-community /root/signoz-community
-COPY ./templates /root/templates
+COPY ./templates/email /root/templates
 COPY frontend/build/ /etc/signoz/web/
 
 RUN chmod 755 /root /root/signoz-community

cmd/community/main.go

@@ -14,7 +14,6 @@ func main() {
 	// register a list of commands to the root command
 	registerServer(cmd.RootCmd, logger)
 	cmd.RegisterGenerate(cmd.RootCmd, logger)
-	cmd.RegisterMetastore(cmd.RootCmd, logger, sqlstoreProviderFactories, sqlschemaProviderFactories)
 
 	cmd.Execute(logger)
 }

cmd/community/metastore.go

@@ -1,16 +0,0 @@
-package main
-
-import (
-	"github.com/SigNoz/signoz/pkg/factory"
-	"github.com/SigNoz/signoz/pkg/signoz"
-	"github.com/SigNoz/signoz/pkg/sqlschema"
-	"github.com/SigNoz/signoz/pkg/sqlstore"
-)
-
-func sqlstoreProviderFactories() factory.NamedMap[factory.ProviderFactory[sqlstore.SQLStore, sqlstore.Config]] {
-	return signoz.NewSQLStoreProviderFactories()
-}
-
-func sqlschemaProviderFactories(sqlstore sqlstore.SQLStore) factory.NamedMap[factory.ProviderFactory[sqlschema.SQLSchema, sqlschema.Config]] {
-	return signoz.NewSQLSchemaProviderFactories(sqlstore)
-}

cmd/community/server.go

@@ -29,13 +29,10 @@ import (
 	"github.com/SigNoz/signoz/pkg/modules/cloudintegration/implcloudintegration"
 	"github.com/SigNoz/signoz/pkg/modules/dashboard"
 	"github.com/SigNoz/signoz/pkg/modules/dashboard/impldashboard"
-	"github.com/SigNoz/signoz/pkg/modules/metricreductionrule"
-	"github.com/SigNoz/signoz/pkg/modules/metricreductionrule/implmetricreductionrule"
 	"github.com/SigNoz/signoz/pkg/modules/organization"
 	"github.com/SigNoz/signoz/pkg/modules/retention"
 	"github.com/SigNoz/signoz/pkg/modules/rulestatehistory"
 	"github.com/SigNoz/signoz/pkg/modules/serviceaccount"
-	"github.com/SigNoz/signoz/pkg/modules/tag"
 	"github.com/SigNoz/signoz/pkg/prometheus"
 	"github.com/SigNoz/signoz/pkg/querier"
 	"github.com/SigNoz/signoz/pkg/query-service/app"
@@ -43,6 +40,7 @@ import (
 	"github.com/SigNoz/signoz/pkg/ruler"
 	"github.com/SigNoz/signoz/pkg/ruler/signozruler"
 	"github.com/SigNoz/signoz/pkg/signoz"
+	"github.com/SigNoz/signoz/pkg/sqlschema"
 	"github.com/SigNoz/signoz/pkg/sqlstore"
 	"github.com/SigNoz/signoz/pkg/telemetrystore"
 	"github.com/SigNoz/signoz/pkg/types/authtypes"
@@ -89,11 +87,13 @@ func runServer(ctx context.Context, config signoz.Config, logger *slog.Logger) e
 		signoz.NewEmailingProviderFactories(),
 		signoz.NewCacheProviderFactories(),
 		signoz.NewWebProviderFactories(config.Global),
-		sqlschemaProviderFactories,
-		sqlstoreProviderFactories(),
+		func(sqlstore sqlstore.SQLStore) factory.NamedMap[factory.ProviderFactory[sqlschema.SQLSchema, sqlschema.Config]] {
+			return signoz.NewSQLSchemaProviderFactories(sqlstore)
+		},
+		signoz.NewSQLStoreProviderFactories(),
 		signoz.NewTelemetryStoreProviderFactories(),
 		func(ctx context.Context, providerSettings factory.ProviderSettings, store authtypes.AuthNStore, licensing licensing.Licensing) (map[authtypes.AuthNProvider]authn.AuthN, error) {
-			return signoz.NewAuthNs(ctx, providerSettings, store, licensing, config.Global)
+			return signoz.NewAuthNs(ctx, providerSettings, store, licensing)
 		},
 		func(ctx context.Context, sqlstore sqlstore.SQLStore, config authz.Config, _ licensing.Licensing, _ []authz.OnBeforeRoleDelete) (factory.ProviderFactory[authz.AuthZ, authz.Config], error) {
 			openfgaDataStore, err := openfgaserver.NewSQLStore(sqlstore, config)
@@ -103,8 +103,8 @@ func runServer(ctx context.Context, config signoz.Config, logger *slog.Logger) e
 
 			return openfgaauthz.NewProviderFactory(sqlstore, openfgaschema.NewSchema().Get(ctx), openfgaDataStore, authtypes.NewRegistry()), nil
 		},
-		func(store sqlstore.SQLStore, settings factory.ProviderSettings, analytics analytics.Analytics, orgGetter organization.Getter, queryParser queryparser.QueryParser, _ querier.Querier, _ licensing.Licensing, tagModule tag.Module) dashboard.Module {
-			return impldashboard.NewModule(impldashboard.NewStore(store), settings, analytics, orgGetter, queryParser, tagModule)
+		func(store sqlstore.SQLStore, settings factory.ProviderSettings, analytics analytics.Analytics, orgGetter organization.Getter, queryParser queryparser.QueryParser, _ querier.Querier, _ licensing.Licensing) dashboard.Module {
+			return impldashboard.NewModule(impldashboard.NewStore(store), settings, analytics, orgGetter, queryParser)
 		},
 		func(_ licensing.Licensing) factory.ProviderFactory[gateway.Gateway, gateway.Config] {
 			return noopgateway.NewProviderFactory()
@@ -118,12 +118,9 @@ func runServer(ctx context.Context, config signoz.Config, logger *slog.Logger) e
 		func(ps factory.ProviderSettings, q querier.Querier, a analytics.Analytics) querier.Handler {
 			return querier.NewHandler(ps, q, a)
 		},
-		func(_ sqlstore.SQLStore, _ dashboard.Module, _ global.Global, _ zeus.Zeus, _ gateway.Gateway, _ licensing.Licensing, _ serviceaccount.Module, _ cloudintegration.Config) (cloudintegration.Module, error) {
+		func(_ sqlstore.SQLStore, _ global.Global, _ zeus.Zeus, _ gateway.Gateway, _ licensing.Licensing, _ serviceaccount.Module, _ cloudintegration.Config) (cloudintegration.Module, error) {
 			return implcloudintegration.NewModule(), nil
 		},
-		func(_ sqlstore.SQLStore, _ telemetrystore.TelemetryStore, _ dashboard.Module, _ queryparser.QueryParser, _ licensing.Licensing, _ flagger.Flagger, _ telemetrytypes.MetadataStore, _ factory.ProviderSettings, _ int) metricreductionrule.Module {
-			return implmetricreductionrule.NewModule()
-		},
 		func(c cache.Cache, am alertmanager.Alertmanager, ss sqlstore.SQLStore, ts telemetrystore.TelemetryStore, ms telemetrytypes.MetadataStore, p prometheus.Prometheus, og organization.Getter, rsh rulestatehistory.Module, q querier.Querier, qp queryparser.QueryParser) factory.NamedMap[factory.ProviderFactory[ruler.Ruler, ruler.Config]] {
 			return factory.MustNewNamedMap(signozruler.NewFactory(c, am, ss, ts, ms, p, og, rsh, q, qp, nil, nil))
 		},

cmd/enterprise/Dockerfile

@@ -11,7 +11,7 @@ RUN apk update && \
 
 
 COPY ./target/${OS}-${TARGETARCH}/signoz /root/signoz
-COPY ./templates /root/templates
+COPY ./templates/email /root/templates
 COPY frontend/build/ /etc/signoz/web/
 
 RUN chmod 755 /root /root/signoz

cmd/enterprise/Dockerfile.integration

@@ -26,7 +26,7 @@ RUN go mod download
 COPY ./cmd/ ./cmd/
 COPY ./ee/ ./ee/
 COPY ./pkg/ ./pkg/
-COPY ./templates /root/templates
+COPY ./templates/email /root/templates
 
 COPY Makefile Makefile
 RUN TARGET_DIR=/root ARCHS=${TARGETARCH} ZEUS_URL=${ZEUSURL} LICENSE_URL=${ZEUSURL}/api/v1 make go-build-enterprise-race

cmd/enterprise/Dockerfile.multi-arch

@@ -12,7 +12,7 @@ RUN apk update && \
     rm -rf /var/cache/apk/*
 
 COPY ./target/${OS}-${ARCH}/signoz /root/signoz
-COPY ./templates /root/templates
+COPY ./templates/email /root/templates
 COPY frontend/build/ /etc/signoz/web/
 
 RUN chmod 755 /root /root/signoz

cmd/enterprise/Dockerfile.with-web.integration

@@ -3,7 +3,7 @@ FROM node:22-bookworm AS build
 WORKDIR /opt/
 COPY ./frontend/ ./
 ENV NODE_OPTIONS=--max-old-space-size=8192
-RUN CI=1 npm i -g pnpm@10
+RUN CI=1 npm i -g pnpm
 RUN CI=1 pnpm install
 RUN CI=1 pnpm build
 
@@ -35,7 +35,7 @@ RUN go mod download
 COPY ./cmd/ ./cmd/
 COPY ./ee/ ./ee/
 COPY ./pkg/ ./pkg/
-COPY ./templates /root/templates
+COPY ./templates/email /root/templates
 
 COPY Makefile Makefile
 RUN TARGET_DIR=/root ARCHS=${TARGETARCH} ZEUS_URL=${ZEUSURL} LICENSE_URL=${ZEUSURL}/api/v1 make go-build-enterprise-race

cmd/enterprise/main.go

@@ -14,7 +14,6 @@ func main() {
 	// register a list of commands to the root command
 	registerServer(cmd.RootCmd, logger)
 	cmd.RegisterGenerate(cmd.RootCmd, logger)
-	cmd.RegisterMetastore(cmd.RootCmd, logger, sqlstoreProviderFactories, sqlschemaProviderFactories)
 
 	cmd.Execute(logger)
 }

cmd/enterprise/metastore.go

@@ -1,29 +0,0 @@
-package main
-
-import (
-	"github.com/SigNoz/signoz/ee/sqlschema/postgressqlschema"
-	"github.com/SigNoz/signoz/ee/sqlstore/postgressqlstore"
-	"github.com/SigNoz/signoz/pkg/factory"
-	"github.com/SigNoz/signoz/pkg/signoz"
-	"github.com/SigNoz/signoz/pkg/sqlschema"
-	"github.com/SigNoz/signoz/pkg/sqlstore"
-	"github.com/SigNoz/signoz/pkg/sqlstore/sqlstorehook"
-)
-
-func sqlstoreProviderFactories() factory.NamedMap[factory.ProviderFactory[sqlstore.SQLStore, sqlstore.Config]] {
-	existingFactories := signoz.NewSQLStoreProviderFactories()
-	if err := existingFactories.Add(postgressqlstore.NewFactory(sqlstorehook.NewLoggingFactory(), sqlstorehook.NewInstrumentationFactory())); err != nil {
-		panic(err)
-	}
-
-	return existingFactories
-}
-
-func sqlschemaProviderFactories(sqlstore sqlstore.SQLStore) factory.NamedMap[factory.ProviderFactory[sqlschema.SQLSchema, sqlschema.Config]] {
-	existingFactories := signoz.NewSQLSchemaProviderFactories(sqlstore)
-	if err := existingFactories.Add(postgressqlschema.NewFactory(sqlstore)); err != nil {
-		panic(err)
-	}
-
-	return existingFactories
-}

cmd/enterprise/server.go

@@ -24,10 +24,11 @@ import (
 	"github.com/SigNoz/signoz/ee/modules/cloudintegration/implcloudintegration"
 	"github.com/SigNoz/signoz/ee/modules/cloudintegration/implcloudintegration/implcloudprovider"
 	"github.com/SigNoz/signoz/ee/modules/dashboard/impldashboard"
-	eeimplmetricreductionrule "github.com/SigNoz/signoz/ee/modules/metricreductionrule/implmetricreductionrule"
 	eequerier "github.com/SigNoz/signoz/ee/querier"
 	enterpriseapp "github.com/SigNoz/signoz/ee/query-service/app"
 	eerules "github.com/SigNoz/signoz/ee/query-service/rules"
+	"github.com/SigNoz/signoz/ee/sqlschema/postgressqlschema"
+	"github.com/SigNoz/signoz/ee/sqlstore/postgressqlstore"
 	enterprisezeus "github.com/SigNoz/signoz/ee/zeus"
 	"github.com/SigNoz/signoz/ee/zeus/httpzeus"
 	"github.com/SigNoz/signoz/pkg/alertmanager"
@@ -47,19 +48,19 @@ import (
 	pkgcloudintegration "github.com/SigNoz/signoz/pkg/modules/cloudintegration/implcloudintegration"
 	"github.com/SigNoz/signoz/pkg/modules/dashboard"
 	pkgimpldashboard "github.com/SigNoz/signoz/pkg/modules/dashboard/impldashboard"
-	"github.com/SigNoz/signoz/pkg/modules/metricreductionrule"
 	"github.com/SigNoz/signoz/pkg/modules/organization"
 	"github.com/SigNoz/signoz/pkg/modules/retention"
 	"github.com/SigNoz/signoz/pkg/modules/rulestatehistory"
 	"github.com/SigNoz/signoz/pkg/modules/serviceaccount"
-	"github.com/SigNoz/signoz/pkg/modules/tag"
 	"github.com/SigNoz/signoz/pkg/prometheus"
 	"github.com/SigNoz/signoz/pkg/querier"
 	"github.com/SigNoz/signoz/pkg/queryparser"
 	"github.com/SigNoz/signoz/pkg/ruler"
 	"github.com/SigNoz/signoz/pkg/ruler/signozruler"
 	"github.com/SigNoz/signoz/pkg/signoz"
+	"github.com/SigNoz/signoz/pkg/sqlschema"
 	"github.com/SigNoz/signoz/pkg/sqlstore"
+	"github.com/SigNoz/signoz/pkg/sqlstore/sqlstorehook"
 	"github.com/SigNoz/signoz/pkg/telemetrystore"
 	"github.com/SigNoz/signoz/pkg/types/authtypes"
 	"github.com/SigNoz/signoz/pkg/types/cloudintegrationtypes"
@@ -93,6 +94,13 @@ func runServer(ctx context.Context, config signoz.Config, logger *slog.Logger) e
 	// print the version
 	version.Info.PrettyPrint(config.Version)
 
+	// add enterprise sqlstore factories to the community sqlstore factories
+	sqlstoreFactories := signoz.NewSQLStoreProviderFactories()
+	if err := sqlstoreFactories.Add(postgressqlstore.NewFactory(sqlstorehook.NewLoggingFactory(), sqlstorehook.NewInstrumentationFactory())); err != nil {
+		logger.ErrorContext(ctx, "failed to add postgressqlstore factory", errors.Attr(err))
+		return err
+	}
+
 	signoz, err := signoz.New(
 		ctx,
 		config,
@@ -105,21 +113,28 @@ func runServer(ctx context.Context, config signoz.Config, logger *slog.Logger) e
 		signoz.NewEmailingProviderFactories(),
 		signoz.NewCacheProviderFactories(),
 		signoz.NewWebProviderFactories(config.Global),
-		sqlschemaProviderFactories,
-		sqlstoreProviderFactories(),
+		func(sqlstore sqlstore.SQLStore) factory.NamedMap[factory.ProviderFactory[sqlschema.SQLSchema, sqlschema.Config]] {
+			existingFactories := signoz.NewSQLSchemaProviderFactories(sqlstore)
+			if err := existingFactories.Add(postgressqlschema.NewFactory(sqlstore)); err != nil {
+				panic(err)
+			}
+
+			return existingFactories
+		},
+		sqlstoreFactories,
 		signoz.NewTelemetryStoreProviderFactories(),
 		func(ctx context.Context, providerSettings factory.ProviderSettings, store authtypes.AuthNStore, licensing licensing.Licensing) (map[authtypes.AuthNProvider]authn.AuthN, error) {
-			samlCallbackAuthN, err := samlcallbackauthn.New(ctx, store, licensing, config.Global)
+			samlCallbackAuthN, err := samlcallbackauthn.New(ctx, store, licensing)
 			if err != nil {
 				return nil, err
 			}
 
-			oidcCallbackAuthN, err := oidccallbackauthn.New(store, licensing, providerSettings, config.Global)
+			oidcCallbackAuthN, err := oidccallbackauthn.New(store, licensing, providerSettings)
 			if err != nil {
 				return nil, err
 			}
 
-			authNs, err := signoz.NewAuthNs(ctx, providerSettings, store, licensing, config.Global)
+			authNs, err := signoz.NewAuthNs(ctx, providerSettings, store, licensing)
 			if err != nil {
 				return nil, err
 			}
@@ -136,8 +151,8 @@ func runServer(ctx context.Context, config signoz.Config, logger *slog.Logger) e
 			}
 			return openfgaauthz.NewProviderFactory(sqlstore, openfgaschema.NewSchema().Get(ctx), openfgaDataStore, licensing, onBeforeRoleDelete, authtypes.NewRegistry()), nil
 		},
-		func(store sqlstore.SQLStore, settings factory.ProviderSettings, analytics analytics.Analytics, orgGetter organization.Getter, queryParser queryparser.QueryParser, querier querier.Querier, licensing licensing.Licensing, tagModule tag.Module) dashboard.Module {
-			return impldashboard.NewModule(pkgimpldashboard.NewStore(store), settings, analytics, orgGetter, queryParser, querier, licensing, tagModule)
+		func(store sqlstore.SQLStore, settings factory.ProviderSettings, analytics analytics.Analytics, orgGetter organization.Getter, queryParser queryparser.QueryParser, querier querier.Querier, licensing licensing.Licensing) dashboard.Module {
+			return impldashboard.NewModule(pkgimpldashboard.NewStore(store), settings, analytics, orgGetter, queryParser, querier, licensing)
 		},
 		func(licensing licensing.Licensing) factory.ProviderFactory[gateway.Gateway, gateway.Config] {
 			return httpgateway.NewProviderFactory(licensing)
@@ -170,7 +185,7 @@ func runServer(ctx context.Context, config signoz.Config, logger *slog.Logger) e
 			communityHandler := querier.NewHandler(ps, q, a)
 			return eequerier.NewHandler(ps, q, communityHandler)
 		},
-		func(sqlStore sqlstore.SQLStore, dashboardModule dashboard.Module, global global.Global, zeus zeus.Zeus, gateway gateway.Gateway, licensing licensing.Licensing, serviceAccount serviceaccount.Module, config cloudintegration.Config) (cloudintegration.Module, error) {
+		func(sqlStore sqlstore.SQLStore, global global.Global, zeus zeus.Zeus, gateway gateway.Gateway, licensing licensing.Licensing, serviceAccount serviceaccount.Module, config cloudintegration.Config) (cloudintegration.Module, error) {
 			defStore := pkgcloudintegration.NewServiceDefinitionStore()
 			awsCloudProviderModule, err := implcloudprovider.NewAWSCloudProvider(defStore)
 			if err != nil {
@@ -182,10 +197,7 @@ func runServer(ctx context.Context, config signoz.Config, logger *slog.Logger) e
 				cloudintegrationtypes.CloudProviderTypeAzure: azureCloudProviderModule,
 			}
 
-			return implcloudintegration.NewModule(pkgcloudintegration.NewStore(sqlStore), dashboardModule, global, zeus, gateway, licensing, serviceAccount, cloudProvidersMap, config)
-		},
-		func(sqlStore sqlstore.SQLStore, ts telemetrystore.TelemetryStore, dashboardModule dashboard.Module, queryParser queryparser.QueryParser, lic licensing.Licensing, flgr pkgflagger.Flagger, ms telemetrytypes.MetadataStore, ps factory.ProviderSettings, threads int) metricreductionrule.Module {
-			return eeimplmetricreductionrule.NewModule(sqlStore, ts, dashboardModule, queryParser, lic, flgr, ms, ps, threads)
+			return implcloudintegration.NewModule(pkgcloudintegration.NewStore(sqlStore), global, zeus, gateway, licensing, serviceAccount, cloudProvidersMap, config)
 		},
 		func(c cache.Cache, am alertmanager.Alertmanager, ss sqlstore.SQLStore, ts telemetrystore.TelemetryStore, ms telemetrytypes.MetadataStore, p prometheus.Prometheus, og organization.Getter, rsh rulestatehistory.Module, q querier.Querier, qp queryparser.QueryParser) factory.NamedMap[factory.ProviderFactory[ruler.Ruler, ruler.Config]] {
 			return factory.MustNewNamedMap(signozruler.NewFactory(c, am, ss, ts, ms, p, og, rsh, q, qp, eerules.PrepareTaskFunc, eerules.TestNotification))

cmd/genconfig.go

@@ -1,101 +0,0 @@
-package cmd
-
-import (
-	"encoding/json"
-	"os"
-	"reflect"
-	"strings"
-
-	"github.com/SigNoz/signoz/pkg/types/authtypes"
-	"github.com/SigNoz/signoz/pkg/web"
-	"github.com/spf13/cobra"
-	"github.com/swaggest/jsonschema-go"
-)
-
-const webSettingsSchemaPath = "frontend/src/schemas/generated/webSettings.schema.json"
-
-const transactionGroupsSchemaPath = "frontend/src/schemas/generated/transactionGroups.schema.json"
-
-func registerGenerateConfig(parentCmd *cobra.Command) {
-	configCmd := &cobra.Command{
-		Use:   "config",
-		Short: "Generate JSON Schema for config",
-	}
-
-	configCmd.AddCommand(&cobra.Command{
-		Use:   "web-settings",
-		Short: "Generate JSON Schema for web settings",
-		RunE: func(currCmd *cobra.Command, args []string) error {
-			return generateWebSettings()
-		},
-	})
-
-	configCmd.AddCommand(&cobra.Command{
-		Use:   "transaction-groups",
-		Short: "Generate JSON Schema for transaction groups",
-		RunE: func(currCmd *cobra.Command, args []string) error {
-			return generateTransactionGroups()
-		},
-	})
-
-	parentCmd.AddCommand(configCmd)
-}
-
-func generateWebSettings() error {
-	falseVal := false
-	noAdditional := jsonschema.SchemaOrBool{TypeBoolean: &falseVal}
-
-	reflector := jsonschema.Reflector{}
-	reflector.DefaultOptions = append(reflector.DefaultOptions,
-		jsonschema.InterceptSchema(func(params jsonschema.InterceptSchemaParams) (bool, error) {
-			if params.Value.Kind() == reflect.Struct {
-				params.Schema.AdditionalProperties = &noAdditional
-			}
-			return false, nil
-		}),
-		jsonschema.InterceptDefName(func(t reflect.Type, defaultDefName string) string {
-			return strings.TrimPrefix(defaultDefName, "Web")
-		}),
-	)
-
-	schema, err := reflector.Reflect(web.Settings{})
-	if err != nil {
-		return err
-	}
-
-	schema.WithTitle("WebSettings")
-	data, err := json.MarshalIndent(schema, "", "  ")
-	if err != nil {
-		return err
-	}
-
-	return os.WriteFile(webSettingsSchemaPath, append(data, '\n'), 0o600)
-}
-
-func generateTransactionGroups() error {
-	falseVal := false
-	noAdditional := jsonschema.SchemaOrBool{TypeBoolean: &falseVal}
-
-	reflector := jsonschema.Reflector{}
-	reflector.DefaultOptions = append(reflector.DefaultOptions,
-		jsonschema.InterceptSchema(func(params jsonschema.InterceptSchemaParams) (bool, error) {
-			if params.Value.Kind() == reflect.Struct {
-				params.Schema.AdditionalProperties = &noAdditional
-			}
-			return false, nil
-		}),
-	)
-
-	schema, err := reflector.Reflect(authtypes.TransactionGroups{})
-	if err != nil {
-		return err
-	}
-
-	schema.WithTitle("TransactionGroups")
-	data, err := json.MarshalIndent(schema, "", "  ")
-	if err != nil {
-		return err
-	}
-
-	return os.WriteFile(transactionGroupsSchemaPath, append(data, '\n'), 0o600)
-}

cmd/generate.go

@@ -17,7 +17,6 @@ func RegisterGenerate(parentCmd *cobra.Command, logger *slog.Logger) {
 
 	registerGenerateOpenAPI(generateCmd)
 	registerGenerateAuthz(generateCmd)
-	registerGenerateConfig(generateCmd)
 
 	parentCmd.AddCommand(generateCmd)
 }

cmd/metastore.go

@@ -1,154 +0,0 @@
-package cmd
-
-import (
-	"context"
-	"log/slog"
-
-	"github.com/spf13/cobra"
-
-	"github.com/SigNoz/signoz/pkg/factory"
-	"github.com/SigNoz/signoz/pkg/instrumentation"
-	"github.com/SigNoz/signoz/pkg/signoz"
-	"github.com/SigNoz/signoz/pkg/sqlmigration"
-	"github.com/SigNoz/signoz/pkg/sqlmigrator"
-	"github.com/SigNoz/signoz/pkg/sqlschema"
-	"github.com/SigNoz/signoz/pkg/sqlstore"
-	"github.com/SigNoz/signoz/pkg/version"
-)
-
-type SQLStoreProviderFactories func() factory.NamedMap[factory.ProviderFactory[sqlstore.SQLStore, sqlstore.Config]]
-type SQLSchemaProviderFactories func(sqlstore.SQLStore) factory.NamedMap[factory.ProviderFactory[sqlschema.SQLSchema, sqlschema.Config]]
-
-func RegisterMetastore(parentCmd *cobra.Command, logger *slog.Logger, sqlstoreProviderFactories SQLStoreProviderFactories, sqlschemaProviderFactories SQLSchemaProviderFactories) {
-	metastoreCmd := &cobra.Command{
-		Use:               "metastore",
-		Short:             "Run commands to interact with the Metastore",
-		SilenceUsage:      true,
-		SilenceErrors:     true,
-		CompletionOptions: cobra.CompletionOptions{DisableDefaultCmd: true},
-	}
-
-	registerMigrate(metastoreCmd, logger, sqlstoreProviderFactories, sqlschemaProviderFactories)
-
-	parentCmd.AddCommand(metastoreCmd)
-}
-
-func registerMigrate(parentCmd *cobra.Command, logger *slog.Logger, sqlstoreProviderFactories SQLStoreProviderFactories, sqlschemaProviderFactories SQLSchemaProviderFactories) {
-	migrateCmd := &cobra.Command{
-		Use:               "migrate",
-		Short:             "Run migrations for the Metastore",
-		SilenceUsage:      true,
-		SilenceErrors:     true,
-		CompletionOptions: cobra.CompletionOptions{DisableDefaultCmd: true},
-	}
-
-	registerSync(migrateCmd, logger, sqlstoreProviderFactories, sqlschemaProviderFactories)
-
-	parentCmd.AddCommand(migrateCmd)
-}
-
-func registerSync(parentCmd *cobra.Command, logger *slog.Logger, sqlstoreProviderFactories SQLStoreProviderFactories, sqlschemaProviderFactories SQLSchemaProviderFactories) {
-	syncCmd := &cobra.Command{
-		Use:               "sync",
-		Short:             "Runs 'sync' migrations for the metastore. Sync migrations are used to mutate schemas of the metastore. These migrations need to be successfully applied before bringing up the application.",
-		SilenceUsage:      true,
-		SilenceErrors:     true,
-		CompletionOptions: cobra.CompletionOptions{DisableDefaultCmd: true},
-	}
-
-	registerSyncUp(syncCmd, logger, sqlstoreProviderFactories, sqlschemaProviderFactories)
-	registerSyncCheck(syncCmd, logger, sqlstoreProviderFactories, sqlschemaProviderFactories)
-
-	parentCmd.AddCommand(syncCmd)
-}
-
-func registerSyncUp(parentCmd *cobra.Command, logger *slog.Logger, sqlstoreProviderFactories SQLStoreProviderFactories, sqlschemaProviderFactories SQLSchemaProviderFactories) {
-	var configFiles []string
-
-	syncUpCmd := &cobra.Command{
-		Use:                "up",
-		Short:              "Runs 'up' migrations for the metastore. Up migrations are used to apply new migrations to the metastore",
-		FParseErrWhitelist: cobra.FParseErrWhitelist{UnknownFlags: true},
-		RunE: func(currCmd *cobra.Command, args []string) error {
-			config, err := NewSigNozConfig(currCmd.Context(), logger, configFiles)
-			if err != nil {
-				return err
-			}
-
-			return runSyncUp(currCmd.Context(), config, sqlstoreProviderFactories, sqlschemaProviderFactories)
-		},
-	}
-
-	syncUpCmd.Flags().StringArrayVar(&configFiles, "config", nil, "path to a YAML configuration file (can be specified multiple times, later files override earlier ones)")
-	parentCmd.AddCommand(syncUpCmd)
-}
-
-func registerSyncCheck(parentCmd *cobra.Command, logger *slog.Logger, sqlstoreProviderFactories SQLStoreProviderFactories, sqlschemaProviderFactories SQLSchemaProviderFactories) {
-	var configFiles []string
-
-	syncCheckCmd := &cobra.Command{
-		Use:                "check",
-		Short:              "Runs a check for 'sync' migrations on the metastore. Returns a non-zero exit code if any migrations are pending.",
-		FParseErrWhitelist: cobra.FParseErrWhitelist{UnknownFlags: true},
-		RunE: func(currCmd *cobra.Command, args []string) error {
-			config, err := NewSigNozConfig(currCmd.Context(), logger, configFiles)
-			if err != nil {
-				return err
-			}
-
-			return runSyncCheck(currCmd.Context(), config, sqlstoreProviderFactories, sqlschemaProviderFactories)
-		},
-	}
-
-	syncCheckCmd.Flags().StringArrayVar(&configFiles, "config", nil, "path to a YAML configuration file (can be specified multiple times, later files override earlier ones)")
-	parentCmd.AddCommand(syncCheckCmd)
-}
-
-func runSyncUp(ctx context.Context, config signoz.Config, sqlstoreProviderFactories SQLStoreProviderFactories, sqlschemaProviderFactories SQLSchemaProviderFactories) error {
-	migrator, err := newSyncMigrator(ctx, config, sqlstoreProviderFactories, sqlschemaProviderFactories)
-	if err != nil {
-		return err
-	}
-
-	return migrator.Migrate(ctx)
-}
-
-func runSyncCheck(ctx context.Context, config signoz.Config, sqlstoreProviderFactories SQLStoreProviderFactories, sqlschemaProviderFactories SQLSchemaProviderFactories) error {
-	migrator, err := newSyncMigrator(ctx, config, sqlstoreProviderFactories, sqlschemaProviderFactories)
-	if err != nil {
-		return err
-	}
-
-	return migrator.Check(ctx)
-}
-
-func newSyncMigrator(ctx context.Context, config signoz.Config, sqlstoreProviderFactories SQLStoreProviderFactories, sqlschemaProviderFactories SQLSchemaProviderFactories) (sqlmigrator.SQLMigrator, error) {
-	instrumentation, err := instrumentation.New(ctx, config.Instrumentation, version.Info, "signoz")
-	if err != nil {
-		return nil, err
-	}
-
-	providerSettings := instrumentation.ToProviderSettings()
-
-	sqlstore, err := factory.NewProviderFromNamedMap(ctx, providerSettings, config.SQLStore, sqlstoreProviderFactories(), config.SQLStore.Provider)
-	if err != nil {
-		return nil, err
-	}
-
-	sqlschema, err := factory.NewProviderFromNamedMap(ctx, providerSettings, config.SQLSchema, sqlschemaProviderFactories(sqlstore), config.SQLStore.Provider)
-	if err != nil {
-		return nil, err
-	}
-
-	telemetrystore, err := factory.NewProviderFromNamedMap(ctx, providerSettings, config.TelemetryStore, signoz.NewTelemetryStoreProviderFactories(), config.TelemetryStore.Provider)
-	if err != nil {
-		return nil, err
-	}
-
-	sqlmigrations, err := sqlmigration.New(ctx, providerSettings, config.SQLMigration, signoz.NewSQLMigrationProviderFactories(sqlstore, sqlschema, telemetrystore, providerSettings))
-	if err != nil {
-		return nil, err
-	}
-
-	return sqlmigrator.New(ctx, providerSettings, sqlstore, sqlmigrations, config.SQLMigrator), nil
-}

conf/example.yaml

@@ -60,36 +60,6 @@ web:
   index: index.html
   # The directory containing the static build files.
   directory: /etc/signoz/web
-  # Settings exposed to the web.
-  settings:
-    posthog:
-      # Whether to enable PostHog in web.
-      enabled: false
-      # The PostHog project API key.
-      key: ""
-      # The PostHog API host. Defaults to https://us.i.posthog.com when empty.
-      api_host: ""
-      # The PostHog UI host. Used when api_host points at a reverse proxy.
-      ui_host: ""
-    appcues:
-      # Whether to enable Appcues in web.
-      enabled: false
-      # The Appcues account/app ID.
-      app_id: ""
-    sentry:
-      # Whether to enable Sentry in web.
-      enabled: false
-      # The Sentry DSN.
-      dsn: ""
-      # The Sentry tunnel URL.
-      tunnel: ""
-    pylon:
-      # Whether to enable Pylon in web.
-      enabled: false
-      # The Pylon app ID.
-      app_id: ""
-      # The Pylon identity verification secret.
-      identity_secret: ""
 
 ##################### Cache #####################
 cache:
@@ -157,10 +127,6 @@ querier:
   flux_interval: 5m
   # The maximum number of concurrent queries for missing ranges.
   max_concurrent_queries: 4
-  # When filtering logs by trace_id, clamp the query window to the trace time
-  # range with padding to include slightly delayed log exports. Logs only; set
-  # to 0 to disable.
-  log_trace_id_window_padding: 5m
 
 ##################### TelemetryStore #####################
 telemetrystore:
@@ -208,11 +174,6 @@ alertmanager:
     poll_interval: 1m
     # The URL under which Alertmanager is externally reachable (for example, if Alertmanager is served via a reverse proxy). Used for generating relative and absolute links back to Alertmanager itself.
     external_url: http://localhost:8080
-    # The list of globs from which SigNoz's alertmanager notification templates are loaded (e.g. the email.signoz.html layout).
-    # This mirrors the upstream alertmanager `templates` config option. The upstream default templates (default.tmpl, email.tmpl)
-    # are always loaded from the embedded alertmanager assets, so only SigNoz's own templates need to be listed here.
-    templates:
-      - /opt/signoz/conf/templates/alertmanager/*.gotmpl
     # The global configuration for the alertmanager. All the exahustive fields can be found in the upstream: https://github.com/prometheus/alertmanager/blob/efa05feffd644ba4accb526e98a8c6545d26a783/config/config.go#L833
     global:
       # ResolveTimeout is the time after which an alert is declared resolved if it has not been updated.
@@ -452,7 +413,7 @@ cloudintegration:
     version: v0.0.8
 
 ##################### Trace Detail #####################
-traces:
+tracedetail:
   waterfall:
     # Number of spans returned per request when the trace is too large to show all at once.
     span_page_size: 500
@@ -460,17 +421,6 @@ traces:
     max_depth_to_auto_expand: 5
     # Threshold below which all spans are returned without windowing.
     max_limit_to_select_all_spans: 10000
-  flamegraph:
-    # Maximum number of BFS depth levels included in a windowed response.
-    max_selected_levels: 50
-    # Maximum spans per level before sampling is applied.
-    max_spans_per_level: 100
-    # Number of highest-latency spans always included when sampling a level.
-    sampling_top_latency_count: 5
-    # Number of timestamp buckets used for uniform sampling within a level.
-    sampling_bucket_count: 50
-    # Threshold below which all spans are returned without windowing or sampling.
-    select_all_spans_limit: 100000
 
 ##################### Authz #################################
 authz:
@@ -482,12 +432,7 @@ authz:
 
 ##################### Meter Reporter #####################
 meterreporter:
-  # The interval between collection ticks. Minimum 10m, maximum 24h.
+  # The interval between collection ticks. Minimum 5m.
   interval: 6h
   # Whether to backfill sealed days from the license creation day.
   backfill: true
-  # Random jitter applied to the first collect and to every subsequent cycle.
-  # The first collect fires at a random time in [0, jitter); each cycle then takes
-  # interval - random(0, jitter). Must be between 10m and interval. Defaults to
-  # min(interval, 2h) when unset.
-  jitter: 2h

deploy/MIGRATION.md

@@ -1,270 +0,0 @@
-# Migrating from the install script and `deploy/` to Foundry
-
-The install script (`install.sh`) and the bundled Compose and Swarm files
-under `deploy/` are deprecated in favor of [Foundry][foundry], the supported
-way to install and manage SigNoz. This guide moves an existing Docker Compose
-or Docker Swarm deployment to Foundry and reattaches your existing volumes, so
-your data is preserved.
-
-> [!IMPORTANT]
-> This guide is only for **existing** `install.sh` / `deploy/` deployments.
-> Setting up SigNoz for the first time? Skip migration and install Foundry
-> directly: [SigNoz install docs][install-docs].
-
-## How it works
-
-Foundry splits a deployment into two commands:
-
-- `foundryctl forge` generates the deployment manifests from a `casting.yaml`.
-  It never touches running containers, so it is safe to re-run while you
-  iterate.
-- `foundryctl cast` applies those manifests: it (re)creates the containers and
-  reuses the volumes you point it at.
-
-You write one `casting.yaml`, point a few patches at your existing data
-volumes, then cast. The steps below are the same for Compose and Swarm; they
-differ only in the casting (step 3) and how you stop the old stack (step 5).
-
-## Prerequisites
-
-- An existing SigNoz deployment from `install.sh` or `deploy/` (Compose or
-  Swarm).
-- `foundryctl` (installed in step 1).
-
-## Migrate
-
-### 1. Install Foundry
-
-```bash
-curl -fsSL https://signoz.io/foundry.sh | bash
-```
-
-### 2. Keep your rollback path
-
-This migration reattaches your existing volumes in place; it does not move or
-delete your data. The only destructive action is passing `--volumes` / `-v`
-when you stop the old stack (step 5), so avoid that flag.
-
-> [!IMPORTANT]
-> Keep a copy of your existing `docker-compose.yaml` / stack file (and any
-> config it references). SigNoz no longer distributes these files, so this copy
-> is your only way to roll back.
-
-### 3. Write your `casting.yaml`
-
-Use the casting for your deployment. Both reproduce the legacy single-node
-setup (ClickHouse + ZooKeeper + SQLite) and reattach your existing volumes;
-they differ only in `spec.deployment.flavor` and the volume-reuse patch
-(Compose volumes have a `name` to replace; Swarm volumes are bare, so the whole
-entry is replaced). If your deployment ran more than one shard or replica,
-adjust the volume patches accordingly. The
-[Docker Compose example][compose-example] is a useful reference.
-
-> [!IMPORTANT]
-> The `replica` and `shard` macros are placeholders. Replace them with the
-> values from your existing ClickHouse config (the `macros` section of
-> `config.xml` / `metrika.xml`), or the generated manifests will not match your
-> existing data.
-
-<details>
-<summary><b>Docker Compose</b> casting.yaml</summary>
-
-```yaml
-# casting.yaml
-apiVersion: v1alpha1
-kind: Installation
-metadata:
-  name: signoz
-spec:
-  deployment:
-    flavor: compose
-    mode: docker
-  metastore:
-    kind: sqlite
-  telemetrykeeper:
-    kind: zookeeper
-  telemetrystore:
-    spec:
-      config:
-        data:
-          config-0-0.yaml: |
-            macros:
-              replica: "example01-01-1" # replace with your replica macro
-              shard: "01" # replace with your shard macro
-  patches:
-    - target: "deployment/compose.yaml"
-      operations:
-        - op: replace
-          path: /volumes/signoz-telemetrykeeper-0-data/name
-          value: signoz-zookeeper-1
-        - op: replace
-          path: /volumes/signoz-telemetrystore-0-0-data/name
-          value: signoz-clickhouse
-        - op: replace
-          path: /volumes/signoz-metastore-sqlite-0-data/name
-          value: signoz-sqlite
-        - op: add
-          path: /services/signoz-telemetrykeeper-zookeeper-0/user
-          value: root
-```
-
-</details>
-
-<details>
-<summary><b>Docker Swarm</b> casting.yaml</summary>
-
-```yaml
-# casting.yaml
-apiVersion: v1alpha1
-kind: Installation
-metadata:
-  name: signoz
-spec:
-  deployment:
-    flavor: swarm
-    mode: docker
-  metastore:
-    kind: sqlite
-  telemetrykeeper:
-    kind: zookeeper
-  telemetrystore:
-    spec:
-      config:
-        data:
-          config-0-0.yaml: |
-            macros:
-              replica: "example01-01-1" # replace with your replica macro
-              shard: "01" # replace with your shard macro
-  patches:
-    - target: "deployment/compose.yaml"
-      operations:
-        - op: replace
-          path: /volumes/signoz-telemetrykeeper-0-data
-          value:
-            name: signoz-zookeeper-1
-        - op: replace
-          path: /volumes/signoz-telemetrystore-0-0-data
-          value:
-            name: signoz-clickhouse
-        - op: replace
-          path: /volumes/signoz-metastore-sqlite-0-data
-          value:
-            name: signoz-sqlite
-        - op: add
-          path: /services/signoz-telemetrykeeper-zookeeper-0/user
-          value: root
-```
-
-</details>
-
-> [!NOTE]
-> The `user: root` patch on the ZooKeeper service lets the container read and
-> write the data in your reused ZooKeeper volume, whose files the legacy setup
-> created as `root`. Without it, ZooKeeper may fail to start with permission
-> errors.
-
-If you had custom configuration (SMTP, extra ingestion receivers/processors,
-or custom ClickHouse settings), carry it over via [patches][patches],
-[custom config files][custom-config], or [environment variables][env-vars].
-
-### 4. Generate and review the manifests
-
-```bash
-foundryctl forge -f casting.yaml
-```
-
-Review `pours/deployment/` before deploying:
-
-- [ ] Container images match your current deployment. Foundry generates with
-  `latest` by default; if your SigNoz version was older than latest, check the
-  [upgrade path][upgrade-path] first.
-- [ ] The generated manifests match your previous configuration, especially
-  `compose.yaml` (the new entry point for your deployment).
-- [ ] The ClickHouse config is now YAML rather than XML; confirm your custom
-  settings carried over (see [ClickHouse configuration files][ch-config] for
-  the XML-to-YAML mapping).
-
-### 5. Stop the old deployment
-
-Use the command for your deployment. Do **not** pass `--volumes` / `-v`; that
-would delete the data you are migrating.
-
-```bash
-docker compose down        # Compose
-docker stack rm signoz     # Swarm
-```
-
-> [!NOTE]
-> This causes downtime, so plan accordingly.
-
-Confirm nothing is still bound to the volumes before continuing:
-
-```bash
-docker ps -a
-```
-
-### 6. Deploy with Foundry
-
-```bash
-foundryctl cast -f casting.yaml
-```
-
-This recreates the containers against your existing volumes and pulls the
-images. The migration container runs the schema migrations as part of `cast`.
-
-**Prefer not to use `cast`?** The manifests in `pours/deployment/` are standard
-Docker artifacts you can apply yourself. Run the command from that directory so
-the relative config paths resolve:
-
-```bash
-cd pours/deployment
-docker compose up -d                        # Compose
-docker stack deploy -c compose.yaml signoz  # Swarm
-```
-
-## Verify
-
-- All SigNoz containers are running.
-- The UI is reachable on `http://localhost:8080`, and OTLP on `4317` (gRPC)
-  and `4318` (HTTP), so already-instrumented apps and saved bookmarks keep
-  working.
-- Your existing data is present in the UI, and new data is being ingested.
-- ClickHouse and ZooKeeper logs show no errors.
-
-## Roll back
-
-Step 5 left your volumes untouched, so your data is intact. To return to the
-previous setup:
-
-1. Bring down the Foundry deployment (`docker compose down` or
-   `docker stack rm signoz`, again without `-v`).
-2. Confirm the containers are gone with `docker ps -a`.
-3. Re-apply your backed-up stack: `docker compose up -d` (Compose) or
-   `docker stack deploy -c docker-compose.yaml signoz` (Swarm). It reattaches
-   the same volumes and restores your prior state.
-
-## Troubleshooting
-
-If the migration runs into trouble, reach out on [Slack][slack] or open a
-[Foundry issue][foundry-issues].
-
-## References
-
-- [Foundry][foundry]
-- [Casting file reference][casting-ref]
-- [Custom config files][custom-config]
-- [Patches][patches]
-- [SigNoz documentation][signoz-docs]
-
-[foundry]: https://github.com/SigNoz/foundry
-[install-docs]: https://signoz.io/docs/install/
-[compose-example]: https://github.com/SigNoz/foundry/tree/main/docs/examples/docker/compose
-[patches]: https://github.com/SigNoz/foundry/blob/main/docs/concepts/patches.md
-[custom-config]: https://github.com/SigNoz/foundry/blob/main/docs/concepts/moldings.md#custom-config-files
-[env-vars]: https://github.com/SigNoz/foundry/blob/main/docs/reference/casting-file.md#molding-spec
-[casting-ref]: https://github.com/SigNoz/foundry/blob/main/docs/reference/casting-file.md
-[ch-config]: https://clickhouse.com/docs/operations/configuration-files
-[upgrade-path]: https://signoz.io/docs/operate/upgrade/
-[slack]: https://signoz.io/slack
-[foundry-issues]: https://github.com/SigNoz/foundry/issues
-[signoz-docs]: https://signoz.io/docs

deploy/README.md

@@ -3,16 +3,77 @@
 Check that you have cloned [signoz/signoz](https://github.com/signoz/signoz)
 and currently are in `signoz/deploy` folder.
 
-## Installation
+## Docker
 
-> **Note:** The `install.sh` script and the `docker-compose` manifests have been deprecated.
+If you don't have docker set up, please follow [this guide](https://docs.docker.com/engine/install/)
+to set up docker before proceeding with the next steps.
 
-SigNoz now installs and runs through [Foundry](https://signoz.io/docs/install/docker/).
+### Using Install Script
 
-> **Already running SigNoz via Docker Compose?** See the [Migration Guide](./MIGRATION.md) to transition your existing deployment to Foundry.
+Now run the following command to install:
 
-Please follow the latest installation instructions at [signoz.io/docs/install/docker](https://signoz.io/docs/install/docker/).
-Foundry has support for **different platforms and architectures**, please review the project documentation for more details.
+```sh
+./install.sh
+```
+
+### Using Docker Compose
+
+If you don't have docker compose set up, please follow [this guide](https://docs.docker.com/compose/install/)
+to set up docker compose before proceeding with the next steps.
+
+```sh
+cd deploy/docker
+docker compose up -d
+```
+
+Open http://localhost:8080 in your favourite browser.
+
+To start collecting logs and metrics from your infrastructure, run the following command:
+
+```sh
+cd generator/infra
+docker compose up -d
+```
+
+To start generating sample traces, run the following command:
+
+```sh
+cd generator/hotrod
+docker compose up -d
+```
+
+In a couple of minutes, you should see the data generated from hotrod in SigNoz UI.
+
+For more details, please refer to the [SigNoz documentation](https://signoz.io/docs/install/docker/).
+
+## Docker Swarm
+
+To install SigNoz using Docker Swarm, run the following command:
+
+```sh
+cd deploy/docker-swarm
+docker stack deploy -c docker-compose.yaml signoz
+```
+
+Open http://localhost:8080 in your favourite browser.
+
+To start collecting logs and metrics from your infrastructure, run the following command:
+
+```sh
+cd generator/infra
+docker stack deploy -c docker-compose.yaml infra
+```
+
+To start generating sample traces, run the following command:
+
+```sh
+cd generator/hotrod
+docker stack deploy -c docker-compose.yaml hotrod
+```
+
+In a couple of minutes, you should see the data generated from hotrod in SigNoz UI.
+
+For more details, please refer to the [SigNoz documentation](https://signoz.io/docs/install/docker-swarm/).
 
 ## Uninstall/Troubleshoot?
 

deploy/common/clickhouse/cluster.ha.xml

@@ -0,0 +1,75 @@
+<?xml version="1.0"?>
+<clickhouse>
+    <!-- ZooKeeper is used to store metadata about replicas, when using Replicated tables.
+         Optional. If you don't use replicated tables, you could omit that.
+
+         See https://clickhouse.com/docs/en/engines/table-engines/mergetree-family/replication/
+      -->
+    <zookeeper>
+        <node index="1">
+            <host>zookeeper-1</host>
+            <port>2181</port>
+        </node>
+        <node index="2">
+            <host>zookeeper-2</host>
+            <port>2181</port>
+        </node>
+        <node index="3">
+            <host>zookeeper-3</host>
+            <port>2181</port>
+        </node>
+    </zookeeper>
+
+    <!-- Configuration of clusters that could be used in Distributed tables.
+         https://clickhouse.com/docs/en/operations/table_engines/distributed/
+      -->
+    <remote_servers>
+        <cluster>
+            <!-- Inter-server per-cluster secret for Distributed queries
+                 default: no secret (no authentication will be performed)
+
+                 If set, then Distributed queries will be validated on shards, so at least:
+                 - such cluster should exist on the shard,
+                 - such cluster should have the same secret.
+
+                 And also (and which is more important), the initial_user will
+                 be used as current user for the query.
+
+                 Right now the protocol is pretty simple and it only takes into account:
+                 - cluster name
+                 - query
+
+                 Also it will be nice if the following will be implemented:
+                 - source hostname (see interserver_http_host), but then it will depends from DNS,
+                   it can use IP address instead, but then the you need to get correct on the initiator node.
+                 - target hostname / ip address (same notes as for source hostname)
+                 - time-based security tokens
+            -->
+            <!-- <secret></secret> -->
+            <shard>
+                <!-- Optional. Whether to write data to just one of the replicas. Default: false (write data to all replicas). -->
+                <!-- <internal_replication>false</internal_replication> -->
+                <!-- Optional. Shard weight when writing data. Default: 1. -->
+                <!-- <weight>1</weight> -->
+                <replica>
+                    <host>clickhouse</host>
+                    <port>9000</port>
+                    <!-- Optional. Priority of the replica for load_balancing. Default: 1 (less value has more priority). -->
+                    <!-- <priority>1</priority> -->
+                </replica>
+            </shard>
+            <shard>
+                <replica>
+                    <host>clickhouse-2</host>
+                    <port>9000</port>
+                </replica>
+            </shard>
+            <shard>
+                <replica>
+                    <host>clickhouse-3</host>
+                    <port>9000</port>
+                </replica>
+            </shard>
+        </cluster>
+    </remote_servers>
+</clickhouse>

deploy/common/clickhouse/cluster.xml

@@ -0,0 +1,75 @@
+<?xml version="1.0"?>
+<clickhouse>
+    <!-- ZooKeeper is used to store metadata about replicas, when using Replicated tables.
+         Optional. If you don't use replicated tables, you could omit that.
+
+         See https://clickhouse.com/docs/en/engines/table-engines/mergetree-family/replication/
+      -->
+    <zookeeper>
+        <node index="1">
+            <host>zookeeper-1</host>
+            <port>2181</port>
+        </node>
+        <!-- <node index="2">
+            <host>zookeeper-2</host>
+            <port>2181</port>
+        </node>
+        <node index="3">
+            <host>zookeeper-3</host>
+            <port>2181</port>
+        </node> -->
+    </zookeeper>
+
+    <!-- Configuration of clusters that could be used in Distributed tables.
+         https://clickhouse.com/docs/en/operations/table_engines/distributed/
+      -->
+    <remote_servers>
+        <cluster>
+            <!-- Inter-server per-cluster secret for Distributed queries
+                 default: no secret (no authentication will be performed)
+
+                 If set, then Distributed queries will be validated on shards, so at least:
+                 - such cluster should exist on the shard,
+                 - such cluster should have the same secret.
+
+                 And also (and which is more important), the initial_user will
+                 be used as current user for the query.
+
+                 Right now the protocol is pretty simple and it only takes into account:
+                 - cluster name
+                 - query
+
+                 Also it will be nice if the following will be implemented:
+                 - source hostname (see interserver_http_host), but then it will depends from DNS,
+                   it can use IP address instead, but then the you need to get correct on the initiator node.
+                 - target hostname / ip address (same notes as for source hostname)
+                 - time-based security tokens
+            -->
+            <!-- <secret></secret> -->
+            <shard>
+                <!-- Optional. Whether to write data to just one of the replicas. Default: false (write data to all replicas). -->
+                <!-- <internal_replication>false</internal_replication> -->
+                <!-- Optional. Shard weight when writing data. Default: 1. -->
+                <!-- <weight>1</weight> -->
+                <replica>
+                    <host>clickhouse</host>
+                    <port>9000</port>
+                    <!-- Optional. Priority of the replica for load_balancing. Default: 1 (less value has more priority). -->
+                    <!-- <priority>1</priority> -->
+                </replica>
+            </shard>
+            <!-- <shard>
+                <replica>
+                    <host>clickhouse-2</host>
+                    <port>9000</port>
+                </replica>
+            </shard>
+            <shard>
+                <replica>
+                    <host>clickhouse-3</host>
+                    <port>9000</port>
+                </replica>
+            </shard> -->
+        </cluster>
+    </remote_servers>
+</clickhouse>

deploy/common/clickhouse/custom-function.xml

@@ -0,0 +1,21 @@
+<functions>
+    <function>
+        <type>executable</type>
+        <name>histogramQuantile</name>
+        <return_type>Float64</return_type>
+        <argument>
+            <type>Array(Float64)</type>
+            <name>buckets</name>
+        </argument>
+        <argument>
+            <type>Array(Float64)</type>
+            <name>counts</name>
+        </argument>
+        <argument>
+            <type>Float64</type>
+            <name>quantile</name>
+        </argument>
+        <format>CSV</format>
+        <command>./histogramQuantile</command>
+    </function>
+</functions>

deploy/common/clickhouse/storage.xml

@@ -0,0 +1,41 @@
+<?xml version="1.0"?>
+<clickhouse>
+<storage_configuration>
+    <disks>
+        <default>
+            <keep_free_space_bytes>10485760</keep_free_space_bytes>
+        </default>
+        <s3>
+            <type>s3</type>
+            <!-- For S3 cold storage,
+                    if region is us-east-1, endpoint can be https://<bucket-name>.s3.amazonaws.com
+                    if region is not us-east-1, endpoint should be https://<bucket-name>.s3-<region>.amazonaws.com
+                For GCS cold storage,
+                    endpoint should be https://storage.googleapis.com/<bucket-name>/data/
+                -->
+            <endpoint>https://BUCKET-NAME.s3-REGION-NAME.amazonaws.com/data/</endpoint>
+            <access_key_id>ACCESS-KEY-ID</access_key_id>
+            <secret_access_key>SECRET-ACCESS-KEY</secret_access_key>
+            <!-- In case of S3, uncomment the below configuration in case you want to read
+                AWS credentials from the Environment variables if they exist. -->
+            <!-- <use_environment_credentials>true</use_environment_credentials> -->
+            <!-- In case of GCS, uncomment the below configuration, since GCS does
+                not support batch deletion and result in error messages in logs. -->
+            <!-- <support_batch_delete>false</support_batch_delete> -->
+        </s3>
+   </disks>
+   <policies>
+       <tiered>
+           <volumes>
+                <default>
+                    <disk>default</disk>
+                </default>
+                <s3>
+                    <disk>s3</disk>
+                    <perform_ttl_move_on_insert>0</perform_ttl_move_on_insert>
+                </s3>
+            </volumes>
+        </tiered>
+    </policies>
+</storage_configuration>
+</clickhouse>

deploy/common/clickhouse/users.xml

@@ -0,0 +1,123 @@
+<?xml version="1.0"?>
+<clickhouse>
+    <!-- See also the files in users.d directory where the settings can be overridden. -->
+
+    <!-- Profiles of settings. -->
+    <profiles>
+        <!-- Default settings. -->
+        <default>
+            <!-- Maximum memory usage for processing single query, in bytes. -->
+            <max_memory_usage>10000000000</max_memory_usage>
+
+            <!-- How to choose between replicas during distributed query processing.
+                 random - choose random replica from set of replicas with minimum number of errors
+                 nearest_hostname - from set of replicas with minimum number of errors, choose replica
+                  with minimum number of different symbols between replica's hostname and local hostname
+                  (Hamming distance).
+                 in_order - first live replica is chosen in specified order.
+                 first_or_random - if first replica one has higher number of errors, pick a random one from replicas with minimum number of errors.
+            -->
+            <load_balancing>random</load_balancing>
+        </default>
+
+        <!-- Profile that allows only read queries. -->
+        <readonly>
+            <readonly>1</readonly>
+        </readonly>
+    </profiles>
+
+    <!-- Users and ACL. -->
+    <users>
+        <!-- If user name was not specified, 'default' user is used. -->
+        <default>
+            <!-- See also the files in users.d directory where the password can be overridden.
+
+                 Password could be specified in plaintext or in SHA256 (in hex format).
+
+                 If you want to specify password in plaintext (not recommended), place it in 'password' element.
+                 Example: <password>qwerty</password>.
+                 Password could be empty.
+
+                 If you want to specify SHA256, place it in 'password_sha256_hex' element.
+                 Example: <password_sha256_hex>65e84be33532fb784c48129675f9eff3a682b27168c0ea744b2cf58ee02337c5</password_sha256_hex>
+                 Restrictions of SHA256: impossibility to connect to ClickHouse using MySQL JS client (as of July 2019).
+
+                 If you want to specify double SHA1, place it in 'password_double_sha1_hex' element.
+                 Example: <password_double_sha1_hex>e395796d6546b1b65db9d665cd43f0e858dd4303</password_double_sha1_hex>
+
+                 If you want to specify a previously defined LDAP server (see 'ldap_servers' in the main config) for authentication,
+                  place its name in 'server' element inside 'ldap' element.
+                 Example: <ldap><server>my_ldap_server</server></ldap>
+
+                 If you want to authenticate the user via Kerberos (assuming Kerberos is enabled, see 'kerberos' in the main config),
+                  place 'kerberos' element instead of 'password' (and similar) elements.
+                 The name part of the canonical principal name of the initiator must match the user name for authentication to succeed.
+                 You can also place 'realm' element inside 'kerberos' element to further restrict authentication to only those requests
+                  whose initiator's realm matches it.
+                 Example: <kerberos />
+                 Example: <kerberos><realm>EXAMPLE.COM</realm></kerberos>
+
+                 How to generate decent password:
+                 Execute: PASSWORD=$(base64 < /dev/urandom | head -c8); echo "$PASSWORD"; echo -n "$PASSWORD" | sha256sum | tr -d '-'
+                 In first line will be password and in second - corresponding SHA256.
+
+                 How to generate double SHA1:
+                 Execute: PASSWORD=$(base64 < /dev/urandom | head -c8); echo "$PASSWORD"; echo -n "$PASSWORD" | sha1sum | tr -d '-' | xxd -r -p | sha1sum | tr -d '-'
+                 In first line will be password and in second - corresponding double SHA1.
+            -->
+            <password></password>
+
+            <!-- List of networks with open access.
+
+                 To open access from everywhere, specify:
+                    <ip>::/0</ip>
+
+                 To open access only from localhost, specify:
+                    <ip>::1</ip>
+                    <ip>127.0.0.1</ip>
+
+                 Each element of list has one of the following forms:
+                 <ip> IP-address or network mask. Examples: 213.180.204.3 or 10.0.0.1/8 or 10.0.0.1/255.255.255.0
+                     2a02:6b8::3 or 2a02:6b8::3/64 or 2a02:6b8::3/ffff:ffff:ffff:ffff::.
+                 <host> Hostname. Example: server01.clickhouse.com.
+                     To check access, DNS query is performed, and all received addresses compared to peer address.
+                 <host_regexp> Regular expression for host names. Example, ^server\d\d-\d\d-\d\.clickhouse\.com$
+                     To check access, DNS PTR query is performed for peer address and then regexp is applied.
+                     Then, for result of PTR query, another DNS query is performed and all received addresses compared to peer address.
+                     Strongly recommended that regexp is ends with $
+                 All results of DNS requests are cached till server restart.
+            -->
+            <networks>
+                <ip>::/0</ip>
+            </networks>
+
+            <!-- Settings profile for user. -->
+            <profile>default</profile>
+
+            <!-- Quota for user. -->
+            <quota>default</quota>
+
+            <!-- User can create other users and grant rights to them. -->
+            <!-- <access_management>1</access_management> -->
+        </default>
+    </users>
+
+    <!-- Quotas. -->
+    <quotas>
+        <!-- Name of quota. -->
+        <default>
+            <!-- Limits for time interval. You could specify many intervals with different limits. -->
+            <interval>
+                <!-- Length of interval. -->
+                <duration>3600</duration>
+
+                <!-- No limits. Just calculate resource usage for time interval. -->
+                <queries>0</queries>
+                <errors>0</errors>
+                <result_rows>0</result_rows>
+                <read_rows>0</read_rows>
+                <execution_time>0</execution_time>
+            </interval>
+        </default>
+    </quotas>
+</clickhouse>

deploy/common/locust-scripts/locustfile.py

@@ -0,0 +1,16 @@
+from locust import HttpUser, task, between
+class UserTasks(HttpUser):
+    wait_time = between(5, 15)
+
+    @task
+    def rachel(self):
+        self.client.get("/dispatch?customer=123&nonse=0.6308392664170006")
+    @task
+    def trom(self):
+        self.client.get("/dispatch?customer=392&nonse=0.015296363321630757")
+    @task
+    def japanese(self):
+        self.client.get("/dispatch?customer=731&nonse=0.8022286220408668")
+    @task
+    def coffee(self):
+        self.client.get("/dispatch?customer=567&nonse=0.0022220379420636593")

deploy/common/signoz/otel-collector-opamp-config.yaml

@@ -0,0 +1 @@
+server_endpoint: ws://signoz:4320/v1/opamp

deploy/common/signoz/prometheus.yml

@@ -0,0 +1,25 @@
+# my global config
+global:
+  scrape_interval:     5s # Set the scrape interval to every 15 seconds. Default is every 1 minute.
+  evaluation_interval: 15s # Evaluate rules every 15 seconds. The default is every 1 minute.
+  # scrape_timeout is set to the global default (10s).
+
+# Alertmanager configuration
+alerting:
+  alertmanagers:
+  - static_configs:
+    - targets:
+      - alertmanager:9093
+
+# Load rules once and periodically evaluate them according to the global 'evaluation_interval'.
+rule_files: []
+  # - "first_rules.yml"
+  # - "second_rules.yml"
+  # - 'alerts.yml'
+
+# A scrape configuration containing exactly one endpoint to scrape:
+# Here it's Prometheus itself.
+scrape_configs: []
+
+remote_read:
+  - url: tcp://clickhouse:9000/signoz_metrics

deploy/docker-swarm/docker-compose.ha.yaml

@@ -0,0 +1,288 @@
+version: "3"
+x-common: &common
+  networks:
+    - signoz-net
+  deploy:
+    restart_policy:
+      condition: on-failure
+  logging:
+    options:
+      max-size: 50m
+      max-file: "3"
+x-clickhouse-defaults: &clickhouse-defaults
+  !!merge <<: *common
+  image: clickhouse/clickhouse-server:25.5.6
+  tty: true
+  deploy:
+    labels:
+      signoz.io/scrape: "true"
+      signoz.io/port: "9363"
+      signoz.io/path: "/metrics"
+  depends_on:
+    - zookeeper-1
+    - zookeeper-2
+    - zookeeper-3
+  healthcheck:
+    test:
+      - CMD
+      - wget
+      - --spider
+      - -q
+      - 0.0.0.0:8123/ping
+    interval: 30s
+    timeout: 5s
+    retries: 3
+  ulimits:
+    nproc: 65535
+    nofile:
+      soft: 262144
+      hard: 262144
+  environment:
+    - CLICKHOUSE_SKIP_USER_SETUP=1
+x-zookeeper-defaults: &zookeeper-defaults
+  !!merge <<: *common
+  image: signoz/zookeeper:3.7.1
+  user: root
+  deploy:
+    labels:
+      signoz.io/scrape: "true"
+      signoz.io/port: "9141"
+      signoz.io/path: "/metrics"
+  healthcheck:
+    test:
+      - CMD-SHELL
+      - curl -s -m 2 http://localhost:8080/commands/ruok | grep error | grep null
+    interval: 30s
+    timeout: 5s
+    retries: 3
+x-db-depend: &db-depend
+  !!merge <<: *common
+  depends_on:
+    - clickhouse
+    - clickhouse-2
+    - clickhouse-3
+services:
+  init-clickhouse:
+    !!merge <<: *common
+    image: clickhouse/clickhouse-server:25.5.6
+    command:
+      - bash
+      - -c
+      - |
+        version="v0.0.1"
+        node_os=$$(uname -s | tr '[:upper:]' '[:lower:]')
+        node_arch=$$(uname -m | sed s/aarch64/arm64/ | sed s/x86_64/amd64/)
+        echo "Fetching histogram-binary for $${node_os}/$${node_arch}"
+        cd /tmp
+        wget -O histogram-quantile.tar.gz "https://github.com/SigNoz/signoz/releases/download/histogram-quantile%2F$${version}/histogram-quantile_$${node_os}_$${node_arch}.tar.gz"
+        tar -xvzf histogram-quantile.tar.gz
+        mv histogram-quantile /var/lib/clickhouse/user_scripts/histogramQuantile
+    deploy:
+      restart_policy:
+        condition: on-failure
+    volumes:
+      - ../common/clickhouse/user_scripts:/var/lib/clickhouse/user_scripts/
+  zookeeper-1:
+    !!merge <<: *zookeeper-defaults
+    # ports:
+    #   - "2181:2181"
+    #   - "2888:2888"
+    #   - "3888:3888"
+    volumes:
+      - ./clickhouse-setup/data/zookeeper-1:/bitnami/zookeeper
+    environment:
+      - ZOO_SERVER_ID=1
+      - ZOO_SERVERS=0.0.0.0:2888:3888,zookeeper-2:2888:3888,zookeeper-3:2888:3888
+      - ALLOW_ANONYMOUS_LOGIN=yes
+      - ZOO_AUTOPURGE_INTERVAL=1
+      - ZOO_ENABLE_PROMETHEUS_METRICS=yes
+      - ZOO_PROMETHEUS_METRICS_PORT_NUMBER=9141
+  zookeeper-2:
+    !!merge <<: *zookeeper-defaults
+    # ports:
+    #   - "2182:2181"
+    #   - "2889:2888"
+    #   - "3889:3888"
+    volumes:
+      - ./clickhouse-setup/data/zookeeper-2:/bitnami/zookeeper
+    environment:
+      - ZOO_SERVER_ID=2
+      - ZOO_SERVERS=zookeeper-1:2888:3888,0.0.0.0:2888:3888,zookeeper-3:2888:3888
+      - ALLOW_ANONYMOUS_LOGIN=yes
+      - ZOO_AUTOPURGE_INTERVAL=1
+      - ZOO_ENABLE_PROMETHEUS_METRICS=yes
+      - ZOO_PROMETHEUS_METRICS_PORT_NUMBER=9141
+  zookeeper-3:
+    !!merge <<: *zookeeper-defaults
+    # ports:
+    #   - "2183:2181"
+    #   - "2890:2888"
+    #   - "3890:3888"
+    volumes:
+      - ./clickhouse-setup/data/zookeeper-3:/bitnami/zookeeper
+    environment:
+      - ZOO_SERVER_ID=3
+      - ZOO_SERVERS=zookeeper-1:2888:3888,zookeeper-2:2888:3888,0.0.0.0:2888:3888
+      - ALLOW_ANONYMOUS_LOGIN=yes
+      - ZOO_AUTOPURGE_INTERVAL=1
+      - ZOO_ENABLE_PROMETHEUS_METRICS=yes
+      - ZOO_PROMETHEUS_METRICS_PORT_NUMBER=9141
+  clickhouse:
+    !!merge <<: *clickhouse-defaults
+    # TODO: needed for schema-migrator to work, remove this redundancy once we have a better solution
+    hostname: clickhouse
+    # ports:
+    #   - "9000:9000"
+    #   - "8123:8123"
+    #   - "9181:9181"
+    configs:
+      - source: clickhouse-config
+        target: /etc/clickhouse-server/config.xml
+      - source: clickhouse-users
+        target: /etc/clickhouse-server/users.xml
+      - source: clickhouse-custom-function
+        target: /etc/clickhouse-server/custom-function.xml
+      - source: clickhouse-cluster
+        target: /etc/clickhouse-server/config.d/cluster.ha.xml
+    volumes:
+      - ../common/clickhouse/user_scripts:/var/lib/clickhouse/user_scripts/
+      - ./clickhouse-setup/data/clickhouse/:/var/lib/clickhouse/
+      # - ../common/clickhouse/storage.xml:/etc/clickhouse-server/config.d/storage.xml
+  clickhouse-2:
+    !!merge <<: *clickhouse-defaults
+    hostname: clickhouse-2
+    # ports:
+    #   - "9001:9000"
+    #   - "8124:8123"
+    #   - "9182:9181"
+    configs:
+      - source: clickhouse-config
+        target: /etc/clickhouse-server/config.xml
+      - source: clickhouse-users
+        target: /etc/clickhouse-server/users.xml
+      - source: clickhouse-custom-function
+        target: /etc/clickhouse-server/custom-function.xml
+      - source: clickhouse-cluster
+        target: /etc/clickhouse-server/config.d/cluster.ha.xml
+    volumes:
+      - ../common/clickhouse/user_scripts:/var/lib/clickhouse/user_scripts/
+      - ./clickhouse-setup/data/clickhouse-2/:/var/lib/clickhouse/
+      # - ../common/clickhouse/storage.xml:/etc/clickhouse-server/config.d/storage.xml
+  clickhouse-3:
+    !!merge <<: *clickhouse-defaults
+    hostname: clickhouse-3
+    # ports:
+    #   - "9002:9000"
+    #   - "8125:8123"
+    #   - "9183:9181"
+    configs:
+      - source: clickhouse-config
+        target: /etc/clickhouse-server/config.xml
+      - source: clickhouse-users
+        target: /etc/clickhouse-server/users.xml
+      - source: clickhouse-custom-function
+        target: /etc/clickhouse-server/custom-function.xml
+      - source: clickhouse-cluster
+        target: /etc/clickhouse-server/config.d/cluster.ha.xml
+    volumes:
+      - ../common/clickhouse/user_scripts:/var/lib/clickhouse/user_scripts/
+      - ./clickhouse-setup/data/clickhouse-3/:/var/lib/clickhouse/
+      # - ../common/clickhouse/storage.xml:/etc/clickhouse-server/config.d/storage.xml
+  signoz:
+    !!merge <<: *db-depend
+    image: signoz/signoz:v0.122.0
+    ports:
+      - "8080:8080" # signoz port
+    #   - "6060:6060"     # pprof port
+    volumes:
+      - ./clickhouse-setup/data/signoz/:/var/lib/signoz/
+    environment:
+      - SIGNOZ_ALERTMANAGER_PROVIDER=signoz
+      - SIGNOZ_TELEMETRYSTORE_CLICKHOUSE_DSN=tcp://clickhouse:9000
+      - SIGNOZ_SQLSTORE_SQLITE_PATH=/var/lib/signoz/signoz.db
+      - SIGNOZ_TOKENIZER_JWT_SECRET=secret
+    healthcheck:
+      test:
+        - CMD
+        - wget
+        - --spider
+        - -q
+        - localhost:8080/api/v1/health
+      interval: 30s
+      timeout: 5s
+      retries: 3
+  otel-collector:
+    !!merge <<: *db-depend
+    image: signoz/signoz-otel-collector:v0.144.4
+    entrypoint:
+      - /bin/sh
+    command:
+      - -c
+      - |
+        /signoz-otel-collector migrate sync check &&
+        /signoz-otel-collector --config=/etc/otel-collector-config.yaml --manager-config=/etc/manager-config.yaml --copy-path=/var/tmp/collector-config.yaml
+    configs:
+      - source: otel-collector-config
+        target: /etc/otel-collector-config.yaml
+      - source: otel-manager-config
+        target: /etc/manager-config.yaml
+    environment:
+      - OTEL_RESOURCE_ATTRIBUTES=host.name={{.Node.Hostname}},os.type={{.Node.Platform.OS}}
+      - LOW_CARDINAL_EXCEPTION_GROUPING=false
+      - SIGNOZ_OTEL_COLLECTOR_CLICKHOUSE_DSN=tcp://clickhouse:9000
+      - SIGNOZ_OTEL_COLLECTOR_CLICKHOUSE_CLUSTER=cluster
+      - SIGNOZ_OTEL_COLLECTOR_CLICKHOUSE_REPLICATION=true
+      - SIGNOZ_OTEL_COLLECTOR_TIMEOUT=10m
+    ports:
+      # - "1777:1777"     # pprof extension
+      - "4317:4317" # OTLP gRPC receiver
+      - "4318:4318" # OTLP HTTP receiver
+    deploy:
+      replicas: 3
+  signoz-telemetrystore-migrator:
+    !!merge <<: *db-depend
+    image: signoz/signoz-otel-collector:v0.144.4
+    environment:
+      - SIGNOZ_OTEL_COLLECTOR_CLICKHOUSE_DSN=tcp://clickhouse:9000
+      - SIGNOZ_OTEL_COLLECTOR_CLICKHOUSE_CLUSTER=cluster
+      - SIGNOZ_OTEL_COLLECTOR_CLICKHOUSE_REPLICATION=true
+      - SIGNOZ_OTEL_COLLECTOR_TIMEOUT=10m
+    entrypoint:
+      - /bin/sh
+    command:
+      - -c
+      - |
+        /signoz-otel-collector migrate bootstrap &&
+        /signoz-otel-collector migrate sync up &&
+        /signoz-otel-collector migrate async up
+networks:
+  signoz-net:
+    name: signoz-net
+volumes:
+  clickhouse:
+    name: signoz-clickhouse
+  clickhouse-2:
+    name: signoz-clickhouse-2
+  clickhouse-3:
+    name: signoz-clickhouse-3
+  sqlite:
+    name: signoz-sqlite
+  zookeeper-1:
+    name: signoz-zookeeper-1
+  zookeeper-2:
+    name: signoz-zookeeper-2
+  zookeeper-3:
+    name: signoz-zookeeper-3
+configs:
+  clickhouse-config:
+    file: ../common/clickhouse/config.xml
+  clickhouse-users:
+    file: ../common/clickhouse/users.xml
+  clickhouse-custom-function:
+    file: ../common/clickhouse/custom-function.xml
+  clickhouse-cluster:
+    file: ../common/clickhouse/cluster.ha.xml
+  otel-collector-config:
+    file: ./otel-collector-config.yaml
+  otel-manager-config:
+    file: ../common/signoz/otel-collector-opamp-config.yaml

deploy/docker-swarm/docker-compose.yaml

@@ -0,0 +1,206 @@
+version: "3"
+x-common: &common
+  networks:
+    - signoz-net
+  deploy:
+    restart_policy:
+      condition: on-failure
+  logging:
+    options:
+      max-size: 50m
+      max-file: "3"
+x-clickhouse-defaults: &clickhouse-defaults
+  !!merge <<: *common
+  image: clickhouse/clickhouse-server:25.5.6
+  tty: true
+  deploy:
+    labels:
+      signoz.io/scrape: "true"
+      signoz.io/port: "9363"
+      signoz.io/path: "/metrics"
+  depends_on:
+    - init-clickhouse
+    - zookeeper-1
+  healthcheck:
+    test:
+      - CMD
+      - wget
+      - --spider
+      - -q
+      - 0.0.0.0:8123/ping
+    interval: 30s
+    timeout: 5s
+    retries: 3
+  ulimits:
+    nproc: 65535
+    nofile:
+      soft: 262144
+      hard: 262144
+  environment:
+    - CLICKHOUSE_SKIP_USER_SETUP=1
+x-zookeeper-defaults: &zookeeper-defaults
+  !!merge <<: *common
+  image: signoz/zookeeper:3.7.1
+  user: root
+  deploy:
+    labels:
+      signoz.io/scrape: "true"
+      signoz.io/port: "9141"
+      signoz.io/path: "/metrics"
+  healthcheck:
+    test:
+      - CMD-SHELL
+      - curl -s -m 2 http://localhost:8080/commands/ruok | grep error | grep null
+    interval: 30s
+    timeout: 5s
+    retries: 3
+x-db-depend: &db-depend
+  !!merge <<: *common
+  depends_on:
+    - clickhouse
+services:
+  init-clickhouse:
+    !!merge <<: *common
+    image: clickhouse/clickhouse-server:25.5.6
+    command:
+      - bash
+      - -c
+      - |
+        version="v0.0.1"
+        node_os=$$(uname -s | tr '[:upper:]' '[:lower:]')
+        node_arch=$$(uname -m | sed s/aarch64/arm64/ | sed s/x86_64/amd64/)
+        echo "Fetching histogram-binary for $${node_os}/$${node_arch}"
+        cd /tmp
+        wget -O histogram-quantile.tar.gz "https://github.com/SigNoz/signoz/releases/download/histogram-quantile%2F$${version}/histogram-quantile_$${node_os}_$${node_arch}.tar.gz"
+        tar -xvzf histogram-quantile.tar.gz
+        mv histogram-quantile /var/lib/clickhouse/user_scripts/histogramQuantile
+    deploy:
+      restart_policy:
+        condition: on-failure
+    volumes:
+      - ../common/clickhouse/user_scripts:/var/lib/clickhouse/user_scripts/
+  zookeeper-1:
+    !!merge <<: *zookeeper-defaults
+    # ports:
+    #   - "2181:2181"
+    #   - "2888:2888"
+    #   - "3888:3888"
+    volumes:
+      - zookeeper-1:/bitnami/zookeeper
+    environment:
+      - ZOO_SERVER_ID=1
+      - ALLOW_ANONYMOUS_LOGIN=yes
+      - ZOO_AUTOPURGE_INTERVAL=1
+      - ZOO_ENABLE_PROMETHEUS_METRICS=yes
+      - ZOO_PROMETHEUS_METRICS_PORT_NUMBER=9141
+  clickhouse:
+    !!merge <<: *clickhouse-defaults
+    # TODO: needed for clickhouse TCP connectio
+    hostname: clickhouse
+    # ports:
+    #   - "9000:9000"
+    #   - "8123:8123"
+    #   - "9181:9181"
+
+    configs:
+      - source: clickhouse-config
+        target: /etc/clickhouse-server/config.xml
+      - source: clickhouse-users
+        target: /etc/clickhouse-server/users.xml
+      - source: clickhouse-custom-function
+        target: /etc/clickhouse-server/custom-function.xml
+      - source: clickhouse-cluster
+        target: /etc/clickhouse-server/config.d/cluster.xml
+    volumes:
+      - clickhouse:/var/lib/clickhouse/
+      - ../common/clickhouse/user_scripts:/var/lib/clickhouse/user_scripts/
+      # - ../common/clickhouse/storage.xml:/etc/clickhouse-server/config.d/storage.xml
+  signoz:
+    !!merge <<: *db-depend
+    image: signoz/signoz:v0.122.0
+    ports:
+      - "8080:8080" # signoz port
+    volumes:
+      - sqlite:/var/lib/signoz/
+    environment:
+      - SIGNOZ_ALERTMANAGER_PROVIDER=signoz
+      - SIGNOZ_TELEMETRYSTORE_CLICKHOUSE_DSN=tcp://clickhouse:9000
+      - SIGNOZ_SQLSTORE_SQLITE_PATH=/var/lib/signoz/signoz.db
+      - SIGNOZ_TOKENIZER_JWT_SECRET=secret
+    healthcheck:
+      test:
+        - CMD
+        - wget
+        - --spider
+        - -q
+        - localhost:8080/api/v1/health
+      interval: 30s
+      timeout: 5s
+      retries: 3
+  otel-collector:
+    !!merge <<: *db-depend
+    image: signoz/signoz-otel-collector:v0.144.4
+    entrypoint:
+      - /bin/sh
+    command:
+      - -c
+      - |
+        /signoz-otel-collector migrate sync check &&
+        /signoz-otel-collector --config=/etc/otel-collector-config.yaml --manager-config=/etc/manager-config.yaml --copy-path=/var/tmp/collector-config.yaml
+    configs:
+      - source: otel-collector-config
+        target: /etc/otel-collector-config.yaml
+      - source: otel-manager-config
+        target: /etc/manager-config.yaml
+    environment:
+      - OTEL_RESOURCE_ATTRIBUTES=host.name={{.Node.Hostname}},os.type={{.Node.Platform.OS}}
+      - LOW_CARDINAL_EXCEPTION_GROUPING=false
+      - SIGNOZ_OTEL_COLLECTOR_CLICKHOUSE_DSN=tcp://clickhouse:9000
+      - SIGNOZ_OTEL_COLLECTOR_CLICKHOUSE_CLUSTER=cluster
+      - SIGNOZ_OTEL_COLLECTOR_CLICKHOUSE_REPLICATION=true
+      - SIGNOZ_OTEL_COLLECTOR_TIMEOUT=10m
+    ports:
+      # - "1777:1777"     # pprof extension
+      - "4317:4317" # OTLP gRPC receiver
+      - "4318:4318" # OTLP HTTP receiver
+    deploy:
+      replicas: 3
+  signoz-telemetrystore-migrator:
+    !!merge <<: *db-depend
+    image: signoz/signoz-otel-collector:v0.144.4
+    environment:
+      - SIGNOZ_OTEL_COLLECTOR_CLICKHOUSE_DSN=tcp://clickhouse:9000
+      - SIGNOZ_OTEL_COLLECTOR_CLICKHOUSE_CLUSTER=cluster
+      - SIGNOZ_OTEL_COLLECTOR_CLICKHOUSE_REPLICATION=true
+      - SIGNOZ_OTEL_COLLECTOR_TIMEOUT=10m
+    entrypoint:
+      - /bin/sh
+    command:
+      - -c
+      - |
+        /signoz-otel-collector migrate bootstrap &&
+        /signoz-otel-collector migrate sync up &&
+        /signoz-otel-collector migrate async up
+networks:
+  signoz-net:
+    name: signoz-net
+volumes:
+  clickhouse:
+    name: signoz-clickhouse
+  sqlite:
+    name: signoz-sqlite
+  zookeeper-1:
+    name: signoz-zookeeper-1
+configs:
+  clickhouse-config:
+    file: ../common/clickhouse/config.xml
+  clickhouse-users:
+    file: ../common/clickhouse/users.xml
+  clickhouse-custom-function:
+    file: ../common/clickhouse/custom-function.xml
+  clickhouse-cluster:
+    file: ../common/clickhouse/cluster.xml
+  otel-collector-config:
+    file: ./otel-collector-config.yaml
+  otel-manager-config:
+    file: ../common/signoz/otel-collector-opamp-config.yaml

deploy/docker-swarm/otel-collector-config.yaml

@@ -0,0 +1,118 @@
+connectors:
+  signozmeter:
+    metrics_flush_interval: 1h
+    dimensions:
+      - name: service.name
+      - name: deployment.environment
+      - name: host.name
+receivers:
+  otlp:
+    protocols:
+      grpc:
+        endpoint: 0.0.0.0:4317
+      http:
+        endpoint: 0.0.0.0:4318
+  prometheus:
+    config:
+      global:
+        scrape_interval: 60s
+      scrape_configs:
+        - job_name: otel-collector
+          static_configs:
+          - targets:
+              - localhost:8888
+            labels:
+              job_name: otel-collector
+processors:
+  batch:
+    send_batch_size: 10000
+    send_batch_max_size: 11000
+    timeout: 10s
+  batch/meter:
+    send_batch_max_size: 25000
+    send_batch_size: 20000
+    timeout: 1s
+  resourcedetection:
+    # Using OTEL_RESOURCE_ATTRIBUTES envvar, env detector adds custom labels.
+    detectors: [env, system]
+    timeout: 2s
+  signozspanmetrics/delta:
+    metrics_exporter: signozclickhousemetrics
+    metrics_flush_interval: 60s
+    latency_histogram_buckets: [100us, 1ms, 2ms, 6ms, 10ms, 50ms, 100ms, 250ms, 500ms, 1000ms, 1400ms, 2000ms, 5s, 10s, 20s, 40s, 60s ]
+    dimensions_cache_size: 100000
+    aggregation_temporality: AGGREGATION_TEMPORALITY_DELTA
+    enable_exp_histogram: true
+    dimensions:
+      - name: service.namespace
+        default: default
+      - name: deployment.environment
+        default: default
+      # This is added to ensure the uniqueness of the timeseries
+      # Otherwise, identical timeseries produced by multiple replicas of
+      # collectors result in incorrect APM metrics
+      - name: signoz.collector.id
+      - name: service.version
+      - name: browser.platform
+      - name: browser.mobile
+      - name: k8s.cluster.name
+      - name: k8s.node.name
+      - name: k8s.namespace.name
+      - name: host.name
+      - name: host.type
+      - name: container.name
+extensions:
+  health_check:
+    endpoint: 0.0.0.0:13133
+  pprof:
+    endpoint: 0.0.0.0:1777
+exporters:
+  clickhousetraces:
+    datasource: tcp://clickhouse:9000/signoz_traces
+    low_cardinal_exception_grouping: ${env:LOW_CARDINAL_EXCEPTION_GROUPING}
+    use_new_schema: true
+  signozclickhousemetrics:
+    dsn: tcp://clickhouse:9000/signoz_metrics
+  clickhouselogsexporter:
+    dsn: tcp://clickhouse:9000/signoz_logs
+    timeout: 10s
+    use_new_schema: true
+  signozclickhousemeter:
+    dsn: tcp://clickhouse:9000/signoz_meter
+    timeout: 45s
+    sending_queue:
+      enabled: false
+  metadataexporter:
+    cache:
+      provider: in_memory
+    dsn: tcp://clickhouse:9000/signoz_metadata
+    enabled: true
+    timeout: 45s
+service:
+  telemetry:
+    logs:
+      encoding: json
+  extensions:
+    - health_check
+    - pprof
+  pipelines:
+    traces:
+      receivers: [otlp]
+      processors: [signozspanmetrics/delta, batch]
+      exporters: [clickhousetraces, metadataexporter, signozmeter]
+    metrics:
+      receivers: [otlp]
+      processors: [batch]
+      exporters: [signozclickhousemetrics, metadataexporter, signozmeter]
+    metrics/prometheus:
+      receivers: [prometheus]
+      processors: [batch]
+      exporters: [signozclickhousemetrics, metadataexporter, signozmeter]
+    logs:
+      receivers: [otlp]
+      processors: [batch]
+      exporters: [clickhouselogsexporter, metadataexporter, signozmeter]
+    metrics/meter:
+      receivers: [signozmeter]
+      processors: [batch/meter]
+      exporters: [signozclickhousemeter]

deploy/docker/.env

@@ -0,0 +1 @@
+COMPOSE_PROJECT_NAME=signoz

deploy/docker/clickhouse-setup/.deprecated

@@ -0,0 +1,3 @@
+This data directory is deprecated and will be removed in the future.
+Please use the migration script under `scripts/volume-migration` to migrate data from bind mounts to Docker volumes.
+The script also renames the project name to `signoz` and the network name to `signoz-net` (if not already in place).

deploy/docker/clickhouse-setup/user_scripts/.deprecated

@@ -0,0 +1,2 @@
+This directory is deprecated and will be removed in the future.
+Please use the new directory for Clickhouse setup scripts: `scripts/clickhouse` instead.

deploy/docker/docker-compose.ha.yaml

@@ -0,0 +1,265 @@
+version: "3"
+x-common: &common
+  networks:
+    - signoz-net
+  restart: unless-stopped
+  logging:
+    options:
+      max-size: 50m
+      max-file: "3"
+x-clickhouse-defaults: &clickhouse-defaults
+  !!merge <<: *common
+  # addding non LTS version due to this fix https://github.com/ClickHouse/ClickHouse/commit/32caf8716352f45c1b617274c7508c86b7d1afab
+  image: clickhouse/clickhouse-server:25.5.6
+  tty: true
+  labels:
+    signoz.io/scrape: "true"
+    signoz.io/port: "9363"
+    signoz.io/path: "/metrics"
+  depends_on:
+    init-clickhouse:
+      condition: service_completed_successfully
+    zookeeper-1:
+      condition: service_healthy
+    zookeeper-2:
+      condition: service_healthy
+    zookeeper-3:
+      condition: service_healthy
+  healthcheck:
+    test:
+      - CMD
+      - wget
+      - --spider
+      - -q
+      - 0.0.0.0:8123/ping
+    interval: 30s
+    timeout: 5s
+    retries: 3
+  ulimits:
+    nproc: 65535
+    nofile:
+      soft: 262144
+      hard: 262144
+  environment:
+    - CLICKHOUSE_SKIP_USER_SETUP=1
+x-zookeeper-defaults: &zookeeper-defaults
+  !!merge <<: *common
+  image: signoz/zookeeper:3.7.1
+  user: root
+  labels:
+    signoz.io/scrape: "true"
+    signoz.io/port: "9141"
+    signoz.io/path: "/metrics"
+  healthcheck:
+    test:
+      - CMD-SHELL
+      - curl -s -m 2 http://localhost:8080/commands/ruok | grep error | grep null
+    interval: 30s
+    timeout: 5s
+    retries: 3
+x-db-depend: &db-depend
+  !!merge <<: *common
+  depends_on:
+    clickhouse:
+      condition: service_healthy
+    clickhouse-2:
+      condition: service_healthy
+    clickhouse-3:
+      condition: service_healthy
+services:
+  init-clickhouse:
+    !!merge <<: *common
+    image: clickhouse/clickhouse-server:25.5.6
+    container_name: signoz-init-clickhouse
+    command:
+      - bash
+      - -c
+      - |
+        version="v0.0.1"
+        node_os=$$(uname -s | tr '[:upper:]' '[:lower:]')
+        node_arch=$$(uname -m | sed s/aarch64/arm64/ | sed s/x86_64/amd64/)
+        echo "Fetching histogram-binary for $${node_os}/$${node_arch}"
+        cd /tmp
+        wget -O histogram-quantile.tar.gz "https://github.com/SigNoz/signoz/releases/download/histogram-quantile%2F$${version}/histogram-quantile_$${node_os}_$${node_arch}.tar.gz"
+        tar -xvzf histogram-quantile.tar.gz
+        mv histogram-quantile /var/lib/clickhouse/user_scripts/histogramQuantile
+    restart: on-failure
+    volumes:
+      - ../common/clickhouse/user_scripts:/var/lib/clickhouse/user_scripts/
+  zookeeper-1:
+    !!merge <<: *zookeeper-defaults
+    container_name: signoz-zookeeper-1
+    # ports:
+    #   - "2181:2181"
+    #   - "2888:2888"
+    #   - "3888:3888"
+    volumes:
+      - zookeeper-1:/bitnami/zookeeper
+    environment:
+      - ZOO_SERVER_ID=1
+      - ZOO_SERVERS=0.0.0.0:2888:3888,zookeeper-2:2888:3888,zookeeper-3:2888:3888
+      - ALLOW_ANONYMOUS_LOGIN=yes
+      - ZOO_AUTOPURGE_INTERVAL=1
+      - ZOO_ENABLE_PROMETHEUS_METRICS=yes
+      - ZOO_PROMETHEUS_METRICS_PORT_NUMBER=9141
+  zookeeper-2:
+    !!merge <<: *zookeeper-defaults
+    container_name: signoz-zookeeper-2
+    # ports:
+    #   - "2182:2181"
+    #   - "2889:2888"
+    #   - "3889:3888"
+    volumes:
+      - zookeeper-2:/bitnami/zookeeper
+    environment:
+      - ZOO_SERVER_ID=2
+      - ZOO_SERVERS=zookeeper-1:2888:3888,0.0.0.0:2888:3888,zookeeper-3:2888:3888
+      - ALLOW_ANONYMOUS_LOGIN=yes
+      - ZOO_AUTOPURGE_INTERVAL=1
+      - ZOO_ENABLE_PROMETHEUS_METRICS=yes
+      - ZOO_PROMETHEUS_METRICS_PORT_NUMBER=9141
+  zookeeper-3:
+    !!merge <<: *zookeeper-defaults
+    container_name: signoz-zookeeper-3
+    # ports:
+    #   - "2183:2181"
+    #   - "2890:2888"
+    #   - "3890:3888"
+    volumes:
+      - zookeeper-3:/bitnami/zookeeper
+    environment:
+      - ZOO_SERVER_ID=3
+      - ZOO_SERVERS=zookeeper-1:2888:3888,zookeeper-2:2888:3888,0.0.0.0:2888:3888
+      - ALLOW_ANONYMOUS_LOGIN=yes
+      - ZOO_AUTOPURGE_INTERVAL=1
+      - ZOO_ENABLE_PROMETHEUS_METRICS=yes
+      - ZOO_PROMETHEUS_METRICS_PORT_NUMBER=9141
+  clickhouse:
+    !!merge <<: *clickhouse-defaults
+    container_name: signoz-clickhouse
+    # ports:
+    #   - "9000:9000"
+    #   - "8123:8123"
+    #   - "9181:9181"
+    volumes:
+      - ../common/clickhouse/config.xml:/etc/clickhouse-server/config.xml
+      - ../common/clickhouse/users.xml:/etc/clickhouse-server/users.xml
+      - ../common/clickhouse/custom-function.xml:/etc/clickhouse-server/custom-function.xml
+      - ../common/clickhouse/user_scripts:/var/lib/clickhouse/user_scripts/
+      - ../common/clickhouse/cluster.ha.xml:/etc/clickhouse-server/config.d/cluster.xml
+      - clickhouse:/var/lib/clickhouse/
+      # - ../common/clickhouse/storage.xml:/etc/clickhouse-server/config.d/storage.xml
+  clickhouse-2:
+    !!merge <<: *clickhouse-defaults
+    container_name: signoz-clickhouse-2
+    # ports:
+    #   - "9001:9000"
+    #   - "8124:8123"
+    #   - "9182:9181"
+    volumes:
+      - ../common/clickhouse/config.xml:/etc/clickhouse-server/config.xml
+      - ../common/clickhouse/users.xml:/etc/clickhouse-server/users.xml
+      - ../common/clickhouse/custom-function.xml:/etc/clickhouse-server/custom-function.xml
+      - ../common/clickhouse/user_scripts:/var/lib/clickhouse/user_scripts/
+      - ../common/clickhouse/cluster.ha.xml:/etc/clickhouse-server/config.d/cluster.xml
+      - clickhouse-2:/var/lib/clickhouse/
+      # - ../common/clickhouse/storage.xml:/etc/clickhouse-server/config.d/storage.xml
+  clickhouse-3:
+    !!merge <<: *clickhouse-defaults
+    container_name: signoz-clickhouse-3
+    # ports:
+    #   - "9002:9000"
+    #   - "8125:8123"
+    #   - "9183:9181"
+    volumes:
+      - ../common/clickhouse/config.xml:/etc/clickhouse-server/config.xml
+      - ../common/clickhouse/users.xml:/etc/clickhouse-server/users.xml
+      - ../common/clickhouse/custom-function.xml:/etc/clickhouse-server/custom-function.xml
+      - ../common/clickhouse/user_scripts:/var/lib/clickhouse/user_scripts/
+      - ../common/clickhouse/cluster.ha.xml:/etc/clickhouse-server/config.d/cluster.xml
+      - clickhouse-3:/var/lib/clickhouse/
+      # - ../common/clickhouse/storage.xml:/etc/clickhouse-server/config.d/storage.xml
+  signoz:
+    !!merge <<: *db-depend
+    image: signoz/signoz:${VERSION:-v0.122.0}
+    container_name: signoz
+    ports:
+      - "8080:8080" # signoz port
+    volumes:
+      - sqlite:/var/lib/signoz/
+    environment:
+      - SIGNOZ_ALERTMANAGER_PROVIDER=signoz
+      - SIGNOZ_TELEMETRYSTORE_CLICKHOUSE_DSN=tcp://clickhouse:9000
+      - SIGNOZ_SQLSTORE_SQLITE_PATH=/var/lib/signoz/signoz.db
+      - SIGNOZ_TOKENIZER_JWT_SECRET=secret
+    healthcheck:
+      test:
+        - CMD
+        - wget
+        - --spider
+        - -q
+        - localhost:8080/api/v1/health
+      interval: 30s
+      timeout: 5s
+      retries: 3
+  otel-collector:
+    !!merge <<: *db-depend
+    image: signoz/signoz-otel-collector:${OTELCOL_TAG:-v0.144.4}
+    container_name: signoz-otel-collector
+    entrypoint:
+      - /bin/sh
+    command:
+      - -c
+      - |
+        /signoz-otel-collector migrate sync check &&
+        /signoz-otel-collector --config=/etc/otel-collector-config.yaml --manager-config=/etc/manager-config.yaml --copy-path=/var/tmp/collector-config.yaml
+    volumes:
+      - ./otel-collector-config.yaml:/etc/otel-collector-config.yaml
+      - ../common/signoz/otel-collector-opamp-config.yaml:/etc/manager-config.yaml
+    environment:
+      - OTEL_RESOURCE_ATTRIBUTES=host.name=signoz-host,os.type=linux
+      - LOW_CARDINAL_EXCEPTION_GROUPING=false
+      - SIGNOZ_OTEL_COLLECTOR_CLICKHOUSE_DSN=tcp://clickhouse:9000
+      - SIGNOZ_OTEL_COLLECTOR_CLICKHOUSE_CLUSTER=cluster
+      - SIGNOZ_OTEL_COLLECTOR_CLICKHOUSE_REPLICATION=true
+      - SIGNOZ_OTEL_COLLECTOR_TIMEOUT=10m
+    ports:
+      # - "1777:1777"     # pprof extension
+      - "4317:4317" # OTLP gRPC receiver
+      - "4318:4318" # OTLP HTTP receiver
+  signoz-telemetrystore-migrator:
+    !!merge <<: *db-depend
+    image: signoz/signoz-otel-collector:${OTELCOL_TAG:-v0.144.4}
+    container_name: signoz-telemetrystore-migrator
+    environment:
+      - SIGNOZ_OTEL_COLLECTOR_CLICKHOUSE_DSN=tcp://clickhouse:9000
+      - SIGNOZ_OTEL_COLLECTOR_CLICKHOUSE_CLUSTER=cluster
+      - SIGNOZ_OTEL_COLLECTOR_CLICKHOUSE_REPLICATION=true
+      - SIGNOZ_OTEL_COLLECTOR_TIMEOUT=10m
+    entrypoint:
+      - /bin/sh
+    command:
+      - -c
+      - |
+        /signoz-otel-collector migrate bootstrap &&
+        /signoz-otel-collector migrate sync up &&
+        /signoz-otel-collector migrate async up
+    restart: on-failure
+networks:
+  signoz-net:
+    name: signoz-net
+volumes:
+  clickhouse:
+    name: signoz-clickhouse
+  clickhouse-2:
+    name: signoz-clickhouse-2
+  clickhouse-3:
+    name: signoz-clickhouse-3
+  sqlite:
+    name: signoz-sqlite
+  zookeeper-1:
+    name: signoz-zookeeper-1
+  zookeeper-2:
+    name: signoz-zookeeper-2
+  zookeeper-3:
+    name: signoz-zookeeper-3

deploy/docker/docker-compose.yaml

@@ -0,0 +1,185 @@
+version: "3"
+x-common: &common
+  networks:
+    - signoz-net
+  restart: unless-stopped
+  logging:
+    options:
+      max-size: 50m
+      max-file: "3"
+x-clickhouse-defaults: &clickhouse-defaults
+  !!merge <<: *common
+  image: clickhouse/clickhouse-server:25.5.6
+  tty: true
+  labels:
+    signoz.io/scrape: "true"
+    signoz.io/port: "9363"
+    signoz.io/path: "/metrics"
+  depends_on:
+    init-clickhouse:
+      condition: service_completed_successfully
+    zookeeper-1:
+      condition: service_healthy
+  healthcheck:
+    test:
+      - CMD
+      - wget
+      - --spider
+      - -q
+      - 0.0.0.0:8123/ping
+    interval: 30s
+    timeout: 5s
+    retries: 3
+  ulimits:
+    nproc: 65535
+    nofile:
+      soft: 262144
+      hard: 262144
+  environment:
+    - CLICKHOUSE_SKIP_USER_SETUP=1
+x-zookeeper-defaults: &zookeeper-defaults
+  !!merge <<: *common
+  image: signoz/zookeeper:3.7.1
+  user: root
+  labels:
+    signoz.io/scrape: "true"
+    signoz.io/port: "9141"
+    signoz.io/path: "/metrics"
+  healthcheck:
+    test:
+      - CMD-SHELL
+      - curl -s -m 2 http://localhost:8080/commands/ruok | grep error | grep null
+    interval: 30s
+    timeout: 5s
+    retries: 3
+x-db-depend: &db-depend
+  !!merge <<: *common
+  depends_on:
+    clickhouse:
+      condition: service_healthy
+services:
+  init-clickhouse:
+    !!merge <<: *common
+    image: clickhouse/clickhouse-server:25.5.6
+    container_name: signoz-init-clickhouse
+    command:
+      - bash
+      - -c
+      - |
+        version="v0.0.1"
+        node_os=$$(uname -s | tr '[:upper:]' '[:lower:]')
+        node_arch=$$(uname -m | sed s/aarch64/arm64/ | sed s/x86_64/amd64/)
+        echo "Fetching histogram-binary for $${node_os}/$${node_arch}"
+        cd /tmp
+        wget -O histogram-quantile.tar.gz "https://github.com/SigNoz/signoz/releases/download/histogram-quantile%2F$${version}/histogram-quantile_$${node_os}_$${node_arch}.tar.gz"
+        tar -xvzf histogram-quantile.tar.gz
+        mv histogram-quantile /var/lib/clickhouse/user_scripts/histogramQuantile
+    restart: on-failure
+    volumes:
+      - ../common/clickhouse/user_scripts:/var/lib/clickhouse/user_scripts/
+  zookeeper-1:
+    !!merge <<: *zookeeper-defaults
+    container_name: signoz-zookeeper-1
+    # ports:
+    #   - "2181:2181"
+    #   - "2888:2888"
+    #   - "3888:3888"
+    volumes:
+      - zookeeper-1:/bitnami/zookeeper
+    environment:
+      - ZOO_SERVER_ID=1
+      - ALLOW_ANONYMOUS_LOGIN=yes
+      - ZOO_AUTOPURGE_INTERVAL=1
+      - ZOO_ENABLE_PROMETHEUS_METRICS=yes
+      - ZOO_PROMETHEUS_METRICS_PORT_NUMBER=9141
+  clickhouse:
+    !!merge <<: *clickhouse-defaults
+    container_name: signoz-clickhouse
+    # ports:
+    #   - "9000:9000"
+    #   - "8123:8123"
+    #   - "9181:9181"
+    volumes:
+      - ../common/clickhouse/config.xml:/etc/clickhouse-server/config.xml
+      - ../common/clickhouse/users.xml:/etc/clickhouse-server/users.xml
+      - ../common/clickhouse/custom-function.xml:/etc/clickhouse-server/custom-function.xml
+      - ../common/clickhouse/user_scripts:/var/lib/clickhouse/user_scripts/
+      - ../common/clickhouse/cluster.xml:/etc/clickhouse-server/config.d/cluster.xml
+      - clickhouse:/var/lib/clickhouse/
+      # - ../common/clickhouse/storage.xml:/etc/clickhouse-server/config.d/storage.xml
+  signoz:
+    !!merge <<: *db-depend
+    image: signoz/signoz:${VERSION:-v0.122.0}
+    container_name: signoz
+    ports:
+      - "8080:8080" # signoz port
+    volumes:
+      - sqlite:/var/lib/signoz/
+    environment:
+      - SIGNOZ_ALERTMANAGER_PROVIDER=signoz
+      - SIGNOZ_TELEMETRYSTORE_CLICKHOUSE_DSN=tcp://clickhouse:9000
+      - SIGNOZ_SQLSTORE_SQLITE_PATH=/var/lib/signoz/signoz.db
+      - SIGNOZ_TOKENIZER_JWT_SECRET=secret
+    healthcheck:
+      test:
+        - CMD
+        - wget
+        - --spider
+        - -q
+        - localhost:8080/api/v1/health
+      interval: 30s
+      timeout: 5s
+      retries: 3
+  otel-collector:
+    !!merge <<: *db-depend
+    image: signoz/signoz-otel-collector:${OTELCOL_TAG:-v0.144.4}
+    container_name: signoz-otel-collector
+    entrypoint:
+      - /bin/sh
+    command:
+      - -c
+      - |
+        /signoz-otel-collector migrate sync check &&
+        /signoz-otel-collector --config=/etc/otel-collector-config.yaml --manager-config=/etc/manager-config.yaml --copy-path=/var/tmp/collector-config.yaml
+    volumes:
+      - ./otel-collector-config.yaml:/etc/otel-collector-config.yaml
+      - ../common/signoz/otel-collector-opamp-config.yaml:/etc/manager-config.yaml
+    environment:
+      - OTEL_RESOURCE_ATTRIBUTES=host.name=signoz-host,os.type=linux
+      - LOW_CARDINAL_EXCEPTION_GROUPING=false
+      - SIGNOZ_OTEL_COLLECTOR_CLICKHOUSE_DSN=tcp://clickhouse:9000
+      - SIGNOZ_OTEL_COLLECTOR_CLICKHOUSE_CLUSTER=cluster
+      - SIGNOZ_OTEL_COLLECTOR_CLICKHOUSE_REPLICATION=true
+      - SIGNOZ_OTEL_COLLECTOR_TIMEOUT=10m
+    ports:
+      # - "1777:1777"     # pprof extension
+      - "4317:4317" # OTLP gRPC receiver
+      - "4318:4318" # OTLP HTTP receiver
+  signoz-telemetrystore-migrator:
+    !!merge <<: *db-depend
+    image: signoz/signoz-otel-collector:${OTELCOL_TAG:-v0.144.4}
+    container_name: signoz-telemetrystore-migrator
+    environment:
+      - SIGNOZ_OTEL_COLLECTOR_CLICKHOUSE_DSN=tcp://clickhouse:9000
+      - SIGNOZ_OTEL_COLLECTOR_CLICKHOUSE_CLUSTER=cluster
+      - SIGNOZ_OTEL_COLLECTOR_CLICKHOUSE_REPLICATION=true
+      - SIGNOZ_OTEL_COLLECTOR_TIMEOUT=10m
+    entrypoint:
+      - /bin/sh
+    command:
+      - -c
+      - |
+        /signoz-otel-collector migrate bootstrap &&
+        /signoz-otel-collector migrate sync up &&
+        /signoz-otel-collector migrate async up
+    restart: on-failure
+networks:
+  signoz-net:
+    name: signoz-net
+volumes:
+  clickhouse:
+    name: signoz-clickhouse
+  sqlite:
+    name: signoz-sqlite
+  zookeeper-1:
+    name: signoz-zookeeper-1

deploy/docker/otel-collector-config.yaml

@@ -0,0 +1,118 @@
+connectors:
+  signozmeter:
+    metrics_flush_interval: 1h
+    dimensions:
+      - name: service.name
+      - name: deployment.environment
+      - name: host.name
+receivers:
+  otlp:
+    protocols:
+      grpc:
+        endpoint: 0.0.0.0:4317
+      http:
+        endpoint: 0.0.0.0:4318
+  prometheus:
+    config:
+      global:
+        scrape_interval: 60s
+      scrape_configs:
+        - job_name: otel-collector
+          static_configs:
+          - targets:
+              - localhost:8888
+            labels:
+              job_name: otel-collector
+processors:
+  batch:
+    send_batch_size: 10000
+    send_batch_max_size: 11000
+    timeout: 10s
+  batch/meter:
+    send_batch_max_size: 25000
+    send_batch_size: 20000
+    timeout: 1s
+  resourcedetection:
+    # Using OTEL_RESOURCE_ATTRIBUTES envvar, env detector adds custom labels.
+    detectors: [env, system]
+    timeout: 2s
+  signozspanmetrics/delta:
+    metrics_exporter: signozclickhousemetrics
+    metrics_flush_interval: 60s
+    latency_histogram_buckets: [100us, 1ms, 2ms, 6ms, 10ms, 50ms, 100ms, 250ms, 500ms, 1000ms, 1400ms, 2000ms, 5s, 10s, 20s, 40s, 60s ]
+    dimensions_cache_size: 100000
+    aggregation_temporality: AGGREGATION_TEMPORALITY_DELTA
+    enable_exp_histogram: true
+    dimensions:
+      - name: service.namespace
+        default: default
+      - name: deployment.environment
+        default: default
+      # This is added to ensure the uniqueness of the timeseries
+      # Otherwise, identical timeseries produced by multiple replicas of
+      # collectors result in incorrect APM metrics
+      - name: signoz.collector.id
+      - name: service.version
+      - name: browser.platform
+      - name: browser.mobile
+      - name: k8s.cluster.name
+      - name: k8s.node.name
+      - name: k8s.namespace.name
+      - name: host.name
+      - name: host.type
+      - name: container.name
+extensions:
+  health_check:
+    endpoint: 0.0.0.0:13133
+  pprof:
+    endpoint: 0.0.0.0:1777
+exporters:
+  clickhousetraces:
+    datasource: tcp://clickhouse:9000/signoz_traces
+    low_cardinal_exception_grouping: ${env:LOW_CARDINAL_EXCEPTION_GROUPING}
+    use_new_schema: true
+  signozclickhousemetrics:
+    dsn: tcp://clickhouse:9000/signoz_metrics
+  clickhouselogsexporter:
+    dsn: tcp://clickhouse:9000/signoz_logs
+    timeout: 10s
+    use_new_schema: true
+  signozclickhousemeter:
+    dsn: tcp://clickhouse:9000/signoz_meter
+    timeout: 45s
+    sending_queue:
+      enabled: false
+  metadataexporter:
+    cache:
+      provider: in_memory
+    dsn: tcp://clickhouse:9000/signoz_metadata
+    enabled: true
+    timeout: 45s
+service:
+  telemetry:
+    logs:
+      encoding: json
+  extensions:
+    - health_check
+    - pprof
+  pipelines:
+    traces:
+      receivers: [otlp]
+      processors: [signozspanmetrics/delta, batch]
+      exporters: [clickhousetraces, metadataexporter, signozmeter]
+    metrics:
+      receivers: [otlp]
+      processors: [batch]
+      exporters: [signozclickhousemetrics, metadataexporter, signozmeter]
+    metrics/prometheus:
+      receivers: [prometheus]
+      processors: [batch]
+      exporters: [signozclickhousemetrics, metadataexporter, signozmeter]
+    logs:
+      receivers: [otlp]
+      processors: [batch]
+      exporters: [clickhouselogsexporter, metadataexporter, signozmeter]
+    metrics/meter:
+      receivers: [signozmeter]
+      processors: [batch/meter]
+      exporters: [signozclickhousemeter]

deploy/install.sh

@@ -2,24 +2,562 @@
 
 set -o errexit
 
+# Variables
+BASE_DIR="$(dirname "$(readlink -f "$0")")"
+DOCKER_STANDALONE_DIR="docker"
+DOCKER_SWARM_DIR="docker-swarm" # TODO: Add docker swarm support
+
 # Regular Colors
-Yellow='\033[0;33m' # Yellow
-Green='\033[0;32m'  # Green
-NC='\033[0m'        # No Color
+Black='\033[0;30m'        # Black
+Red='\[\e[0;31m\]'        # Red
+Green='\033[0;32m'        # Green
+Yellow='\033[0;33m'       # Yellow
+Blue='\033[0;34m'         # Blue
+Purple='\033[0;35m'       # Purple
+Cyan='\033[0;36m'         # Cyan
+White='\033[0;37m'        # White
+NC='\033[0m' # No Color
+
+is_command_present() {
+    type "$1" >/dev/null 2>&1
+}
+
+# Check whether 'wget' command exists.
+has_wget() {
+    has_cmd wget
+}
+
+# Check whether 'curl' command exists.
+has_curl() {
+    has_cmd curl
+}
+
+# Check whether the given command exists.
+has_cmd() {
+    command -v "$1" > /dev/null 2>&1
+}
+
+# Check if docker compose plugin is present
+has_docker_compose_plugin() {
+    docker compose version > /dev/null 2>&1
+}
+
+is_mac() {
+    [[ $OSTYPE == darwin* ]]
+}
+
+is_arm64(){
+    [[ `uname -m` == 'arm64' || `uname -m` == 'aarch64' ]]
+}
+
+check_os() {
+    if is_mac; then
+        package_manager="brew"
+        desired_os=1
+        os="Mac"
+        return
+    fi
+
+    if is_arm64; then
+        arch="arm64"
+        arch_official="aarch64"
+    else
+        arch="amd64"
+        arch_official="x86_64"
+    fi
+
+    platform=$(uname -s | tr '[:upper:]' '[:lower:]')
+
+    os_name="$(cat /etc/*-release | awk -F= '$1 == "NAME" { gsub(/"/, ""); print $2; exit }')"
+
+    case "$os_name" in
+        Ubuntu*|Pop!_OS)
+            desired_os=1
+            os="ubuntu"
+            package_manager="apt-get"
+            ;;
+        Amazon\ Linux*)
+            desired_os=1
+            os="amazon linux"
+            package_manager="yum"
+            ;;
+        Debian*)
+            desired_os=1
+            os="debian"
+            package_manager="apt-get"
+            ;;
+        Linux\ Mint*)
+            desired_os=1
+            os="linux mint"
+            package_manager="apt-get"
+            ;;
+        Red\ Hat*)
+            desired_os=1
+            os="rhel"
+            package_manager="yum"
+            ;;
+        CentOS*)
+            desired_os=1
+            os="centos"
+            package_manager="yum"
+            ;;
+        Rocky*)
+            desired_os=1
+            os="centos"
+            package_manager="yum"
+            ;;
+        SLES*)
+            desired_os=1
+            os="sles"
+            package_manager="zypper"
+            ;;
+        openSUSE*)
+            desired_os=1
+            os="opensuse"
+            package_manager="zypper"
+            ;;
+        *)
+            desired_os=0
+            os="Not Found: $os_name"
+    esac
+}
+
+
+# This function checks if the relevant ports required by SigNoz are available or not
+# The script should error out in case they aren't available
+check_ports_occupied() {
+    local port_check_output
+    local ports_pattern="8080|4317"
+
+    if is_mac; then
+        port_check_output="$(netstat -anp tcp | awk '$6 == "LISTEN" && $4 ~ /^.*\.('"$ports_pattern"')$/')"
+    elif is_command_present ss; then
+        # The `ss` command seems to be a better/faster version of `netstat`, but is not available on all Linux
+        # distributions by default. Other distributions have `ss` but no `netstat`. So, we try for `ss` first, then
+        # fallback to `netstat`.
+        port_check_output="$(ss --all --numeric --tcp | awk '$1 == "LISTEN" && $4 ~ /^.*:('"$ports_pattern"')$/')"
+    elif is_command_present netstat; then
+        port_check_output="$(netstat --all --numeric --tcp | awk '$6 == "LISTEN" && $4 ~ /^.*:('"$ports_pattern"')$/')"
+    fi
+
+    if [[ -n $port_check_output ]]; then
+        send_event "port_not_available"
+
+        echo "+++++++++++ ERROR ++++++++++++++++++++++"
+        echo "SigNoz requires ports 8080 & 4317 to be open. Please shut down any other service(s) that may be running on these ports."
+        echo "You can run SigNoz on another port following this guide https://signoz.io/docs/install/troubleshooting/"
+        echo "++++++++++++++++++++++++++++++++++++++++"
+        echo ""
+        exit 1
+    fi
+}
+
+install_docker() {
+    echo "++++++++++++++++++++++++"
+    echo "Setting up docker repos"
+
+
+    if [[ $package_manager == apt-get ]]; then
+        apt_cmd="$sudo_cmd apt-get --yes --quiet"
+        $apt_cmd update
+        $apt_cmd install software-properties-common gnupg-agent
+        curl -fsSL "https://download.docker.com/linux/$os/gpg" | $sudo_cmd apt-key add -
+        $sudo_cmd add-apt-repository \
+            "deb [arch=$arch] https://download.docker.com/linux/$os $(lsb_release -cs) stable"
+        $apt_cmd update
+        echo "Installing docker"
+        $apt_cmd install docker-ce docker-ce-cli containerd.io
+    elif [[ $package_manager == zypper ]]; then
+        zypper_cmd="$sudo_cmd zypper --quiet --no-gpg-checks --non-interactive"
+        echo "Installing docker"
+        if [[ $os == sles ]]; then
+            os_sp="$(cat /etc/*-release | awk -F= '$1 == "VERSION_ID" { gsub(/"/, ""); print $2; exit }')"
+            os_arch="$(uname -i)"
+            SUSEConnect -p sle-module-containers/$os_sp/$os_arch -r ''
+        fi
+        $zypper_cmd install docker docker-runc containerd
+        $sudo_cmd systemctl enable docker.service
+    elif [[ $package_manager == yum && $os == 'amazon linux' ]]; then
+        echo
+        echo "Amazon Linux detected ... "
+        echo
+        # yum install docker
+        # service docker start
+        $sudo_cmd yum install -y amazon-linux-extras
+        $sudo_cmd amazon-linux-extras enable docker
+        $sudo_cmd yum install -y docker
+    else
+
+        yum_cmd="$sudo_cmd yum --assumeyes --quiet"
+        $yum_cmd install yum-utils
+        $sudo_cmd yum-config-manager --add-repo https://download.docker.com/linux/$os/docker-ce.repo
+        echo "Installing docker"
+        $yum_cmd install docker-ce docker-ce-cli containerd.io
+    fi
+}
+
+compose_version () {
+    local compose_version
+    compose_version="$(curl -s https://api.github.com/repos/docker/compose/releases/latest | grep 'tag_name' | cut -d\" -f4)"
+    echo "${compose_version:-v2.18.1}"
+}
+
+install_docker_compose() {
+    if [[ $package_manager == "apt-get" || $package_manager == "zypper" || $package_manager == "yum" ]]; then
+        if [[ ! -f /usr/bin/docker-compose ]];then
+            echo "++++++++++++++++++++++++"
+            echo "Installing docker-compose"
+            compose_url="https://github.com/docker/compose/releases/download/$(compose_version)/docker-compose-$platform-$arch_official"
+            echo "Downloading docker-compose from $compose_url"
+            $sudo_cmd curl -L "$compose_url" -o /usr/local/bin/docker-compose
+            $sudo_cmd chmod +x /usr/local/bin/docker-compose
+            $sudo_cmd ln -s /usr/local/bin/docker-compose /usr/bin/docker-compose
+            echo "docker-compose installed!"
+            echo ""
+        fi
+    else
+        send_event "docker_compose_not_found"
+
+        echo "+++++++++++ IMPORTANT READ ++++++++++++++++++++++"
+        echo "docker-compose not found! Please install docker-compose first and then continue with this installation."
+        echo "Refer https://docs.docker.com/compose/install/ for installing docker-compose."
+        echo "+++++++++++++++++++++++++++++++++++++++++++++++++"
+        exit 1
+    fi
+}
+
+start_docker() {
+    echo -e "🐳 Starting Docker ...\n"
+    if [[ $os == "Mac" ]]; then
+        open --background -a Docker && while ! docker system info > /dev/null 2>&1; do sleep 1; done
+    else
+        if ! $sudo_cmd systemctl is-active docker.service > /dev/null; then
+            echo "Starting docker service"
+            $sudo_cmd systemctl start docker.service
+        fi
+        if [[ -z $sudo_cmd ]]; then
+            if ! docker ps > /dev/null && true; then
+                request_sudo
+            fi
+        fi
+    fi
+}
+
+wait_for_containers_start() {
+    local timeout=$1
+
+    # The while loop is important because for-loops don't work for dynamic values
+    while [[ $timeout -gt 0 ]]; do
+        status_code="$(curl -s -o /dev/null -w "%{http_code}" "http://localhost:8080/api/v1/health?live=1" || true)"
+        if [[ status_code -eq 200 ]]; then
+            break
+        else
+            echo -ne "Waiting for all containers to start. This check will timeout in $timeout seconds ...\r\c"
+        fi
+        ((timeout--))
+        sleep 1
+    done
+
+    echo ""
+}
+
+bye() {  # Prints a friendly good bye message and exits the script.
+    # Switch back to the original directory
+    popd > /dev/null 2>&1
+    if [[ "$?" -ne 0 ]]; then
+        set +o errexit
+
+        echo "🔴 The containers didn't seem to start correctly. Please run the following command to check containers that may have errored out:"
+        echo ""
+        echo -e "cd ${DOCKER_STANDALONE_DIR}"
+        echo -e "$sudo_cmd $docker_compose_cmd ps -a"
+
+        echo "Please read our troubleshooting guide https://signoz.io/docs/install/troubleshooting/"
+        echo "or reach us for support in #help channel in our Slack Community https://signoz.io/slack"
+        echo "++++++++++++++++++++++++++++++++++++++++"
+
+        if [[ $email == "" ]]; then
+            echo -e "\n📨 Please share your email to receive support with the installation"
+            read -rp 'Email: ' email
+
+            while [[ $email == "" ]]
+            do
+                read -rp 'Email: ' email
+            done
+        fi
+
+        send_event "installation_support"
+
+
+        echo ""
+        echo -e "\nWe will reach out to you at the email provided shortly, Exiting for now. Bye! 👋 \n"
+        exit 0
+    fi
+}
+
+request_sudo() {
+    if hash sudo 2>/dev/null; then
+        echo -e "\n\n🙇 We will need sudo access to complete the installation."
+        if (( $EUID != 0 )); then
+            sudo_cmd="sudo"
+            echo -e "Please enter your sudo password, if prompted."
+            if ! $sudo_cmd -l | grep -e "NOPASSWD: ALL" > /dev/null && ! $sudo_cmd -v; then
+                echo "Need sudo privileges to proceed with the installation."
+                exit 1;
+            fi
+
+            echo -e "Got it! Thanks!! 🙏\n"
+            echo -e "Okay! We will bring up the SigNoz cluster from here 🚀\n"
+        fi
+	fi
+}
 
 echo ""
-echo -e "👋 Thank you for trying out SigNoz!"
-echo ""
-echo -e "SigNoz now installs and runs through ${Green}Foundry${NC}."
-echo ""
-echo -e "${Yellow}⚠️  This install script has been deprecated and is no longer maintained.${NC}"
-echo -e "${Yellow}⚠️  Please see https://github.com/SigNoz/signoz/blob/main/deploy/README.md for new installation and migrations to Foundry.${NC}"
-echo ""
-echo ""
-echo -e "Please follow the latest installation instructions here:"
-echo -e "${Green}👉 https://signoz.io/docs/install/docker/${NC}"
-echo ""
-echo -e "🙏 Thank you!"
+echo -e "👋 Thank you for trying out SigNoz! "
 echo ""
 
-exit 0
+sudo_cmd=""
+docker_compose_cmd=""
+
+# Check sudo permissions
+if (( $EUID != 0 )); then
+    echo "🟡 Running installer with non-sudo permissions."
+    echo "   In case of any failure or prompt, please consider running the script with sudo privileges."
+    echo ""
+else
+    sudo_cmd="sudo"
+fi
+
+# Checking OS and assigning package manager
+desired_os=0
+os=""
+email=""
+echo -e "🌏 Detecting your OS ...\n"
+check_os
+
+# Obtain unique installation id
+# sysinfo="$(uname -a)"
+# if [[ $? -ne 0 ]]; then
+#     uuid="$(uuidgen)"
+#     uuid="${uuid:-$(cat /proc/sys/kernel/random/uuid)}"
+#     sysinfo="${uuid:-$(cat /proc/sys/kernel/random/uuid)}"
+# fi
+if ! sysinfo="$(uname -a)"; then
+    uuid="$(uuidgen)"
+    uuid="${uuid:-$(cat /proc/sys/kernel/random/uuid)}"
+    sysinfo="${uuid:-$(cat /proc/sys/kernel/random/uuid)}"
+fi
+
+digest_cmd=""
+if hash shasum 2>/dev/null; then
+    digest_cmd="shasum -a 256"
+elif hash sha256sum 2>/dev/null; then
+    digest_cmd="sha256sum"
+elif hash openssl 2>/dev/null; then
+    digest_cmd="openssl dgst -sha256"
+fi
+
+if [[ -z $digest_cmd ]]; then
+    SIGNOZ_INSTALLATION_ID="$sysinfo"
+else
+    SIGNOZ_INSTALLATION_ID=$(echo "$sysinfo" | $digest_cmd | grep -E -o '[a-zA-Z0-9]{64}')
+fi
+
+setup_type='clickhouse'
+
+# Run bye if failure happens
+trap bye EXIT
+
+URL="https://api.segment.io/v1/track"
+HEADER_1="Content-Type: application/json"
+HEADER_2="Authorization: Basic OWtScko3b1BDR1BFSkxGNlFqTVBMdDVibGpGaFJRQnI="
+
+send_event() {
+    error=""
+
+    case "$1" in
+        'install_started')
+            event="Installation Started"
+            ;;
+        'os_not_supported')
+            event="Installation Error"
+            error="OS Not Supported"
+            ;;
+        'docker_not_installed')
+            event="Installation Error"
+            error="Docker not installed"
+            ;;
+        'docker_compose_not_found')
+            event="Installation Error"
+            event="Docker Compose not found"
+            ;;
+        'port_not_available')
+            event="Installation Error"
+            error="port not available"
+            ;;
+        'installation_error_checks')
+            event="Installation Error - Checks"
+            error="Containers not started"
+            others='"data": "some_checks",'
+            ;;
+        'installation_support')
+            event="Installation Support"
+            others='"email": "'"$email"'",'
+            ;;
+        'installation_success')
+            event="Installation Success"
+            ;;
+        'identify_successful_installation')
+            event="Identify Successful Installation"
+            others='"email": "'"$email"'",'
+            ;;
+        *)
+            print_error "unknown event type: $1"
+            exit 1
+            ;;
+    esac
+
+    if [[ "$error" != "" ]]; then
+        error='"error": "'"$error"'", '
+    fi
+
+    DATA='{ "anonymousId": "'"$SIGNOZ_INSTALLATION_ID"'", "event": "'"$event"'", "properties": { "os": "'"$os"'", '"$error $others"' "setup_type": "'"$setup_type"'" } }'
+
+    if has_curl; then
+        curl -sfL -d "$DATA" --header "$HEADER_1" --header "$HEADER_2" "$URL" > /dev/null 2>&1
+    elif has_wget; then
+        wget -q --post-data="$DATA" --header "$HEADER_1" --header "$HEADER_2" "$URL" > /dev/null 2>&1
+    fi
+}
+
+send_event "install_started"
+
+if [[ $desired_os -eq 0 ]]; then
+    send_event "os_not_supported"
+fi
+
+# Check is Docker daemon is installed and available. If not, the install & start Docker for Linux machines. We cannot automatically install Docker Desktop on Mac OS
+if ! is_command_present docker; then
+
+    if [[ $package_manager == "apt-get" || $package_manager == "zypper" || $package_manager == "yum" ]]; then
+        request_sudo
+        install_docker
+        # enable docker without sudo from next reboot
+        sudo usermod -aG docker "${USER}"
+    elif is_mac; then
+        echo ""
+        echo "+++++++++++ IMPORTANT READ ++++++++++++++++++++++"
+        echo "Docker Desktop must be installed manually on Mac OS to proceed. Docker can only be installed automatically on Ubuntu / openSUSE / SLES / Redhat / Cent OS"
+        echo "https://docs.docker.com/docker-for-mac/install/"
+        echo "++++++++++++++++++++++++++++++++++++++++++++++++"
+
+        send_event "docker_not_installed"
+        exit 1
+    else
+        echo ""
+        echo "+++++++++++ IMPORTANT READ ++++++++++++++++++++++"
+        echo "Docker must be installed manually on your machine to proceed. Docker can only be installed automatically on Ubuntu / openSUSE / SLES / Redhat / Cent OS"
+        echo "https://docs.docker.com/get-docker/"
+        echo "++++++++++++++++++++++++++++++++++++++++++++++++"
+
+        send_event "docker_not_installed"
+        exit 1
+    fi
+fi
+
+if has_docker_compose_plugin; then
+    echo "docker compose plugin is present, using it"
+    docker_compose_cmd="docker compose"
+# Install docker-compose
+else
+    docker_compose_cmd="docker-compose"
+    if ! is_command_present docker-compose; then
+        request_sudo
+        install_docker_compose
+    fi
+fi
+
+start_docker
+
+# Switch to the Docker Standalone directory
+pushd "${BASE_DIR}/${DOCKER_STANDALONE_DIR}" > /dev/null 2>&1
+
+# check for open ports, if signoz is not installed
+if is_command_present docker-compose; then
+    if $sudo_cmd $docker_compose_cmd ps | grep "signoz" | grep -q "healthy" > /dev/null 2>&1; then
+        echo "SigNoz already installed, skipping the occupied ports check"
+    else
+        check_ports_occupied
+    fi
+fi
+
+echo ""
+echo -e "\n🟡 Pulling the latest container images for SigNoz.\n"
+$sudo_cmd $docker_compose_cmd pull
+
+echo ""
+echo "🟡 Starting the SigNoz containers. It may take a few minutes ..."
+echo
+# The $docker_compose_cmd command does some nasty stuff for the `--detach` functionality. So we add a `|| true` so that the
+# script doesn't exit because this command looks like it failed to do it's thing.
+$sudo_cmd $docker_compose_cmd up --detach --remove-orphans || true
+
+wait_for_containers_start 60
+echo ""
+
+if [[ $status_code -ne 200 ]]; then
+    echo "+++++++++++ ERROR ++++++++++++++++++++++"
+    echo "🔴 The containers didn't seem to start correctly. Please run the following command to check containers that may have errored out:"
+    echo ""
+
+    echo "cd ${DOCKER_STANDALONE_DIR}"
+    echo "$sudo_cmd $docker_compose_cmd ps -a"
+    echo ""
+
+    echo "Try bringing down the containers and retrying the installation"
+    echo "cd ${DOCKER_STANDALONE_DIR}"
+    echo "$sudo_cmd $docker_compose_cmd down -v"
+    echo ""
+
+    echo "Please read our troubleshooting guide https://signoz.io/docs/install/troubleshooting/"
+    echo "or reach us on SigNoz for support https://signoz.io/slack"
+    echo "++++++++++++++++++++++++++++++++++++++++"
+
+    send_event "installation_error_checks"
+    exit 1
+
+else
+    send_event "installation_success"
+
+    echo "++++++++++++++++++ SUCCESS ++++++++++++++++++++++"
+    echo ""
+    echo "🟢 Your installation is complete!"
+    echo ""
+    echo -e "🟢 SigNoz is running on http://localhost:8080"
+    echo ""
+    echo "ℹ️  By default, retention period is set to 15 days for logs and traces, and 30 days for metrics."
+    echo -e "To change this, navigate to the General tab on the Settings page of SigNoz UI. For more details, refer to https://signoz.io/docs/userguide/retention-period \n"
+
+    echo "ℹ️  To bring down SigNoz and clean volumes:"
+    echo ""
+    echo "cd ${DOCKER_STANDALONE_DIR}"
+    echo "$sudo_cmd $docker_compose_cmd down -v"
+
+    echo ""
+    echo "+++++++++++++++++++++++++++++++++++++++++++++++++"
+    echo ""
+    echo "👉 Need help in Getting Started?"
+    echo -e "Join us on Slack https://signoz.io/slack"
+    echo ""
+    echo -e "\n📨 Please share your email to receive support & updates about SigNoz!"
+    read -rp 'Email: ' email
+
+    while [[ $email == "" ]]
+    do
+        read -rp 'Email: ' email
+    done
+
+    send_event "identify_successful_installation"
+fi
+
+echo -e "\n🙏 Thank you!\n"

docs/contributing/go/errors.md

@@ -36,55 +36,6 @@ var (
 
 > 💡 **Note**: Error codes must match the regex `^[a-z_]+$` otherwise the code will panic.
 
-### Message
-The primary, human-readable summary of what went wrong, set when the error is created via `errors.New` / `errors.Newf`. Note there are two distinct `message` fields in the response: this top-level one states the overall failure, while each entry under [Additional](#additional) carries its own [message](#message-1) explaining one specific facet of it.
-
-### Url
-An optional link to documentation that explains the error in more depth, set with `WithUrl`. It is left empty when the error has no associated doc.
-
-```go
-return errors.New(errors.TypeInvalidInput, CodeBadThing, "bad thing").
-    WithUrl("https://signoz.io/docs/...")
-```
-
-### Additional
-`errors` is a list of supplementary details that explain the top-level `message`. Each entry has its own `message` and `suggestions`, so a single error can surface several distinct problems individually. Attach details with `WithAdditional` (message only) or `WithSuggestiveAdditional` (message plus the suggestions that belong to it):
-
-#### Message
-A single, self-contained sentence describing one specific facet of the error (e.g. ``field `filed` not found``), distinct from the top-level [Message](#message). Prefer one detail per distinct problem over concatenating several into one message.
-
-#### Suggestions
-The suggestions tied to that specific detail — typically a ``did you mean: `x` `` correction for the value the detail is about. These are distinct from the error-wide [Suggestions](#suggestions) below: detail-scoped suggestions never leak into the top-level list.
-
-```go
-return errors.NewInvalidInputf(errors.CodeInvalidInput, "unknown field %q", field).
-    WithAdditional("field `field` not found")
-return errors.NewInvalidInputf(errors.CodeInvalidInput, "unknown field %q", field).
-    WithSuggestiveAdditional("field `filed` not found", "did you mean: `field`")
-```
-
-### Retry
-Carries the `delay` the client should wait before retrying, set with `WithRetryAfter`. It is `null` when the error is not retryable.
-
-```go
-return errors.NewTimeoutf(CodeSlow, "upstream timed out").
-    WithRetryAfter(5 * time.Second)
-```
-
-### Suggestions
-`WithSuggestions` sets the error-wide `suggestions` list — hints about the error as a whole (e.g. "narrow the time range window"), as opposed to suggestions tied to a single detail. Prefer the builders in [pkg/errors/suggestions.go](/pkg/errors/suggestions.go) over hand-writing the strings so the phrasing stays consistent:
-
-- `NewSuggestionsOnLevenshteinDistance(invalidInput, noun, validInputs)` — returns a ``did you mean: `x` `` correction (when a close typo match exists) followed by the valid-references list.
-- `NewValidReferences(noun, values...)` — formats a capped list as ``valid <noun> are `a`, `b` `` (e.g. `"valid fields are"`, `"valid keys are"`). Returns `""` for an empty set.
-- `NewSuggestionsFromFunc(produce)` — wraps a caller-computed correction string as a one-element ``did you mean: `x` `` slice (or nil when it returns `""`), for callers with their own matching strategy.
-
-`noun` names the kind of value being suggested. Use one of the exported `Noun*` constants (`errors.NounFields`, `errors.NounKeys`, `errors.NounServices`, …) so the wording stays uniform across the codebase.
-
-```go
-return errors.NewInvalidInputf(errors.CodeInvalidInput, "unknown field %q", field).
-    WithSuggestions(errors.NewSuggestionsOnLevenshteinDistance(field, errors.NounFields, validFields)...)
-```
-
 ## Show me some examples
 
 ### Using the error

docs/contributing/go/handler.md

@@ -109,20 +109,6 @@ func (h *handler) CreateThing(rw http.ResponseWriter, req *http.Request) {
 }
 ```
 
-When you need an ID from `claims` as a `valuer.UUID` (for example to pass it to a module), derive it with the `Must*` constructor instead of `NewUUID` plus an error check. Claims are validated by the auth middleware, so the conversion cannot fail and the error branch would be dead code:
-
-```go
-// Good — claims are pre-validated, the conversion cannot fail.
-orgID := valuer.MustNewUUID(claims.OrgID)
-
-// Avoid — the error path is unreachable.
-orgID, err := valuer.NewUUID(claims.OrgID)
-if err != nil {
-    render.Error(rw, err)
-    return
-}
-```
-
 ### 3. Register the handler in `signozapiserver`
 
 In `pkg/apiserver/signozapiserver`, add a route in the appropriate `add*Routes` function (`addUserRoutes`, `addSessionRoutes`, `addOrgRoutes`, etc.). The pattern is:
@@ -347,50 +333,6 @@ func (Step) JSONSchema() (jsonschema.Schema, error) {
 }
 ```
 
-### `oneOf` with a discriminator
-
-For a sum type whose variants are keyed by a property (e.g. `kind`), expose the variants via `JSONSchemaOneOf()` and add a discriminator. Without it, code generators intersect the variants (`A & B & C`) instead of producing a clean discriminated union (`A | B | C`).
-
-The parent keeps its `JSONSchemaOneOf()` (the `oneOf` itself) and *additionally* tags it via `PrepareJSONSchema` with the `x-signoz-discriminator` extension; `signoz.attachDiscriminators` then promotes that marker to a real OpenAPI 3 `discriminator` (and strips the duplicate parent properties) after reflection.
-
-```go
-// On the parent: expose the oneOf variants...
-func (Plugin) JSONSchemaOneOf() []any {
-    return []any{FooVariant{}}
-}
-
-// ...and tag that same oneOf with the discriminator marker.
-func (Plugin) PrepareJSONSchema(s *jsonschema.Schema) error {
-    if s.ExtraProperties == nil {
-        s.ExtraProperties = map[string]any{}
-    }
-    s.ExtraProperties["x-signoz-discriminator"] = map[string]any{
-        "propertyName": "kind",
-        "mapping": map[string]string{
-            "signoz/Foo": "#/components/schemas/FooVariant",
-        },
-    }
-    return nil
-}
-```
-
-Each variant must declare the discriminator property (`kind`) and mark it `required`. 
-
-This produces the following in the generated OpenAPI spec:
-
-```yaml
-Plugin:
-  discriminator:
-    propertyName: kind
-    mapping:
-      signoz/Foo: '#/components/schemas/FooVariant'
-  oneOf:
-  - $ref: '#/components/schemas/FooVariant'
-  type: object
-```
-
-Note the discriminator property lives in the variants, not on the parent — the parent is only the union.
-
 
 ## What should I remember?
 
@@ -401,4 +343,3 @@ Note the discriminator property lives in the variants, not on the parent — the
 - **Add `nullable:"true"`** on fields that can be `null`. Pay special attention to slices and maps -- in Go these default to `nil` which serializes to `null`. If the field should always be an array, initialize it and do not mark it nullable.
 - **Implement `Enum()`** on every type that has a fixed set of acceptable values so the JSON schema generates proper `enum` constraints.
 - **Add request examples** via `RequestExamples` in `OpenAPIDef` for any non-trivial endpoint. See `pkg/apiserver/signozapiserver/querier.go` for reference.
-- **Derive IDs from `claims` with `valuer.MustNewUUID`** (e.g. `claims.OrgID`, `claims.UserID`). Claims are pre-validated by the auth middleware, so use the `Must*` constructor — don't write `NewUUID` followed by an `if err != nil { render.Error(...); return }` block.

ee/authn/callbackauthn/oidccallbackauthn/authn.go

@@ -5,12 +5,10 @@ import (
 	"fmt"
 	"log/slog"
 	"net/url"
-	"path"
 
 	"github.com/SigNoz/signoz/pkg/authn"
 	"github.com/SigNoz/signoz/pkg/errors"
 	"github.com/SigNoz/signoz/pkg/factory"
-	"github.com/SigNoz/signoz/pkg/global"
 	"github.com/SigNoz/signoz/pkg/http/client"
 	"github.com/SigNoz/signoz/pkg/licensing"
 	"github.com/SigNoz/signoz/pkg/types/authtypes"
@@ -28,14 +26,13 @@ var defaultScopes []string = []string{"email", "profile", oidc.ScopeOpenID}
 var _ authn.CallbackAuthN = (*AuthN)(nil)
 
 type AuthN struct {
-	settings     factory.ScopedProviderSettings
-	store        authtypes.AuthNStore
-	licensing    licensing.Licensing
-	httpClient   *client.Client
-	globalConfig global.Config
+	settings   factory.ScopedProviderSettings
+	store      authtypes.AuthNStore
+	licensing  licensing.Licensing
+	httpClient *client.Client
 }
 
-func New(store authtypes.AuthNStore, licensing licensing.Licensing, providerSettings factory.ProviderSettings, globalConfig global.Config) (*AuthN, error) {
+func New(store authtypes.AuthNStore, licensing licensing.Licensing, providerSettings factory.ProviderSettings) (*AuthN, error) {
 	settings := factory.NewScopedProviderSettings(providerSettings, "github.com/SigNoz/signoz/ee/authn/callbackauthn/oidccallbackauthn")
 
 	httpClient, err := client.New(providerSettings.Logger, providerSettings.TracerProvider, providerSettings.MeterProvider)
@@ -44,11 +41,10 @@ func New(store authtypes.AuthNStore, licensing licensing.Licensing, providerSett
 	}
 
 	return &AuthN{
-		settings:     settings,
-		store:        store,
-		licensing:    licensing,
-		httpClient:   httpClient,
-		globalConfig: globalConfig,
+		settings:   settings,
+		store:      store,
+		licensing:  licensing,
+		httpClient: httpClient,
 	}, nil
 }
 
@@ -201,7 +197,7 @@ func (a *AuthN) oidcProviderAndoauth2Config(ctx context.Context, siteURL *url.UR
 		RedirectURL: (&url.URL{
 			Scheme: siteURL.Scheme,
 			Host:   siteURL.Host,
-			Path:   path.Join(a.globalConfig.ExternalPath(), redirectPath),
+			Path:   redirectPath,
 		}).String(),
 	}, nil
 }

ee/authn/callbackauthn/samlcallbackauthn/authn.go

@@ -6,12 +6,10 @@ import (
 	"encoding/base64"
 	"encoding/pem"
 	"net/url"
-	"path"
 	"strings"
 
 	"github.com/SigNoz/signoz/pkg/authn"
 	"github.com/SigNoz/signoz/pkg/errors"
-	"github.com/SigNoz/signoz/pkg/global"
 	"github.com/SigNoz/signoz/pkg/licensing"
 	"github.com/SigNoz/signoz/pkg/types/authtypes"
 	"github.com/SigNoz/signoz/pkg/valuer"
@@ -26,16 +24,14 @@ const (
 var _ authn.CallbackAuthN = (*AuthN)(nil)
 
 type AuthN struct {
-	store        authtypes.AuthNStore
-	licensing    licensing.Licensing
-	globalConfig global.Config
+	store     authtypes.AuthNStore
+	licensing licensing.Licensing
 }
 
-func New(ctx context.Context, store authtypes.AuthNStore, licensing licensing.Licensing, globalConfig global.Config) (*AuthN, error) {
+func New(ctx context.Context, store authtypes.AuthNStore, licensing licensing.Licensing) (*AuthN, error) {
 	return &AuthN{
-		store:        store,
-		licensing:    licensing,
-		globalConfig: globalConfig,
+		store:     store,
+		licensing: licensing,
 	}, nil
 }
 
@@ -136,7 +132,7 @@ func (a *AuthN) serviceProvider(siteURL *url.URL, authDomain *authtypes.AuthDoma
 		return nil, err
 	}
 
-	acsURL := &url.URL{Scheme: siteURL.Scheme, Host: siteURL.Host, Path: path.Join(a.globalConfig.ExternalPath(), redirectPath)}
+	acsURL := &url.URL{Scheme: siteURL.Scheme, Host: siteURL.Host, Path: redirectPath}
 
 	// Note:
 	// The ServiceProviderIssuer is the client id in case of keycloak. Since we set it to the host here, we need to set the client id == host in keycloak.

ee/authz/openfgaauthz/provider.go

@@ -87,7 +87,7 @@ func (provider *provider) BatchCheck(ctx context.Context, tupleReq map[string]*o
 }
 
 func (provider *provider) CheckTransactions(ctx context.Context, subject string, orgID valuer.UUID, transactions []*authtypes.Transaction) ([]*authtypes.TransactionWithAuthorization, error) {
-	tuples, correlations, err := authtypes.NewTuplesFromTransactionsWithCorrelations(transactions, subject, orgID)
+	tuples, err := authtypes.NewTuplesFromTransactions(transactions, subject, orgID)
 	if err != nil {
 		return nil, err
 	}
@@ -99,21 +99,10 @@ func (provider *provider) CheckTransactions(ctx context.Context, subject string,
 
 	results := make([]*authtypes.TransactionWithAuthorization, len(transactions))
 	for i, txn := range transactions {
-		txnID := txn.ID.StringValue()
-		authorized := batchResults[txnID].Authorized
-
-		if !authorized {
-			for _, correlationID := range correlations[txnID] {
-				if result, exists := batchResults[correlationID]; exists && result.Authorized {
-					authorized = true
-					break
-				}
-			}
-		}
-
+		result := batchResults[txn.ID.StringValue()]
 		results[i] = &authtypes.TransactionWithAuthorization{
 			Transaction: txn,
-			Authorized:  authorized,
+			Authorized:  result.Authorized,
 		}
 	}
 	return results, nil
@@ -143,10 +132,6 @@ func (provider *provider) List(ctx context.Context, orgID valuer.UUID) ([]*autht
 	return provider.pkgAuthzService.List(ctx, orgID)
 }
 
-func (provider *provider) Collect(ctx context.Context, orgID valuer.UUID) (map[string]any, error) {
-	return provider.pkgAuthzService.Collect(ctx, orgID)
-}
-
 func (provider *provider) ListByOrgIDAndNames(ctx context.Context, orgID valuer.UUID, names []string) ([]*authtypes.Role, error) {
 	return provider.pkgAuthzService.ListByOrgIDAndNames(ctx, orgID, names)
 }
@@ -183,36 +168,13 @@ func (provider *provider) CreateManagedUserRoleTransactions(ctx context.Context,
 	return provider.Write(ctx, tuples, nil)
 }
 
-func (provider *provider) Create(ctx context.Context, orgID valuer.UUID, role *authtypes.RoleWithTransactionGroups) error {
+func (provider *provider) Create(ctx context.Context, orgID valuer.UUID, role *authtypes.Role) error {
 	_, err := provider.licensing.GetActive(ctx, orgID)
 	if err != nil {
 		return errors.New(errors.TypeLicenseUnavailable, errors.CodeLicenseUnavailable, "a valid license is not available").WithAdditional("this feature requires a valid license").WithAdditional(err.Error())
 	}
 
-	existingRole, err := provider.GetByOrgIDAndName(ctx, orgID, role.Name)
-	if err != nil && !errors.Asc(err, authtypes.ErrCodeRoleNotFound) {
-		return err
-	}
-
-	if existingRole != nil {
-		return errors.Newf(errors.TypeAlreadyExists, authtypes.ErrCodeRoleAlreadyExists, "role with name: %s already exists", existingRole.Name)
-	}
-
-	tuples, err := authtypes.NewTuplesFromTransactionGroups(role.Name, orgID, role.TransactionGroups)
-	if err != nil {
-		return err
-	}
-
-	err = provider.Write(ctx, tuples, nil)
-	if err != nil {
-		return err
-	}
-
-	if err := provider.store.Create(ctx, role.Role); err != nil {
-		return err
-	}
-
-	return nil
+	return provider.store.Create(ctx, role)
 }
 
 func (provider *provider) GetOrCreate(ctx context.Context, orgID valuer.UUID, role *authtypes.Role) (*authtypes.Role, error) {
@@ -240,26 +202,6 @@ func (provider *provider) GetOrCreate(ctx context.Context, orgID valuer.UUID, ro
 	return role, nil
 }
 
-func (provider *provider) GetWithTransactionGroups(ctx context.Context, orgID valuer.UUID, id valuer.UUID) (*authtypes.RoleWithTransactionGroups, error) {
-	_, err := provider.licensing.GetActive(ctx, orgID)
-	if err != nil {
-		return nil, errors.New(errors.TypeLicenseUnavailable, errors.CodeLicenseUnavailable, "a valid license is not available").WithAdditional("this feature requires a valid license").WithAdditional(err.Error())
-	}
-
-	role, err := provider.store.Get(ctx, orgID, id)
-	if err != nil {
-		return nil, err
-	}
-
-	tuples, err := provider.readAllTuplesForRole(ctx, role.Name, orgID)
-	if err != nil {
-		return nil, err
-	}
-
-	transactionGroups := authtypes.MustNewTransactionGroupsFromTuples(tuples)
-	return authtypes.MakeRoleWithTransactionGroups(role, transactionGroups), nil
-}
-
 func (provider *provider) GetObjects(ctx context.Context, orgID valuer.UUID, id valuer.UUID, relation authtypes.Relation) ([]*coretypes.Object, error) {
 	_, err := provider.licensing.GetActive(ctx, orgID)
 	if err != nil {
@@ -294,36 +236,6 @@ func (provider *provider) GetObjects(ctx context.Context, orgID valuer.UUID, id
 	return objects, nil
 }
 
-func (provider *provider) Update(ctx context.Context, orgID valuer.UUID, updatedRole *authtypes.RoleWithTransactionGroups) error {
-	_, err := provider.licensing.GetActive(ctx, orgID)
-	if err != nil {
-		return errors.New(errors.TypeLicenseUnavailable, errors.CodeLicenseUnavailable, "a valid license is not available").WithAdditional("this feature requires a valid license").WithAdditional(err.Error())
-	}
-
-	existingRole, err := provider.GetWithTransactionGroups(ctx, orgID, updatedRole.ID)
-	if err != nil {
-		return err
-	}
-
-	additions, deletions := existingRole.TransactionGroups.Diff(updatedRole.TransactionGroups)
-	additionTuples, err := authtypes.NewTuplesFromTransactionGroups(existingRole.Name, orgID, additions)
-	if err != nil {
-		return err
-	}
-
-	deletionTuples, err := authtypes.NewTuplesFromTransactionGroups(existingRole.Name, orgID, deletions)
-	if err != nil {
-		return err
-	}
-
-	err = provider.Write(ctx, additionTuples, deletionTuples)
-	if err != nil {
-		return err
-	}
-
-	return provider.store.Update(ctx, orgID, updatedRole.Role)
-}
-
 func (provider *provider) Patch(ctx context.Context, orgID valuer.UUID, role *authtypes.Role) error {
 	_, err := provider.licensing.GetActive(ctx, orgID)
 	if err != nil {
@@ -363,7 +275,7 @@ func (provider *provider) Delete(ctx context.Context, orgID valuer.UUID, id valu
 		return errors.New(errors.TypeLicenseUnavailable, errors.CodeLicenseUnavailable, "a valid license is not available").WithAdditional("this feature requires a valid license").WithAdditional(err.Error())
 	}
 
-	role, err := provider.GetWithTransactionGroups(ctx, orgID, id)
+	role, err := provider.store.Get(ctx, orgID, id)
 	if err != nil {
 		return err
 	}
@@ -374,17 +286,12 @@ func (provider *provider) Delete(ctx context.Context, orgID valuer.UUID, id valu
 	}
 
 	for _, cb := range provider.onBeforeRoleDelete {
-		if err := cb(ctx, orgID, id, role.Name); err != nil {
+		if err := cb(ctx, orgID, id); err != nil {
 			return err
 		}
 	}
 
-	tuples, err := authtypes.NewTuplesFromTransactionGroups(role.Name, orgID, role.TransactionGroups)
-	if err != nil {
-		return err
-	}
-
-	if err := provider.Write(ctx, nil, tuples); err != nil {
+	if err := provider.deleteTuples(ctx, role.Name, orgID); err != nil {
 		return errors.WithAdditionalf(err, "failed to delete tuples for the role: %s", role.Name)
 	}
 
@@ -443,7 +350,7 @@ func (provider *provider) getManagedRoleTransactionTuples(orgID valuer.UUID) []*
 	return tuples
 }
 
-func (provider *provider) readAllTuplesForRole(ctx context.Context, roleName string, orgID valuer.UUID) ([]*openfgav1.TupleKey, error) {
+func (provider *provider) deleteTuples(ctx context.Context, roleName string, orgID valuer.UUID) error {
 	subject := authtypes.MustNewSubject(coretypes.NewResourceRole(), roleName, orgID, &coretypes.VerbAssignee)
 
 	tuples := make([]*openfgav1.TupleKey, 0)
@@ -453,10 +360,26 @@ func (provider *provider) readAllTuplesForRole(ctx context.Context, roleName str
 			Object: objectType.StringValue() + ":",
 		})
 		if err != nil {
-			return nil, err
+			return err
 		}
 		tuples = append(tuples, typeTuples...)
 	}
 
-	return tuples, nil
+	if len(tuples) == 0 {
+		return nil
+	}
+
+	for idx := 0; idx < len(tuples); idx += provider.config.OpenFGA.MaxTuplesPerWrite {
+		end := idx + provider.config.OpenFGA.MaxTuplesPerWrite
+		if end > len(tuples) {
+			end = len(tuples)
+		}
+
+		err := provider.Write(ctx, nil, tuples[idx:end])
+		if err != nil {
+			return err
+		}
+	}
+
+	return nil
 }

ee/authz/openfgaschema/base.fga

@@ -7,27 +7,17 @@ type organization
 
 type user
   relations
-    define create: [user, serviceaccount, role#assignee]
-    define list: [user, serviceaccount, role#assignee]
-
     define read: [user, serviceaccount, role#assignee]
     define update: [user, serviceaccount, role#assignee]
     define delete: [user, serviceaccount, role#assignee]
-
     define attach: [user, serviceaccount, role#assignee]
-    define detach: [user, serviceaccount, role#assignee]
 
 type serviceaccount
   relations
-    define create: [user, serviceaccount, role#assignee]
-    define list: [user, serviceaccount, role#assignee]
-
     define read: [user, serviceaccount, role#assignee]
     define update: [user, serviceaccount, role#assignee]
     define delete: [user, serviceaccount, role#assignee]
-
     define attach: [user, serviceaccount, role#assignee]
-    define detach: [user, serviceaccount, role#assignee]
 
 type anonymous
 
@@ -35,31 +25,25 @@ type role
   relations
     define assignee: [user, serviceaccount, anonymous]
 
-    define create: [user, serviceaccount, role#assignee]
-    define list: [user, serviceaccount, role#assignee]
-
     define read: [user, serviceaccount, role#assignee]
     define update: [user, serviceaccount, role#assignee]
     define delete: [user, serviceaccount, role#assignee]
-
     define attach: [user, serviceaccount, role#assignee]
-    define detach: [user, serviceaccount, role#assignee]
 
-type metaresource
+type metaresources
   relations
     define create: [user, serviceaccount, role#assignee]
     define list: [user, serviceaccount, role#assignee]
 
-    define read: [user, serviceaccount, anonymous, role#assignee]
-    define update: [user, serviceaccount, role#assignee]
-    define delete: [user, serviceaccount, role#assignee]
+type metaresource
+  relations
+      define read: [user, serviceaccount, anonymous, role#assignee]
+      define update: [user, serviceaccount, role#assignee]
+      define delete: [user, serviceaccount, role#assignee]
 
-    define attach: [user, serviceaccount, role#assignee]
-    define detach: [user, serviceaccount, role#assignee]
-
-    define block: [user, serviceaccount, role#assignee]
+      define block: [user, serviceaccount, role#assignee]
 
 
 type telemetryresource
   relations
-    define read: [user, serviceaccount, role#assignee]
+      define read: [user, serviceaccount, role#assignee]

ee/meterreporter/httpmeterreporter/provider.go

@@ -94,19 +94,17 @@ func newProvider(
 func (provider *Provider) Start(ctx context.Context) error {
 	close(provider.healthyC)
 
-	startDelay := provider.config.NewJitter()
+	provider.collect(ctx)
 
-	timer := time.NewTimer(startDelay)
-	defer timer.Stop()
+	ticker := time.NewTicker(provider.config.Interval)
+	defer ticker.Stop()
 
 	for {
 		select {
 		case <-provider.stopC:
 			return nil
-		case <-timer.C:
+		case <-ticker.C:
 			provider.collect(ctx)
-			next := provider.config.Interval - provider.config.NewJitter()
-			timer.Reset(next)
 		}
 	}
 }
@@ -259,7 +257,6 @@ func (provider *Provider) report(ctx context.Context, orgID valuer.UUID, license
 		collectedReadings, err := collector.Collect(ctx, orgID, license, window)
 		if err != nil {
 			provider.metrics.collections.Add(ctx, 1, metric.WithAttributes(meterAttr, errors.TypeAttr(err)))
-			provider.settings.Logger().ErrorContext(ctx, "meter collector failed", errors.Attr(err), slog.String("org_id", orgID.StringValue()), slog.String("meter", collector.Name().String()))
 			continue
 		}
 

ee/modules/cloudintegration/implcloudintegration/implcloudprovider/awscloudprovider.go

@@ -54,6 +54,11 @@ func (provider *awscloudprovider) GetServiceDefinition(ctx context.Context, serv
 		return nil, err
 	}
 
+	// override cloud integration dashboard id
+	for index, dashboard := range serviceDef.Assets.Dashboards {
+		serviceDef.Assets.Dashboards[index].ID = cloudintegrationtypes.GetCloudIntegrationDashboardID(cloudintegrationtypes.CloudProviderTypeAWS, serviceID.StringValue(), dashboard.ID)
+	}
+
 	return serviceDef, nil
 }
 

ee/modules/cloudintegration/implcloudintegration/implcloudprovider/azurecloudprovider.go

@@ -38,6 +38,11 @@ func (provider *azurecloudprovider) GetServiceDefinition(ctx context.Context, se
 		return nil, err
 	}
 
+	// override cloud integration dashboard id.
+	for index, dashboard := range serviceDef.Assets.Dashboards {
+		serviceDef.Assets.Dashboards[index].ID = cloudintegrationtypes.GetCloudIntegrationDashboardID(cloudintegrationtypes.CloudProviderTypeAzure, serviceID.StringValue(), dashboard.ID)
+	}
+
 	return serviceDef, nil
 }
 

ee/modules/cloudintegration/implcloudintegration/module.go

@@ -3,6 +3,7 @@ package implcloudintegration
 import (
 	"context"
 	"fmt"
+	"sort"
 	"time"
 
 	"github.com/SigNoz/signoz/pkg/errors"
@@ -10,7 +11,6 @@ import (
 	"github.com/SigNoz/signoz/pkg/global"
 	"github.com/SigNoz/signoz/pkg/licensing"
 	"github.com/SigNoz/signoz/pkg/modules/cloudintegration"
-	"github.com/SigNoz/signoz/pkg/modules/dashboard"
 	"github.com/SigNoz/signoz/pkg/modules/serviceaccount"
 	"github.com/SigNoz/signoz/pkg/types/authtypes"
 	"github.com/SigNoz/signoz/pkg/types/cloudintegrationtypes"
@@ -23,7 +23,6 @@ import (
 
 type module struct {
 	store             cloudintegrationtypes.Store
-	dashboardModule   dashboard.Module
 	gateway           gateway.Gateway
 	zeus              zeus.Zeus
 	licensing         licensing.Licensing
@@ -35,7 +34,6 @@ type module struct {
 
 func NewModule(
 	store cloudintegrationtypes.Store,
-	dashboardModule dashboard.Module,
 	global global.Global,
 	zeus zeus.Zeus,
 	gateway gateway.Gateway,
@@ -46,7 +44,6 @@ func NewModule(
 ) (cloudintegration.Module, error) {
 	return &module{
 		store:             store,
-		dashboardModule:   dashboardModule,
 		global:            global,
 		zeus:              zeus,
 		gateway:           gateway,
@@ -257,41 +254,7 @@ func (module *module) DisconnectAccount(ctx context.Context, orgID valuer.UUID,
 		return errors.New(errors.TypeLicenseUnavailable, errors.CodeLicenseUnavailable, "a valid license is not available").WithAdditional("this feature requires a valid license").WithAdditional(err.Error())
 	}
 
-	return module.store.RunInTx(ctx, func(ctx context.Context) error {
-		services, err := module.store.ListServices(ctx, accountID)
-		if err != nil {
-			return err
-		}
-
-		sharedServices, err := module.store.ListSharedServices(ctx, orgID, provider, accountID)
-		if err != nil {
-			return err
-		}
-
-		for _, svc := range services {
-			svcCfg, err := cloudintegrationtypes.NewServiceConfigFromJSON(provider, svc.Config)
-			if err != nil {
-				return err
-			}
-			if !svcCfg.IsMetricsEnabled(provider) {
-				continue
-			}
-
-			if cloudintegrationtypes.IsServiceSharedWithMetricsEnabled(provider, sharedServices[svc.Type]) {
-				continue
-			}
-
-			if err := module.deprovisionDashboards(ctx, orgID, provider, svc.Type); err != nil {
-				return err
-			}
-		}
-
-		if err := module.store.DeleteServicesByCloudIntegrationID(ctx, orgID, accountID); err != nil {
-			return err
-		}
-
-		return module.store.RemoveAccount(ctx, orgID, accountID, provider)
-	})
+	return module.store.RemoveAccount(ctx, orgID, accountID, provider)
 }
 
 func (module *module) ListServicesMetadata(ctx context.Context, orgID valuer.UUID, provider cloudintegrationtypes.CloudProviderType, integrationID valuer.UUID) ([]*cloudintegrationtypes.ServiceMetadata, error) {
@@ -355,35 +318,25 @@ func (module *module) GetService(ctx context.Context, orgID valuer.UUID, service
 
 	var integrationService *cloudintegrationtypes.CloudIntegrationService
 
-	if cloudIntegrationID.IsZero() {
-		return cloudintegrationtypes.NewService(provider, serviceDefinition, nil, nil), nil
+	if !cloudIntegrationID.IsZero() {
+		storedService, err := module.store.GetServiceByServiceID(ctx, cloudIntegrationID, serviceID)
+		if err != nil && !errors.Ast(err, errors.TypeNotFound) {
+			return nil, err
+		}
+		if storedService != nil {
+			serviceConfig, err := cloudintegrationtypes.NewServiceConfigFromJSON(provider, storedService.Config)
+			if err != nil {
+				return nil, err
+			}
+
+			integrationService = cloudintegrationtypes.NewCloudIntegrationServiceFromStorable(storedService, serviceConfig)
+		}
 	}
 
-	storedService, err := module.store.GetServiceByServiceID(ctx, cloudIntegrationID, serviceID)
-	if err != nil && !errors.Ast(err, errors.TypeNotFound) {
-		return nil, err
-	}
-	if storedService == nil {
-		return cloudintegrationtypes.NewService(provider, serviceDefinition, nil, nil), nil
-	}
-
-	serviceConfig, err := cloudintegrationtypes.NewServiceConfigFromJSON(provider, storedService.Config)
-	if err != nil {
-		return nil, err
-	}
-
-	integrationService = cloudintegrationtypes.NewCloudIntegrationServiceFromStorable(storedService, serviceConfig)
-
-	slugPrefix := cloudintegrationtypes.CloudIntegrationDashboardSlugPrefix(provider, serviceID)
-	integrationDashboards, err := module.store.ListIntegrationDashboardsBySlugPrefix(ctx, orgID, cloudintegrationtypes.IntegrationDashboardProviderCloudIntegration, slugPrefix)
-	if err != nil {
-		return nil, err
-	}
-
-	return cloudintegrationtypes.NewService(provider, serviceDefinition, integrationService, integrationDashboards), nil
+	return cloudintegrationtypes.NewService(*serviceDefinition, integrationService), nil
 }
 
-func (module *module) CreateService(ctx context.Context, orgID valuer.UUID, createdBy string, creator valuer.UUID, service *cloudintegrationtypes.CloudIntegrationService, provider cloudintegrationtypes.CloudProviderType) error {
+func (module *module) CreateService(ctx context.Context, orgID valuer.UUID, service *cloudintegrationtypes.CloudIntegrationService, provider cloudintegrationtypes.CloudProviderType) error {
 	_, err := module.licensing.GetActive(ctx, orgID)
 	if err != nil {
 		return errors.New(errors.TypeLicenseUnavailable, errors.CodeLicenseUnavailable, "a valid license is not available").WithAdditional("this feature requires a valid license").WithAdditional(err.Error())
@@ -404,21 +357,10 @@ func (module *module) CreateService(ctx context.Context, orgID valuer.UUID, crea
 		return err
 	}
 
-	metricsEnabled := service.Config.IsMetricsEnabled(provider)
-	storableService := cloudintegrationtypes.NewStorableCloudIntegrationService(service, string(configJSON))
-
-	return module.store.RunInTx(ctx, func(ctx context.Context) error {
-		if err := module.store.CreateService(ctx, storableService); err != nil {
-			return err
-		}
-		if metricsEnabled {
-			return module.provisionDashboards(ctx, orgID, createdBy, creator, provider, service, serviceDefinition)
-		}
-		return nil
-	})
+	return module.store.CreateService(ctx, cloudintegrationtypes.NewStorableCloudIntegrationService(service, string(configJSON)))
 }
 
-func (module *module) UpdateService(ctx context.Context, orgID valuer.UUID, createdBy string, creator valuer.UUID, integrationService *cloudintegrationtypes.CloudIntegrationService, provider cloudintegrationtypes.CloudProviderType) error {
+func (module *module) UpdateService(ctx context.Context, orgID valuer.UUID, integrationService *cloudintegrationtypes.CloudIntegrationService, provider cloudintegrationtypes.CloudProviderType) error {
 	_, err := module.licensing.GetActive(ctx, orgID)
 	if err != nil {
 		return errors.New(errors.TypeLicenseUnavailable, errors.CodeLicenseUnavailable, "a valid license is not available").WithAdditional("this feature requires a valid license").WithAdditional(err.Error())
@@ -439,28 +381,43 @@ func (module *module) UpdateService(ctx context.Context, orgID valuer.UUID, crea
 		return err
 	}
 
-	metricsEnabled := integrationService.Config.IsMetricsEnabled(provider)
 	storableService := cloudintegrationtypes.NewStorableCloudIntegrationService(integrationService, string(configJSON))
 
-	return module.store.RunInTx(ctx, func(ctx context.Context) error {
-		if err := module.store.UpdateService(ctx, storableService); err != nil {
-			return err
-		}
+	return module.store.UpdateService(ctx, storableService)
+}
 
-		if metricsEnabled {
-			return module.provisionDashboards(ctx, orgID, createdBy, creator, provider, integrationService, serviceDefinition)
-		}
+func (module *module) GetDashboardByID(ctx context.Context, orgID valuer.UUID, id string) (*dashboardtypes.Dashboard, error) {
+	_, err := module.licensing.GetActive(ctx, orgID)
+	if err != nil {
+		return nil, errors.New(errors.TypeLicenseUnavailable, errors.CodeLicenseUnavailable, "a valid license is not available").WithAdditional("this feature requires a valid license").WithAdditional(err.Error())
+	}
 
-		sharedServices, err := module.store.ListSharedServices(ctx, orgID, provider, integrationService.CloudIntegrationID)
-		if err != nil {
-			return err
-		}
-		if cloudintegrationtypes.IsServiceSharedWithMetricsEnabled(provider, sharedServices[integrationService.Type]) {
-			return nil
-		}
+	_, _, _, err = cloudintegrationtypes.ParseCloudIntegrationDashboardID(id)
+	if err != nil {
+		return nil, err
+	}
 
-		return module.deprovisionDashboards(ctx, orgID, provider, integrationService.Type)
-	})
+	allDashboards, err := module.listDashboards(ctx, orgID)
+	if err != nil {
+		return nil, err
+	}
+
+	for _, d := range allDashboards {
+		if d.ID == id {
+			return d, nil
+		}
+	}
+
+	return nil, errors.New(errors.TypeNotFound, cloudintegrationtypes.ErrCodeCloudIntegrationNotFound, "cloud integration dashboard not found")
+}
+
+func (module *module) ListDashboards(ctx context.Context, orgID valuer.UUID) ([]*dashboardtypes.Dashboard, error) {
+	_, err := module.licensing.GetActive(ctx, orgID)
+	if err != nil {
+		return nil, errors.New(errors.TypeLicenseUnavailable, errors.CodeLicenseUnavailable, "a valid license is not available").WithAdditional("this feature requires a valid license").WithAdditional(err.Error())
+	}
+
+	return module.listDashboards(ctx, orgID)
 }
 
 func (module *module) Collect(ctx context.Context, orgID valuer.UUID) (map[string]any, error) {
@@ -536,56 +493,52 @@ func (module *module) getOrCreateAPIKey(ctx context.Context, orgID valuer.UUID,
 	return factorAPIKey.Key, nil
 }
 
-// provisionDashboards creates dashboard and integration_dashboard rows for each dashboard in the service definition.
-// Must be called within a transaction (ctx carries the tx).
-func (module *module) provisionDashboards(ctx context.Context, orgID valuer.UUID, createdBy string, creator valuer.UUID, provider cloudintegrationtypes.CloudProviderType, service *cloudintegrationtypes.CloudIntegrationService, serviceDefinition *cloudintegrationtypes.ServiceDefinition) error {
-	// TODO: DB calls are in for loop, can be optimized later.
-	for _, dashboard := range serviceDefinition.Assets.Dashboards {
-		slug := cloudintegrationtypes.CloudIntegrationDashboardSlug(provider, service.Type, dashboard.ID)
+func (module *module) listDashboards(ctx context.Context, orgID valuer.UUID) ([]*dashboardtypes.Dashboard, error) {
+	var allDashboards []*dashboardtypes.Dashboard
 
-		existing, err := module.store.GetIntegrationDashboardBySlug(ctx, orgID, cloudintegrationtypes.IntegrationDashboardProviderCloudIntegration, slug)
-		if err != nil && !errors.Ast(err, errors.TypeNotFound) {
-			return err
-		}
-		if existing != nil {
-			continue
-		}
-
-		createdDashboard, err := module.dashboardModule.Create(ctx, orgID, createdBy, creator, dashboardtypes.SourceIntegration, dashboardtypes.PostableDashboard(dashboard.Definition))
+	for provider := range module.cloudProvidersMap {
+		cloudProvider, err := module.getCloudProvider(provider)
 		if err != nil {
-			return err
+			return nil, err
 		}
 
-		integrationDashboard := cloudintegrationtypes.NewStorableIntegrationDashboard(createdDashboard.ID, cloudintegrationtypes.IntegrationDashboardProviderCloudIntegration, slug)
-		if err := module.store.CreateIntegrationDashboard(ctx, integrationDashboard); err != nil {
-			return err
-		}
-	}
-
-	return nil
-}
-
-// deprovisionDashboards deletes all dashboard and integration_dashboard rows for the given service.
-// make sure to call this within a transaction.
-func (module *module) deprovisionDashboards(ctx context.Context, orgID valuer.UUID, provider cloudintegrationtypes.CloudProviderType, serviceID cloudintegrationtypes.ServiceID) error {
-	slugPrefix := cloudintegrationtypes.CloudIntegrationDashboardSlugPrefix(provider, serviceID)
-	rows, err := module.store.ListIntegrationDashboardsBySlugPrefix(ctx, orgID, cloudintegrationtypes.IntegrationDashboardProviderCloudIntegration, slugPrefix)
-	if err != nil {
-		return err
-	}
-	for _, row := range rows {
-		dashID, err := valuer.NewUUID(row.DashboardID)
+		connectedAccounts, err := module.store.ListConnectedAccounts(ctx, orgID, provider)
 		if err != nil {
-			return err
+			return nil, err
 		}
 
-		if err := module.store.DeleteIntegrationDashboardBySlug(ctx, orgID, cloudintegrationtypes.IntegrationDashboardProviderCloudIntegration, row.Slug); err != nil {
-			return err
-		}
+		for _, storableAccount := range connectedAccounts {
+			storedServices, err := module.store.ListServices(ctx, storableAccount.ID)
+			if err != nil {
+				return nil, err
+			}
 
-		if err := module.dashboardModule.DeleteUnsafe(ctx, orgID, dashID); err != nil {
-			return err
+			for _, storedSvc := range storedServices {
+				serviceConfig, err := cloudintegrationtypes.NewServiceConfigFromJSON(provider, storedSvc.Config)
+				if err != nil || !serviceConfig.IsMetricsEnabled(provider) {
+					continue
+				}
+
+				svcDef, err := cloudProvider.GetServiceDefinition(ctx, storedSvc.Type)
+				if err != nil || svcDef == nil {
+					continue
+				}
+
+				dashboards := cloudintegrationtypes.GetDashboardsFromAssets(
+					storedSvc.Type.StringValue(),
+					orgID,
+					provider,
+					storableAccount.CreatedAt,
+					svcDef.Assets,
+				)
+				allDashboards = append(allDashboards, dashboards...)
+			}
 		}
 	}
-	return nil
+
+	sort.Slice(allDashboards, func(i, j int) bool {
+		return allDashboards[i].ID < allDashboards[j].ID
+	})
+
+	return allDashboards, nil
 }

ee/modules/dashboard/impldashboard/module.go

@@ -11,7 +11,6 @@ import (
 	"github.com/SigNoz/signoz/pkg/modules/dashboard"
 	pkgimpldashboard "github.com/SigNoz/signoz/pkg/modules/dashboard/impldashboard"
 	"github.com/SigNoz/signoz/pkg/modules/organization"
-	"github.com/SigNoz/signoz/pkg/modules/tag"
 	"github.com/SigNoz/signoz/pkg/querier"
 	"github.com/SigNoz/signoz/pkg/queryparser"
 	"github.com/SigNoz/signoz/pkg/types"
@@ -31,9 +30,9 @@ type module struct {
 	licensing          licensing.Licensing
 }
 
-func NewModule(store dashboardtypes.Store, settings factory.ProviderSettings, analytics analytics.Analytics, orgGetter organization.Getter, queryParser queryparser.QueryParser, querier querier.Querier, licensing licensing.Licensing, tagModule tag.Module) dashboard.Module {
+func NewModule(store dashboardtypes.Store, settings factory.ProviderSettings, analytics analytics.Analytics, orgGetter organization.Getter, queryParser queryparser.QueryParser, querier querier.Querier, licensing licensing.Licensing) dashboard.Module {
 	scopedProviderSettings := factory.NewScopedProviderSettings(settings, "github.com/SigNoz/signoz/ee/modules/dashboard/impldashboard")
-	pkgDashboardModule := pkgimpldashboard.NewModule(store, settings, analytics, orgGetter, queryParser, tagModule)
+	pkgDashboardModule := pkgimpldashboard.NewModule(store, settings, analytics, orgGetter, queryParser)
 
 	return &module{
 		pkgDashboardModule: pkgDashboardModule,
@@ -50,14 +49,6 @@ func (module *module) CreatePublic(ctx context.Context, orgID valuer.UUID, publi
 		return errors.New(errors.TypeLicenseUnavailable, errors.CodeLicenseUnavailable, "a valid license is not available").WithAdditional("this feature requires a valid license").WithAdditional(err.Error())
 	}
 
-	dashboard, err := module.Get(ctx, orgID, publicDashboard.DashboardID)
-	if err != nil {
-		return err
-	}
-	if err := dashboard.ErrIfNotPublishable(); err != nil {
-		return err
-	}
-
 	storablePublicDashboard, err := module.store.GetPublic(ctx, publicDashboard.DashboardID.StringValue())
 	if err != nil && !errors.Ast(err, errors.TypeNotFound) {
 		return err
@@ -138,14 +129,6 @@ func (module *module) UpdatePublic(ctx context.Context, orgID valuer.UUID, publi
 		return errors.New(errors.TypeLicenseUnavailable, errors.CodeLicenseUnavailable, "a valid license is not available").WithAdditional("this feature requires a valid license").WithAdditional(err.Error())
 	}
 
-	dashboard, err := module.Get(ctx, orgID, publicDashboard.DashboardID)
-	if err != nil {
-		return err
-	}
-	if err := dashboard.ErrIfNotPublishable(); err != nil {
-		return err
-	}
-
 	return module.store.UpdatePublic(ctx, dashboardtypes.NewStorablePublicDashboardFromPublicDashboard(publicDashboard))
 }
 
@@ -155,19 +138,28 @@ func (module *module) Delete(ctx context.Context, orgID valuer.UUID, id valuer.U
 		return err
 	}
 
-	if err := dashboard.ErrIfNotDeletable(); err != nil {
-		return err
-	}
-
 	if dashboard.Locked {
 		return errors.New(errors.TypeInvalidInput, errors.CodeInvalidInput, "dashboard is locked, please unlock the dashboard to be delete it")
 	}
 
-	return module.delete(ctx, orgID, id)
-}
+	err = module.store.RunInTx(ctx, func(ctx context.Context) error {
+		err := module.store.DeletePublic(ctx, id.String())
+		if err != nil && !errors.Ast(err, errors.TypeNotFound) {
+			return err
+		}
 
-func (module *module) DeleteUnsafe(ctx context.Context, orgID, id valuer.UUID) error {
-	return module.delete(ctx, orgID, id)
+		err = module.store.Delete(ctx, orgID, id)
+		if err != nil {
+			return err
+		}
+
+		return nil
+	})
+	if err != nil {
+		return err
+	}
+
+	return nil
 }
 
 func (module *module) DeletePublic(ctx context.Context, orgID valuer.UUID, dashboardID valuer.UUID) error {
@@ -176,14 +168,6 @@ func (module *module) DeletePublic(ctx context.Context, orgID valuer.UUID, dashb
 		return errors.New(errors.TypeLicenseUnavailable, errors.CodeLicenseUnavailable, "a valid license is not available").WithAdditional("this feature requires a valid license").WithAdditional(err.Error())
 	}
 
-	dashboard, err := module.Get(ctx, orgID, dashboardID)
-	if err != nil {
-		return err
-	}
-	if err := dashboard.ErrIfNotPublishable(); err != nil {
-		return err
-	}
-
 	err = module.store.DeletePublic(ctx, dashboardID.StringValue())
 	if err != nil {
 		return err
@@ -209,77 +193,8 @@ func (module *module) Collect(ctx context.Context, orgID valuer.UUID) (map[strin
 	return stats, nil
 }
 
-func (module *module) Create(ctx context.Context, orgID valuer.UUID, createdBy string, creator valuer.UUID, source dashboardtypes.Source, data dashboardtypes.PostableDashboard) (*dashboardtypes.Dashboard, error) {
-	return module.pkgDashboardModule.Create(ctx, orgID, createdBy, creator, source, data)
-}
-
-func (module *module) CreateV2(ctx context.Context, orgID valuer.UUID, createdBy string, creator valuer.UUID, source dashboardtypes.Source, postable dashboardtypes.PostableDashboardV2) (*dashboardtypes.DashboardV2, error) {
-	return module.pkgDashboardModule.CreateV2(ctx, orgID, createdBy, creator, source, postable)
-}
-
-func (module *module) CloneV2(ctx context.Context, orgID valuer.UUID, createdBy string, creator valuer.UUID, id valuer.UUID) (*dashboardtypes.DashboardV2, error) {
-	return module.pkgDashboardModule.CloneV2(ctx, orgID, createdBy, creator, id)
-}
-
-func (module *module) GetV2(ctx context.Context, orgID valuer.UUID, id valuer.UUID) (*dashboardtypes.DashboardV2, error) {
-	return module.pkgDashboardModule.GetV2(ctx, orgID, id)
-}
-
-func (module *module) UpdateV2(ctx context.Context, orgID valuer.UUID, id valuer.UUID, updatedBy string, updatable dashboardtypes.UpdatableDashboardV2) (*dashboardtypes.DashboardV2, error) {
-	return module.pkgDashboardModule.UpdateV2(ctx, orgID, id, updatedBy, updatable)
-}
-
-func (module *module) PatchV2(ctx context.Context, orgID valuer.UUID, id valuer.UUID, updatedBy string, patch dashboardtypes.PatchableDashboardV2) (*dashboardtypes.DashboardV2, error) {
-	return module.pkgDashboardModule.PatchV2(ctx, orgID, id, updatedBy, patch)
-}
-
-func (module *module) DeleteV2(ctx context.Context, orgID valuer.UUID, id valuer.UUID) error {
-	return module.store.RunInTx(ctx, func(ctx context.Context) error {
-		if err := module.store.DeletePublic(ctx, id.String()); err != nil && !errors.Ast(err, errors.TypeNotFound) {
-			return err
-		}
-		return module.pkgDashboardModule.DeleteV2(ctx, orgID, id)
-	})
-}
-
-func (module *module) LockUnlockV2(ctx context.Context, orgID valuer.UUID, id valuer.UUID, updatedBy string, isAdmin bool, lock bool) error {
-	return module.pkgDashboardModule.LockUnlockV2(ctx, orgID, id, updatedBy, isAdmin, lock)
-}
-
-func (module *module) ListV2(ctx context.Context, orgID valuer.UUID, params *dashboardtypes.ListDashboardsV2Params) (*dashboardtypes.ListableDashboardV2, error) {
-	return module.pkgDashboardModule.ListV2(ctx, orgID, params)
-}
-
-func (module *module) ListForUserV2(ctx context.Context, orgID valuer.UUID, userID valuer.UUID, params *dashboardtypes.ListDashboardsV2Params) (*dashboardtypes.ListableDashboardForUserV2, error) {
-	return module.pkgDashboardModule.ListForUserV2(ctx, orgID, userID, params)
-}
-
-func (module *module) PinV2(ctx context.Context, orgID valuer.UUID, userID valuer.UUID, id valuer.UUID) error {
-	return module.pkgDashboardModule.PinV2(ctx, orgID, userID, id)
-}
-
-func (module *module) UnpinV2(ctx context.Context, orgID valuer.UUID, userID valuer.UUID, id valuer.UUID) error {
-	return module.pkgDashboardModule.UnpinV2(ctx, orgID, userID, id)
-}
-
-func (module *module) DeletePreferencesForUser(ctx context.Context, orgID valuer.UUID, userID valuer.UUID) error {
-	return module.pkgDashboardModule.DeletePreferencesForUser(ctx, orgID, userID)
-}
-
-func (module *module) CreateView(ctx context.Context, orgID valuer.UUID, postable dashboardtypes.PostableDashboardView) (*dashboardtypes.DashboardView, error) {
-	return module.pkgDashboardModule.CreateView(ctx, orgID, postable)
-}
-
-func (module *module) ListViews(ctx context.Context, orgID valuer.UUID) (*dashboardtypes.ListableDashboardView, error) {
-	return module.pkgDashboardModule.ListViews(ctx, orgID)
-}
-
-func (module *module) UpdateView(ctx context.Context, orgID valuer.UUID, id valuer.UUID, updateable dashboardtypes.UpdatableDashboardView) (*dashboardtypes.DashboardView, error) {
-	return module.pkgDashboardModule.UpdateView(ctx, orgID, id, updateable)
-}
-
-func (module *module) DeleteView(ctx context.Context, orgID valuer.UUID, id valuer.UUID) error {
-	return module.pkgDashboardModule.DeleteView(ctx, orgID, id)
+func (module *module) Create(ctx context.Context, orgID valuer.UUID, createdBy string, creator valuer.UUID, data dashboardtypes.PostableDashboard) (*dashboardtypes.Dashboard, error) {
+	return module.pkgDashboardModule.Create(ctx, orgID, createdBy, creator, data)
 }
 
 func (module *module) Get(ctx context.Context, orgID valuer.UUID, id valuer.UUID) (*dashboardtypes.Dashboard, error) {
@@ -290,10 +205,6 @@ func (module *module) GetByMetricNames(ctx context.Context, orgID valuer.UUID, m
 	return module.pkgDashboardModule.GetByMetricNames(ctx, orgID, metricNames)
 }
 
-func (module *module) GetByMetricNamesV2(ctx context.Context, orgID valuer.UUID, metricNames []string) (map[string][]dashboardtypes.DashboardPanelRef, error) {
-	return module.pkgDashboardModule.GetByMetricNamesV2(ctx, orgID, metricNames)
-}
-
 func (module *module) List(ctx context.Context, orgID valuer.UUID) ([]*dashboardtypes.Dashboard, error) {
 	return module.pkgDashboardModule.List(ctx, orgID)
 }
@@ -305,12 +216,3 @@ func (module *module) Update(ctx context.Context, orgID valuer.UUID, id valuer.U
 func (module *module) LockUnlock(ctx context.Context, orgID valuer.UUID, id valuer.UUID, updatedBy string, isAdmin bool, lock bool) error {
 	return module.pkgDashboardModule.LockUnlock(ctx, orgID, id, updatedBy, isAdmin, lock)
 }
-
-func (module *module) delete(ctx context.Context, orgID, id valuer.UUID) error {
-	return module.store.RunInTx(ctx, func(ctx context.Context) error {
-		if err := module.store.DeletePublic(ctx, id.String()); err != nil && !errors.Ast(err, errors.TypeNotFound) {
-			return err
-		}
-		return module.store.Delete(ctx, orgID, id)
-	})
-}

ee/modules/metricreductionrule/implmetricreductionrule/clickhouse.go

@@ -1,565 +0,0 @@
-package implmetricreductionrule
-
-import (
-	"context"
-	"slices"
-	"time"
-
-	sqlbuilder "github.com/huandu/go-sqlbuilder"
-
-	"github.com/SigNoz/signoz/pkg/errors"
-	"github.com/SigNoz/signoz/pkg/telemetrymetrics"
-	"github.com/SigNoz/signoz/pkg/telemetrystore"
-	"github.com/SigNoz/signoz/pkg/types/ctxtypes"
-	"github.com/SigNoz/signoz/pkg/types/metricreductionruletypes"
-)
-
-var (
-	reductionRulesTable = telemetrymetrics.DBName + "." + telemetrymetrics.ReductionRulesTableName
-	metadataTable       = telemetrymetrics.DBName + "." + telemetrymetrics.AttributesMetadataTableName
-	bufferSeriesTable   = telemetrymetrics.DBName + "." + telemetrymetrics.TimeseriesV4BufferTableName
-)
-
-const timeSeriesBucketMilli = int64(time.Hour / time.Millisecond)
-
-type volumeRow struct {
-	MetricName string
-	Ingested   uint64
-	Reduced    uint64
-}
-
-type volumePoint struct {
-	TimestampMs int64
-	Ingested    uint64
-	Reduced     uint64
-}
-
-type clickhouse struct {
-	telemetryStore telemetrystore.TelemetryStore
-	threads        int
-}
-
-func newClickhouse(telemetryStore telemetrystore.TelemetryStore, threads int) *clickhouse {
-	return &clickhouse{telemetryStore: telemetryStore, threads: threads}
-}
-
-func (c *clickhouse) withThreads(ctx context.Context) context.Context {
-	return ctxtypes.SetClickhouseMaxThreads(ctx, c.threads)
-}
-
-func floorToTimeSeriesBucket(ms int64) int64 {
-	return ms - (ms % timeSeriesBucketMilli)
-}
-
-func strictEffectiveFrom(sb *sqlbuilder.SelectBuilder, metricNames []string, effectiveFrom map[string]int64) string {
-	names := make([]any, 0, len(metricNames))
-	froms := make([]any, 0, len(metricNames))
-	for _, name := range metricNames {
-		names = append(names, name)
-		froms = append(froms, effectiveFrom[name])
-	}
-	return "unix_milli >= transform(metric_name, " + sb.Var(names) + ", " + sb.Var(froms) + ", 0)"
-}
-
-func (c *clickhouse) Sync(ctx context.Context, metricName string, labels []string, matchType string, effectiveFromMs int64, deleted bool, updatedAt time.Time) error {
-	ctx = c.withThreads(ctx)
-
-	ib := sqlbuilder.NewInsertBuilder()
-	ib.InsertInto(reductionRulesTable)
-	ib.Cols("metric_name", "labels", "match_type", "effective_from_unix_milli", "deleted", "updated_at")
-	ib.Values(metricName, labels, matchType, effectiveFromMs, deleted, updatedAt)
-
-	query, args := ib.BuildWithFlavor(sqlbuilder.ClickHouse)
-	if err := c.telemetryStore.ClickhouseDB().Exec(ctx, query, args...); err != nil {
-		return errors.WrapInternalf(err, errors.CodeInternal, "failed to sync reduction rule to clickhouse")
-	}
-	return nil
-}
-
-func (c *clickhouse) AttributeKeys(ctx context.Context, metricName string, startMs, endMs int64) ([]string, error) {
-	ctx = c.withThreads(ctx)
-
-	sb := sqlbuilder.NewSelectBuilder()
-	sb.Select("attr_name")
-	sb.Distinct()
-	sb.From(metadataTable)
-	sb.Where(
-		sb.E("metric_name", metricName),
-		"NOT startsWith(attr_name, '__')",
-		sb.GE("last_reported_unix_milli", startMs),
-		sb.LE("first_reported_unix_milli", endMs),
-	)
-
-	query, args := sb.BuildWithFlavor(sqlbuilder.ClickHouse)
-	rows, err := c.telemetryStore.ClickhouseDB().Query(ctx, query, args...)
-	if err != nil {
-		return nil, errors.WrapInternalf(err, errors.CodeInternal, "failed to fetch metric attribute keys")
-	}
-	defer rows.Close()
-
-	keys := make([]string, 0)
-	for rows.Next() {
-		var key string
-		if err := rows.Scan(&key); err != nil {
-			return nil, errors.WrapInternalf(err, errors.CodeInternal, "failed to scan attribute key")
-		}
-		keys = append(keys, key)
-	}
-	return keys, rows.Err()
-}
-
-func (c *clickhouse) EstimateCardinality(ctx context.Context, metricName string, keptLabels []string, startMs, endMs int64) (uint64, uint64, error) {
-	ctx = c.withThreads(ctx)
-	startMs = floorToTimeSeriesBucket(startMs)
-
-	sb := sqlbuilder.NewSelectBuilder()
-
-	reducedExpr := "1"
-	if len(keptLabels) > 0 {
-		reducedExpr = "uniq(("
-		for i, label := range keptLabels {
-			if i > 0 {
-				reducedExpr += ", "
-			}
-			reducedExpr += "JSONExtractString(labels, " + sb.Var(label) + ")"
-		}
-		reducedExpr += "))"
-	}
-
-	sb.Select("uniq(fingerprint)", reducedExpr)
-	sb.From(bufferSeriesTable)
-	conds := []string{
-		sb.E("metric_name", metricName),
-		sb.GE("unix_milli", startMs),
-		sb.LT("unix_milli", endMs),
-		sb.E("is_reduced", false),
-	}
-	sb.Where(conds...)
-
-	query, args := sb.BuildWithFlavor(sqlbuilder.ClickHouse)
-	var current, reduced uint64
-	if err := c.telemetryStore.ClickhouseDB().QueryRow(ctx, query, args...).Scan(&current, &reduced); err != nil {
-		return 0, 0, errors.WrapInternalf(err, errors.CodeInternal, "failed to estimate reduction impact")
-	}
-	if len(keptLabels) == 0 && current == 0 {
-		reduced = 0
-	}
-	if reduced > current {
-		reduced = current
-	}
-	return current, reduced, nil
-}
-
-// VolumeByMetric returns ingested vs reduced series counts per metric.
-func (c *clickhouse) VolumeByMetric(ctx context.Context, metricNames []string, effectiveFrom map[string]int64, startMs, endMs int64) (map[string]volumeRow, error) {
-	if len(metricNames) == 0 {
-		return map[string]volumeRow{}, nil
-	}
-	ctx = c.withThreads(ctx)
-
-	ingested, err := c.ingestedSeriesCount(ctx, metricNames, effectiveFrom, startMs, endMs)
-	if err != nil {
-		return nil, err
-	}
-
-	reduced, err := c.reducedSeriesCount(ctx, metricNames, effectiveFrom, startMs, endMs)
-	if err != nil {
-		return nil, err
-	}
-
-	out := make(map[string]volumeRow, len(metricNames))
-	for metricName, count := range ingested {
-		out[metricName] = volumeRow{MetricName: metricName, Ingested: count, Reduced: out[metricName].Reduced}
-	}
-	for metricName, count := range reduced {
-		row := out[metricName]
-		row.MetricName = metricName
-		row.Reduced = count
-		out[metricName] = row
-	}
-	return out, nil
-}
-
-// ingestedSeriesCount counts distinct raw fingerprints per metric from the samples buffer over the
-// window.
-func (c *clickhouse) ingestedSeriesCount(ctx context.Context, metricNames []string, effectiveFrom map[string]int64, startMs, endMs int64) (map[string]uint64, error) {
-	names := make([]any, len(metricNames))
-	for i, name := range metricNames {
-		names[i] = name
-	}
-
-	sb := sqlbuilder.NewSelectBuilder()
-	sb.Select("metric_name", "uniq(fingerprint)")
-	sb.From(telemetrymetrics.DBName + "." + telemetrymetrics.SamplesV4BufferTableName)
-	conds := []string{
-		sb.In("metric_name", names...),
-		sb.GE("unix_milli", startMs),
-		sb.LT("unix_milli", endMs),
-	}
-	if len(effectiveFrom) > 0 {
-		conds = append(conds, strictEffectiveFrom(sb, metricNames, effectiveFrom))
-	}
-	sb.Where(conds...)
-	sb.GroupBy("metric_name")
-
-	query, args := sb.BuildWithFlavor(sqlbuilder.ClickHouse)
-	rows, err := c.telemetryStore.ClickhouseDB().Query(ctx, query, args...)
-	if err != nil {
-		return nil, errors.WrapInternalf(err, errors.CodeInternal, "failed to count ingested series")
-	}
-	defer rows.Close()
-
-	out := make(map[string]uint64, len(metricNames))
-	for rows.Next() {
-		var (
-			metricName string
-			count      uint64
-		)
-		if err := rows.Scan(&metricName, &count); err != nil {
-			return nil, errors.WrapInternalf(err, errors.CodeInternal, "failed to scan series count")
-		}
-		out[metricName] = count
-	}
-	return out, rows.Err()
-}
-
-// reducedSeriesCount counts distinct reduced_fingerprints per metric, summed across the two 60s
-// reduced sample tables.
-func (c *clickhouse) reducedSeriesCount(ctx context.Context, metricNames []string, effectiveFrom map[string]int64, startMs, endMs int64) (map[string]uint64, error) {
-	out := make(map[string]uint64, len(metricNames))
-	for _, table := range []string{telemetrymetrics.SamplesV4ReducedLastTableName, telemetrymetrics.SamplesV4ReducedSumTableName} {
-		counts, err := c.reducedSeriesCountForTable(ctx, telemetrymetrics.DBName+"."+table, metricNames, effectiveFrom, startMs, endMs)
-		if err != nil {
-			return nil, err
-		}
-		for metricName, count := range counts {
-			out[metricName] += count
-		}
-	}
-	return out, nil
-}
-
-func (c *clickhouse) reducedSeriesCountForTable(ctx context.Context, table string, metricNames []string, effectiveFrom map[string]int64, startMs, endMs int64) (map[string]uint64, error) {
-	names := make([]any, len(metricNames))
-	for i, name := range metricNames {
-		names[i] = name
-	}
-
-	sb := sqlbuilder.NewSelectBuilder()
-	sb.Select("metric_name", "uniq(reduced_fingerprint)")
-	sb.From(table)
-	conds := []string{
-		sb.In("metric_name", names...),
-		sb.GE("unix_milli", startMs),
-		sb.LT("unix_milli", endMs),
-	}
-	if len(effectiveFrom) > 0 {
-		conds = append(conds, strictEffectiveFrom(sb, metricNames, effectiveFrom))
-	}
-	sb.Where(conds...)
-	sb.GroupBy("metric_name")
-
-	query, args := sb.BuildWithFlavor(sqlbuilder.ClickHouse)
-	rows, err := c.telemetryStore.ClickhouseDB().Query(ctx, query, args...)
-	if err != nil {
-		return nil, errors.WrapInternalf(err, errors.CodeInternal, "failed to count reduced series")
-	}
-	defer rows.Close()
-
-	out := make(map[string]uint64, len(metricNames))
-	for rows.Next() {
-		var (
-			metricName string
-			count      uint64
-		)
-		if err := rows.Scan(&metricName, &count); err != nil {
-			return nil, errors.WrapInternalf(err, errors.CodeInternal, "failed to scan series count")
-		}
-		out[metricName] = count
-	}
-	return out, rows.Err()
-}
-
-// RankByVolume ranks metrics by ingested/reduced series volume. Like VolumeByMetric, the counts read
-// the samples tables with a strict effective_from gate; the reduced count sums distinct
-// reduced_fingerprints across the two 60s reduced sample tables.
-func (c *clickhouse) RankByVolume(ctx context.Context, metricNames []string, effectiveFrom map[string]int64, orderBy metricreductionruletypes.ReductionRuleOrderBy, order metricreductionruletypes.Order, startMs, endMs int64, offset, limit int) ([]volumeRow, error) {
-	if len(metricNames) == 0 {
-		return []volumeRow{}, nil
-	}
-	ctx = c.withThreads(ctx)
-
-	orderExpr := "ingested"
-	switch orderBy {
-	case metricreductionruletypes.OrderByReducedVolume:
-		orderExpr = "reduced"
-	case metricreductionruletypes.OrderByReduction:
-		orderExpr = "if(ingested = 0, 0, (toFloat64(ingested) - toFloat64(reduced)) / toFloat64(ingested))"
-	}
-	direction := "ASC"
-	if order == metricreductionruletypes.OrderDesc {
-		direction = "DESC"
-	}
-
-	ingestedTable := telemetrymetrics.DBName + "." + telemetrymetrics.SamplesV4BufferTableName
-	reducedLast := telemetrymetrics.DBName + "." + telemetrymetrics.SamplesV4ReducedLastTableName
-	reducedSum := telemetrymetrics.DBName + "." + telemetrymetrics.SamplesV4ReducedSumTableName
-
-	sb := sqlbuilder.NewSelectBuilder()
-	sb.Select("base.metric_name AS metric_name", "ifNull(i.cnt, 0) AS ingested", "ifNull(d.cnt, 0) AS reduced")
-	sb.From("(SELECT arrayJoin(" + sb.Var(metricNames) + ") AS metric_name) AS base")
-	sb.JoinWithOption(
-		sqlbuilder.LeftJoin,
-		"(SELECT metric_name, uniq(fingerprint) AS cnt FROM "+ingestedTable+" WHERE has("+sb.Var(metricNames)+", metric_name) AND unix_milli >= "+sb.Var(startMs)+" AND unix_milli < "+sb.Var(endMs)+" AND "+strictEffectiveFrom(sb, metricNames, effectiveFrom)+" GROUP BY metric_name) AS i",
-		"base.metric_name = i.metric_name",
-	)
-	// Reduced series are spread across two type-specific tables; union the per-table distinct
-	// reduced_fingerprints and sum per metric (a metric only lands in the table matching its type).
-	sb.JoinWithOption(
-		sqlbuilder.LeftJoin,
-		"(SELECT metric_name, sum(cnt) AS cnt FROM ("+
-			"SELECT metric_name, uniq(reduced_fingerprint) AS cnt FROM "+reducedLast+" WHERE has("+sb.Var(metricNames)+", metric_name) AND unix_milli >= "+sb.Var(startMs)+" AND unix_milli < "+sb.Var(endMs)+" AND "+strictEffectiveFrom(sb, metricNames, effectiveFrom)+" GROUP BY metric_name"+
-			" UNION ALL "+
-			"SELECT metric_name, uniq(reduced_fingerprint) AS cnt FROM "+reducedSum+" WHERE has("+sb.Var(metricNames)+", metric_name) AND unix_milli >= "+sb.Var(startMs)+" AND unix_milli < "+sb.Var(endMs)+" AND "+strictEffectiveFrom(sb, metricNames, effectiveFrom)+" GROUP BY metric_name"+
-			") GROUP BY metric_name) AS d",
-		"base.metric_name = d.metric_name",
-	)
-	sb.OrderBy(orderExpr + " " + direction)
-	if limit > 0 {
-		sb.Limit(limit).Offset(offset)
-	}
-
-	query, args := sb.BuildWithFlavor(sqlbuilder.ClickHouse)
-	rows, err := c.telemetryStore.ClickhouseDB().Query(ctx, query, args...)
-	if err != nil {
-		return nil, errors.WrapInternalf(err, errors.CodeInternal, "failed to rank reduction rules by volume")
-	}
-	defer rows.Close()
-
-	out := make([]volumeRow, 0, len(metricNames))
-	for rows.Next() {
-		var row volumeRow
-		if err := rows.Scan(&row.MetricName, &row.Ingested, &row.Reduced); err != nil {
-			return nil, errors.WrapInternalf(err, errors.CodeInternal, "failed to scan volume row")
-		}
-		out = append(out, row)
-	}
-	return out, rows.Err()
-}
-
-func (c *clickhouse) SampleVolume(ctx context.Context, metricNames []string, effectiveFrom map[string]int64, startMs, endMs int64) (uint64, uint64, error) {
-	if len(metricNames) == 0 {
-		return 0, 0, nil
-	}
-	ctx = c.withThreads(ctx)
-
-	ingested, err := c.countRawSamples(ctx, telemetrymetrics.DBName+"."+telemetrymetrics.SamplesV4BufferTableName, metricNames, effectiveFrom, startMs, endMs)
-	if err != nil {
-		return 0, 0, err
-	}
-
-	last, err := c.countReducedSamples(ctx, telemetrymetrics.DBName+"."+telemetrymetrics.SamplesV4ReducedLastTableName, metricNames, effectiveFrom, startMs, endMs)
-	if err != nil {
-		return 0, 0, err
-	}
-	sum, err := c.countReducedSamples(ctx, telemetrymetrics.DBName+"."+telemetrymetrics.SamplesV4ReducedSumTableName, metricNames, effectiveFrom, startMs, endMs)
-	if err != nil {
-		return 0, 0, err
-	}
-
-	return ingested, min(last+sum, ingested), nil
-}
-
-func (c *clickhouse) countRawSamples(ctx context.Context, table string, metricNames []string, effectiveFrom map[string]int64, startMs, endMs int64) (uint64, error) {
-	names := make([]any, len(metricNames))
-	for i, name := range metricNames {
-		names[i] = name
-	}
-
-	sb := sqlbuilder.NewSelectBuilder()
-	sb.Select("count()")
-	sb.From(table)
-	conds := []string{sb.In("metric_name", names...), sb.GE("unix_milli", startMs), sb.LT("unix_milli", endMs)}
-	if len(effectiveFrom) > 0 {
-		conds = append(conds, strictEffectiveFrom(sb, metricNames, effectiveFrom))
-	}
-	sb.Where(conds...)
-
-	query, args := sb.BuildWithFlavor(sqlbuilder.ClickHouse)
-	var count uint64
-	if err := c.telemetryStore.ClickhouseDB().QueryRow(ctx, query, args...).Scan(&count); err != nil {
-		return 0, errors.WrapInternalf(err, errors.CodeInternal, "failed to count ingested samples")
-	}
-	return count, nil
-}
-
-func (c *clickhouse) countReducedSamples(ctx context.Context, table string, metricNames []string, effectiveFrom map[string]int64, startMs, endMs int64) (uint64, error) {
-	names := make([]any, len(metricNames))
-	for i, name := range metricNames {
-		names[i] = name
-	}
-
-	sb := sqlbuilder.NewSelectBuilder()
-	// Reduced tables key the series on reduced_fingerprint (not fingerprint); dedupe ReplacingMergeTree recomputes.
-	sb.Select("uniq(reduced_fingerprint, unix_milli)")
-	sb.From(table)
-	conds := []string{sb.In("metric_name", names...), sb.GE("unix_milli", startMs), sb.LT("unix_milli", endMs)}
-	if len(effectiveFrom) > 0 {
-		conds = append(conds, strictEffectiveFrom(sb, metricNames, effectiveFrom))
-	}
-	sb.Where(conds...)
-
-	query, args := sb.BuildWithFlavor(sqlbuilder.ClickHouse)
-	var count uint64
-	if err := c.telemetryStore.ClickhouseDB().QueryRow(ctx, query, args...).Scan(&count); err != nil {
-		return 0, errors.WrapInternalf(err, errors.CodeInternal, "failed to count reduced samples")
-	}
-	return count, nil
-}
-
-// SeriesTimeseries returns ingested vs reduced series per 60s bucket from the samples tables, gated
-// to each metric's strict effective_from (see strictEffectiveFrom).
-func (c *clickhouse) SeriesTimeseries(ctx context.Context, allMetrics, reducedMetrics []string, effectiveFrom map[string]int64, startMs, endMs int64) ([]volumePoint, error) {
-	if len(allMetrics) == 0 {
-		return []volumePoint{}, nil
-	}
-	ctx = c.withThreads(ctx)
-
-	ingested, err := c.ingestedSeriesByBucket(ctx, allMetrics, effectiveFrom, startMs, endMs)
-	if err != nil {
-		return nil, err
-	}
-
-	retained := make(map[int64]uint64)
-	if len(reducedMetrics) > 0 {
-		reduced, err := c.reducedSeriesByBucket(ctx, reducedMetrics, effectiveFrom, startMs, endMs)
-		if err != nil {
-			return nil, err
-		}
-		for ts, count := range reduced {
-			retained[ts] += count
-		}
-	}
-	reducedSet := make(map[string]struct{}, len(reducedMetrics))
-	for _, name := range reducedMetrics {
-		reducedSet[name] = struct{}{}
-	}
-	nonReduced := make([]string, 0, len(allMetrics))
-	for _, name := range allMetrics {
-		if _, ok := reducedSet[name]; !ok {
-			nonReduced = append(nonReduced, name)
-		}
-	}
-	if len(nonReduced) > 0 {
-		nonReducedIngested, err := c.ingestedSeriesByBucket(ctx, nonReduced, effectiveFrom, startMs, endMs)
-		if err != nil {
-			return nil, err
-		}
-		for ts, count := range nonReducedIngested {
-			retained[ts] += count
-		}
-	}
-
-	return mergeVolumePoints(ingested, retained), nil
-}
-
-func mergeVolumePoints(ingested, reduced map[int64]uint64) []volumePoint {
-	buckets := make(map[int64]struct{}, len(ingested))
-	for ts := range ingested {
-		buckets[ts] = struct{}{}
-	}
-	for ts := range reduced {
-		buckets[ts] = struct{}{}
-	}
-	timestamps := make([]int64, 0, len(buckets))
-	for ts := range buckets {
-		timestamps = append(timestamps, ts)
-	}
-	slices.Sort(timestamps)
-
-	points := make([]volumePoint, 0, len(timestamps))
-	for _, ts := range timestamps {
-		points = append(points, volumePoint{
-			TimestampMs: ts,
-			Ingested:    ingested[ts],
-			Reduced:     reduced[ts],
-		})
-	}
-	return points
-}
-
-// ingestedSeriesByBucket counts distinct raw fingerprints per hourly bucket from the samples buffer.
-func (c *clickhouse) ingestedSeriesByBucket(ctx context.Context, metricNames []string, effectiveFrom map[string]int64, startMs, endMs int64) (map[int64]uint64, error) {
-	names := make([]any, len(metricNames))
-	for i, name := range metricNames {
-		names[i] = name
-	}
-
-	sb := sqlbuilder.NewSelectBuilder()
-	bucketExpr := "toInt64(toUnixTimestamp(toStartOfInterval(toDateTime(intDiv(unix_milli, 1000)), toIntervalHour(1)))) * 1000 AS bucket"
-	sb.Select(bucketExpr, "uniq(fingerprint)")
-	sb.From(telemetrymetrics.DBName + "." + telemetrymetrics.SamplesV4BufferTableName)
-	conds := []string{sb.In("metric_name", names...), sb.GE("unix_milli", startMs), sb.LT("unix_milli", endMs)}
-	if len(effectiveFrom) > 0 {
-		conds = append(conds, strictEffectiveFrom(sb, metricNames, effectiveFrom))
-	}
-	sb.Where(conds...)
-	sb.GroupBy("bucket")
-
-	return c.scanBuckets(ctx, sb)
-}
-
-// reducedSeriesByBucket counts distinct reduced_fingerprints per hourly bucket, summed across the two
-// reduced sample tables (a metric only lands in the table matching its type, so per-bucket sums are
-// exact).
-func (c *clickhouse) reducedSeriesByBucket(ctx context.Context, metricNames []string, effectiveFrom map[string]int64, startMs, endMs int64) (map[int64]uint64, error) {
-	out := make(map[int64]uint64)
-	for _, table := range []string{telemetrymetrics.SamplesV4ReducedLastTableName, telemetrymetrics.SamplesV4ReducedSumTableName} {
-		names := make([]any, len(metricNames))
-		for i, name := range metricNames {
-			names[i] = name
-		}
-
-		sb := sqlbuilder.NewSelectBuilder()
-		bucketExpr := "toInt64(toUnixTimestamp(toStartOfInterval(toDateTime(intDiv(unix_milli, 1000)), toIntervalHour(1)))) * 1000 AS bucket"
-		sb.Select(bucketExpr, "uniq(reduced_fingerprint)")
-		sb.From(telemetrymetrics.DBName + "." + table)
-		conds := []string{sb.In("metric_name", names...), sb.GE("unix_milli", startMs), sb.LT("unix_milli", endMs)}
-		if len(effectiveFrom) > 0 {
-			conds = append(conds, strictEffectiveFrom(sb, metricNames, effectiveFrom))
-		}
-		sb.Where(conds...)
-		sb.GroupBy("bucket")
-
-		counts, err := c.scanBuckets(ctx, sb)
-		if err != nil {
-			return nil, err
-		}
-		for ts, count := range counts {
-			out[ts] += count
-		}
-	}
-	return out, nil
-}
-
-func (c *clickhouse) scanBuckets(ctx context.Context, sb *sqlbuilder.SelectBuilder) (map[int64]uint64, error) {
-	query, args := sb.BuildWithFlavor(sqlbuilder.ClickHouse)
-	rows, err := c.telemetryStore.ClickhouseDB().Query(ctx, query, args...)
-	if err != nil {
-		return nil, errors.WrapInternalf(err, errors.CodeInternal, "failed to bucket series by time")
-	}
-	defer rows.Close()
-
-	out := make(map[int64]uint64)
-	for rows.Next() {
-		var (
-			ts    int64
-			count uint64
-		)
-		if err := rows.Scan(&ts, &count); err != nil {
-			return nil, errors.WrapInternalf(err, errors.CodeInternal, "failed to scan series bucket")
-		}
-		out[ts] = count
-	}
-	return out, rows.Err()
-}

ee/modules/metricreductionrule/implmetricreductionrule/module.go

@@ -1,571 +0,0 @@
-package implmetricreductionrule
-
-import (
-	"context"
-	"log/slog"
-	"sort"
-	"strings"
-	"time"
-
-	"github.com/SigNoz/signoz/pkg/errors"
-	"github.com/SigNoz/signoz/pkg/factory"
-	"github.com/SigNoz/signoz/pkg/flagger"
-	"github.com/SigNoz/signoz/pkg/licensing"
-	"github.com/SigNoz/signoz/pkg/modules/dashboard"
-	"github.com/SigNoz/signoz/pkg/modules/metricreductionrule"
-	"github.com/SigNoz/signoz/pkg/queryparser"
-	"github.com/SigNoz/signoz/pkg/ruler/rulestore/sqlrulestore"
-	"github.com/SigNoz/signoz/pkg/sqlstore"
-	"github.com/SigNoz/signoz/pkg/telemetrystore"
-	"github.com/SigNoz/signoz/pkg/types/featuretypes"
-	"github.com/SigNoz/signoz/pkg/types/metricreductionruletypes"
-	"github.com/SigNoz/signoz/pkg/types/metrictypes"
-	"github.com/SigNoz/signoz/pkg/types/querybuildertypes/querybuildertypesv5"
-	"github.com/SigNoz/signoz/pkg/types/ruletypes"
-	"github.com/SigNoz/signoz/pkg/types/telemetrytypes"
-	"github.com/SigNoz/signoz/pkg/valuer"
-)
-
-const (
-	// effectiveFromMargin delays effective_from so the collector picks up the synced rule before it
-	// goes live; it must be >= the collector's rule-refresh interval (see signoz-otel-collector#839).
-	effectiveFromMargin    = 5 * time.Minute
-	defaultPreviewLookback = 24 * time.Hour
-
-	pricePerMillionSamplesUSD = 0.1
-	monthDuration             = 30 * 24 * time.Hour
-)
-
-type module struct {
-	store         metricreductionruletypes.Store
-	ch            *clickhouse
-	dashboard     dashboard.Module
-	ruleStore     ruletypes.RuleStore
-	licensing     licensing.Licensing
-	flagger       flagger.Flagger
-	metadataStore telemetrytypes.MetadataStore
-	logger        *slog.Logger
-}
-
-func NewModule(sqlStore sqlstore.SQLStore, telemetryStore telemetrystore.TelemetryStore, dashboardModule dashboard.Module, queryParser queryparser.QueryParser, licensing licensing.Licensing, flagger flagger.Flagger, metadataStore telemetrytypes.MetadataStore, providerSettings factory.ProviderSettings, threads int) metricreductionrule.Module {
-	scoped := factory.NewScopedProviderSettings(providerSettings, "github.com/SigNoz/signoz/ee/modules/metricreductionrule/implmetricreductionrule")
-	return &module{
-		store:         NewStore(sqlStore),
-		ch:            newClickhouse(telemetryStore, threads),
-		dashboard:     dashboardModule,
-		ruleStore:     sqlrulestore.NewRuleStore(sqlStore, queryParser, providerSettings),
-		licensing:     licensing,
-		flagger:       flagger,
-		metadataStore: metadataStore,
-		logger:        scoped.Logger(),
-	}
-}
-
-func (m *module) checkAccess(ctx context.Context, orgID valuer.UUID) error {
-	if !m.flagger.BooleanOrEmpty(ctx, flagger.FeatureEnableMetricsReduction, featuretypes.NewFlaggerEvaluationContext(orgID)) {
-		return errors.Newf(errors.TypeUnsupported, metricreductionruletypes.ErrCodeMetricReductionRuleUnsupported, "metric volume control is not enabled")
-	}
-	if _, err := m.licensing.GetActive(ctx, orgID); err != nil {
-		return errors.New(errors.TypeLicenseUnavailable, errors.CodeLicenseUnavailable, "metric volume control requires a valid license").WithAdditional(err.Error())
-	}
-	return nil
-}
-
-func (m *module) List(ctx context.Context, orgID valuer.UUID, params *metricreductionruletypes.ListReductionRulesParams) (*metricreductionruletypes.GettableReductionRules, error) {
-	if err := m.checkAccess(ctx, orgID); err != nil {
-		return nil, err
-	}
-	if err := params.Validate(); err != nil {
-		return nil, err
-	}
-
-	now := time.Now()
-	startMs := now.Add(-defaultPreviewLookback).UnixMilli()
-	endMs := now.UnixMilli()
-
-	switch params.OrderBy {
-	case metricreductionruletypes.OrderByMetricName, metricreductionruletypes.OrderByLastUpdated:
-		return m.listSortedByColumn(ctx, orgID, params, startMs, endMs)
-	default:
-		return m.listSortedByVolume(ctx, orgID, params, startMs, endMs)
-	}
-}
-
-func (m *module) listSortedByColumn(ctx context.Context, orgID valuer.UUID, params *metricreductionruletypes.ListReductionRulesParams, startMs, endMs int64) (*metricreductionruletypes.GettableReductionRules, error) {
-	domainRules, total, err := m.store.List(ctx, orgID, params)
-	if err != nil {
-		return nil, err
-	}
-
-	metricNames := make([]string, len(domainRules))
-	effectiveFrom := make(map[string]int64, len(domainRules))
-	for i, rule := range domainRules {
-		metricNames[i] = rule.MetricName
-		effectiveFrom[rule.MetricName] = rule.EffectiveFrom.UnixMilli()
-	}
-	volumes, err := m.ch.VolumeByMetric(ctx, metricNames, effectiveFrom, startMs, endMs)
-	if err != nil {
-		return nil, err
-	}
-
-	rules := make([]metricreductionruletypes.GettableReductionRule, 0, len(domainRules))
-	for _, rule := range domainRules {
-		rules = append(rules, withVolume(toGettableReductionRule(rule), volumes[rule.MetricName]))
-	}
-
-	return &metricreductionruletypes.GettableReductionRules{Rules: rules, Total: total}, nil
-}
-
-func (m *module) listSortedByVolume(ctx context.Context, orgID valuer.UUID, params *metricreductionruletypes.ListReductionRulesParams, startMs, endMs int64) (*metricreductionruletypes.GettableReductionRules, error) {
-	allRules, total, err := m.store.List(ctx, orgID, &metricreductionruletypes.ListReductionRulesParams{Search: params.Search, MetricName: params.MetricName})
-	if err != nil {
-		return nil, err
-	}
-	if total == 0 {
-		return &metricreductionruletypes.GettableReductionRules{Rules: []metricreductionruletypes.GettableReductionRule{}, Total: 0}, nil
-	}
-
-	metricNames := make([]string, len(allRules))
-	effectiveFrom := make(map[string]int64, len(allRules))
-	ruleByMetric := make(map[string]*metricreductionruletypes.ReductionRule, len(allRules))
-	for i, rule := range allRules {
-		metricNames[i] = rule.MetricName
-		effectiveFrom[rule.MetricName] = rule.EffectiveFrom.UnixMilli()
-		ruleByMetric[rule.MetricName] = rule
-	}
-
-	ranked, err := m.ch.RankByVolume(ctx, metricNames, effectiveFrom, params.OrderBy, params.Order, startMs, endMs, params.Offset, params.Limit)
-	if err != nil {
-		return nil, err
-	}
-
-	rules := make([]metricreductionruletypes.GettableReductionRule, 0, len(ranked))
-	for _, row := range ranked {
-		rule, ok := ruleByMetric[row.MetricName]
-		if !ok {
-			continue
-		}
-		rules = append(rules, withVolume(toGettableReductionRule(rule), row))
-	}
-
-	return &metricreductionruletypes.GettableReductionRules{Rules: rules, Total: total}, nil
-}
-
-func (m *module) Create(ctx context.Context, orgID valuer.UUID, userEmail string, req *metricreductionruletypes.PostableReductionRule) (*metricreductionruletypes.GettableReductionRule, error) {
-	if err := m.checkAccess(ctx, orgID); err != nil {
-		return nil, err
-	}
-	if err := req.Validate(); err != nil {
-		return nil, err
-	}
-	if err := m.validateMetricForReduction(ctx, orgID, req.MetricName); err != nil {
-		return nil, err
-	}
-	now := time.Now()
-	rule := metricreductionruletypes.NewReductionRule(orgID, req.MetricName, req.MatchType, req.Labels, now.Add(effectiveFromMargin), userEmail)
-
-	if err := m.store.RunInTx(ctx, func(ctx context.Context) error {
-		if err := m.store.Create(ctx, rule); err != nil {
-			return err
-		}
-		return m.ch.Sync(ctx, rule.MetricName, rule.Labels, rule.MatchType.StringValue(), rule.EffectiveFrom.UnixMilli(), false, rule.UpdatedAt)
-	}); err != nil {
-		return nil, err
-	}
-
-	gettable := toGettableReductionRule(rule)
-	return &gettable, nil
-}
-
-func (m *module) GetByID(ctx context.Context, orgID valuer.UUID, id valuer.UUID) (*metricreductionruletypes.GettableReductionRule, error) {
-	if err := m.checkAccess(ctx, orgID); err != nil {
-		return nil, err
-	}
-	rule, err := m.store.GetByID(ctx, orgID, id)
-	if err != nil {
-		return nil, err
-	}
-	gettable := toGettableReductionRule(rule)
-	return &gettable, nil
-}
-
-func (m *module) UpdateByID(ctx context.Context, orgID valuer.UUID, userEmail string, id valuer.UUID, req *metricreductionruletypes.UpdatableReductionRule) (*metricreductionruletypes.GettableReductionRule, error) {
-	if err := m.checkAccess(ctx, orgID); err != nil {
-		return nil, err
-	}
-	existing, err := m.store.GetByID(ctx, orgID, id)
-	if err != nil {
-		return nil, err
-	}
-	if err := req.Validate(); err != nil {
-		return nil, err
-	}
-
-	now := time.Now()
-	existing.MatchType = req.MatchType
-	existing.Labels = metricreductionruletypes.LabelList(req.Labels)
-	existing.EffectiveFrom = now.Add(effectiveFromMargin)
-	existing.UpdatedAt = now
-	existing.UpdatedBy = userEmail
-
-	if err := m.store.RunInTx(ctx, func(ctx context.Context) error {
-		if err := m.store.Upsert(ctx, existing); err != nil {
-			return err
-		}
-		return m.ch.Sync(ctx, existing.MetricName, existing.Labels, existing.MatchType.StringValue(), existing.EffectiveFrom.UnixMilli(), false, existing.UpdatedAt)
-	}); err != nil {
-		return nil, err
-	}
-
-	gettable := toGettableReductionRule(existing)
-	return &gettable, nil
-}
-
-func (m *module) DeleteByID(ctx context.Context, orgID valuer.UUID, id valuer.UUID) error {
-	if err := m.checkAccess(ctx, orgID); err != nil {
-		return err
-	}
-	rule, err := m.store.GetByID(ctx, orgID, id)
-	if err != nil {
-		return err
-	}
-
-	now := time.Now()
-	effectiveFromMs := now.Add(effectiveFromMargin).UnixMilli()
-	return m.store.RunInTx(ctx, func(ctx context.Context) error {
-		if err := m.store.DeleteByID(ctx, orgID, id); err != nil {
-			return err
-		}
-		return m.ch.Sync(ctx, rule.MetricName, []string{}, metricreductionruletypes.MatchTypeDrop.StringValue(), effectiveFromMs, true, now)
-	})
-}
-
-func (m *module) Preview(ctx context.Context, orgID valuer.UUID, req *metricreductionruletypes.PostableReductionRulePreview) (*metricreductionruletypes.GettableReductionRulePreview, error) {
-	if err := m.checkAccess(ctx, orgID); err != nil {
-		return nil, err
-	}
-	if err := req.Validate(); err != nil {
-		return nil, err
-	}
-	if err := m.validateMetricForReduction(ctx, orgID, req.MetricName); err != nil {
-		return nil, err
-	}
-	lookback := time.Duration(req.LookbackMs) * time.Millisecond
-	if lookback <= 0 {
-		lookback = defaultPreviewLookback
-	}
-	now := time.Now()
-	startMs := now.Add(-lookback).UnixMilli()
-	endMs := now.UnixMilli()
-	current, reduced, reductionPercent, dropped, err := m.estimateVolume(ctx, req.MetricName, req.MatchType, req.Labels, startMs, endMs)
-	if err != nil {
-		return nil, err
-	}
-
-	// Baseline is what the metric keeps today (its current rule, or raw if none) so the preview reads
-	// as current -> proposed.
-	currentReduced := current
-	if existing, gerr := m.store.Get(ctx, orgID, req.MetricName); gerr == nil {
-		if _, existingReduced, _, _, eerr := m.estimateVolume(ctx, req.MetricName, existing.MatchType, existing.Labels, startMs, endMs); eerr == nil {
-			currentReduced = existingReduced
-		}
-	}
-
-	return &metricreductionruletypes.GettableReductionRulePreview{
-		IngestedSeries:        current,
-		CurrentRetainedSeries: currentReduced,
-		RetainedSeries:        reduced,
-		ReductionPercent:      reductionPercent,
-		DroppedLabels:         dropped,
-		AffectedAssets:        m.relatedAssetImpact(ctx, orgID, req.MetricName, dropped),
-		EffectiveFrom:         now.Add(effectiveFromMargin),
-	}, nil
-}
-
-func (m *module) Stats(ctx context.Context, orgID valuer.UUID) (*metricreductionruletypes.GettableReductionRuleStats, error) {
-	if err := m.checkAccess(ctx, orgID); err != nil {
-		return nil, err
-	}
-
-	now := time.Now()
-	startMs := now.Add(-defaultPreviewLookback).UnixMilli()
-	endMs := now.UnixMilli()
-
-	allRules, total, err := m.store.List(ctx, orgID, &metricreductionruletypes.ListReductionRulesParams{})
-	if err != nil {
-		return nil, err
-	}
-	if total == 0 {
-		return &metricreductionruletypes.GettableReductionRuleStats{}, nil
-	}
-
-	metricNames := make([]string, len(allRules))
-	effectiveFrom := make(map[string]int64, len(allRules))
-	for i, rule := range allRules {
-		metricNames[i] = rule.MetricName
-		effectiveFrom[rule.MetricName] = rule.EffectiveFrom.UnixMilli()
-	}
-
-	volumes, err := m.ch.VolumeByMetric(ctx, metricNames, effectiveFrom, startMs, endMs)
-	if err != nil {
-		return nil, err
-	}
-	var ingestedSeries, retainedSeries uint64
-	reducedMetricNames := make([]string, 0, len(volumes))
-	reducedEffectiveFrom := make(map[string]int64, len(volumes))
-	for name, volume := range volumes {
-		ingestedSeries += volume.Ingested
-		retained := effectiveRetained(volume.Ingested, volume.Reduced)
-		retainedSeries += retained
-		if retained < volume.Ingested {
-			reducedMetricNames = append(reducedMetricNames, name)
-			reducedEffectiveFrom[name] = effectiveFrom[name]
-		}
-	}
-
-	ingestedSamples, reducedSamples, err := m.ch.SampleVolume(ctx, reducedMetricNames, reducedEffectiveFrom, startMs, endMs)
-	if err != nil {
-		return nil, err
-	}
-
-	return &metricreductionruletypes.GettableReductionRuleStats{
-		IngestedSeries:             ingestedSeries,
-		RetainedSeries:             retainedSeries,
-		EstimatedMonthlySavingsUsd: monthlySavingsUSD(ingestedSamples, reducedSamples, startMs, endMs),
-	}, nil
-}
-
-// monthlySavingsUSD extrapolates the windowed sample reduction to a monthly figure at the per-sample
-// list price. Ingested is gated to effective_from upstream, so pre-activation hours don't inflate it.
-func monthlySavingsUSD(ingestedSamples, reducedSamples uint64, startMs, endMs int64) float64 {
-	if reducedSamples >= ingestedSamples || endMs <= startMs {
-		return 0
-	}
-	savedSamples := float64(ingestedSamples - reducedSamples)
-	monthlySamples := savedSamples * float64(monthDuration.Milliseconds()) / float64(endMs-startMs)
-	return monthlySamples / 1_000_000 * pricePerMillionSamplesUSD
-}
-
-func (m *module) Timeseries(ctx context.Context, orgID valuer.UUID) (*querybuildertypesv5.QueryRangeResponse, error) {
-	if err := m.checkAccess(ctx, orgID); err != nil {
-		return nil, err
-	}
-
-	now := time.Now()
-	startMs := now.Add(-defaultPreviewLookback).UnixMilli()
-	endMs := now.UnixMilli()
-
-	allRules, _, err := m.store.List(ctx, orgID, &metricreductionruletypes.ListReductionRulesParams{})
-	if err != nil {
-		return nil, err
-	}
-	metricNames := make([]string, len(allRules))
-	effectiveFrom := make(map[string]int64, len(allRules))
-	for i, rule := range allRules {
-		metricNames[i] = rule.MetricName
-		effectiveFrom[rule.MetricName] = rule.EffectiveFrom.UnixMilli()
-	}
-
-	volumes, err := m.ch.VolumeByMetric(ctx, metricNames, effectiveFrom, startMs, endMs)
-	if err != nil {
-		return nil, err
-	}
-	reducedNames := make([]string, 0, len(volumes))
-	for name, volume := range volumes {
-		if effectiveRetained(volume.Ingested, volume.Reduced) < volume.Ingested {
-			reducedNames = append(reducedNames, name)
-		}
-	}
-
-	points, err := m.ch.SeriesTimeseries(ctx, metricNames, reducedNames, effectiveFrom, startMs, endMs)
-	if err != nil {
-		return nil, err
-	}
-
-	return buildVolumeTimeseries(points), nil
-}
-
-func buildVolumeTimeseries(points []volumePoint) *querybuildertypesv5.QueryRangeResponse {
-	ingested := make([]*querybuildertypesv5.TimeSeriesValue, 0, len(points))
-	reduced := make([]*querybuildertypesv5.TimeSeriesValue, 0, len(points))
-	for _, point := range points {
-		ingested = append(ingested, &querybuildertypesv5.TimeSeriesValue{Timestamp: point.TimestampMs, Value: float64(point.Ingested)})
-		reduced = append(reduced, &querybuildertypesv5.TimeSeriesValue{Timestamp: point.TimestampMs, Value: float64(point.Reduced)})
-	}
-
-	return &querybuildertypesv5.QueryRangeResponse{
-		Type: querybuildertypesv5.RequestTypeTimeSeries,
-		Data: querybuildertypesv5.QueryData{
-			Results: []any{
-				&querybuildertypesv5.TimeSeriesData{
-					QueryName: "reduction_volume",
-					Aggregations: []*querybuildertypesv5.AggregationBucket{
-						{
-							Series: []*querybuildertypesv5.TimeSeries{
-								{Labels: []*querybuildertypesv5.Label{{Key: telemetrytypes.TelemetryFieldKey{Name: "series"}, Value: "ingested"}}, Values: ingested},
-								{Labels: []*querybuildertypesv5.Label{{Key: telemetrytypes.TelemetryFieldKey{Name: "series"}, Value: "retained"}}, Values: reduced},
-							},
-						},
-					},
-				},
-			},
-		},
-	}
-}
-
-func (m *module) validateMetricForReduction(ctx context.Context, orgID valuer.UUID, metricName string) error {
-	lastSeen, err := m.metadataStore.FetchLastSeenInfoMulti(ctx, metricName)
-	if err != nil {
-		return err
-	}
-	if lastSeen[metricName] == 0 {
-		return errors.NewNotFoundf(errors.CodeNotFound, "metric not found: %q", metricName)
-	}
-
-	now := time.Now()
-	startTs := uint64(now.Add(-defaultPreviewLookback).UnixMilli())
-	endTs := uint64(now.UnixMilli())
-	_, types, _, err := m.metadataStore.FetchTemporalityAndTypeMulti(ctx, orgID, startTs, endTs, metricName)
-	if err != nil {
-		return err
-	}
-	if types[metricName] == metrictypes.ExpHistogramType {
-		return errors.Newf(errors.TypeInvalidInput, metricreductionruletypes.ErrCodeMetricReductionRuleUnsupportedMetricType,
-			"exponential histogram metrics cannot be reduced in v1")
-	}
-	return nil
-}
-
-func (m *module) relatedAssetImpact(ctx context.Context, orgID valuer.UUID, metricName string, dropped []string) []metricreductionruletypes.AffectedAsset {
-	affected := make([]metricreductionruletypes.AffectedAsset, 0)
-	droppedSet := make(map[string]struct{}, len(dropped))
-	for _, label := range dropped {
-		droppedSet[label] = struct{}{}
-	}
-
-	if dashboards, err := m.dashboard.GetByMetricNames(ctx, orgID, []string{metricName}); err != nil {
-		m.logger.WarnContext(ctx, "failed to fetch related dashboards for reduction preview", slog.String("metric_name", metricName), errors.Attr(err))
-	} else {
-		for _, item := range dashboards[metricName] {
-			usedLabels := append(splitCSV(item["group_by"]), splitCSV(item["filter_by"])...)
-			affected = append(affected, metricreductionruletypes.AffectedAsset{
-				Type:           metricreductionruletypes.AssetTypeDashboard,
-				ID:             item["dashboard_id"],
-				Name:           item["dashboard_name"],
-				Widget:         &metricreductionruletypes.AffectedWidget{ID: item["widget_id"], Name: item["widget_name"]},
-				ImpactedLabels: intersectLabels(usedLabels, droppedSet),
-			})
-		}
-	}
-
-	if alerts, err := m.ruleStore.GetStoredRulesByMetricName(ctx, orgID.String(), metricName); err != nil {
-		m.logger.WarnContext(ctx, "failed to fetch related alerts for reduction preview", slog.String("metric_name", metricName), errors.Attr(err))
-	} else {
-		for _, a := range alerts {
-			affected = append(affected, metricreductionruletypes.AffectedAsset{
-				Type: metricreductionruletypes.AssetTypeAlert,
-				ID:   a.AlertID,
-				Name: a.AlertName,
-			})
-		}
-	}
-
-	return affected
-}
-
-func toGettableReductionRule(rule *metricreductionruletypes.ReductionRule) metricreductionruletypes.GettableReductionRule {
-	return metricreductionruletypes.GettableReductionRule{
-		Identifiable:  rule.Identifiable,
-		TimeAuditable: rule.TimeAuditable,
-		UserAuditable: rule.UserAuditable,
-		MetricName:    rule.MetricName,
-		MatchType:     rule.MatchType,
-		Labels:        rule.Labels,
-		EffectiveFrom: rule.EffectiveFrom,
-		Active:        !rule.EffectiveFrom.After(time.Now()),
-	}
-}
-
-func effectiveRetained(ingested, reduced uint64) uint64 {
-	if reduced == 0 || reduced > ingested {
-		return ingested
-	}
-	return reduced
-}
-
-func withVolume(rule metricreductionruletypes.GettableReductionRule, volume volumeRow) metricreductionruletypes.GettableReductionRule {
-	rule.IngestedSeries = volume.Ingested
-	rule.RetainedSeries = effectiveRetained(volume.Ingested, volume.Reduced)
-	if volume.Ingested > 0 {
-		rule.ReductionPercent = (1 - float64(rule.RetainedSeries)/float64(volume.Ingested)) * 100
-	}
-	return rule
-}
-
-func intersectLabels(keys []string, droppedSet map[string]struct{}) []string {
-	seen := make(map[string]struct{})
-	var out []string
-	for _, key := range keys {
-		if _, ok := droppedSet[key]; !ok {
-			continue
-		}
-		if _, dup := seen[key]; dup {
-			continue
-		}
-		seen[key] = struct{}{}
-		out = append(out, key)
-	}
-	return out
-}
-
-func splitCSV(s string) []string {
-	if s == "" {
-		return nil
-	}
-	return strings.Split(s, ",")
-}
-
-func resolveDroppedKept(matchType metricreductionruletypes.MatchType, ruleLabels, keys []string) (dropped, kept []string) {
-	ruleSet := make(map[string]struct{}, len(ruleLabels))
-	for _, l := range ruleLabels {
-		ruleSet[l] = struct{}{}
-	}
-
-	for _, k := range keys {
-		if metricreductionruletypes.IsProtectedLabel(k) {
-			kept = append(kept, k)
-			continue
-		}
-		_, listed := ruleSet[k]
-		drop := listed
-		if matchType == metricreductionruletypes.MatchTypeKeep {
-			drop = !listed
-		}
-		if drop {
-			dropped = append(dropped, k)
-		} else {
-			kept = append(kept, k)
-		}
-	}
-
-	sort.Strings(dropped)
-	sort.Strings(kept)
-	return dropped, kept
-}
-
-func (m *module) estimateVolume(ctx context.Context, metricName string, matchType metricreductionruletypes.MatchType, labels []string, startMs, endMs int64) (current uint64, reduced uint64, reductionPercent float64, dropped []string, err error) {
-	keys, err := m.ch.AttributeKeys(ctx, metricName, startMs, endMs)
-	if err != nil {
-		return 0, 0, 0, nil, err
-	}
-	dropped, kept := resolveDroppedKept(matchType, labels, keys)
-
-	current, reduced, err = m.ch.EstimateCardinality(ctx, metricName, kept, startMs, endMs)
-	if err != nil {
-		return 0, 0, 0, nil, err
-	}
-	if current > 0 && reduced <= current {
-		reductionPercent = (1 - float64(reduced)/float64(current)) * 100
-	}
-	return current, reduced, reductionPercent, dropped, nil
-}

ee/modules/metricreductionrule/implmetricreductionrule/store.go

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

ee/querier/handler.go

@@ -3,13 +3,13 @@ package querier
 import (
 	"bytes"
 	"context"
+	"encoding/json"
 	"io"
 	"net/http"
 
 	anomalyV2 "github.com/SigNoz/signoz/ee/anomaly"
 	"github.com/SigNoz/signoz/pkg/errors"
 	"github.com/SigNoz/signoz/pkg/factory"
-	"github.com/SigNoz/signoz/pkg/http/binding"
 	"github.com/SigNoz/signoz/pkg/http/render"
 	"github.com/SigNoz/signoz/pkg/querier"
 	"github.com/SigNoz/signoz/pkg/types/authtypes"
@@ -48,8 +48,8 @@ func (h *handler) QueryRange(rw http.ResponseWriter, req *http.Request) {
 	}
 
 	var queryRangeRequest qbtypes.QueryRangeRequest
-	if err := binding.JSON.BindBody(req.Body, &queryRangeRequest); err != nil {
-		render.Error(rw, err)
+	if err := json.NewDecoder(req.Body).Decode(&queryRangeRequest); err != nil {
+		render.Error(rw, errors.NewInvalidInputf(errors.CodeInvalidInput, "failed to decode request body: %v", err))
 		return
 	}
 
@@ -101,10 +101,6 @@ func (h *handler) QueryRange(rw http.ResponseWriter, req *http.Request) {
 	h.community.QueryRange(rw, req)
 }
 
-func (h *handler) QueryRangePreview(rw http.ResponseWriter, req *http.Request) {
-	h.community.QueryRangePreview(rw, req)
-}
-
 func (h *handler) QueryRawStream(rw http.ResponseWriter, req *http.Request) {
 	h.community.QueryRawStream(rw, req)
 }