release: v0.5.3

* minor change for volume permission spec

Signed-off-by: Yash Sharma <yashrsharma44@gmail.com>

* added basic files of clickhouse chart

Signed-off-by: Yash Sharma <yashrsharma44@gmail.com>

* added a simple deployment yaml

Signed-off-by: Yash Sharma <yashrsharma44@gmail.com>

* added clickhouse support in signoz

Signed-off-by: Yash Sharma <yashrsharma44@gmail.com>

* clickhouse working

Signed-off-by: Yash Sharma <yashrsharma44@gmail.com>

* chore: helm charts wip

* chore: fixing path of otel-path in hotrod

* chore: wip running clickhouse in templates

* chore: clickhouse working in templates

* chore: clickhouse helm chart upgraded to latest query-service and frontend images

* chore: cleanup and upgrading signoz chart version

* chore: adding alertmanager and minor fixes

* chore: persistence enabled for query-service and clickhouse

* chore: scrape interval reduced to 30s

* chore: changed crd api version from v1beta1 to v1

* chore: removed druid parts in values.yaml

* chore: log container removed from clickhouse

* chore: removed *.tgz from gitignore to add charts

* chore: added dependency charts

* chore: added clickhouse-operator templates

Co-authored-by: Yash Sharma <yashrsharma44@gmail.com>

.github/workflows/README.md

@@ -23,3 +23,8 @@ To run GitHub workflow, a few environment variables needs to add in GitHub secre
     <td> Docker hub password/token with push permission </td>
     <td> **** </td>
   </tr>
+  <tr>
+    <td> SONAR_TOKEN </td>
+    <td> <a href="https://sonarcloud.io">SonarCloud</a> token </td>
+    <td> **** </td>
+  </tr>

.github/workflows/build.yaml

@@ -37,6 +37,14 @@ jobs:
     steps:
       - name: Checkout code
         uses: actions/checkout@v2
+      - name: Install dependencies
+        run: cd frontend && yarn install
+      - name: Run Prettier
+        run: cd frontend && npm run prettify
+        continue-on-error: true
+      - name: Run ESLint
+        run: cd frontend && npm run lint
+        continue-on-error: true
       - name: Build frontend docker image
         shell: bash
         run: |

.github/workflows/codeql.yaml

@@ -0,0 +1,71 @@
+# For most projects, this workflow file will not need changing; you simply need
+# to commit it to your repository.
+#
+# You may wish to alter this file to override the set of languages analyzed,
+# or to provide custom queries or build logic.
+#
+# ******** NOTE ********
+# We have attempted to detect the languages in your repository. Please check
+# the `language` matrix defined below to confirm you have the correct set of
+# supported CodeQL languages.
+#
+name: "CodeQL"
+
+on:
+  push:
+    branches: [ main, v* ]
+  pull_request:
+    # The branches below must be a subset of the branches above
+    branches: [ main ]
+  schedule:
+    - cron: '32 5 * * 5'
+
+jobs:
+  analyze:
+    name: Analyze
+    runs-on: ubuntu-latest
+    permissions:
+      actions: read
+      contents: read
+      security-events: write
+
+    strategy:
+      fail-fast: false
+      matrix:
+        language: [ 'go', 'javascript', 'python' ]
+        # CodeQL supports [ 'cpp', 'csharp', 'go', 'java', 'javascript', 'python' ]
+        # Learn more:
+        # https://docs.github.com/en/free-pro-team@latest/github/finding-security-vulnerabilities-and-errors-in-your-code/configuring-code-scanning#changing-the-languages-that-are-analyzed
+
+    steps:
+    - name: Checkout repository
+      uses: actions/checkout@v2
+
+    # Initializes the CodeQL tools for scanning.
+    - name: Initialize CodeQL
+      uses: github/codeql-action/init@v1
+      with:
+        languages: ${{ matrix.language }}
+        # If you wish to specify custom queries, you can do so here or in a config file.
+        # By default, queries listed here will override any specified in a config file.
+        # Prefix the list here with "+" to use these queries and those in the config file.
+        # queries: ./path/to/local/query, your-org/your-repo/queries@main
+
+    # Autobuild attempts to build any compiled languages  (C/C++, C#, or Java).
+    # If this step fails, then you should remove it and run the build manually (see below)
+    - name: Autobuild
+      uses: github/codeql-action/autobuild@v1
+
+    # ℹ️ Command-line programs to run using the OS shell.
+    # 📚 https://git.io/JvXDl
+
+    # ✏️ If the Autobuild fails above, remove it and uncomment the following three lines
+    #    and modify them (or add more) to build your code if your project
+    #    uses a compiled language
+
+    #- run: |
+    #   make bootstrap
+    #   make release
+
+    - name: Perform CodeQL Analysis
+      uses: github/codeql-action/analyze@v1

.github/workflows/commitlint.yml

@@ -1,5 +1,8 @@
 name: commitlint
 on: [pull_request]
+defaults:
+  run:
+    working-directory: frontend
 jobs:
   lint-commits:
     runs-on: ubuntu-latest
@@ -11,4 +14,5 @@ jobs:
       - uses: actions/setup-node@v2.1.0
       # or just "yarn" if you depend on "@commitlint/cli" already
       - run: yarn add @commitlint/cli
-      - run: yarn run commitlint --from HEAD~${{ github.event.pull_request.commits }} --to HEAD
+      - run: yarn add @commitlint/config-conventional
+      - run: yarn run commitlint --config ./node_modules/@commitlint/config-conventional/index.js  --from HEAD~${{ github.event.pull_request.commits }} --to HEAD

.github/workflows/push.yaml

@@ -6,7 +6,13 @@ on:
       - ^v[0-9]*.[0-9]*.x$
     tags:
       - "*"
-
+  # pull_request:
+  #   branches:
+  #     - main
+  #     - v*
+  #   paths:
+  #     - 'pkg/**'
+  #     - 'frontend/**'
 jobs:
   get-envs:
     runs-on: ubuntu-latest
@@ -21,6 +27,9 @@ jobs:
           then
               echo "tag build"
               img_tag=${GITHUB_REF#refs/*/v}
+          elif [ ${array[1]} == "pull" ]
+          then
+            img_tag="pull-${{ github.event.number }}"
           else
               echo "non tag build"
               img_tag="latest"
@@ -74,7 +83,7 @@ jobs:
         run: |
           branch=${GITHUB_REF#refs/*/}
           array=(`echo ${GITHUB_REF} | sed 's/\//\n/g'`)
-          if [ $branch == "main" ] || [ ${array[1]} == "tags" ] || [[ $branch =~ ^v[0-9]*.[0-9]*.x$ ]]
+          if [ $branch == "main" ] || [ ${array[1]} == "tags" ] || [ ${array[1]} == "pull" ] || [[ $branch =~ ^v[0-9]*.[0-9]*.x$ ]]
           then
             source env-vars
             make build-push-frontend
@@ -115,7 +124,7 @@ jobs:
         run: |
           branch=${GITHUB_REF#refs/*/}
           array=(`echo ${GITHUB_REF} | sed 's/\//\n/g'`)
-          if [ $branch == "main" ] || [ ${array[1]} == "tags" ] || [[ $branch =~ ^v[0-9]*.[0-9]*.x$ ]]
+          if [ $branch == "main" ] || [ ${array[1]} == "tags" ] || [ ${array[1]} == "pull" ] ||[[ $branch =~ ^v[0-9]*.[0-9]*.x$ ]]
           then
             source env-vars
             make build-push-query-service
@@ -156,7 +165,7 @@ jobs:
         run: |
           branch=${GITHUB_REF#refs/*/}
           array=(`echo ${GITHUB_REF} | sed 's/\//\n/g'`)
-          if [ $branch == "main" ] || [ ${array[1]} == "tags" ] || [[ $branch =~ ^v[0-9]*.[0-9]*.x$ ]]
+          if [ $branch == "main" ] || [ ${array[1]} == "tags" ] || [ ${array[1]} == "pull" ] || [[ $branch =~ ^v[0-9]*.[0-9]*.x$ ]]
           then
             source env-vars
             make build-push-flattener

.github/workflows/sonar.yml

@@ -0,0 +1,27 @@
+name: sonar
+on:
+  pull_request:
+    branches:
+      - main
+      - v*
+    paths:
+      - 'frontend/**'
+defaults:
+  run:
+    working-directory: frontend
+jobs:
+  sonar-analysis:
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v2
+        with: 
+          fetch-depth: 0
+      - name: Sonar analysis
+        uses: sonarsource/sonarcloud-github-action@master
+        with:
+          projectBaseDir: frontend
+        env:
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+          SONAR_TOKEN: ${{ secrets.SONAR_TOKEN }}
+      

.gitignore

@@ -1,3 +1,7 @@
+node_modules
+yarn.lock
+package.json
+
 deploy/docker/environment_tiny/common_test
 frontend/node_modules
 frontend/.pnp
@@ -10,6 +14,8 @@ frontend/coverage
 frontend/build
 frontend/.vscode
 frontend/.yarnclean
+frontend/.temp_cache
+
 # misc
 .DS_Store
 .env.local
@@ -21,13 +27,18 @@ frontend/npm-debug.log*
 frontend/yarn-debug.log*
 frontend/yarn-error.log*
 frontend/src/constants/env.ts
+frontend/cypress/**/*.mp4
+
+# env file for cypress
+frontend/cypress.env.json
 
 .idea
 
 **/.vscode
-*.tgz
 **/build
 **/storage
 **/locust-scripts/__pycache__/
+**/__debug_bin
 
 frontend/*.env
+pkg/query-service/signoz.db

CONTRIBUTING.md

@@ -16,7 +16,10 @@ Need to update [https://github.com/SigNoz/signoz/tree/main/frontend](https://git
 
 - `git clone https://github.com/SigNoz/signoz.git && cd signoz`
 - comment out frontend service section at `deploy/docker/clickhouse-setup/docker-compose.yaml#L38`
-- run `cd deploy && docker-compose -f docker/clickhouse-setup/docker-compose.yaml up -d` (this will install signoz locally without the frontend service)
+- run `cd deploy` to move to deploy directory
+- Install signoz locally without the frontend
+  - If you are using x86_64 processors (All Intel/AMD processors) run `sudo docker-compose --env-file ./docker/clickhouse-setup/env/x86_64.env -f docker/clickhouse-setup/docker-compose.yaml up -d`
+  - If you are on arm64 processors (Apple M1 Macbooks) run `sudo docker-compose --env-file ./docker/clickhouse-setup/env/arm64.env -f docker/clickhouse-setup/docker-compose.yaml up -d`
 - `cd ../frontend` and change baseURL to `http://localhost:8080` in file `src/constants/env.ts`
 - `yarn install`
 - `yarn dev`
@@ -26,7 +29,7 @@ Need to update [https://github.com/SigNoz/signoz/tree/main/frontend](https://git
 If you don't want to install SigNoz backend just for doing frontend development, we can provide you with test environments which you can use as the backend. Please ping us in #contributing channel in our [slack community](https://join.slack.com/t/signoz-community/shared_invite/zt-lrjknbbp-J_mI13rlw8pGF4EWBnorJA) and we will DM you with `<test environment URL>`
 
 - `git clone https://github.com/SigNoz/signoz.git && cd signoz/frontend`
-- change baseURL to `<test environment URL>` in file `src/constants/env.ts`
+- Create a file `.env` with `FRONTEND_API_ENDPOINT=<test environment URL>`
 - `yarn install`
 - `yarn dev`
 
@@ -41,7 +44,9 @@ Need to update [https://github.com/SigNoz/signoz/tree/main/pkg/query-service](ht
 - `git clone https://github.com/SigNoz/signoz.git && cd signoz/deploy`
 - comment out frontend service section at `docker/clickhouse-setup/docker-compose.yaml#L38`
 - comment out query-service section at `docker/clickhouse-setup/docker-compose.yaml#L22`
-- Run `docker-compose -f docker/clickhouse-setup/docker-compose.yaml up -d` (this will install signoz locally without the frontend and query-service)
+- Install signoz locally without the frontend and query-service
+  - If you are using x86_64 processors (All Intel/AMD processors) run `sudo docker-compose --env-file ./docker/clickhouse-setup/env/x86_64.env -f docker/clickhouse-setup/docker-compose.yaml up -d`
+  - If you are on arm64 processors (Apple M1 Macbooks) run `sudo docker-compose --env-file ./docker/clickhouse-setup/env/arm64.env -f docker/clickhouse-setup/docker-compose.yaml up -d`
 - `STORAGE=clickhouse ClickHouseUrl=tcp://localhost:9001 go run main.go`
 
 **_Query Service should now be available at `http://localhost:8080`_**
@@ -64,11 +69,12 @@ You can always reach out to `ankit@signoz.io` to understand more about the repo
 - If you want to discuss something about the product, start a new [discussion](https://github.com/SigNoz/signoz/discussions)
 
 ### Conventions to follow when submitting commits, PRs
+
 1. We try to follow https://www.conventionalcommits.org/en/v1.0.0/
 
 More specifically the commits and PRs should have type specifiers prefixed in the name. [This](https://www.conventionalcommits.org/en/v1.0.0/#specification) should give you a better idea.
 
-e.g. If you are submitting a fix for an issue in frontend - PR name should be prefixed with `fix(FE):` 
+e.g. If you are submitting a fix for an issue in frontend - PR name should be prefixed with `fix(FE):`
 
 2. Follow [GitHub Flow](https://guides.github.com/introduction/flow/) guidelines for your contribution flows
 

README.de-de.md

@@ -0,0 +1,160 @@
+<p align="center">
+  <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">
+    <img alt="Lizenz" src="https://img.shields.io/badge/license-MIT-brightgreen"> </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>Dokumentation</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://bit.ly/signoz-slack"><b>Slack Community</b></a> &bull;
+  <a href="https://twitter.com/SigNozHq"><b>Twitter</b></a>
+</h3>
+
+## 
+
+SigNoz hilft Entwicklern, Anwendungen zu überwachen und Probleme in ihren bereitgestellten Anwendungen zu beheben. SigNoz benutzt verteilte Einzelschritt-Fehlersuchen, um Einblick in deinen Software-Stack zu bekommen.
+
+👉 Du kannst Werte wie die P99-Latenz und die Fehler Häufigkeit von deinen Services, externen API Aufrufen und einzelnen Endpunkten sehen.
+
+👉 Du kannst die Ursache des Problems finden, indem du zu dem Einzelschritt gehst, der das Problem verursacht und dir detaillierte Flamegraphs von einzelnen Abfragefehlersuchen anzeigen lassen.
+
+👉 Erstelle Aggregate auf Basis von Fehlersuche Daten, um geschäftsrelevante Metriken zu erhalten.
+
+![SigNoz Feature](https://signoz-public.s3.us-east-2.amazonaws.com/signoz_hero_github.png)
+
+<br /><br />
+
+<img align="left" src="https://signoz-public.s3.us-east-2.amazonaws.com/Contributing.svg" width="50px" />
+
+## Werde Teil unserer Slack Community
+
+Sag Hi zu uns auf [Slack](https://join.slack.com/t/signoz-community/shared_invite/zt-lrjknbbp-J_mI13rlw8pGF4EWBnorJA) 👋
+
+<br /><br />
+
+<img align="left" src="https://signoz-public.s3.us-east-2.amazonaws.com/Features.svg" width="50px" />
+
+## Funktionen:
+
+- Übersichtsmetriken deiner Anwendung wie RPS, 50tes/90tes/99tes Quantil Latenzen und Fehler Häufigkeiten.
+- Übersicht der langsamsten Endpunkte deiner Anwendung.
+- Sieh dir die genaue Einzelschritt-Fehlersuche deiner Abfrage an, um Fehler in nachgelagerten Diensten, langsamen Datenbank Abfragen und Aufrufen von Drittanbieter Diensten wie Zahlungsportalen, etc. zu finden.
+- Filtere Einzelschritt-Fehlersuchen nach Dienstname, Latenz, Fehler, Stichworten/ Anmerkungen.
+- Führe Aggregate auf Basis von Einzelschritt-Fehlersuche Daten (Ereignisse/Abstände) aus, um geschäftsrelevante Metriken zu erhalten. Du kannst dir z. B. die Fehlerrate und 99tes Quantil Latenz von `customer_type: gold`, `deployment_version: v2` oder `external_call: paypal` ausgeben lassen.
+- Einheitliche Benutzeroberfläche für Metriken und Einzelschritt-Fehlersuchen. Du musst nicht zwischen Prometheus und Jaeger hin und her wechseln, um Fehler zu beheben.
+
+<br /><br />
+
+<img align="left" src="https://signoz-public.s3.us-east-2.amazonaws.com/WhatsCool.svg" width="50px" />
+
+## Wieso SigNoz?
+
+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.
+
+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.
+
+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.
+
+### Unterstützte Programmiersprachen:
+
+Wir unterstützen [OpenTelemetry](https://opentelemetry.io) als die Software Library, die du nutzen kannst um deine Anwendungen auszuführen. Jedes Framework und jede Sprache die von OpenTelemetry unterstützt wird, wird auch von SigNoz unterstützt. Einige der unterstützten, größeren Programmiersprachen sind:
+
+- Java
+- Python
+- NodeJS
+- Go
+
+Hier findest du die vollständige Liste von unterstützten Programmiersprachen - https://opentelemetry.io/docs/
+
+<br /><br />
+
+<img align="left" src="https://signoz-public.s3.us-east-2.amazonaws.com/Philosophy.svg" width="50px" />
+
+## Erste Schritte mit SigNoz
+  
+  
+### Bereitstellung mit Docker
+
+Bitte folge den [hier](https://signoz.io/docs/deployment/docker/) aufgelisteten Schritten um deine Anwendung mit Docker bereitzustellen.
+
+Die [Anleitungen zur Fehlerbehebung](https://signoz.io/docs/deployment/troubleshooting) könnten hilfreich sein, falls du auf irgendwelche Schwierigkeiten stößt.
+
+<p>&nbsp  </p>
+  
+  
+### Bereitstellung mit Kubernetes und Helm
+
+Bitte folge den [hier](https://signoz.io/docs/deployment/helm_chart) aufgelisteten Schritten, um deine Anwendung mit Helm Charts bereitzustellen.
+  
+
+<br /><br />
+
+<img align="left" src="https://signoz-public.s3.us-east-2.amazonaws.com/UseSigNoz.svg" width="50px" />
+
+## Vergleiche mit anderen Lösungen
+
+### SigNoz vs. Prometheus
+
+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.
+
+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.
+
+<p>&nbsp  </p>
+
+### SigNoz vs. Jaeger
+
+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.
+
+Außerdem hat SigNoz noch mehr spezielle Funktionen im Vergleich zu Jaeger:
+
+- 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.
+
+<br /><br />
+
+<img align="left" src="https://signoz-public.s3.us-east-2.amazonaws.com/Contributors.svg" width="50px" />
+
+## Zum Projekt beitragen
+
+
+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://join.slack.com/t/signoz-community/shared_invite/zt-lrjknbbp-J_mI13rlw8pGF4EWBnorJA).
+
+<br /><br />
+
+<img align="left" src="https://signoz-public.s3.us-east-2.amazonaws.com/DevelopingLocally.svg" width="50px" />
+
+## 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 />
+
+<img align="left" src="https://signoz-public.s3.us-east-2.amazonaws.com/Contributing.svg" width="50px" />
+
+## Community
+
+Werde Teil der [Slack Community](https://join.slack.com/t/signoz-community/shared_invite/zt-lrjknbbp-J_mI13rlw8pGF4EWBnorJA) 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, danke an unsere großartigen Unterstützer!
+
+<a href="https://github.com/signoz/signoz/graphs/contributors">
+  <img src="https://contrib.rocks/image?repo=signoz/signoz" />
+</a>
+
+
+

README.md

@@ -16,6 +16,8 @@
 <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://bit.ly/signoz-slack"><b>Slack Community</b></a> &bull;
   <a href="https://twitter.com/SigNozHq"><b>Twitter</b></a>
 </h3>
@@ -28,6 +30,8 @@ SigNoz helps developers monitor applications and troubleshoot problems in their
 
 👉 You can find the root cause of the problem by going to the exact traces which are causing the problem and see detailed flamegraphs of individual request traces.
 
+👉 Run aggregates on trace data to get business relevant metrics
+
 
 ![SigNoz Feature](https://signoz-public.s3.us-east-2.amazonaws.com/signoz_hero_github.png)
 
@@ -49,7 +53,7 @@ Come say Hi to us on [Slack](https://join.slack.com/t/signoz-community/shared_in
 - Slowest endpoints in your application
 - See exact request trace to figure out issues in downstream services, slow DB queries, call to 3rd party services like payment gateways, etc
 - Filter traces by service name, operation, latency, error, tags/annotations.
-- Aggregate metrics on filtered traces. Eg, you can get error rate and 99th percentile latency of `customer_type: gold` or `deployment_version: v2` or `external_call: paypal`
+- Run aggregates on trace data (events/spans) to get business relevant metrics. e.g. You can get error rate and 99th percentile latency of `customer_type: gold` or `deployment_version: v2` or `external_call: paypal`
 - Unified UI for metrics and traces. No need to switch from Prometheus to Jaeger to debug issues.
 
 <br /><br />

README.pt-br.md

@@ -0,0 +1,159 @@
+<p align="center">
+  <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">
+    <img alt="License" src="https://img.shields.io/badge/license-MIT-brightgreen"> </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://bit.ly/signoz-slack"><b>Comunidade no Slack</b></a> &bull;
+  <a href="https://twitter.com/SigNozHq"><b>Twitter</b></a>
+</h3>
+
+##
+
+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. 
+
+👉 Você pode verificar métricas como latência p99, taxas de erro em seus serviços, requisições às APIs externas e endpoints individuais.
+
+👉 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.
+
+👉 Execute agregações em dados de rastreamento para obter métricas de negócios relevantes.
+
+
+![SigNoz Feature](https://signoz-public.s3.us-east-2.amazonaws.com/signoz_hero_github.png)
+
+<br /><br />
+
+<img align="left" src="https://signoz-public.s3.us-east-2.amazonaws.com/Contributing.svg" width="50px" />
+
+## Junte-se à nossa comunidade no Slack 
+
+Venha dizer oi para nós no [Slack](https://join.slack.com/t/signoz-community/shared_invite/zt-lrjknbbp-J_mI13rlw8pGF4EWBnorJA) 👋
+
+<br /><br />
+
+<img align="left" src="https://signoz-public.s3.us-east-2.amazonaws.com/Features.svg" width="50px" />
+
+## Funções:
+
+- 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.
+
+<br /><br />
+
+<img align="left" src="https://signoz-public.s3.us-east-2.amazonaws.com/WhatsCool.svg" width="50px" />
+
+## Por que escolher SigNoz?
+
+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 .
+
+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. 
+
+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.
+
+### Linguagens Suportadas:
+
+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: 
+
+- Java
+- Python
+- NodeJS
+- Go
+
+Você pode encontrar a lista completa de linguagens aqui - https://opentelemetry.io/docs/
+
+<br /><br />
+
+<img align="left" src="https://signoz-public.s3.us-east-2.amazonaws.com/Philosophy.svg" width="50px" />
+
+## Iniciando
+  
+  
+### Implantar usando Docker
+
+Siga as etapas listadas [aqui](https://signoz.io/docs/deployment/docker/) para instalar usando o Docker.
+
+Esse [guia para solução de problemas](https://signoz.io/docs/deployment/troubleshooting) pode ser útil se você enfrentar quaisquer problemas. 
+
+<p>&nbsp  </p>
+  
+  
+### Implentar no Kubernetes usando Helm
+
+Siga as etapas listadas [aqui](https://signoz.io/docs/deployment/helm_chart) para instalar usando helm charts.
+  
+
+<br /><br />
+
+<img align="left" src="https://signoz-public.s3.us-east-2.amazonaws.com/UseSigNoz.svg" width="50px" />
+
+## Comparações com ferramentas similares 
+
+### SigNoz ou Prometheus
+
+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.
+
+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. 
+
+<p>&nbsp  </p>
+
+### SigNoz ou Jaeger
+
+Jaeger só faz rastreamento distribuído. SigNoz faz métricas e rastreia, e também temos gerenciamento de log em nossos planos.
+
+Além disso, SigNoz tem alguns recursos mais avançados do que Jaeger:
+
+- 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.
+
+<br /><br />
+
+<img align="left" src="https://signoz-public.s3.us-east-2.amazonaws.com/Contributors.svg" width="50px" />
+
+## Contribuindo
+
+
+Nós ❤️ contribuições grandes ou pequenas. Leia [CONTRIBUTING.md](CONTRIBUTING.md) para começar a fazer contribuições para o SigNoz. 
+
+Não sabe como começar? Basta enviar um sinal para nós no canal `#contributing` em nossa [comunidade no Slack.](https://join.slack.com/t/signoz-community/shared_invite/zt-lrjknbbp-J_mI13rlw8pGF4EWBnorJA)
+
+<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://join.slack.com/t/signoz-community/shared_invite/zt-lrjknbbp-J_mI13rlw8pGF4EWBnorJA) 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 src="https://contrib.rocks/image?repo=signoz/signoz" />
+</a>
+
+
+

deploy/docker-swarm/clickhouse-setup/clickhouse-config.xml

@@ -0,0 +1,517 @@
+<?xml version="1.0"?>
+<yandex>
+    <logger>
+        <level>trace</level>
+        <log>/var/log/clickhouse-server/clickhouse-server.log</log>
+        <errorlog>/var/log/clickhouse-server/clickhouse-server.err.log</errorlog>
+        <size>1000M</size>
+        <count>10</count>
+    </logger>
+
+    <http_port>8123</http_port>
+    <tcp_port>9000</tcp_port>
+
+    <!-- For HTTPS and SSL over native protocol. -->
+    <!--
+    <https_port>8443</https_port>
+    <tcp_ssl_port>9440</tcp_ssl_port>
+-->
+
+<!-- Used with https_port and tcp_ssl_port. Full ssl options list: https://github.com/yandex/ClickHouse/blob/master/contrib/libpoco/NetSSL_OpenSSL/include/Poco/Net/SSLManager.h#L71 -->
+<openSSL>
+    <server> <!-- Used for https server AND secure tcp port -->
+        <!-- openssl req -subj "/CN=localhost" -new -newkey rsa:2048 -days 365 -nodes -x509 -keyout /etc/clickhouse-server/server.key -out /etc/clickhouse-server/server.crt -->
+        <certificateFile>/etc/clickhouse-server/server.crt</certificateFile>
+        <privateKeyFile>/etc/clickhouse-server/server.key</privateKeyFile>
+        <!-- openssl dhparam -out /etc/clickhouse-server/dhparam.pem 4096 -->
+        <dhParamsFile>/etc/clickhouse-server/dhparam.pem</dhParamsFile>
+        <verificationMode>none</verificationMode>
+        <loadDefaultCAFile>true</loadDefaultCAFile>
+        <cacheSessions>true</cacheSessions>
+        <disableProtocols>sslv2,sslv3</disableProtocols>
+        <preferServerCiphers>true</preferServerCiphers>
+    </server>
+
+    <client> <!-- Used for connecting to https dictionary source -->
+        <loadDefaultCAFile>true</loadDefaultCAFile>
+        <cacheSessions>true</cacheSessions>
+        <disableProtocols>sslv2,sslv3</disableProtocols>
+        <preferServerCiphers>true</preferServerCiphers>
+        <!-- Use for self-signed: <verificationMode>none</verificationMode> -->
+        <invalidCertificateHandler>
+            <!-- Use for self-signed: <name>AcceptCertificateHandler</name> -->
+            <name>RejectCertificateHandler</name>
+        </invalidCertificateHandler>
+    </client>
+</openSSL>
+
+<!-- Default root page on http[s] server. For example load UI from https://tabix.io/ when opening http://localhost:8123 -->
+    <!--
+    <http_server_default_response><![CDATA[<html ng-app="SMI2"><head><base href="http://ui.tabix.io/"></head><body><div ui-view="" class="content-ui"></div><script src="http://loader.tabix.io/master.js"></script></body></html>]]></http_server_default_response>
+-->
+
+<!-- Port for communication between replicas. Used for data exchange. -->
+<interserver_http_port>9009</interserver_http_port>
+
+    <!-- Hostname that is used by other replicas to request this server.
+         If not specified, than it is determined analoguous to 'hostname -f' command.
+         This setting could be used to switch replication to another network interface.
+     -->
+    <!--
+    <interserver_http_host>example.yandex.ru</interserver_http_host>
+-->
+
+<!-- Listen specified host. use :: (wildcard IPv6 address), if you want to accept connections both with IPv4 and IPv6 from everywhere. -->
+<listen_host>::</listen_host>
+<!-- Same for hosts with disabled ipv6: -->
+<!-- <listen_host>0.0.0.0</listen_host> -->
+
+<!-- Default values - try listen localhost on ipv4 and ipv6: -->
+<!-- <listen_host>0.0.0.0</listen_host> -->
+
+<max_connections>4096</max_connections>
+<keep_alive_timeout>3</keep_alive_timeout>
+
+<!-- Maximum number of concurrent queries. -->
+<max_concurrent_queries>100</max_concurrent_queries>
+
+    <!-- Set limit on number of open files (default: maximum). This setting makes sense on Mac OS X because getrlimit() fails to retrieve
+    correct maximum value. -->
+    <!-- <max_open_files>262144</max_open_files> -->
+
+    <!-- Size of cache of uncompressed blocks of data, used in tables of MergeTree family.
+         In bytes. Cache is single for server. Memory is allocated only on demand.
+         Cache is used when 'use_uncompressed_cache' user setting turned on (off by default).
+         Uncompressed cache is advantageous only for very short queries and in rare cases.
+     -->
+     <uncompressed_cache_size>8589934592</uncompressed_cache_size>
+
+    <!-- Approximate size of mark cache, used in tables of MergeTree family.
+         In bytes. Cache is single for server. Memory is allocated only on demand.
+         You should not lower this value.
+     -->
+     <mark_cache_size>5368709120</mark_cache_size>
+
+
+     <!-- Path to data directory, with trailing slash. -->
+     <path>/var/lib/clickhouse/</path>
+
+     <!-- Path to temporary data for processing hard queries. -->
+     <tmp_path>/var/lib/clickhouse/tmp/</tmp_path>
+
+     <!-- Path to configuration file with users, access rights, profiles of settings, quotas. -->
+     <users_config>users.xml</users_config>
+
+     <!-- Default profile of settings.. -->
+     <default_profile>default</default_profile>
+
+     <!-- Default database. -->
+     <default_database>default</default_database>
+
+    <!-- Server time zone could be set here.
+
+         Time zone is used when converting between String and DateTime types,
+          when printing DateTime in text formats and parsing DateTime from text,
+          it is used in date and time related functions, if specific time zone was not passed as an argument.
+
+         Time zone is specified as identifier from IANA time zone database, like UTC or Africa/Abidjan.
+         If not specified, system time zone at server startup is used.
+
+         Please note, that server could display time zone alias instead of specified name.
+         Example: W-SU is an alias for Europe/Moscow and Zulu is an alias for UTC.
+     -->
+     <!-- <timezone>Europe/Moscow</timezone> -->
+
+    <!-- You can specify umask here (see "man umask"). Server will apply it on startup.
+         Number is always parsed as octal. Default umask is 027 (other users cannot read logs, data files, etc; group can only read).
+     -->
+     <!-- <umask>022</umask> -->
+
+    <!-- Configuration of clusters that could be used in Distributed tables.
+         https://clickhouse.yandex/reference_en.html#Distributed
+     -->
+     <remote_servers incl="clickhouse_remote_servers" >
+        <!-- Test only shard config for testing distributed storage -->
+        <test_shard_localhost>
+            <shard>
+                <replica>
+                    <host>localhost</host>
+                    <port>9000</port>
+                </replica>
+            </shard>
+        </test_shard_localhost>
+    </remote_servers>
+
+
+    <!-- If element has 'incl' attribute, then for it's value will be used corresponding substitution from another file.
+         By default, path to file with substitutions is /etc/metrika.xml. It could be changed in config in 'include_from' element.
+         Values for substitutions are specified in /yandex/name_of_substitution elements in that file.
+     -->
+
+    <!-- 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.yandex/reference_en.html#Data%20replication
+     -->
+     <zookeeper incl="zookeeper-servers" optional="true" />
+
+    <!-- Substitutions for parameters of replicated tables.
+          Optional. If you don't use replicated tables, you could omit that.
+
+         See https://clickhouse.yandex/reference_en.html#Creating%20replicated%20tables
+     -->
+     <macros incl="macros" optional="true" />
+
+
+     <!-- Reloading interval for embedded dictionaries, in seconds. Default: 3600. -->
+     <builtin_dictionaries_reload_interval>3600</builtin_dictionaries_reload_interval>
+
+
+     <!-- Maximum session timeout, in seconds. Default: 3600. -->
+     <max_session_timeout>3600</max_session_timeout>
+
+     <!-- Default session timeout, in seconds. Default: 60. -->
+     <default_session_timeout>60</default_session_timeout>
+
+     <!-- Sending data to Graphite for monitoring. Several sections can be defined. -->
+    <!--
+        interval - send every X second
+        root_path - prefix for keys
+        hostname_in_path - append hostname to root_path (default = true)
+        metrics - send data from table system.metrics
+        events - send data from table system.events
+        asynchronous_metrics - send data from table system.asynchronous_metrics
+    -->
+    <!--
+    <graphite>
+        <host>localhost</host>
+        <port>42000</port>
+        <timeout>0.1</timeout>
+        <interval>60</interval>
+        <root_path>one_min</root_path>
+        <hostname_in_path>true<hostname_in_path>
+
+        <metrics>true</metrics>
+        <events>true</events>
+        <asynchronous_metrics>true</asynchronous_metrics>
+    </graphite>
+    <graphite>
+        <host>localhost</host>
+        <port>42000</port>
+        <timeout>0.1</timeout>
+        <interval>1</interval>
+        <root_path>one_sec</root_path>
+
+        <metrics>true</metrics>
+        <events>true</events>
+        <asynchronous_metrics>false</asynchronous_metrics>
+    </graphite>
+-->
+
+
+<!-- Query log. Used only for queries with setting log_queries = 1. -->
+<query_log>
+        <!-- What table to insert data. If table is not exist, it will be created.
+             When query log structure is changed after system update,
+              then old table will be renamed and new table will be created automatically.
+          -->
+          <database>system</database>
+          <table>query_log</table>
+
+          <!-- Interval of flushing data. -->
+          <flush_interval_milliseconds>7500</flush_interval_milliseconds>
+      </query_log>
+
+
+    <!-- Uncomment if use part_log
+    <part_log>
+        <database>system</database>
+        <table>part_log</table>
+
+        <flush_interval_milliseconds>7500</flush_interval_milliseconds>
+    </part_log>
+-->
+
+
+    <!-- Parameters for embedded dictionaries, used in Yandex.Metrica.
+         See https://clickhouse.yandex/reference_en.html#Internal%20dictionaries
+     -->
+
+     <!-- Path to file with region hierarchy. -->
+     <!-- <path_to_regions_hierarchy_file>/opt/geo/regions_hierarchy.txt</path_to_regions_hierarchy_file> -->
+
+     <!-- Path to directory with files containing names of regions -->
+     <!-- <path_to_regions_names_files>/opt/geo/</path_to_regions_names_files> -->
+
+
+    <!-- Configuration of external dictionaries. See:
+         https://clickhouse.yandex/reference_en.html#External%20Dictionaries
+     -->
+     <dictionaries_config>*_dictionary.xml</dictionaries_config>
+
+    <!-- Uncomment if you want data to be compressed 30-100% better.
+         Don't do that if you just started using ClickHouse.
+     -->
+     <compression incl="clickhouse_compression">
+    <!--
+        <!- - Set of variants. Checked in order. Last matching case wins. If nothing matches, lz4 will be used. - ->
+        <case>
+
+            <!- - Conditions. All must be satisfied. Some conditions may be omitted. - ->
+            <min_part_size>10000000000</min_part_size>        <!- - Min part size in bytes. - ->
+            <min_part_size_ratio>0.01</min_part_size_ratio>   <!- - Min size of part relative to whole table size. - ->
+
+            <!- - What compression method to use. - ->
+            <method>zstd</method>
+        </case>
+    -->
+</compression>
+
+    <!-- Allow to execute distributed DDL queries (CREATE, DROP, ALTER, RENAME) on cluster.
+    Works only if ZooKeeper is enabled. Comment it if such functionality isn't required. -->
+    <distributed_ddl>
+        <!-- Path in ZooKeeper to queue with DDL queries -->
+        <path>/clickhouse/task_queue/ddl</path>
+    </distributed_ddl>
+
+    <!-- Settings to fine tune MergeTree tables. See documentation in source code, in MergeTreeSettings.h -->
+    <!--
+    <merge_tree>
+        <max_suspicious_broken_parts>5</max_suspicious_broken_parts>
+    </merge_tree>
+-->
+
+    <!-- Protection from accidental DROP.
+         If size of a MergeTree table is greater than max_table_size_to_drop (in bytes) than table could not be dropped with any DROP query.
+         If you want do delete one table and don't want to restart clickhouse-server, you could create special file <clickhouse-path>/flags/force_drop_table and make DROP once.
+         By default max_table_size_to_drop is 50GB, max_table_size_to_drop=0 allows to DROP any tables.
+         Uncomment to disable protection.
+     -->
+     <!-- <max_table_size_to_drop>0</max_table_size_to_drop> -->
+
+     <!-- Example of parameters for GraphiteMergeTree table engine -->
+     <graphite_rollup>
+        <!-- carbon -->
+        <pattern>
+            <regexp>^carbon\.</regexp>
+            <function>any</function>
+            <retention>
+                <age>0</age>
+                <precision>60</precision>
+            </retention>
+            <retention>
+                <age>7776000</age>
+                <precision>3600</precision>
+            </retention>
+            <retention>
+                <age>10368000</age>
+                <precision>21600</precision>
+            </retention>
+            <retention>
+                <age>34560000</age>
+                <precision>43200</precision>
+            </retention>
+            <retention>
+                <age>63072000</age>
+                <precision>86400</precision>
+            </retention>
+            <retention>
+                <age>94608000</age>
+                <precision>604800</precision>
+            </retention>
+        </pattern>
+        <!-- collectd -->
+        <pattern>
+            <regexp>^collectd\.</regexp>
+            <function>any</function>
+            <retention>
+                <age>0</age>
+                <precision>10</precision>
+            </retention>
+            <retention>
+                <age>43200</age>
+                <precision>60</precision>
+            </retention>
+            <retention>
+                <age>864000</age>
+                <precision>900</precision>
+            </retention>
+            <retention>
+                <age>1728000</age>
+                <precision>1800</precision>
+            </retention>
+            <retention>
+                <age>3456000</age>
+                <precision>3600</precision>
+            </retention>
+            <retention>
+                <age>10368000</age>
+                <precision>21600</precision>
+            </retention>
+            <retention>
+                <age>34560000</age>
+                <precision>43200</precision>
+            </retention>
+            <retention>
+                <age>63072000</age>
+                <precision>86400</precision>
+            </retention>
+            <retention>
+                <age>94608000</age>
+                <precision>604800</precision>
+            </retention>
+        </pattern>
+        <!-- high -->
+        <pattern>
+            <regexp>^high\.</regexp>
+            <function>any</function>
+            <retention>
+                <age>0</age>
+                <precision>10</precision>
+            </retention>
+            <retention>
+                <age>172800</age>
+                <precision>60</precision>
+            </retention>
+            <retention>
+                <age>864000</age>
+                <precision>900</precision>
+            </retention>
+            <retention>
+                <age>1728000</age>
+                <precision>1800</precision>
+            </retention>
+            <retention>
+                <age>3456000</age>
+                <precision>3600</precision>
+            </retention>
+            <retention>
+                <age>10368000</age>
+                <precision>21600</precision>
+            </retention>
+            <retention>
+                <age>34560000</age>
+                <precision>43200</precision>
+            </retention>
+            <retention>
+                <age>63072000</age>
+                <precision>86400</precision>
+            </retention>
+            <retention>
+                <age>94608000</age>
+                <precision>604800</precision>
+            </retention>
+        </pattern>
+        <!-- medium -->
+        <pattern>
+            <regexp>^medium\.</regexp>
+            <function>any</function>
+            <retention>
+                <age>0</age>
+                <precision>60</precision>
+            </retention>
+            <retention>
+                <age>864000</age>
+                <precision>900</precision>
+            </retention>
+            <retention>
+                <age>1728000</age>
+                <precision>1800</precision>
+            </retention>
+            <retention>
+                <age>3456000</age>
+                <precision>3600</precision>
+            </retention>
+            <retention>
+                <age>10368000</age>
+                <precision>21600</precision>
+            </retention>
+            <retention>
+                <age>34560000</age>
+                <precision>43200</precision>
+            </retention>
+            <retention>
+                <age>63072000</age>
+                <precision>86400</precision>
+            </retention>
+            <retention>
+                <age>94608000</age>
+                <precision>604800</precision>
+            </retention>
+        </pattern>
+        <!-- low -->
+        <pattern>
+            <regexp>^low\.</regexp>
+            <function>any</function>
+            <retention>
+                <age>0</age>
+                <precision>600</precision>
+            </retention>
+            <retention>
+                <age>15552000</age>
+                <precision>1800</precision>
+            </retention>
+            <retention>
+                <age>31536000</age>
+                <precision>3600</precision>
+            </retention>
+            <retention>
+                <age>63072000</age>
+                <precision>21600</precision>
+            </retention>
+            <retention>
+                <age>126144000</age>
+                <precision>43200</precision>
+            </retention>
+            <retention>
+                <age>252288000</age>
+                <precision>86400</precision>
+            </retention>
+            <retention>
+                <age>315360000</age>
+                <precision>604800</precision>
+            </retention>
+        </pattern>
+        <!-- default -->
+        <default>
+            <function>any</function>
+            <retention>
+                <age>0</age>
+                <precision>60</precision>
+            </retention>
+            <retention>
+                <age>864000</age>
+                <precision>900</precision>
+            </retention>
+            <retention>
+                <age>1728000</age>
+                <precision>1800</precision>
+            </retention>
+            <retention>
+                <age>3456000</age>
+                <precision>3600</precision>
+            </retention>
+            <retention>
+                <age>10368000</age>
+                <precision>21600</precision>
+            </retention>
+            <retention>
+                <age>34560000</age>
+                <precision>43200</precision>
+            </retention>
+            <retention>
+                <age>63072000</age>
+                <precision>86400</precision>
+            </retention>
+            <retention>
+                <age>94608000</age>
+                <precision>604800</precision>
+            </retention>
+        </default>
+    </graphite_rollup>
+
+    <!-- Directory in <clickhouse-path> containing schema files for various input formats.
+         The directory will be created if it doesn't exist.
+     -->
+     <format_schema_path>/var/lib/clickhouse/format_schemas/</format_schema_path>
+ </yandex>

deploy/docker-swarm/clickhouse-setup/docker-compose.yaml

@@ -0,0 +1,113 @@
+version: "3"
+
+services:
+  clickhouse:
+      image: yandex/clickhouse-server
+      expose:
+        - 8123
+        - 9000
+      ports:
+        - 9001:9000
+        - 8123:8123
+      volumes:
+        - ./clickhouse-config.xml:/etc/clickhouse-server/config.xml
+        - ./docker-entrypoint-initdb.d/init-db.sql:/docker-entrypoint-initdb.d/init-db.sql
+        - ./data/clickhouse/:/var/lib/clickhouse/
+
+      healthcheck:
+        # "clickhouse", "client", "-u ${CLICKHOUSE_USER}", "--password ${CLICKHOUSE_PASSWORD}", "-q 'SELECT 1'"
+        test: ["CMD", "wget", "--spider", "-q", "localhost:8123/ping"]
+        interval: 30s
+        timeout: 5s
+        retries: 3
+
+  query-service:
+    image: signoz/query-service:0.4.1
+    container_name: query-service
+    restart: always
+    command: ["-config=/root/config/prometheus.yml"]
+    ports:
+      - "8080:8080"
+    volumes:
+      - ./prometheus.yml:/root/config/prometheus.yml
+      - ../dashboards:/root/config/dashboards
+      - ./data/signoz/:/var/lib/signoz/
+    environment:
+      - ClickHouseUrl=tcp://clickhouse:9000
+      - STORAGE=clickhouse
+      - POSTHOG_API_KEY=H-htDCae7CR3RV57gUzmol6IAKtm5IMCvbcm_fwnL-w
+      - GODEBUG=netdns=go
+    depends_on:
+    - clickhouse
+
+
+  frontend:
+    image: signoz/frontend:0.4.1
+    container_name: frontend
+
+    depends_on:
+      - query-service
+    links:
+      - "query-service"
+    ports:
+      - "3000:3000"
+    volumes:
+      - ../common/nginx-config.conf:/etc/nginx/conf.d/default.conf
+
+
+  otel-collector:
+    image: signoz/otelcontribcol:0.4.0
+    command: ["--config=/etc/otel-collector-config.yaml", "--mem-ballast-size-mib=2000"]
+    volumes:
+      - ./otel-collector-config.yaml:/etc/otel-collector-config.yaml
+    ports:
+      - "1777:1777"   # pprof extension
+      - "8887:8888"   # Prometheus metrics exposed by the agent
+      - "14268:14268"       # Jaeger receiver
+      - "55678"       # OpenCensus receiver
+      - "55680:55680"       # OTLP HTTP/2.0 legacy port
+      - "55681:55681"       # OTLP HTTP/1.0 receiver
+      - "4317:4317"       # OTLP GRPC receiver
+      - "55679:55679" # zpages extension
+      - "13133"       # health_check
+    deploy:
+      mode: replicated
+      replicas: 3
+    depends_on:
+    - clickhouse
+
+  otel-collector-hostmetrics:
+    image: signoz/otelcontribcol:0.4.0
+    command: ["--config=/etc/otel-collector-config-hostmetrics.yaml", "--mem-ballast-size-mib=683"]
+    volumes:
+      - ./otel-collector-config-hostmetrics.yaml:/etc/otel-collector-config-hostmetrics.yaml
+    depends_on:
+    - clickhouse
+
+
+  hotrod:
+    image: jaegertracing/example-hotrod:latest
+    container_name: hotrod
+    ports:
+    - "9000:8080"
+    command: ["all"]
+    environment:
+    - JAEGER_ENDPOINT=http://otel-collector:14268/api/traces
+
+
+  load-hotrod:
+    image: "grubykarol/locust:1.2.3-python3.9-alpine3.12"
+    container_name: load-hotrod
+    hostname: load-hotrod
+    ports:
+     - "8089:8089"
+    environment:
+      ATTACKED_HOST: http://hotrod:8080
+      LOCUST_MODE: standalone
+      NO_PROXY: standalone
+      TASK_DELAY_FROM: 5
+      TASK_DELAY_TO: 30
+      QUIET_MODE: "${QUIET_MODE:-false}"
+      LOCUST_OPTS: "--headless -u 10 -r 1"
+    volumes:
+      - ../common/locust-scripts:/locust

deploy/docker-swarm/clickhouse-setup/docker-entrypoint-initdb.d/init-db.sql

@@ -0,0 +1,31 @@
+CREATE TABLE IF NOT EXISTS signoz_index (
+  timestamp DateTime64(9) CODEC(Delta, ZSTD(1)),
+  traceID String CODEC(ZSTD(1)),
+  spanID String CODEC(ZSTD(1)),
+  parentSpanID String CODEC(ZSTD(1)),
+  serviceName LowCardinality(String) CODEC(ZSTD(1)),
+  name LowCardinality(String) CODEC(ZSTD(1)),
+  kind Int32 CODEC(ZSTD(1)),
+  durationNano UInt64 CODEC(ZSTD(1)),
+  tags Array(String) CODEC(ZSTD(1)),
+  tagsKeys Array(String) CODEC(ZSTD(1)),
+  tagsValues Array(String) CODEC(ZSTD(1)),
+  statusCode Int64 CODEC(ZSTD(1)),
+  references String CODEC(ZSTD(1)),
+  externalHttpMethod Nullable(String) CODEC(ZSTD(1)),
+  externalHttpUrl Nullable(String) CODEC(ZSTD(1)),
+  component Nullable(String) CODEC(ZSTD(1)),
+  dbSystem Nullable(String) CODEC(ZSTD(1)),
+  dbName Nullable(String) CODEC(ZSTD(1)),
+  dbOperation Nullable(String) CODEC(ZSTD(1)),
+  peerService Nullable(String) CODEC(ZSTD(1)),
+  INDEX idx_traceID traceID TYPE bloom_filter GRANULARITY 4,
+  INDEX idx_service serviceName TYPE bloom_filter GRANULARITY 4,
+  INDEX idx_name name TYPE bloom_filter GRANULARITY 4,
+  INDEX idx_kind kind TYPE minmax GRANULARITY 4,
+  INDEX idx_tagsKeys tagsKeys TYPE bloom_filter(0.01) GRANULARITY 64,
+  INDEX idx_tagsValues tagsValues TYPE bloom_filter(0.01) GRANULARITY 64,
+  INDEX idx_duration durationNano TYPE minmax GRANULARITY 1
+) ENGINE MergeTree()
+PARTITION BY toDate(timestamp)
+ORDER BY (serviceName, -toUnixTimestamp(timestamp))

deploy/docker-swarm/clickhouse-setup/otel-collector-config-hostmetrics.yaml

@@ -0,0 +1,72 @@
+receivers:
+  otlp:
+    protocols:
+      grpc:
+      http:
+  jaeger:
+    protocols:
+      grpc:
+      thrift_http:
+
+  hostmetrics:
+    collection_interval: 60s
+    scrapers:
+      cpu:
+      load:
+      memory:
+      disk:
+      filesystem:
+      network:
+
+  # Data sources: metrics
+  prometheus:
+    config:
+      scrape_configs:
+        - job_name: "otel-collector"
+          dns_sd_configs:
+          - names:
+            - 'tasks.signoz_otel-collector'
+            type: 'A'
+            port: 8888
+        - job_name: "otel-collector-hostmetrics"
+          scrape_interval: 10s
+          static_configs:
+            - targets: ["otel-collector-hostmetrics:8888"]
+processors:
+  batch:
+    send_batch_size: 1000
+    timeout: 10s
+  memory_limiter:
+    # Same as --mem-ballast-size-mib CLI argument
+    ballast_size_mib: 683
+    # 80% of maximum memory up to 2G
+    limit_mib: 1500
+    # 25% of limit up to 2G
+    spike_limit_mib: 512
+    check_interval: 5s
+  # queued_retry:
+  #   num_workers: 4
+  #   queue_size: 100
+  #   retry_on_failure: true
+extensions:
+  health_check: {}
+  zpages: {}
+exporters:
+  clickhouse:
+    datasource: tcp://clickhouse:9000
+  clickhousemetricswrite:
+    endpoint: tcp://clickhouse:9000/?database=signoz_metrics
+    resource_to_telemetry_conversion:
+      enabled: true
+
+service:
+  extensions: [health_check, zpages]
+  pipelines:
+    traces:
+      receivers: [jaeger, otlp]
+      processors: [batch]
+      exporters: [clickhouse]
+    metrics:
+      receivers: [otlp, prometheus, hostmetrics]
+      processors: [batch]
+      exporters: [clickhousemetricswrite]

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

@@ -0,0 +1,47 @@
+receivers:
+  otlp:
+    protocols:
+      grpc:
+      http:
+  jaeger:
+    protocols:
+      grpc:
+      thrift_http:
+processors:
+  batch:
+    send_batch_size: 1000
+    timeout: 10s
+  memory_limiter:
+    # Same as --mem-ballast-size-mib CLI argument
+    ballast_size_mib: 683
+    # 80% of maximum memory up to 2G
+    limit_mib: 1500
+    # 25% of limit up to 2G
+    spike_limit_mib: 512
+    check_interval: 5s
+  # queued_retry:
+  #   num_workers: 4
+  #   queue_size: 100
+  #   retry_on_failure: true
+extensions:
+  health_check: {}
+  zpages: {}
+exporters:
+  clickhouse:
+    datasource: tcp://clickhouse:9000
+  clickhousemetricswrite:
+    endpoint: tcp://clickhouse:9000/?database=signoz_metrics
+    resource_to_telemetry_conversion:
+      enabled: true
+
+service:
+  extensions: [health_check, zpages]
+  pipelines:
+    traces:
+      receivers: [jaeger, otlp]
+      processors: [batch]
+      exporters: [clickhouse]
+    metrics:
+      receivers: [otlp]
+      processors: [batch]
+      exporters: [clickhousemetricswrite]

deploy/docker-swarm/clickhouse-setup/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"
+
+# A scrape configuration containing exactly one endpoint to scrape:
+# Here it's Prometheus itself.
+scrape_configs:
+  
+
+remote_read:
+  - url: tcp://clickhouse:9000/?database=signoz_metrics

deploy/docker-swarm/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/docker-swarm/common/nginx-config.conf

@@ -0,0 +1,30 @@
+server {
+    listen       3000;
+    server_name  _;
+    
+    gzip on;
+    gzip_static on;    
+    gzip_types text/plain text/css application/json application/x-javascript text/xml application/xml application/xml+rss text/javascript;
+    gzip_proxied  any;
+    gzip_vary on;
+    gzip_comp_level 6;
+    gzip_buffers 16 8k;
+    gzip_http_version 1.1; 
+
+    location / {
+    root   /usr/share/nginx/html;
+    index  index.html index.htm;
+    try_files $uri $uri/ /index.html;
+    }
+    location /api {
+    proxy_pass http://query-service:8080/api;
+    
+    }
+
+    # redirect server error pages to the static page /50x.html
+    #
+    error_page   500 502 503 504  /50x.html;
+    location = /50x.html {
+    root   /usr/share/nginx/html;
+    }
+}

deploy/docker/clickhouse-setup/alertmanager.yml

@@ -0,0 +1,35 @@
+global:
+  resolve_timeout: 1m
+  slack_api_url: 'https://hooks.slack.com/services/xxx'
+
+route:
+  receiver: 'slack-notifications'
+
+receivers:
+- name: 'slack-notifications'
+  slack_configs:
+  - channel: '#alerts'
+    send_resolved: true
+    icon_url: https://avatars3.githubusercontent.com/u/3380462
+    title: |-
+     [{{ .Status | toUpper }}{{ if eq .Status "firing" }}:{{ .Alerts.Firing | len }}{{ end }}] {{ .CommonLabels.alertname }} for {{ .CommonLabels.job }}
+     {{- if gt (len .CommonLabels) (len .GroupLabels) -}}
+       {{" "}}(
+       {{- with .CommonLabels.Remove .GroupLabels.Names }}
+         {{- range $index, $label := .SortedPairs -}}
+           {{ if $index }}, {{ end }}
+           {{- $label.Name }}="{{ $label.Value -}}"
+         {{- end }}
+       {{- end -}}
+       )
+     {{- end }}
+    text: >-
+     {{ range .Alerts -}}
+     *Alert:* {{ .Annotations.title }}{{ if .Labels.severity }} - `{{ .Labels.severity }}`{{ end }}
+
+     *Description:* {{ .Annotations.description }}
+
+     *Details:*
+       {{ range .Labels.SortedPairs }} • *{{ .Name }}:* `{{ .Value }}`
+       {{ end }}
+     {{ end }}

deploy/docker/clickhouse-setup/alerts.yml

@@ -0,0 +1,11 @@
+groups:
+- name: ExampleCPULoadGroup
+  rules:
+  - alert: HighCpuLoad
+    expr: system_cpu_load_average_1m > 0.1
+    for: 0m
+    labels:
+      severity: warning
+    annotations:
+      summary: High CPU load
+      description: "CPU load is > 0.1\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"

deploy/docker/clickhouse-setup/docker-compose.yaml

@@ -2,7 +2,7 @@ version: "2.4"
 
 services:
   clickhouse:
-      image: yandex/clickhouse-server
+      image: ${clickhouse_image}
       expose:
         - 8123
         - 9000
@@ -12,6 +12,8 @@ services:
       volumes:
         - ./clickhouse-config.xml:/etc/clickhouse-server/config.xml
         - ./docker-entrypoint-initdb.d/init-db.sql:/docker-entrypoint-initdb.d/init-db.sql
+        - ./data/clickhouse/:/var/lib/clickhouse/
+
       healthcheck:
         # "clickhouse", "client", "-u ${CLICKHOUSE_USER}", "--password ${CLICKHOUSE_PASSWORD}", "-q 'SELECT 1'"
         test: ["CMD", "wget", "--spider", "-q", "localhost:8123/ping"]
@@ -19,24 +21,40 @@ services:
         timeout: 5s
         retries: 3
 
-  query-service:
-    image: signoz/query-service:0.3.4
-    container_name: query-service
+  alertmanager:
+    image: signoz/alertmanager:0.5.0
+    volumes:
+      - ./alertmanager.yml:/prometheus/alertmanager.yml
+      - ./data/alertmanager:/data
+    command:
+      - '--config.file=/prometheus/alertmanager.yml'
+      - '--storage.path=/data'
+    ports:
+      - 9093:9093
 
+  query-service:
+    image: signoz/query-service:0.5.3
+    container_name: query-service
+    command: ["-config=/root/config/prometheus.yml"]
     ports:
       - "8080:8080"
+    volumes:
+      - ./prometheus.yml:/root/config/prometheus.yml
+      - ../dashboards:/root/config/dashboards
+      - ./data/signoz/:/var/lib/signoz/
 
     environment:
       - ClickHouseUrl=tcp://clickhouse:9000
       - STORAGE=clickhouse
       - POSTHOG_API_KEY=H-htDCae7CR3RV57gUzmol6IAKtm5IMCvbcm_fwnL-w
+      - GODEBUG=netdns=go
 
     depends_on:
       clickhouse:
         condition: service_healthy
     
   frontend:
-    image: signoz/frontend:0.3.4
+    image: signoz/frontend:0.5.3
     container_name: frontend
 
     depends_on:
@@ -50,7 +68,7 @@ services:
 
 
   otel-collector:
-    image: signoz/otelcol:latest
+    image: signoz/otelcontribcol:0.4.2
     command: ["--config=/etc/otel-collector-config.yaml", "--mem-ballast-size-mib=683"]
     volumes:
       - ./otel-collector-config.yaml:/etc/otel-collector-config.yaml
@@ -64,11 +82,19 @@ services:
       - "4317:4317"       # OTLP GRPC receiver
       - "55679:55679" # zpages extension
       - "13133"       # health_check
-
+      - "8889:8889"   # prometheus exporter
     depends_on:
       clickhouse:
         condition: service_healthy
 
+  otel-collector-metrics:
+    image: signoz/otelcontribcol:0.4.2
+    command: ["--config=/etc/otel-collector-metrics-config.yaml", "--mem-ballast-size-mib=683"]
+    volumes:
+      - ./otel-collector-metrics-config.yaml:/etc/otel-collector-metrics-config.yaml
+    depends_on:
+      clickhouse:
+        condition: service_healthy
   hotrod:
     image: jaegertracing/example-hotrod:latest
     container_name: hotrod

deploy/docker/clickhouse-setup/docker-entrypoint-initdb.d/init-db.sql

@@ -19,6 +19,10 @@ CREATE TABLE IF NOT EXISTS signoz_index (
   dbName Nullable(String) CODEC(ZSTD(1)),
   dbOperation Nullable(String) CODEC(ZSTD(1)),
   peerService Nullable(String) CODEC(ZSTD(1)),
+  INDEX idx_traceID traceID TYPE bloom_filter GRANULARITY 4,
+  INDEX idx_service serviceName TYPE bloom_filter GRANULARITY 4,
+  INDEX idx_name name TYPE bloom_filter GRANULARITY 4,
+  INDEX idx_kind kind TYPE minmax GRANULARITY 4,
   INDEX idx_tagsKeys tagsKeys TYPE bloom_filter(0.01) GRANULARITY 64,
   INDEX idx_tagsValues tagsValues TYPE bloom_filter(0.01) GRANULARITY 64,
   INDEX idx_duration durationNano TYPE minmax GRANULARITY 1

deploy/docker/clickhouse-setup/env/arm64.env

@@ -0,0 +1 @@
+clickhouse_image=altinity/clickhouse-server:21.8.12.1.testingarm

deploy/docker/clickhouse-setup/env/x86_64.env

@@ -0,0 +1 @@
+clickhouse_image=yandex/clickhouse-server

deploy/docker/clickhouse-setup/otel-collector-config.yaml

@@ -1,4 +1,8 @@
 receivers:
+  otlp/spanmetrics:
+    protocols:
+      grpc:
+        endpoint: "localhost:12345"
   otlp:
     protocols:
       grpc:
@@ -7,10 +11,22 @@ receivers:
     protocols:
       grpc:
       thrift_http:
+  hostmetrics:
+    collection_interval: 30s
+    scrapers:
+      cpu:
+      load:
+      memory:
+      disk:
+      filesystem:
+      network:
 processors:
   batch:
     send_batch_size: 1000
     timeout: 10s
+  signozspanmetrics/prometheus:
+    metrics_exporter: prometheus
+    latency_histogram_buckets: [100us, 1ms, 2ms, 6ms, 10ms, 50ms, 100ms, 250ms, 500ms, 1000ms, 1400ms, 2000ms, 5s, 10s, 20s, 40s, 60s ]
   memory_limiter:
     # Same as --mem-ballast-size-mib CLI argument
     ballast_size_mib: 683
@@ -29,11 +45,23 @@ extensions:
 exporters:
   clickhouse:
     datasource: tcp://clickhouse:9000
-
+  clickhousemetricswrite:
+    endpoint: tcp://clickhouse:9000/?database=signoz_metrics
+    resource_to_telemetry_conversion:
+      enabled: true
+  prometheus:
+    endpoint: "0.0.0.0:8889"
 service:
   extensions: [health_check, zpages]
   pipelines:
     traces:
       receivers: [jaeger, otlp]
+      processors: [signozspanmetrics/prometheus, batch]
+      exporters: [clickhouse]
+    metrics:
+      receivers: [otlp, hostmetrics]
       processors: [batch]
-      exporters: [clickhouse]
+      exporters: [clickhousemetricswrite]
+    metrics/spanmetrics:
+      receivers: [otlp/spanmetrics]
+      exporters: [prometheus]

deploy/docker/clickhouse-setup/otel-collector-metrics-config.yaml

@@ -0,0 +1,44 @@
+receivers:
+  otlp:
+    protocols:
+      grpc:
+      http:
+
+  # Data sources: metrics
+  prometheus:
+    config:
+      scrape_configs:
+        - job_name: "otel-collector"
+          scrape_interval: 30s
+          static_configs:
+            - targets: ["otel-collector:8889"]
+processors:
+  batch:
+    send_batch_size: 1000
+    timeout: 10s
+  memory_limiter:
+    # Same as --mem-ballast-size-mib CLI argument
+    ballast_size_mib: 683
+    # 80% of maximum memory up to 2G
+    limit_mib: 1500
+    # 25% of limit up to 2G
+    spike_limit_mib: 512
+    check_interval: 5s
+  # queued_retry:
+  #   num_workers: 4
+  #   queue_size: 100
+  #   retry_on_failure: true
+extensions:
+  health_check: {}
+  zpages: {}
+exporters:
+  clickhousemetricswrite:
+    endpoint: tcp://clickhouse:9000/?database=signoz_metrics
+
+service:
+  extensions: [health_check, zpages]
+  pipelines:
+    metrics:
+      receivers: [otlp, prometheus]
+      processors: [batch]
+      exporters: [clickhousemetricswrite]

deploy/docker/clickhouse-setup/prometheus.yml

@@ -0,0 +1,26 @@
+# 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/?database=signoz_metrics

deploy/docker/common/nginx-config.conf

@@ -16,6 +16,9 @@ server {
     index  index.html index.htm;
     try_files $uri $uri/ /index.html;
     }
+    location /api/alertmanager{
+    proxy_pass http://alertmanager:9093/api/v2;
+    }
     location /api {
     proxy_pass http://query-service:8080/api;
     

deploy/docker/druid-kafka-setup/docker-compose-tiny.yaml

@@ -147,7 +147,7 @@ services:
       retries: 5
 
   flatten-processor:
-    image: signoz/flattener-processor:0.3.4
+    image: signoz/flattener-processor:0.4.0
     container_name: flattener-processor
 
     depends_on:
@@ -163,26 +163,29 @@ services:
     
 
   query-service:
-    image: signoz.docker.scarf.sh/signoz/query-service:0.3.4
+    image: signoz.docker.scarf.sh/signoz/query-service:0.4.1
     container_name: query-service
 
     depends_on:
       - router
     ports:
       - "8080:8080"
-
+    volumes:
+      - ../dashboards:/root/config/dashboards
+      - ./data/signoz/:/var/lib/signoz/
     environment:
       - DruidClientUrl=http://router:8888
       - DruidDatasource=flattened_spans
       - STORAGE=druid
       - POSTHOG_API_KEY=H-htDCae7CR3RV57gUzmol6IAKtm5IMCvbcm_fwnL-w
-      
+      - GODEBUG=netdns=go
+
     depends_on: 
       router:
         condition: service_healthy
     
   frontend:
-    image: signoz/frontend:0.3.4
+    image: signoz/frontend:0.4.1
     container_name: frontend
 
     depends_on:

deploy/docker/druid-kafka-setup/docker-compose.yaml

@@ -142,7 +142,7 @@ services:
       retries: 5
 
   flatten-processor:
-    image: signoz/flattener-processor:0.3.4
+    image: signoz/flattener-processor:0.4.0
     container_name: flattener-processor
 
     depends_on:
@@ -158,26 +158,30 @@ services:
     
 
   query-service:
-    image: signoz.docker.scarf.sh/signoz/query-service:0.3.4
+    image: signoz.docker.scarf.sh/signoz/query-service:0.4.1
     container_name: query-service
 
     depends_on:
       - router
     ports:
       - "8080:8080"
-
+      
+    volumes:
+      - ../dashboards:/root/config/dashboards
+      - ./data/signoz/:/var/lib/signoz/
     environment:
       - DruidClientUrl=http://router:8888
       - DruidDatasource=flattened_spans
       - STORAGE=druid
       - POSTHOG_API_KEY=H-htDCae7CR3RV57gUzmol6IAKtm5IMCvbcm_fwnL-w
+      - GODEBUG=netdns=go
 
     depends_on: 
       router:
         condition: service_healthy
     
   frontend:
-    image: signoz/frontend:0.3.4
+    image: signoz/frontend:0.4.1
     container_name: frontend
 
     depends_on:

deploy/install.sh

@@ -36,6 +36,10 @@ is_mac() {
     [[ $OSTYPE == darwin* ]]
 }
 
+is_arm64(){
+    [[ `uname -m` == 'arm64' ]]
+}
+
 check_os() {
     if is_mac; then
         package_manager="brew"
@@ -160,8 +164,9 @@ install_docker() {
         echo
         echo "Amazon Linux detected ... "
         echo
-        sudo yum install docker
-        sudo service docker start
+        # sudo yum install docker
+        # sudo service docker start
+        sudo amazon-linux-extras install docker
     else
 
         yum_cmd="sudo yum --assumeyes --quiet"
@@ -266,7 +271,11 @@ bye() {  # Prints a friendly good bye message and exits the script.
         echo "🔴 The containers didn't seem to start correctly. Please run the following command to check containers that may have errored out:"
         echo ""
         if [ $setup_type == 'clickhouse' ]; then
-            echo -e "sudo docker-compose -f docker/clickhouse-setup/docker-compose.yaml ps -a"
+            if is_arm64; then
+                echo -e "sudo docker-compose --env-file ./docker/clickhouse-setup/env/arm64.env -f docker/clickhouse-setup/docker-compose.yaml ps -a"
+            else
+                echo -e "sudo docker-compose --env-file ./docker/clickhouse-setup/env/x86_64.env -f docker/clickhouse-setup/docker-compose.yaml ps -a"
+            fi
         else   
             echo -e "sudo docker-compose -f docker/druid-kafka-setup/docker-compose-tiny.yaml ps -a"
         fi
@@ -313,28 +322,30 @@ check_os
 
 SIGNOZ_INSTALLATION_ID=$(curl -s 'https://api64.ipify.org')
 
-echo ""
+# echo ""
 
-echo -e "👉 ${RED}Two ways to go forward\n"  
-echo -e "${RED}1) ClickHouse as database (default)\n"  
-echo -e "${RED}2) Kafka + Druid setup to handle scale (recommended for production use)\n"  
-read -p "⚙️  Enter your preference (1/2):" choice_setup 
+# echo -e "👉 ${RED}Two ways to go forward\n"  
+# echo -e "${RED}1) ClickHouse as database (default)\n"  
+# echo -e "${RED}2) Kafka + Druid as datastore \n"  
+# read -p "⚙️  Enter your preference (1/2):" choice_setup 
 
-while [[ $choice_setup != "1"   &&  $choice_setup != "2" && $choice_setup != "" ]]
-do
-    # echo $choice_setup
-    echo -e "\n❌ ${CYAN}Please enter either 1 or 2"
-    read -p "⚙️  Enter your preference (1/2):  " choice_setup 
-    # echo $choice_setup
-done
+# while [[ $choice_setup != "1"   &&  $choice_setup != "2" && $choice_setup != "" ]]
+# do
+#     # echo $choice_setup
+#     echo -e "\n❌ ${CYAN}Please enter either 1 or 2"
+#     read -p "⚙️  Enter your preference (1/2):  " choice_setup 
+#     # echo $choice_setup
+# done
 
-if [[ $choice_setup == "1" || $choice_setup == "" ]];then
-    setup_type='clickhouse'
-else
-    setup_type='druid'
-fi
+# if [[ $choice_setup == "1" || $choice_setup == "" ]];then
+#     setup_type='clickhouse'
+# else
+#     setup_type='druid'
+# fi
 
-echo -e "\n✅ ${CYAN}You have chosen: ${setup_type} setup\n"
+setup_type='clickhouse'
+
+# echo -e "\n✅ ${CYAN}You have chosen: ${setup_type} setup\n"
 
 # Run bye if failure happens
 trap bye EXIT
@@ -405,7 +416,11 @@ start_docker
 echo ""
 echo -e "\n🟡 Pulling the latest container images for SigNoz. To run as sudo it may ask for system password\n"
 if [ $setup_type == 'clickhouse' ]; then
-    sudo docker-compose -f ./docker/clickhouse-setup/docker-compose.yaml pull
+    if is_arm64; then
+        sudo docker-compose --env-file ./docker/clickhouse-setup/env/arm64.env -f ./docker/clickhouse-setup/docker-compose.yaml pull
+    else
+        sudo docker-compose --env-file ./docker/clickhouse-setup/env/x86_64.env -f ./docker/clickhouse-setup/docker-compose.yaml pull
+    fi
 else
     sudo docker-compose -f ./docker/druid-kafka-setup/docker-compose-tiny.yaml pull
 fi
@@ -417,7 +432,11 @@ echo
 # The docker-compose 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.
 if [ $setup_type == 'clickhouse' ]; then
-    sudo docker-compose -f ./docker/clickhouse-setup/docker-compose.yaml up --detach --remove-orphans || true
+    if is_arm64; then
+        sudo docker-compose --env-file ./docker/clickhouse-setup/env/arm64.env -f ./docker/clickhouse-setup/docker-compose.yaml up --detach --remove-orphans || true
+    else
+        sudo docker-compose --env-file ./docker/clickhouse-setup/env/x86_64.env -f ./docker/clickhouse-setup/docker-compose.yaml up --detach --remove-orphans || true
+    fi
 else
     sudo docker-compose -f ./docker/druid-kafka-setup/docker-compose-tiny.yaml up --detach --remove-orphans || true
 fi
@@ -477,7 +496,7 @@ else
     echo ""
 
     if [ $setup_type == 'clickhouse' ]; then
-        echo "ℹ️  To bring down SigNoz and clean volumes : sudo docker-compose -f docker/clickhouse-setup/docker-compose.yaml down -v"
+        echo "ℹ️  To bring down SigNoz and clean volumes : sudo docker-compose --env-file ./docker/clickhouse-setup/env/arm64.env -f docker/clickhouse-setup/docker-compose.yaml down -v"
     else
         echo "ℹ️  To bring down SigNoz and clean volumes : sudo docker-compose -f docker/druid-kafka-setup/docker-compose-tiny.yaml down -v"
     fi
@@ -508,4 +527,4 @@ else
 
 fi
 
-echo -e "\n🙏 Thank you!\n"
+echo -e "\n🙏 Thank you!\n"

deploy/kubernetes/jobs/retention/retention-config.yaml

@@ -1,7 +0,0 @@
-apiVersion: v1
-kind: ConfigMap
-metadata:
-  name: retention-config
-data:
-  retention-spec.json: |
-    [{"period":"P3D","includeFuture":true,"tieredReplicants":{"_default_tier":1},"type":"loadByPeriod"},{"type":"dropForever"}]

deploy/kubernetes/jobs/retention/retention.yaml

@@ -1,29 +0,0 @@
-apiVersion: batch/v1
-kind: Job
-metadata:
-  name: set-retention
-  annotations:
-    "helm.sh/hook": post-install,post-upgrade
-spec:
-  ttlSecondsAfterFinished: 100
-  template:
-    spec:
-      containers:
-          - name: set-retention
-            image: theithollow/hollowapp-blog:curl
-            volumeMounts:
-            - name: retention-config-volume
-              mountPath: /app/retention-spec.json
-              subPath: retention-spec.json
-            args:
-            - /bin/sh
-            - -c
-            - "curl -X POST -H 'Content-Type: application/json' -d @/app/retention-spec.json http://signoz-druid-router:8888/druid/coordinator/v1/rules/flattened_spans"
-
-      volumes:
-          - name: retention-config-volume
-            configMap:
-              name: retention-config
-
-      restartPolicy: Never
-  backoffLimit: 8

deploy/kubernetes/jobs/supervisor/supervisor-config.yaml

@@ -1,76 +0,0 @@
-apiVersion: v1
-kind: ConfigMap
-metadata:
-  name: supervisor-config
-data:
-  supervisor-spec.json: |
-    {
-        "type": "kafka",
-        "dataSchema": {
-          "dataSource": "flattened_spans",
-          "parser": {
-            "type": "string",
-            "parseSpec": {
-              "format": "json",
-              "timestampSpec": {
-                "column": "StartTimeUnixNano",
-                "format": "nano"
-              },
-              "dimensionsSpec": {
-                "dimensions": [
-                  "TraceId",
-                  "SpanId",
-                  "ParentSpanId",
-                  "Name",
-                  "ServiceName",
-                  "References",
-                  "Tags",
-                  "ExternalHttpMethod",
-                  "ExternalHttpUrl",
-                  "Component",
-                  "DBSystem",
-                  "DBName",
-                  "DBOperation",
-                  "PeerService",
-                  { 
-                      "type": "string",
-                      "name": "TagsKeys", 
-                      "multiValueHandling": "ARRAY" 
-                  },
-                  { 
-                      "type": "string",
-                      "name": "TagsValues", 
-                      "multiValueHandling": "ARRAY" 
-                  },
-                  { "name": "DurationNano", "type": "Long" },
-                  { "name": "Kind", "type": "int" },
-                  { "name": "StatusCode", "type": "int" }
-                ]
-              }
-            }
-          },
-          "metricsSpec" : [
-              { "type": "quantilesDoublesSketch", "name": "QuantileDuration", "fieldName": "DurationNano" }
-          ],
-          "granularitySpec": {
-            "type": "uniform",
-            "segmentGranularity": "DAY",
-            "queryGranularity": "NONE",
-            "rollup": false
-          }
-        },
-        "tuningConfig": {
-          "type": "kafka",
-          "reportParseExceptions": true
-        },
-        "ioConfig": {
-          "topic": "flattened_spans",
-          "replicas": 1,
-          "taskDuration": "PT20M",
-          "completionTimeout": "PT30M",
-          "consumerProperties": {
-            "bootstrap.servers": "signoz-kafka:9092"
-          }
-        }
-      }
-

deploy/kubernetes/jobs/supervisor/supervisor.yaml

@@ -1,27 +0,0 @@
-apiVersion: batch/v1
-kind: Job
-metadata:
-  name: create-supervisor
-  annotations:
-    "helm.sh/hook": post-install,post-upgrade
-spec:
-  ttlSecondsAfterFinished: 100
-  template:
-    spec:
-      containers:
-          - name: create-supervisor
-            image: theithollow/hollowapp-blog:curl
-            volumeMounts:
-            - name: supervisor-config-volume
-              mountPath: /app/supervisor-spec.json
-              subPath: supervisor-spec.json
-            args:
-            - /bin/sh
-            - -c
-            - "curl -X POST -H 'Content-Type: application/json' -d @/app/supervisor-spec.json http://signoz-druid-router:8888/druid/indexer/v1/supervisor"
-      volumes:
-          - name: supervisor-config-volume
-            configMap:
-              name: supervisor-config
-      restartPolicy: Never
-  backoffLimit: 8

deploy/kubernetes/otel-collector/config.yaml

@@ -1,60 +0,0 @@
-apiVersion: v1
-kind: ConfigMap
-metadata:
-  name: otel-collector-conf
-  labels:
-    app: opentelemetry
-    component: otel-collector-conf
-data:
-  otel-collector-config: |
-    receivers:
-      otlp:
-        protocols:
-          grpc:
-          http:
-      jaeger:
-        protocols:
-          grpc:
-          thrift_http:
-    processors:
-      batch:
-        send_batch_size: 1000
-        timeout: 10s
-      memory_limiter:
-        # Same as --mem-ballast-size-mib CLI argument
-        ballast_size_mib: 683
-        # 80% of maximum memory up to 2G
-        limit_mib: 1500
-        # 25% of limit up to 2G
-        spike_limit_mib: 512
-        check_interval: 5s
-      queued_retry:
-        num_workers: 4
-        queue_size: 100
-        retry_on_failure: true
-    extensions:
-      health_check: {}
-      zpages: {}
-    exporters:
-      kafka/traces:
-        brokers:
-          - signoz-kafka:9092
-        topic: 'otlp_spans'
-        protocol_version: 2.0.0
-
-      kafka/metrics:
-        brokers:
-          - signoz-kafka:9092
-        topic: 'otlp_metrics'
-        protocol_version: 2.0.0
-    service:
-      extensions: [health_check, zpages]
-      pipelines:
-        traces:
-          receivers: [jaeger, otlp]
-          processors: [memory_limiter, batch, queued_retry]
-          exporters: [kafka/traces]
-        metrics:
-          receivers: [otlp]
-          processors: [batch]
-          exporters: [kafka/metrics]

deploy/kubernetes/platform/Chart.lock

@@ -2,20 +2,14 @@ dependencies:
 - name: zookeeper
   repository: https://charts.bitnami.com/bitnami
   version: 6.0.0
-- name: kafka
-  repository: https://charts.bitnami.com/bitnami
-  version: 12.0.0
-- name: druid
-  repository: https://charts.helm.sh/incubator
-  version: 0.2.18
-- name: flattener-processor
-  repository: file://./signoz-charts/flattener-processor
-  version: 0.3.4
 - name: query-service
   repository: file://./signoz-charts/query-service
-  version: 0.3.4
+  version: 0.5.3
 - name: frontend
   repository: file://./signoz-charts/frontend
-  version: 0.3.4
-digest: sha256:49f8b43acecdb7cb0fb8ed5af1488bfbef5b66be02e17bb716403750a6894844
-generated: "2021-08-10T23:37:01.176317+05:30"
+  version: 0.5.3
+- name: alertmanager
+  repository: file://./signoz-charts/alertmanager
+  version: 0.5.0
+digest: sha256:891df4e1a3d9fc7bf2b4b67beb4e505f1ec4da20952c2e294ad8b16fcc4eccb7
+generated: "2021-12-11T11:40:26.756851+05:30"

deploy/kubernetes/platform/Chart.yaml

@@ -15,29 +15,23 @@ type: application
 # This is the chart version. This version number should be incremented each time you make changes
 # to the chart and its templates, including the app version.
 # Versions are expected to follow Semantic Versioning (https://semver.org/)
-version: 0.3.2
+version: 0.5.3
 
 # This is the version number of the application being deployed. This version number should be
 # incremented each time you make changes to the application. Versions are not expected to
 # follow Semantic Versioning. They should reflect the version the application is using.
-appVersion: 0.3.2
+appVersion: 0.5.3
 
 dependencies:
   - name: zookeeper
     repository: "https://charts.bitnami.com/bitnami"
     version: 6.0.0
-  - name: kafka
-    repository: "https://charts.bitnami.com/bitnami"
-    version: 12.0.0
-  - name: druid
-    repository: "https://charts.helm.sh/incubator"
-    version: 0.2.18
-  - name: flattener-processor
-    repository: "file://./signoz-charts/flattener-processor"
-    version: 0.3.4
   - name: query-service
     repository: "file://./signoz-charts/query-service"
-    version: 0.3.4
+    version: 0.5.3
   - name: frontend
     repository: "file://./signoz-charts/frontend"
-    version: 0.3.4
+    version: 0.5.3
+  - name: alertmanager
+    repository: "file://./signoz-charts/alertmanager"
+    version: 0.5.0

deploy/kubernetes/platform/signoz-charts/alertmanager/.helmignore

@@ -21,3 +21,5 @@
 .idea/
 *.tmproj
 .vscode/
+
+unittests/

deploy/kubernetes/platform/signoz-charts/alertmanager/Chart.yaml

@@ -0,0 +1,7 @@
+apiVersion: v2
+name: alertmanager
+description: The Alertmanager handles alerts sent by client applications such as the Prometheus server.
+type: application
+version: 0.5.0
+appVersion: 0.5.0
+

deploy/kubernetes/platform/signoz-charts/alertmanager/ci/config-reload-values.yaml

@@ -0,0 +1,2 @@
+configmapReload:
+  enabled: true

deploy/kubernetes/platform/signoz-charts/alertmanager/templates/NOTES.txt

@@ -2,20 +2,20 @@
 {{- if .Values.ingress.enabled }}
 {{- range $host := .Values.ingress.hosts }}
   {{- range .paths }}
-  http{{ if $.Values.ingress.tls }}s{{ end }}://{{ $host.host }}{{ . }}
+  http{{ if $.Values.ingress.tls }}s{{ end }}://{{ $host.host }}{{ .path }}
   {{- end }}
 {{- end }}
 {{- else if contains "NodePort" .Values.service.type }}
-  export NODE_PORT=$(kubectl get --namespace {{ .Release.Namespace }} -o jsonpath="{.spec.ports[0].nodePort}" services {{ include "flattener-processor.fullname" . }})
+  export NODE_PORT=$(kubectl get --namespace {{ .Release.Namespace }} -o jsonpath="{.spec.ports[0].nodePort}" services {{ include "alertmanager.fullname" . }})
   export NODE_IP=$(kubectl get nodes --namespace {{ .Release.Namespace }} -o jsonpath="{.items[0].status.addresses[0].address}")
   echo http://$NODE_IP:$NODE_PORT
 {{- else if contains "LoadBalancer" .Values.service.type }}
      NOTE: It may take a few minutes for the LoadBalancer IP to be available.
-           You can watch the status of by running 'kubectl get --namespace {{ .Release.Namespace }} svc -w {{ include "flattener-processor.fullname" . }}'
-  export SERVICE_IP=$(kubectl get svc --namespace {{ .Release.Namespace }} {{ include "flattener-processor.fullname" . }} --template "{{"{{ range (index .status.loadBalancer.ingress 0) }}{{.}}{{ end }}"}}")
+           You can watch the status of by running 'kubectl get --namespace {{ .Release.Namespace }} svc -w {{ include "alertmanager.fullname" . }}'
+  export SERVICE_IP=$(kubectl get svc --namespace {{ .Release.Namespace }} {{ include "alertmanager.fullname" . }} --template "{{"{{ range (index .status.loadBalancer.ingress 0) }}{{.}}{{ end }}"}}")
   echo http://$SERVICE_IP:{{ .Values.service.port }}
 {{- else if contains "ClusterIP" .Values.service.type }}
-  export POD_NAME=$(kubectl get pods --namespace {{ .Release.Namespace }} -l "app.kubernetes.io/name={{ include "flattener-processor.name" . }},app.kubernetes.io/instance={{ .Release.Name }}" -o jsonpath="{.items[0].metadata.name}")
-  echo "Visit http://127.0.0.1:8080 to use your application"
-  kubectl --namespace {{ .Release.Namespace }} port-forward $POD_NAME 8080:80
+  export POD_NAME=$(kubectl get pods --namespace {{ .Release.Namespace }} -l "app.kubernetes.io/name={{ include "alertmanager.name" . }},app.kubernetes.io/instance={{ .Release.Name }}" -o jsonpath="{.items[0].metadata.name}")
+  echo "Visit http://127.0.0.1:{{ .Values.service.port }} to use your application"
+  kubectl --namespace {{ .Release.Namespace }} port-forward $POD_NAME {{ .Values.service.port }}:80
 {{- end }}

deploy/kubernetes/platform/signoz-charts/alertmanager/templates/_helpers.tpl

@@ -2,7 +2,7 @@
 {{/*
 Expand the name of the chart.
 */}}
-{{- define "flattener-processor.name" -}}
+{{- define "alertmanager.name" -}}
 {{- default .Chart.Name .Values.nameOverride | trunc 63 | trimSuffix "-" -}}
 {{- end -}}
 
@@ -11,7 +11,7 @@ Create a default fully qualified app name.
 We truncate at 63 chars because some Kubernetes name fields are limited to this (by the DNS naming spec).
 If release name contains chart name it will be used as a full name.
 */}}
-{{- define "flattener-processor.fullname" -}}
+{{- define "alertmanager.fullname" -}}
 {{- if .Values.fullnameOverride -}}
 {{- .Values.fullnameOverride | trunc 63 | trimSuffix "-" -}}
 {{- else -}}
@@ -27,16 +27,16 @@ If release name contains chart name it will be used as a full name.
 {{/*
 Create chart name and version as used by the chart label.
 */}}
-{{- define "flattener-processor.chart" -}}
+{{- define "alertmanager.chart" -}}
 {{- printf "%s-%s" .Chart.Name .Chart.Version | replace "+" "_" | trunc 63 | trimSuffix "-" -}}
 {{- end -}}
 
 {{/*
 Common labels
 */}}
-{{- define "flattener-processor.labels" -}}
-helm.sh/chart: {{ include "flattener-processor.chart" . }}
-{{ include "flattener-processor.selectorLabels" . }}
+{{- define "alertmanager.labels" -}}
+helm.sh/chart: {{ include "alertmanager.chart" . }}
+{{ include "alertmanager.selectorLabels" . }}
 {{- if .Chart.AppVersion }}
 app.kubernetes.io/version: {{ .Chart.AppVersion | quote }}
 {{- end }}
@@ -46,17 +46,17 @@ app.kubernetes.io/managed-by: {{ .Release.Service }}
 {{/*
 Selector labels
 */}}
-{{- define "flattener-processor.selectorLabels" -}}
-app.kubernetes.io/name: {{ include "flattener-processor.name" . }}
+{{- define "alertmanager.selectorLabels" -}}
+app.kubernetes.io/name: {{ include "alertmanager.name" . }}
 app.kubernetes.io/instance: {{ .Release.Name }}
 {{- end -}}
 
 {{/*
 Create the name of the service account to use
 */}}
-{{- define "flattener-processor.serviceAccountName" -}}
+{{- define "alertmanager.serviceAccountName" -}}
 {{- if .Values.serviceAccount.create -}}
-    {{ default (include "flattener-processor.fullname" .) .Values.serviceAccount.name }}
+    {{ default (include "alertmanager.fullname" .) .Values.serviceAccount.name }}
 {{- else -}}
     {{ default "default" .Values.serviceAccount.name }}
 {{- end -}}

deploy/kubernetes/platform/signoz-charts/alertmanager/templates/configmap.yaml

@@ -0,0 +1,15 @@
+{{- if .Values.config }}
+apiVersion: v1
+kind: ConfigMap
+metadata:
+  name: {{ include "alertmanager.fullname" . }}
+  labels:
+    {{- include "alertmanager.labels" . | nindent 4 }}
+data:
+  alertmanager.yml: |
+    {{- toYaml .Values.config | default "{}" | nindent 4 }}
+  {{- range $key, $value := .Values.templates }}
+  {{ $key }}: |-
+    {{- $value | nindent 4 }}
+  {{- end }}
+{{- end }}

deploy/kubernetes/platform/signoz-charts/alertmanager/templates/ingress.yaml

@@ -0,0 +1,61 @@
+{{- if .Values.ingress.enabled -}}
+{{- $fullName := include "alertmanager.fullname" . -}}
+{{- $svcPort := .Values.service.port -}}
+{{- if and .Values.ingress.className (not (semverCompare ">=1.18-0" .Capabilities.KubeVersion.GitVersion)) }}
+  {{- if not (hasKey .Values.ingress.annotations "kubernetes.io/ingress.class") }}
+  {{- $_ := set .Values.ingress.annotations "kubernetes.io/ingress.class" .Values.ingress.className}}
+  {{- end }}
+{{- end }}
+{{- if semverCompare ">=1.19-0" .Capabilities.KubeVersion.GitVersion -}}
+apiVersion: networking.k8s.io/v1
+{{- else if semverCompare ">=1.14-0" .Capabilities.KubeVersion.GitVersion -}}
+apiVersion: networking.k8s.io/v1beta1
+{{- else -}}
+apiVersion: extensions/v1beta1
+{{- end }}
+kind: Ingress
+metadata:
+  name: {{ $fullName }}
+  labels:
+    {{- include "alertmanager.labels" . | nindent 4 }}
+  {{- with .Values.ingress.annotations }}
+  annotations:
+    {{- toYaml . | nindent 4 }}
+  {{- end }}
+spec:
+  {{- if and .Values.ingress.className (semverCompare ">=1.18-0" .Capabilities.KubeVersion.GitVersion) }}
+  ingressClassName: {{ .Values.ingress.className }}
+  {{- end }}
+  {{- if .Values.ingress.tls }}
+  tls:
+    {{- range .Values.ingress.tls }}
+    - hosts:
+        {{- range .hosts }}
+        - {{ . | quote }}
+        {{- end }}
+      secretName: {{ .secretName }}
+    {{- end }}
+  {{- end }}
+  rules:
+    {{- range .Values.ingress.hosts }}
+    - host: {{ .host | quote }}
+      http:
+        paths:
+          {{- range .paths }}
+          - path: {{ .path }}
+            {{- if and .pathType (semverCompare ">=1.18-0" $.Capabilities.KubeVersion.GitVersion) }}
+            pathType: {{ .pathType }}
+            {{- end }}
+            backend:
+              {{- if semverCompare ">=1.19-0" $.Capabilities.KubeVersion.GitVersion }}
+              service:
+                name: {{ $fullName }}
+                port:
+                  number: {{ $svcPort }}
+              {{- else }}
+              serviceName: {{ $fullName }}
+              servicePort: {{ $svcPort }}
+              {{- end }}
+          {{- end }}
+    {{- end }}
+{{- end }}

deploy/kubernetes/platform/signoz-charts/alertmanager/templates/pdb.yaml

@@ -0,0 +1,13 @@
+{{- if .Values.podDisruptionBudget -}}
+apiVersion: policy/v1beta1
+kind: PodDisruptionBudget
+metadata:
+  name: {{ template "alertmanager.fullname" . }}
+  labels:
+    {{- include "alertmanager.labels" . | nindent 4 }}
+spec:
+  selector:
+    matchLabels:
+      {{- include "alertmanager.selectorLabels" . | nindent 6 }}
+{{ toYaml .Values.podDisruptionBudget | indent 2 }}
+{{- end -}}

deploy/kubernetes/platform/signoz-charts/alertmanager/templates/serviceaccount.yaml

@@ -2,9 +2,9 @@
 apiVersion: v1
 kind: ServiceAccount
 metadata:
-  name: {{ include "flattener-processor.serviceAccountName" . }}
+  name: {{ include "alertmanager.serviceAccountName" . }}
   labels:
-    {{- include "flattener-processor.labels" . | nindent 4 }}
+    {{- include "alertmanager.labels" . | nindent 4 }}
   {{- with .Values.serviceAccount.annotations }}
   annotations:
     {{- toYaml . | nindent 4 }}

deploy/kubernetes/platform/signoz-charts/alertmanager/templates/services.yaml

@@ -0,0 +1,48 @@
+apiVersion: v1
+kind: Service
+metadata:
+  name: alertmanager
+  labels:
+    {{- include "alertmanager.labels" . | nindent 4 }}
+{{- if .Values.service.annotations }}
+  annotations:
+    {{- toYaml .Values.service.annotations | nindent 4 }}
+{{- end }}
+spec:
+  type: {{ .Values.service.type }}
+  ports:
+    - port: {{ .Values.service.port }}
+      targetPort: http
+      protocol: TCP
+      name: http
+      {{- if (and (eq .Values.service.type "NodePort") .Values.service.nodePort) }}
+      nodePort: {{ .Values.service.nodePort }}
+      {{- end }}
+  selector:
+    {{- include "alertmanager.selectorLabels" . | nindent 4 }}
+---
+apiVersion: v1
+kind: Service
+metadata:
+  name: {{ include "alertmanager.fullname" . }}-headless
+  labels:
+    {{- include "alertmanager.labels" . | nindent 4 }}
+spec:
+  clusterIP: None
+  ports:
+    - port: {{ .Values.service.port }}
+      targetPort: http
+      protocol: TCP
+      name: http
+    {{- if or (gt .Values.replicaCount 1.0) (.Values.additionalPeers) }}
+    - port: 9094
+      targetPort: 9094
+      protocol: TCP
+      name: cluster-tcp
+    - port: 9094
+      targetPort: 9094
+      protocol: UDP
+      name: cluster-udp
+    {{- end }}
+  selector:
+    {{- include "alertmanager.selectorLabels" . | nindent 4 }}

deploy/kubernetes/platform/signoz-charts/alertmanager/templates/statefulset.yaml

@@ -0,0 +1,152 @@
+apiVersion: apps/v1
+kind: StatefulSet
+metadata:
+  name: {{ include "alertmanager.fullname" . }}
+  labels:
+    {{- include "alertmanager.labels" . | nindent 4 }}
+{{- if .Values.statefulSet.annotations }}
+  annotations:
+    {{ toYaml .Values.statefulSet.annotations | nindent 4 }}
+{{- end }}
+spec:
+  replicas: {{ .Values.replicaCount }}
+  selector:
+    matchLabels:
+      {{- include "alertmanager.selectorLabels" . | nindent 6 }}
+  serviceName: {{ include "alertmanager.fullname" . }}-headless
+  template:
+    metadata:
+      labels:
+        {{- include "alertmanager.selectorLabels" . | nindent 8 }}
+{{- if .Values.podLabels }}
+        {{ toYaml .Values.podLabels | nindent 8 }}
+{{- end }}
+      annotations:
+      {{- if not .Values.configmapReload.enabled }}
+        checksum/config: {{ include (print $.Template.BasePath "/configmap.yaml") . | sha256sum }}
+      {{- end }}
+{{- if .Values.podAnnotations }}
+        {{- toYaml .Values.podAnnotations | nindent 8 }}
+{{- end }}
+    spec:
+    {{- with .Values.imagePullSecrets }}
+      imagePullSecrets:
+        {{- toYaml . | nindent 8 }}
+    {{- end }}
+      serviceAccountName: {{ include "alertmanager.serviceAccountName" . }}
+    {{- with .Values.dnsConfig }}
+      dnsConfig:
+        {{- toYaml . | nindent 8 }}
+    {{- end }}
+    {{- with .Values.nodeSelector }}
+      nodeSelector:
+        {{- toYaml . | nindent 8 }}
+      {{- end }}
+    {{- with .Values.affinity }}
+      affinity:
+        {{- toYaml . | nindent 8 }}
+    {{- end }}
+    {{- with .Values.tolerations }}
+      tolerations:
+        {{- toYaml . | nindent 8 }}
+    {{- end }}
+      securityContext:
+        {{- toYaml .Values.podSecurityContext | nindent 8 }}
+      containers:
+        {{- if and (.Values.configmapReload.enabled) (.Values.config) }}
+        - name: {{ .Chart.Name }}-{{ .Values.configmapReload.name }}
+          image: "{{ .Values.configmapReload.image.repository }}:{{ .Values.configmapReload.image.tag }}"
+          imagePullPolicy: "{{ .Values.configmapReload.image.pullPolicy }}"
+          args:
+            - --volume-dir=/etc/alertmanager
+            - --webhook-url=http://127.0.0.1:{{ .Values.service.port }}/-/reload
+          resources:
+            {{- toYaml .Values.configmapReload.resources | nindent 12 }}
+          volumeMounts:
+            - name: config
+              mountPath: /etc/alertmanager
+        {{- end }}
+        - name: {{ .Chart.Name }}
+          securityContext:
+            {{- toYaml .Values.securityContext | nindent 12 }}
+          image: "{{ .Values.image.repository }}:{{ .Values.image.tag | default .Chart.AppVersion }}"
+          imagePullPolicy: {{ .Values.image.pullPolicy }}
+          env:
+            - name: POD_IP
+              valueFrom:
+                fieldRef:
+                  apiVersion: v1
+                  fieldPath: status.podIP
+{{- if .Values.command }}
+          command:
+            {{- toYaml .Values.command | nindent 12 }}
+{{- end }}
+          args:
+            - --storage.path=/alertmanager
+            - --config.file=/etc/alertmanager/alertmanager.yml
+            {{- if or (gt .Values.replicaCount 1.0) (.Values.additionalPeers) }}
+            - --cluster.advertise-address=$(POD_IP):9094
+            - --cluster.listen-address=0.0.0.0:9094
+            {{- end }}
+            {{- if gt .Values.replicaCount 1.0}}
+            {{- $fullName := include "alertmanager.fullname" . }}
+            {{- range $i := until (int .Values.replicaCount) }}
+            - --cluster.peer={{ $fullName }}-{{ $i }}.{{ $fullName }}-headless:9094
+            {{- end }}
+            {{- end }}
+            {{- if .Values.additionalPeers }}
+            {{- range $item := .Values.additionalPeers }}
+            - --cluster.peer={{ $item }}
+            {{- end }}
+            {{- end }}
+            {{- range $key, $value := .Values.extraArgs }}
+            - --{{ $key }}={{ $value }}
+            {{- end }}
+          ports:
+            - name: http
+              containerPort: 9093
+              protocol: TCP
+          livenessProbe:
+            httpGet:
+              path: /
+              port: http
+          readinessProbe:
+            httpGet:
+              path: /
+              port: http
+          resources:
+            {{- toYaml .Values.resources | nindent 12 }}
+          volumeMounts:
+            {{- if .Values.config }}
+            - name: config
+              mountPath: /etc/alertmanager
+            {{- end }}
+            - name: storage
+              mountPath: /alertmanager
+      {{- if .Values.config }}
+      volumes:
+        - name: config
+          configMap:
+            name: {{ include "alertmanager.fullname" . }}
+      {{- end }}
+      {{- if .Values.persistence.enabled }}
+  volumeClaimTemplates:
+    - metadata:
+        name: storage
+      spec:
+        accessModes:
+          {{- toYaml .Values.persistence.accessModes | nindent 10 }}
+        resources:
+          requests:
+            storage: {{ .Values.persistence.size }}
+      {{- if .Values.persistence.storageClass }}
+      {{- if (eq "-" .Values.persistence.storageClass) }}
+        storageClassName: ""
+      {{- else }}
+        storageClassName: {{ .Values.persistence.storageClass }}
+      {{- end }}
+      {{- end }}
+{{- else }}
+        - name: storage
+          emptyDir: {}
+{{- end -}}

deploy/kubernetes/platform/signoz-charts/alertmanager/unittests/__snapshot__/ingress_test.yaml.snap

@@ -0,0 +1,48 @@
+should match snapshot of default values:
+  1: |
+    apiVersion: networking.k8s.io/v1
+    kind: Ingress
+    metadata:
+      labels:
+        app.kubernetes.io/instance: RELEASE-NAME
+        app.kubernetes.io/managed-by: Helm
+        app.kubernetes.io/name: alertmanager
+        app.kubernetes.io/version: 1.0.0
+        helm.sh/chart: alertmanager-1.0.0
+      name: RELEASE-NAME-alertmanager
+    spec:
+      ingressClassName: nginx-test
+      rules:
+      - host: alertmanager.domain.com
+        http:
+          paths:
+          - backend:
+              service:
+                name: RELEASE-NAME-alertmanager
+                port:
+                  number: 9093
+            path: /
+            pathType: ImplementationSpecific
+should match snapshot of default values with old kubernetes ingress:
+  1: |
+    apiVersion: networking.k8s.io/v1beta1
+    kind: Ingress
+    metadata:
+      annotations:
+        kubernetes.io/ingress.class: nginx-test
+      labels:
+        app.kubernetes.io/instance: RELEASE-NAME
+        app.kubernetes.io/managed-by: Helm
+        app.kubernetes.io/name: alertmanager
+        app.kubernetes.io/version: 1.0.0
+        helm.sh/chart: alertmanager-1.0.0
+      name: RELEASE-NAME-alertmanager
+    spec:
+      rules:
+      - host: alertmanager.domain.com
+        http:
+          paths:
+          - backend:
+              serviceName: RELEASE-NAME-alertmanager
+              servicePort: 9093
+            path: /

deploy/kubernetes/platform/signoz-charts/alertmanager/unittests/ingress_test.yaml

@@ -0,0 +1,81 @@
+suite: test ingress
+templates:
+  - ingress.yaml
+tests:
+  - it: should be empty if ingress is not enabled
+    asserts:
+      - hasDocuments:
+          count: 0
+  - it: should have apiVersion extensions/v1beta1 for k8s < 1.14
+    set:
+      ingress.enabled: true
+    capabilities:
+      majorVersion: 1
+      minorVersion: 13
+    asserts:
+      - hasDocuments:
+          count: 1
+      - isKind:
+          of: Ingress
+      - isAPIVersion:
+          of: extensions/v1beta1
+  - it: should have apiVersion networking.k8s.io/v1beta1 for k8s < 1.19
+    set:
+      ingress.enabled: true
+    capabilities:
+      majorVersion: 1
+      minorVersion: 18
+    asserts:
+      - hasDocuments:
+          count: 1
+      - isKind:
+          of: Ingress
+      - isAPIVersion:
+          of: networking.k8s.io/v1beta1
+  - it: should have apiVersion networking.k8s.io/v1 for k8s >= 1.19
+    set:
+      ingress.enabled: true
+    capabilities:
+      majorVersion: 1
+      minorVersion: 19
+    asserts:
+      - hasDocuments:
+          count: 1
+      - isKind:
+          of: Ingress
+      - isAPIVersion:
+          of: networking.k8s.io/v1
+  - it: should have an ingressClassName for k8s >= 1.19
+    set:
+      ingress.enabled: true
+      ingress.className: nginx-test
+    capabilities:
+      majorVersion: 1
+      minorVersion: 19
+    asserts:
+      - hasDocuments:
+          count: 1
+      - equal:
+          path: spec.ingressClassName
+          value: nginx-test
+  - it: should match snapshot of default values
+    set:
+      ingress.enabled: true
+      ingress.className: nginx-test
+    chart:
+      version: 1.0.0
+      appVersion: 1.0.0
+    asserts:
+      - matchSnapshot: { }
+  - it: should match snapshot of default values with old kubernetes ingress
+    set:
+      ingress.enabled: true
+      ingress.className: nginx-test
+    capabilities:
+      majorVersion: 1
+      minorVersion: 17
+    chart:
+      version: 1.0.0
+      appVersion: 1.0.0
+    asserts:
+      - matchSnapshot: { }

deploy/kubernetes/platform/signoz-charts/alertmanager/values.yaml

@@ -0,0 +1,189 @@
+# Default values for alertmanager.
+# This is a YAML-formatted file.
+# Declare variables to be passed into your templates.
+
+replicaCount: 1
+
+image:
+  repository: signoz/alertmanager
+  pullPolicy: IfNotPresent
+  # Overrides the image tag whose default is the chart appVersion.
+  tag: "0.5.0"
+
+extraArgs: {}
+
+imagePullSecrets: []
+nameOverride: ""
+fullnameOverride: ""
+
+serviceAccount:
+  # Specifies whether a service account should be created
+  create: true
+  # Annotations to add to the service account
+  annotations: {}
+  # The name of the service account to use.
+  # If not set and create is true, a name is generated using the fullname template
+  name:
+
+podSecurityContext:
+  fsGroup: 65534
+dnsConfig: {}
+  # nameservers:
+  #   - 1.2.3.4
+  # searches:
+  #   - ns1.svc.cluster-domain.example
+  #   - my.dns.search.suffix
+  # options:
+  #   - name: ndots
+  #     value: "2"
+  #   - name: edns0
+securityContext:
+  # capabilities:
+  #   drop:
+  #   - ALL
+  # readOnlyRootFilesystem: true
+  runAsUser: 65534
+  runAsNonRoot: true
+  runAsGroup: 65534
+
+additionalPeers: []
+
+service:
+  annotations: {}
+  type: ClusterIP
+  port: 9093
+  # if you want to force a specific nodePort. Must be use with service.type=NodePort
+  # nodePort:
+
+ingress:
+  enabled: false
+  className: ""
+  annotations: {}
+    # kubernetes.io/ingress.class: nginx
+    # kubernetes.io/tls-acme: "true"
+  hosts:
+    - host: alertmanager.domain.com
+      paths:
+        - path: /
+          pathType: ImplementationSpecific
+  tls: []
+  #  - secretName: chart-example-tls
+  #    hosts:
+  #      - alertmanager.domain.com
+
+resources: {}
+  # We usually recommend not to specify default resources and to leave this as a conscious
+  # choice for the user. This also increases chances charts run on environments with little
+  # resources, such as Minikube. If you do want to specify resources, uncomment the following
+  # lines, adjust them as necessary, and remove the curly braces after 'resources:'.
+  # limits:
+  #   cpu: 100m
+  #   memory: 128Mi
+  # requests:
+  #   cpu: 10m
+  #   memory: 32Mi
+
+nodeSelector: {}
+
+tolerations: []
+
+affinity: {}
+
+statefulSet:
+  annotations: {}
+
+podAnnotations: {}
+podLabels: {}
+
+# Ref: https://kubernetes.io/docs/tasks/run-application/configure-pdb/
+podDisruptionBudget: {}
+  # maxUnavailable: 1
+  # minAvailable: 1
+
+command: []
+
+persistence:
+  enabled: true
+  ## Persistent Volume Storage Class
+  ## If defined, storageClassName: <storageClass>
+  ## If set to "-", storageClassName: "", which disables dynamic provisioning
+  ## If undefined (the default) or set to null, no storageClassName spec is
+  ## set, choosing the default provisioner.
+  ##
+  # storageClass: "-"
+  accessModes:
+    - ReadWriteOnce
+  size: 100Mi
+
+config:
+  global: 
+    resolve_timeout: 1m
+    slack_api_url: 'https://hooks.slack.com/services/xxx'
+
+  templates:
+    - '/etc/alertmanager/*.tmpl'
+
+  receivers:
+  - name: 'slack-notifications'
+    slack_configs:
+    - channel: '#alerts'
+      send_resolved: true
+      icon_url: https://avatars3.githubusercontent.com/u/3380462
+      title: '{{ template "slack.title" . }}'
+      text: '{{ template "slack.text" . }}'
+
+
+  route:
+    receiver: 'slack-notifications'
+
+## Monitors ConfigMap changes and POSTs to a URL
+## Ref: https://github.com/jimmidyson/configmap-reload
+##
+configmapReload:
+  ## If false, the configmap-reload container will not be deployed
+  ##
+  enabled: false
+
+  ## configmap-reload container name
+  ##
+  name: configmap-reload
+
+  ## configmap-reload container image
+  ##
+  image:
+    repository: jimmidyson/configmap-reload
+    tag: v0.5.0
+    pullPolicy: IfNotPresent
+
+  ## configmap-reload resource requests and limits
+  ## Ref: http://kubernetes.io/docs/user-guide/compute-resources/
+  ##
+  resources: {}
+
+templates: 
+  title.tmpl: |-
+      {{ define "slack.title" }}
+      [{{ .Status | toUpper }}{{ if eq .Status "firing" }}:{{ .Alerts.Firing | len }}{{ end }}] {{ .CommonLabels.alertname }} for {{ .CommonLabels.job }}
+      {{- if gt (len .CommonLabels) (len .GroupLabels) -}}
+        {{" "}}(
+        {{- with .CommonLabels.Remove .GroupLabels.Names }}
+          {{- range $index, $label := .SortedPairs -}}
+            {{ if $index }}, {{ end }}
+            {{- $label.Name }}="{{ $label.Value -}}"
+          {{- end }}
+        {{- end -}}
+        )
+      {{- end }}
+      {{ end }}
+  text.tmpl: |-
+      {{ define "slack.text" }}
+      {{ range .Alerts -}}
+      *Alert:* {{ .Annotations.title }}{{ if .Labels.severity }} - `{{ .Labels.severity }}`{{ end }}
+
+      *Description:* {{ .Annotations.description }}
+
+      *Details:*
+        {{ range .Labels.SortedPairs }} • *{{ .Name }}:* `{{ .Value }}`
+        {{ end }}
+      {{ end }}
+      {{ end }}

deploy/kubernetes/platform/signoz-charts/flattener-processor/Chart.yaml

@@ -1,21 +0,0 @@
-apiVersion: v2
-name: flattener-processor
-description: A Helm chart for Kubernetes
-
-# A chart can be either an 'application' or a 'library' chart.
-#
-# Application charts are a collection of templates that can be packaged into versioned archives
-# to be deployed.
-#
-# Library charts provide useful utilities or functions for the chart developer. They're included as
-# a dependency of application charts to inject those utilities and functions into the rendering
-# pipeline. Library charts do not define any templates and therefore cannot be deployed.
-type: application
-
-# This is the chart version. This version number should be incremented each time you make changes
-# to the chart and its templates, including the app version.
-version: 0.3.4
-
-# This is the version number of the application being deployed. This version number should be
-# incremented each time you make changes to the application.
-appVersion: 0.3.4

deploy/kubernetes/platform/signoz-charts/flattener-processor/templates/deployment.yaml

@@ -1,65 +0,0 @@
-apiVersion: apps/v1
-kind: Deployment
-metadata:
-  name: {{ include "flattener-processor.fullname" . }}
-  labels:
-    {{- include "flattener-processor.labels" . | nindent 4 }}
-spec:
-  replicas: {{ .Values.replicaCount }}
-  selector:
-    matchLabels:
-      {{- include "flattener-processor.selectorLabels" . | nindent 6 }}
-  template:
-    metadata:
-      labels:
-        {{- include "flattener-processor.selectorLabels" . | nindent 8 }}
-    spec:
-    {{- with .Values.imagePullSecrets }}
-      imagePullSecrets:
-        {{- toYaml . | nindent 8 }}
-    {{- end }}
-      serviceAccountName: {{ include "flattener-processor.serviceAccountName" . }}
-      securityContext:
-        {{- toYaml .Values.podSecurityContext | nindent 8 }}
-      containers:
-        - name: {{ .Chart.Name }}
-          securityContext:
-            {{- toYaml .Values.securityContext | nindent 12 }}
-          image: "{{ .Values.image.repository }}:{{ .Chart.AppVersion }}"
-          imagePullPolicy: {{ .Values.image.pullPolicy }}
-          command:
-          - "/root/flattener"
-          ports:
-          - name: http
-            containerPort: 8080
-            protocol: TCP
-          env:
-          - name: KAFKA_BROKER
-            value: {{ .Values.configVars.KAFKA_BROKER }}
-          - name: KAFKA_INPUT_TOPIC
-            value: {{ .Values.configVars.KAFKA_INPUT_TOPIC }}
-          - name: KAFKA_OUTPUT_TOPIC
-            value: {{ .Values.configVars.KAFKA_OUTPUT_TOPIC }}
-            
-          # livenessProbe:
-          #   httpGet:
-          #     path: /
-          #     port: http
-          # readinessProbe:
-          #   httpGet:
-          #     path: /
-          #     port: http
-          resources:
-            {{- toYaml .Values.resources | nindent 12 }}
-      {{- with .Values.nodeSelector }}
-      nodeSelector:
-        {{- toYaml . | nindent 8 }}
-      {{- end }}
-    {{- with .Values.affinity }}
-      affinity:
-        {{- toYaml . | nindent 8 }}
-    {{- end }}
-    {{- with .Values.tolerations }}
-      tolerations:
-        {{- toYaml . | nindent 8 }}
-    {{- end }}

deploy/kubernetes/platform/signoz-charts/flattener-processor/templates/ingress.yaml

@@ -1,41 +0,0 @@
-{{- if .Values.ingress.enabled -}}
-{{- $fullName := include "flattener-processor.fullname" . -}}
-{{- $svcPort := .Values.service.port -}}
-{{- if semverCompare ">=1.14-0" .Capabilities.KubeVersion.GitVersion -}}
-apiVersion: networking.k8s.io/v1beta1
-{{- else -}}
-apiVersion: extensions/v1beta1
-{{- end }}
-kind: Ingress
-metadata:
-  name: {{ $fullName }}
-  labels:
-    {{- include "flattener-processor.labels" . | nindent 4 }}
-  {{- with .Values.ingress.annotations }}
-  annotations:
-    {{- toYaml . | nindent 4 }}
-  {{- end }}
-spec:
-{{- if .Values.ingress.tls }}
-  tls:
-  {{- range .Values.ingress.tls }}
-    - hosts:
-      {{- range .hosts }}
-        - {{ . | quote }}
-      {{- end }}
-      secretName: {{ .secretName }}
-  {{- end }}
-{{- end }}
-  rules:
-  {{- range .Values.ingress.hosts }}
-    - host: {{ .host | quote }}
-      http:
-        paths:
-        {{- range .paths }}
-          - path: {{ . }}
-            backend:
-              serviceName: {{ $fullName }}
-              servicePort: {{ $svcPort }}
-        {{- end }}
-  {{- end }}
-{{- end }}

deploy/kubernetes/platform/signoz-charts/flattener-processor/templates/service.yaml

@@ -1,15 +0,0 @@
-apiVersion: v1
-kind: Service
-metadata:
-  name: {{ include "flattener-processor.fullname" . }}
-  labels:
-    {{- include "flattener-processor.labels" . | nindent 4 }}
-spec:
-  type: {{ .Values.service.type }}
-  ports:
-    - port: {{ .Values.service.port }}
-      targetPort: http
-      protocol: TCP
-      name: http
-  selector:
-    {{- include "flattener-processor.selectorLabels" . | nindent 4 }}

deploy/kubernetes/platform/signoz-charts/flattener-processor/templates/tests/test-connection.yaml

@@ -1,15 +0,0 @@
-apiVersion: v1
-kind: Pod
-metadata:
-  name: "{{ include "flattener-processor.fullname" . }}-test-connection"
-  labels:
-    {{- include "flattener-processor.labels" . | nindent 4 }}
-  annotations:
-    "helm.sh/hook": test-success
-spec:
-  containers:
-    - name: wget
-      image: busybox
-      command: ['wget']
-      args: ['{{ include "flattener-processor.fullname" . }}:{{ .Values.service.port }}']
-  restartPolicy: Never

deploy/kubernetes/platform/signoz-charts/flattener-processor/values.yaml

@@ -1,74 +0,0 @@
-# Default values for flattener-processor.
-# This is a YAML-formatted file.
-# Declare variables to be passed into your templates.
-
-replicaCount: 1
-
-image:
-  repository: signoz/flattener-processor
-  pullPolicy: IfNotPresent
-
-imagePullSecrets: []
-nameOverride: ""
-fullnameOverride: ""
-
-
-configVars:
-  KAFKA_BROKER: signoz-kafka:9092
-  KAFKA_INPUT_TOPIC: otlp_spans
-  KAFKA_OUTPUT_TOPIC: flattened_spans
-
-serviceAccount:
-  # Specifies whether a service account should be created
-  create: false
-  # Annotations to add to the service account
-  annotations: {}
-  # The name of the service account to use.
-  # If not set and create is true, a name is generated using the fullname template
-  name:
-
-podSecurityContext: {}
-  # fsGroup: 2000
-
-securityContext: {}
-  # capabilities:
-  #   drop:
-  #   - ALL
-  # readOnlyRootFilesystem: true
-  # runAsNonRoot: true
-  # runAsUser: 1000
-
-service:
-  type: ClusterIP
-  port: 8080
-
-ingress:
-  enabled: false
-  annotations: {}
-    # kubernetes.io/ingress.class: nginx
-    # kubernetes.io/tls-acme: "true"
-  hosts:
-    - host: chart-example.local
-      paths: []
-  tls: []
-  #  - secretName: chart-example-tls
-  #    hosts:
-  #      - chart-example.local
-
-resources: {}
-  # We usually recommend not to specify default resources and to leave this as a conscious
-  # choice for the user. This also increases chances charts run on environments with little
-  # resources, such as Minikube. If you do want to specify resources, uncomment the following
-  # lines, adjust them as necessary, and remove the curly braces after 'resources:'.
-  # limits:
-  #   cpu: 100m
-  #   memory: 128Mi
-  # requests:
-  #   cpu: 100m
-  #   memory: 128Mi
-
-nodeSelector: {}
-
-tolerations: []
-
-affinity: {}

deploy/kubernetes/platform/signoz-charts/frontend/Chart.yaml

@@ -14,8 +14,8 @@ type: application
 
 # This is the chart version. This version number should be incremented each time you make changes
 # to the chart and its templates, including the app version.
-version: 0.3.4
+version: 0.5.3
 
 # This is the version number of the application being deployed. This version number should be
 # incremented each time you make changes to the application.
-appVersion: 0.3.4
+appVersion: 0.5.3

deploy/kubernetes/platform/signoz-charts/frontend/templates/config.yaml

@@ -24,6 +24,9 @@ data:
         index  index.html index.htm;
         try_files $uri $uri/ /index.html;
       }
+      location /api/alertmanager{
+        proxy_pass http://{{ .Values.config.alertmanagerUrl }}/api/v2;
+      }
       location /api {
         proxy_pass http://{{ .Values.config.queryServiceUrl }}/api;
       }

deploy/kubernetes/platform/signoz-charts/frontend/values.yaml

@@ -17,6 +17,7 @@ configVars: {}
 config:
   name: signoz-nginx-config
   queryServiceUrl: signoz-query-service:8080
+  alertmanagerUrl: alertmanager:9093
 
 serviceAccount:
   # Specifies whether a service account should be created

deploy/kubernetes/platform/signoz-charts/query-service/Chart.yaml

@@ -14,8 +14,8 @@ type: application
 
 # This is the chart version. This version number should be incremented each time you make changes
 # to the chart and its templates, including the app version.
-version: 0.3.4
+version: 0.5.3
 
 # This is the version number of the application being deployed. This version number should be
 # incremented each time you make changes to the application.
-appVersion: 0.3.4
+appVersion: 0.5.3

deploy/kubernetes/platform/signoz-charts/query-service/templates/prometheus-configmap.yaml

@@ -0,0 +1,33 @@
+apiVersion: v1
+kind: ConfigMap
+metadata:
+  name: prometheus-config
+data:
+  prometheus.yml: |
+    # 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://signoz-clickhouse:9000/?database=signoz_metrics&username=clickhouse_operator&password=clickhouse_operator_password
+

deploy/kubernetes/platform/signoz-charts/query-service/templates/statefulset.yaml

@@ -1,10 +1,11 @@
 apiVersion: apps/v1
-kind: Deployment
+kind: StatefulSet
 metadata:
   name: {{ include "query-service.fullname" . }}
   labels:
     {{- include "query-service.labels" . | nindent 4 }}
 spec:
+  serviceName: query-service
   replicas: {{ .Values.replicaCount }}
   selector:
     matchLabels:
@@ -14,19 +15,17 @@ spec:
       labels:
         {{- include "query-service.selectorLabels" . | nindent 8 }}
     spec:
-    {{- with .Values.imagePullSecrets }}
-      imagePullSecrets:
-        {{- toYaml . | nindent 8 }}
-    {{- end }}
-      serviceAccountName: {{ include "query-service.serviceAccountName" . }}
-      securityContext:
-        {{- toYaml .Values.podSecurityContext | nindent 8 }}
       containers:
         - name: {{ .Chart.Name }}
+        {{- with .Values.imagePullSecrets }}
+          imagePullSecrets:
+            {{- toYaml . | nindent 8 }}
+        {{- end }}
           securityContext:
             {{- toYaml .Values.securityContext | nindent 12 }}
           image: "{{ .Values.image.repository }}:{{ .Chart.AppVersion }}"
           imagePullPolicy: {{ .Values.image.pullPolicy }}
+          args: ["-config=/root/config/prometheus.yml"]
           ports:
             - name: http
               containerPort: 8080
@@ -38,7 +37,10 @@ spec:
             value: {{ .Values.configVars.DruidDatasource }}
           - name: STORAGE
             value: {{ .Values.configVars.STORAGE }}
-            
+          - name: ClickHouseUrl
+            value: {{ .Values.configVars.ClickHouseUrl}}
+          - name: GODEBUG
+            value: netdns=go
           # livenessProbe:
           #   httpGet:
           #     path: /
@@ -47,6 +49,13 @@ spec:
           #   httpGet:
           #     path: /
           #     port: http
+          volumeMounts:
+          - name: prometheus
+            mountPath: /root/config
+          - name: signoz-db
+            mountPath: /var/lib/signoz/
+          - name: dashboards
+            mountPath: /root/config/dashboards
           resources:
             {{- toYaml .Values.resources | nindent 12 }}
       {{- with .Values.nodeSelector }}
@@ -61,3 +70,18 @@ spec:
       tolerations:
         {{- toYaml . | nindent 8 }}
     {{- end }}
+      volumes:
+      - name: prometheus
+        configMap:
+          name: prometheus-config
+      - name: dashboards
+        emptyDir: {}
+
+  volumeClaimTemplates:
+  - metadata:
+      name: signoz-db
+    spec:
+      accessModes: [ "ReadWriteOnce" ]
+      resources:
+        requests:
+          storage: 1Gi

deploy/kubernetes/platform/signoz-charts/query-service/values.yaml

@@ -16,7 +16,8 @@ fullnameOverride: ""
 configVars:
   DruidClientUrl: http://signoz-druid-router:8888
   DruidDatasource: flattened_spans
-  STORAGE: druid
+  ClickHouseUrl: http://signoz-clickhouse:9000?username=clickhouse_operator&password=clickhouse_operator_password
+  STORAGE: clickhouse
   POSTHOG_API_KEY: "H-htDCae7CR3RV57gUzmol6IAKtm5IMCvbcm_fwnL-w"
 
 

deploy/kubernetes/platform/templates/clickhouse-config.yaml

@@ -0,0 +1,33 @@
+apiVersion: v1
+kind: ConfigMap
+metadata:
+  name: initdb-config
+data:
+  init-db.sql: |-
+    CREATE TABLE IF NOT EXISTS signoz_index (
+    timestamp DateTime64(9) CODEC(Delta, ZSTD(1)),
+    traceID String CODEC(ZSTD(1)),
+    spanID String CODEC(ZSTD(1)),
+    parentSpanID String CODEC(ZSTD(1)),
+    serviceName LowCardinality(String) CODEC(ZSTD(1)),
+    name LowCardinality(String) CODEC(ZSTD(1)),
+    kind Int32 CODEC(ZSTD(1)),
+    durationNano UInt64 CODEC(ZSTD(1)),
+    tags Array(String) CODEC(ZSTD(1)),
+    tagsKeys Array(String) CODEC(ZSTD(1)),
+    tagsValues Array(String) CODEC(ZSTD(1)),
+    statusCode Int64 CODEC(ZSTD(1)),
+    references String CODEC(ZSTD(1)),
+    externalHttpMethod Nullable(String) CODEC(ZSTD(1)),
+    externalHttpUrl Nullable(String) CODEC(ZSTD(1)),
+    component Nullable(String) CODEC(ZSTD(1)),
+    dbSystem Nullable(String) CODEC(ZSTD(1)),
+    dbName Nullable(String) CODEC(ZSTD(1)),
+    dbOperation Nullable(String) CODEC(ZSTD(1)),
+    peerService Nullable(String) CODEC(ZSTD(1)),
+    INDEX idx_tagsKeys tagsKeys TYPE bloom_filter(0.01) GRANULARITY 64,
+    INDEX idx_tagsValues tagsValues TYPE bloom_filter(0.01) GRANULARITY 64,
+    INDEX idx_duration durationNano TYPE minmax GRANULARITY 1
+    ) ENGINE MergeTree()
+    PARTITION BY toDate(timestamp)
+    ORDER BY (serviceName, -toUnixTimestamp(timestamp))

deploy/kubernetes/platform/templates/clickhouse-instance.yaml

@@ -0,0 +1,104 @@
+{{ if (eq (.Values.cloud | toString) "gcp" )}}
+apiVersion: storage.k8s.io/v1
+kind: StorageClass
+metadata:
+  name: gce-resizable
+provisioner: kubernetes.io/gce-pd
+parameters:
+  type: pd-standard
+  fstype: ext4
+  replication-type: none
+reclaimPolicy: Retain
+#volumeBindingMode: Immediate
+allowVolumeExpansion: true
+{{- else if (eq (.Values.cloud | toString) "aws") }}
+#
+# AWS resizable disk example
+#
+apiVersion: storage.k8s.io/v1
+kind: StorageClass
+metadata:
+  name: gp2-resizable
+provisioner: kubernetes.io/aws-ebs
+parameters:
+  type: gp2
+reclaimPolicy: Retain
+#volumeBindingMode: Immediate
+allowVolumeExpansion: true
+{{- end }}
+---
+apiVersion: "clickhouse.altinity.com/v1"
+kind: "ClickHouseInstallation"
+metadata:
+  name: signoz
+spec:
+  defaults:
+    templates:
+      dataVolumeClaimTemplate: default-volume-claim
+      # logVolumeClaimTemplate: default-volume-claim
+      serviceTemplate: chi-service-template
+  configuration:
+    zookeeper:
+      nodes:
+        - host: signoz-zookeeper
+          port: 2181
+      session_timeout_ms: 6000
+    clusters:
+      - name: cluster
+        # Templates are specified for this cluster explicitly
+        templates:
+          dataVolumeClaimTemplate: default-volume-claim
+          # logVolumeClaimTemplate: default-volume-claim
+          podTemplate: pod-template-with-volume
+        layout:
+          shardsCount: 1
+          replicasCount: 1
+  templates:
+    hostTemplates:
+      - name: port-distribution
+        portDistribution:
+          - type: ClusterScopeIndex
+        spec:
+          tcpPort: 9000
+          httpPort: 8123
+          interserverHTTPPort: 9009
+
+    podTemplates:
+      - name: pod-template-with-volume
+        spec:
+          containers:
+            - name: clickhouse
+              image: yandex/clickhouse-server:21.7
+              volumeMounts:
+                - name: default-volume-claim
+                  mountPath: /var/lib/clickhouse
+                - name: initdb
+                  mountPath: /docker-entrypoint-initdb.d
+          volumes:
+            - name: initdb
+              configMap:
+                name: initdb-config
+    serviceTemplates:
+      - name: chi-service-template
+        generateName: signoz-clickhouse
+        spec:
+          ports:
+            - name: http
+              port: 8123
+            - name: tcp
+              port: 9000
+          type: {{ .Values.clickhouseOperator.serviceType }}
+    volumeClaimTemplates:
+      - name: default-volume-claim
+        reclaimPolicy: Retain
+        spec:
+          {{- if (eq (.Values.cloud | toString) "gcp" )}}
+          storageClassName: gce-resizable
+          {{- else if (eq (.Values.cloud | toString) "aws") }}
+          storageClassName: gp2-resizable
+          {{- end }}
+          accessModes:
+            - ReadWriteOnce
+          resources:
+            requests:
+              storage: {{ .Values.clickhouseOperator.storage | quote }}

deploy/kubernetes/platform/templates/clickhouse-operator/clusterrole.yaml

@@ -0,0 +1,157 @@
+{{- if .Values.clickhouseOperator.enabled }}
+# Template Parameters:
+#
+# NAMESPACE=posthog
+# COMMENT=#
+# ROLE_KIND=ClusterRole
+# ROLE_NAME=clickhouse-operator-posthog
+# ROLE_BINDING_KIND=ClusterRoleBinding
+# ROLE_BINDING_NAME=clickhouse-operator-posthog
+#
+apiVersion: rbac.authorization.k8s.io/v1
+kind: ClusterRole
+metadata:
+  name: clickhouse-operator-posthog
+  namespace: {{ .Values.clickhouseOperator.namespace | default .Release.Namespace }}
+rules:
+- apiGroups:
+    - ""
+  resources:
+    - configmaps
+    - services
+  verbs:
+    - create
+    - delete
+    - get
+    - patch
+    - update
+    - list
+    - watch
+- apiGroups:
+    - ""
+  resources:
+    - endpoints
+  verbs:
+    - get
+    - list
+    - watch
+- apiGroups:
+    - ""
+  resources:
+    - events
+  verbs:
+    - create
+- apiGroups:
+    - ""
+  resources:
+    - persistentvolumeclaims
+  verbs:
+    - delete
+    - get
+    - list
+    - patch
+    - update
+    - watch
+- apiGroups:
+    - ""
+  resources:
+    - persistentvolumes
+    - pods
+  verbs:
+    - get
+    - list
+    - patch
+    - update
+    - watch
+- apiGroups:
+    - apps
+  resources:
+    - statefulsets
+  verbs:
+    - create
+    - delete
+    - get
+    - patch
+    - update
+    - list
+    - watch
+- apiGroups:
+    - apps
+  resources:
+    - replicasets
+  verbs:
+    - delete
+    - get
+    - patch
+    - update
+- apiGroups:
+    - apps
+  resourceNames:
+    - clickhouse-operator
+  resources:
+    - deployments
+  verbs:
+    - get
+    - patch
+    - update
+    - delete
+- apiGroups:
+    - policy
+  resources:
+    - poddisruptionbudgets
+  verbs:
+    - create
+    - delete
+    - get
+    - patch
+    - update
+    - list
+    - watch
+- apiGroups:
+    - clickhouse.altinity.com
+  resources:
+    - clickhouseinstallations
+  verbs:
+    - delete
+    - get
+    - patch
+    - update
+- apiGroups:
+    - clickhouse.altinity.com
+  resources:
+    - clickhouseinstallations
+    - clickhouseinstallationtemplates
+    - clickhouseoperatorconfigurations
+  verbs:
+    - get
+    - list
+    - watch
+- apiGroups:
+    - clickhouse.altinity.com
+  resources:
+    - clickhouseinstallations/finalizers
+    - clickhouseinstallationtemplates/finalizers
+    - clickhouseoperatorconfigurations/finalizers
+  verbs:
+    - update
+- apiGroups:
+    - clickhouse.altinity.com
+  resources:
+    - clickhouseinstallations/status
+    - clickhouseinstallationtemplates/status
+    - clickhouseoperatorconfigurations/status
+  verbs:
+    - create
+    - delete
+    - get
+    - update
+    - patch
+- apiGroups:
+    - ""
+  resources:
+    - secrets
+  verbs:
+    - get
+    - list
+
+{{- end }}

deploy/kubernetes/platform/templates/clickhouse-operator/clusterrolebinding.yaml

@@ -0,0 +1,18 @@
+{{- if .Values.clickhouseOperator.enabled }}
+# Setup ClusterRoleBinding between ClusterRole and ServiceAccount.
+# ClusterRoleBinding is namespace-less and must have unique name
+apiVersion: rbac.authorization.k8s.io/v1
+kind: ClusterRoleBinding
+metadata:
+  name: clickhouse-operator-posthog
+  namespace: {{ .Values.clickhouseOperator.namespace | default .Release.Namespace }}
+roleRef:
+  apiGroup: rbac.authorization.k8s.io
+  kind: ClusterRole
+  name: clickhouse-operator-posthog
+subjects:
+- kind: ServiceAccount
+  name: clickhouse-operator
+  namespace: {{ .Values.clickhouseOperator.namespace | default .Release.Namespace }}
+
+{{- end }}

deploy/kubernetes/platform/templates/clickhouse-operator/configmap.yaml

@@ -0,0 +1,418 @@
+{{- if .Values.clickhouseOperator.enabled }}
+# Template Parameters:
+#
+# NAME=etc-clickhouse-operator-files
+# NAMESPACE=posthog
+# COMMENT=
+#
+apiVersion: v1
+kind: ConfigMap
+metadata:
+  name: etc-clickhouse-operator-files
+  namespace: {{ .Values.clickhouseOperator.namespace | default .Release.Namespace }}
+  labels:
+    app: clickhouse-operator
+data:
+  config.yaml: |
+    ################################################
+    ##
+    ## Watch Namespaces Section
+    ##
+    ################################################
+    
+    # List of namespaces where clickhouse-operator watches for events.
+    # Concurrently running operators should watch on different namespaces
+    #watchNamespaces: ["dev", "test"]
+    watchNamespaces: []
+    
+    ################################################
+    ##
+    ## Additional Configuration Files Section
+    ##
+    ################################################
+    
+    # Path to folder where ClickHouse configuration files common for all instances within CHI are located.
+    chCommonConfigsPath: config.d
+    
+    # Path to folder where ClickHouse configuration files unique for each instance (host) within CHI are located.
+    chHostConfigsPath: conf.d
+    
+    # Path to folder where ClickHouse configuration files with users settings are located.
+    # Files are common for all instances within CHI
+    chUsersConfigsPath: users.d
+    
+    # Path to folder where ClickHouseInstallation .yaml manifests are located.
+    # Manifests are applied in sorted alpha-numeric order
+    chiTemplatesPath: templates.d
+    
+    ################################################
+    ##
+    ## Cluster Create/Update/Delete Objects Section
+    ##
+    ################################################
+    
+    # How many seconds to wait for created/updated StatefulSet to be Ready
+    statefulSetUpdateTimeout: 300
+    
+    # How many seconds to wait between checks for created/updated StatefulSet status
+    statefulSetUpdatePollPeriod: 5
+    
+    # What to do in case created StatefulSet is not in Ready after `statefulSetUpdateTimeout` seconds
+    # Possible options:
+    # 1. abort - do nothing, just break the process and wait for admin
+    # 2. delete - delete newly created problematic StatefulSet
+    # 3. ignore - ignore error, pretend nothing happened and move on to the next StatefulSet
+    onStatefulSetCreateFailureAction: ignore
+    
+    # What to do in case updated StatefulSet is not in Ready after `statefulSetUpdateTimeout` seconds
+    # Possible options:
+    # 1. abort - do nothing, just break the process and wait for admin
+    # 2. rollback - delete Pod and rollback StatefulSet to previous Generation.
+    # Pod would be recreated by StatefulSet based on rollback-ed configuration
+    # 3. ignore - ignore error, pretend nothing happened and move on to the next StatefulSet
+    onStatefulSetUpdateFailureAction: rollback
+    
+    ################################################
+    ##
+    ## ClickHouse Settings Section
+    ##
+    ################################################
+    
+    # Default values for ClickHouse user configuration
+    # 1. user/profile - string
+    # 2. user/quota - string
+    # 3. user/networks/ip - multiple strings
+    # 4. user/password - string
+    chConfigUserDefaultProfile: default
+    chConfigUserDefaultQuota: default
+    chConfigUserDefaultNetworksIP:
+      - "::1"
+      - "127.0.0.1"
+    chConfigUserDefaultPassword: "default"
+    
+    # Default host_regexp to limit network connectivity from outside
+    chConfigNetworksHostRegexpTemplate: "(chi-{chi}-[^.]+\\d+-\\d+|clickhouse\\-{chi})\\.{namespace}\\.svc\\.cluster\\.local$"
+    
+    ################################################
+    ##
+    ## Access to ClickHouse instances
+    ##
+    ################################################
+    
+    # ClickHouse credentials (username, password and port) to be used by operator to connect to ClickHouse instances
+    # for:
+    # 1. Metrics requests
+    # 2. Schema maintenance
+    # 3. DROP DNS CACHE
+    # User with such credentials can be specified in additional ClickHouse .xml config files,
+    # located in `chUsersConfigsPath` folder
+    chUsername: "clickhouse_operator"
+    chPassword: "clickhouse_operator_password"
+    
+    # Location of k8s Secret with username and password to be used by operator to connect to ClickHouse instances
+    # Can be used instead of explicitly specified username and password
+    chCredentialsSecretNamespace: ""
+    chCredentialsSecretName: ""
+    
+    # Port where to connect to ClickHouse instances to
+    chPort: 8123
+    
+    ################################################
+    ##
+    ## Log parameters
+    ##
+    ################################################
+    
+    logtostderr: "true"
+    alsologtostderr: "false"
+    v: "1"
+    stderrthreshold: ""
+    vmodule: ""
+    log_backtrace_at: ""
+    
+    ################################################
+    ##
+    ## Runtime parameters
+    ##
+    ################################################
+    
+    # Max number of concurrent reconciles in progress
+    reconcileThreadsNumber: 10
+    reconcileWaitExclude: true
+    reconcileWaitInclude: false
+    
+    ################################################
+    ##
+    ## Labels management parameters
+    ##
+    ################################################
+    
+    # When propagating labels from the chi's `metadata.labels` section to child objects' `metadata.labels`,
+    # exclude labels from the following list:
+    #excludeFromPropagationLabels:
+    #  - "labelA"
+    #  - "labelB"
+    
+    # Whether to append *Scope* labels to StatefulSet and Pod.
+    # Full list of available *scope* labels check in labeler.go
+    #  LabelShardScopeIndex
+    #  LabelReplicaScopeIndex
+    #  LabelCHIScopeIndex
+    #  LabelCHIScopeCycleSize
+    #  LabelCHIScopeCycleIndex
+    #  LabelCHIScopeCycleOffset
+    #  LabelClusterScopeIndex
+    #  LabelClusterScopeCycleSize
+    #  LabelClusterScopeCycleIndex
+    #  LabelClusterScopeCycleOffset
+    appendScopeLabels: "no"
+    
+    ################################################
+    ##
+    ## Pod management parameters
+    ##
+    ################################################
+    # Grace period for Pod termination.
+    # How many seconds to wait between sending
+    # SIGTERM and SIGKILL during Pod termination process.
+    # Increase this number is case of slow shutdown.
+    terminationGracePeriod: 30
+
+---
+
+# Template Parameters:
+#
+# NAME=etc-clickhouse-operator-confd-files
+# NAMESPACE=posthog
+# COMMENT=
+#
+apiVersion: v1
+kind: ConfigMap
+metadata:
+  name: etc-clickhouse-operator-confd-files
+  namespace: {{ .Values.clickhouseOperator.namespace | default .Release.Namespace }}
+  labels:
+    app: clickhouse-operator
+data:
+
+---
+
+# Template Parameters:
+#
+# NAME=etc-clickhouse-operator-configd-files
+# NAMESPACE=posthog
+# COMMENT=
+#
+apiVersion: v1
+kind: ConfigMap
+metadata:
+  name: etc-clickhouse-operator-configd-files
+  namespace: {{ .Values.clickhouseOperator.namespace | default .Release.Namespace }}
+  labels:
+    app: clickhouse-operator
+data:
+  01-clickhouse-01-listen.xml: |
+    <yandex>
+        <!-- Listen wildcard address to allow accepting connections from other containers and host network. -->
+        <listen_host>::</listen_host>
+        <listen_host>0.0.0.0</listen_host>
+        <listen_try>1</listen_try>
+    </yandex>
+
+  01-clickhouse-02-logger.xml: |
+    <yandex>
+        <logger>
+            <!-- Possible levels: https://github.com/pocoproject/poco/blob/develop/Foundation/include/Poco/Logger.h#L105 -->
+            <level>debug</level>
+            <log>/var/log/clickhouse-server/clickhouse-server.log</log>
+            <errorlog>/var/log/clickhouse-server/clickhouse-server.err.log</errorlog>
+            <size>1000M</size>
+            <count>10</count>
+            <!-- Default behavior is autodetection (log to console if not daemon mode and is tty) -->
+            <console>1</console>
+        </logger>
+    </yandex>
+
+  01-clickhouse-03-query_log.xml: |
+    <yandex>
+        <query_log replace="1">
+            <database>system</database>
+            <table>query_log</table>
+            <engine>Engine = MergeTree PARTITION BY event_date ORDER BY event_time TTL event_date + interval 30 day</engine>
+            <flush_interval_milliseconds>7500</flush_interval_milliseconds>
+        </query_log>
+        <query_thread_log remove="1"/>
+    </yandex>
+
+  01-clickhouse-04-part_log.xml: |
+    <yandex>
+        <part_log replace="1">
+            <database>system</database>
+            <table>part_log</table>
+            <engine>Engine = MergeTree PARTITION BY event_date ORDER BY event_time TTL event_date + interval 30 day</engine>
+            <flush_interval_milliseconds>7500</flush_interval_milliseconds>
+        </part_log>
+    </yandex>
+
+---
+
+# Template Parameters:
+#
+# NAME=etc-clickhouse-operator-templatesd-files
+# NAMESPACE=posthog
+# COMMENT=
+#
+apiVersion: v1
+kind: ConfigMap
+metadata:
+  name: etc-clickhouse-operator-templatesd-files
+  namespace: {{ .Values.clickhouseOperator.namespace | default .Release.Namespace }}
+  labels:
+    app: clickhouse-operator
+data:
+  001-templates.json.example: |
+    {
+      "apiVersion": "clickhouse.altinity.com/v1",
+      "kind": "ClickHouseInstallationTemplate",
+      "metadata": {
+        "name": "01-default-volumeclaimtemplate"
+      },
+      "spec": {
+        "templates": {
+          "volumeClaimTemplates": [
+            {
+              "name": "chi-default-volume-claim-template",
+              "spec": {
+                "accessModes": [
+                  "ReadWriteOnce"
+                ],
+                "resources": {
+                  "requests": {
+                    "storage": "2Gi"
+                  }
+                }
+              }
+            }
+          ],
+          "podTemplates": [
+            {
+              "name": "chi-default-oneperhost-pod-template",
+              "distribution": "OnePerHost",
+              "spec": {
+                "containers" : [
+                  {
+                    "name": "clickhouse",
+                    "image": "yandex/clickhouse-server:19.3.7",
+                    "ports": [
+                      {
+                        "name": "http",
+                        "containerPort": 8123
+                      },
+                      {
+                        "name": "client",
+                        "containerPort": 9000
+                      },
+                      {
+                        "name": "interserver",
+                        "containerPort": 9009
+                      }
+                    ]
+                  }
+                ]
+              }
+            }
+          ]
+        }
+      }
+    }
+
+  default-pod-template.yaml.example: |
+    apiVersion: "clickhouse.altinity.com/v1"
+    kind: "ClickHouseInstallationTemplate"
+    metadata:
+      name: "default-oneperhost-pod-template"
+    spec:
+      templates:
+        podTemplates:
+          - name: default-oneperhost-pod-template
+            distribution: "OnePerHost"
+  default-storage-template.yaml.example: |
+    apiVersion: "clickhouse.altinity.com/v1"
+    kind: "ClickHouseInstallationTemplate"
+    metadata:
+      name: "default-storage-template-2Gi"
+    spec:
+      templates:
+        volumeClaimTemplates:
+          - name: default-storage-template-2Gi
+            spec:
+              accessModes:
+                - ReadWriteOnce
+              resources:
+                requests:
+                  storage: 2Gi
+
+  readme: |
+    Templates in this folder are packaged with an operator and available via 'useTemplate'
+
+---
+
+# Template Parameters:
+#
+# NAME=etc-clickhouse-operator-usersd-files
+# NAMESPACE=posthog
+# COMMENT=
+#
+apiVersion: v1
+kind: ConfigMap
+metadata:
+  name: etc-clickhouse-operator-usersd-files
+  namespace: {{ .Values.clickhouseOperator.namespace | default .Release.Namespace }}
+  labels:
+    app: clickhouse-operator
+data:
+  01-clickhouse-user.xml: |
+    <yandex>
+        <users>
+            <clickhouse_operator>
+                <networks>
+                    <ip>127.0.0.1</ip>
+                    <ip>0.0.0.0/0</ip>
+                    <ip>::/0</ip>
+                </networks>
+                <password_sha256_hex>716b36073a90c6fe1d445ac1af85f4777c5b7a155cea359961826a030513e448</password_sha256_hex>
+                <profile>clickhouse_operator</profile>
+                <quota>default</quota>
+            </clickhouse_operator>
+        </users>
+        <profiles>
+            <clickhouse_operator>
+                <log_queries>0</log_queries>
+                <skip_unavailable_shards>1</skip_unavailable_shards>
+                <http_connection_timeout>10</http_connection_timeout>
+            </clickhouse_operator>
+        </profiles>
+    </yandex>
+
+  02-clickhouse-default-profile.xml: |
+    <yandex>
+      <profiles>
+        <default>
+          <log_queries>1</log_queries>
+          <connect_timeout_with_failover_ms>1000</connect_timeout_with_failover_ms>
+          <distributed_aggregation_memory_efficient>1</distributed_aggregation_memory_efficient>
+          <parallel_view_processing>1</parallel_view_processing>
+        </default>
+      </profiles>
+    </yandex>
+  03-database-ordinary.xml: |
+    <!--  Remove it for ClickHouse versions before 20.4 -->
+    <yandex>
+        <profiles>
+            <default>
+                <default_database_engine>Ordinary</default_database_engine>
+            </default>
+        </profiles>
+    </yandex>
+
+{{- end }}

deploy/kubernetes/platform/templates/clickhouse-operator/deployment.yaml

@@ -0,0 +1,129 @@
+{{- if .Values.clickhouseOperator.enabled }}
+# Template Parameters:
+#
+# NAMESPACE=posthog
+# COMMENT=
+# OPERATOR_IMAGE=altinity/clickhouse-operator:latest
+# METRICS_EXPORTER_IMAGE=altinity/metrics-exporter:latest
+#
+# Setup Deployment for clickhouse-operator
+# Deployment would be created in kubectl-specified namespace
+kind: Deployment
+apiVersion: apps/v1
+metadata:
+  name: clickhouse-operator
+  namespace: {{ .Values.clickhouseOperator.namespace | default .Release.Namespace }}
+  labels:
+    app: clickhouse-operator
+spec:
+  replicas: 1
+  selector:
+    matchLabels:
+      app: clickhouse-operator
+  template:
+    metadata:
+      labels:
+        app: clickhouse-operator
+      annotations:
+        prometheus.io/port: '8888'
+        prometheus.io/scrape: 'true'
+    spec:
+      serviceAccountName: clickhouse-operator
+      volumes:
+        - name: etc-clickhouse-operator-folder
+          configMap:
+            name: etc-clickhouse-operator-files
+        - name: etc-clickhouse-operator-confd-folder
+          configMap:
+            name: etc-clickhouse-operator-confd-files
+        - name: etc-clickhouse-operator-configd-folder
+          configMap:
+            name: etc-clickhouse-operator-configd-files
+        - name: etc-clickhouse-operator-templatesd-folder
+          configMap:
+            name: etc-clickhouse-operator-templatesd-files
+        - name: etc-clickhouse-operator-usersd-folder
+          configMap:
+            name: etc-clickhouse-operator-usersd-files
+      containers:
+        - name: clickhouse-operator
+          image: altinity/clickhouse-operator:latest
+          imagePullPolicy: Always
+          volumeMounts:
+            - name: etc-clickhouse-operator-folder
+              mountPath: /etc/clickhouse-operator
+            - name: etc-clickhouse-operator-confd-folder
+              mountPath: /etc/clickhouse-operator/conf.d
+            - name: etc-clickhouse-operator-configd-folder
+              mountPath: /etc/clickhouse-operator/config.d
+            - name: etc-clickhouse-operator-templatesd-folder
+              mountPath: /etc/clickhouse-operator/templates.d
+            - name: etc-clickhouse-operator-usersd-folder
+              mountPath: /etc/clickhouse-operator/users.d
+          env:
+            # Pod-specific
+            # spec.nodeName: ip-172-20-52-62.ec2.internal
+            - name: OPERATOR_POD_NODE_NAME
+              valueFrom:
+                fieldRef:
+                  fieldPath: spec.nodeName
+            # metadata.name: clickhouse-operator-6f87589dbb-ftcsf
+            - name: OPERATOR_POD_NAME
+              valueFrom:
+                fieldRef:
+                  fieldPath: metadata.name
+            # metadata.namespace: kube-system
+            - name: OPERATOR_POD_NAMESPACE
+              valueFrom:
+                fieldRef:
+                  fieldPath: metadata.namespace
+            # status.podIP: 100.96.3.2
+            - name: OPERATOR_POD_IP
+              valueFrom:
+                fieldRef:
+                  fieldPath: status.podIP
+            # spec.serviceAccount: clickhouse-operator
+            # spec.serviceAccountName: clickhouse-operator
+            - name: OPERATOR_POD_SERVICE_ACCOUNT
+              valueFrom:
+                fieldRef:
+                  fieldPath: spec.serviceAccountName
+
+            # Container-specific
+            - name: OPERATOR_CONTAINER_CPU_REQUEST
+              valueFrom:
+                resourceFieldRef:
+                  containerName: clickhouse-operator
+                  resource: requests.cpu
+            - name: OPERATOR_CONTAINER_CPU_LIMIT
+              valueFrom:
+                resourceFieldRef:
+                  containerName: clickhouse-operator
+                  resource: limits.cpu
+            - name: OPERATOR_CONTAINER_MEM_REQUEST
+              valueFrom:
+                resourceFieldRef:
+                  containerName: clickhouse-operator
+                  resource: requests.memory
+            - name: OPERATOR_CONTAINER_MEM_LIMIT
+              valueFrom:
+                resourceFieldRef:
+                  containerName: clickhouse-operator
+                  resource: limits.memory
+
+        - name: metrics-exporter
+          image: altinity/metrics-exporter:latest
+          imagePullPolicy: Always
+          volumeMounts:
+            - name: etc-clickhouse-operator-folder
+              mountPath: /etc/clickhouse-operator
+            - name: etc-clickhouse-operator-confd-folder
+              mountPath: /etc/clickhouse-operator/conf.d
+            - name: etc-clickhouse-operator-configd-folder
+              mountPath: /etc/clickhouse-operator/config.d
+            - name: etc-clickhouse-operator-templatesd-folder
+              mountPath: /etc/clickhouse-operator/templates.d
+            - name: etc-clickhouse-operator-usersd-folder
+              mountPath: /etc/clickhouse-operator/users.d
+
+{{- end }}

deploy/kubernetes/platform/templates/clickhouse-operator/service.yaml

@@ -0,0 +1,26 @@
+{{- if .Values.clickhouseOperator.enabled }}
+# Template Parameters:
+#
+# NAMESPACE=posthog
+# COMMENT=
+#
+# Setup ClusterIP Service to provide monitoring metrics for Prometheus
+# Service would be created in kubectl-specified namespace
+# In order to get access outside of k8s it should be exposed as:
+# kubectl --namespace prometheus port-forward service/prometheus 9090
+# and point browser to localhost:9090
+kind: Service
+apiVersion: v1
+metadata:
+  name: clickhouse-operator-metrics
+  namespace: {{ .Values.clickhouseOperator.namespace | default .Release.Namespace }}
+  labels:
+    app: clickhouse-operator
+spec:
+  ports:
+    - port: 8888
+      name: clickhouse-operator-metrics
+  selector:
+    app: clickhouse-operator
+
+{{- end }}

deploy/kubernetes/platform/templates/clickhouse-operator/serviceaccount.yaml

@@ -0,0 +1,15 @@
+{{- if .Values.clickhouseOperator.enabled }}
+# Template Parameters:
+#
+# COMMENT=
+# NAMESPACE=posthog
+# NAME=clickhouse-operator
+#
+# Setup ServiceAccount
+apiVersion: v1
+kind: ServiceAccount
+metadata:
+  name: clickhouse-operator
+  namespace: {{ .Values.clickhouseOperator.namespace | default .Release.Namespace }}
+
+{{- end }}

deploy/kubernetes/platform/templates/otel-collector-metrics/otel-collector-metrics-config.yaml

@@ -0,0 +1,53 @@
+apiVersion: v1
+kind: ConfigMap
+metadata:
+  name: otel-collector-metrics-conf
+  labels:
+    app: opentelemetry
+    component: otel-collector-metrics-conf
+data:
+  otel-collector-metrics-config: |
+    receivers:
+      otlp:
+        protocols:
+          grpc:
+          http:
+
+      # Data sources: metrics
+      prometheus:
+        config:
+          scrape_configs:
+            - job_name: "otel-collector"
+              scrape_interval: 30s
+              static_configs:
+                - targets: ["otel-collector:8889"]
+    processors:
+      batch:
+        send_batch_size: 1000
+        timeout: 10s
+      memory_limiter:
+        # Same as --mem-ballast-size-mib CLI argument
+        ballast_size_mib: 683
+        # 80% of maximum memory up to 2G
+        limit_mib: 1500
+        # 25% of limit up to 2G
+        spike_limit_mib: 512
+        check_interval: 5s
+      # queued_retry:
+      #   num_workers: 4
+      #   queue_size: 100
+      #   retry_on_failure: true
+    extensions:
+      health_check: {}
+      zpages: {}
+    exporters:
+      clickhousemetricswrite:
+        endpoint: tcp://signoz-clickhouse:9000/?database=signoz_metrics&username=clickhouse_operator&password=clickhouse_operator_password
+
+    service:
+      extensions: [health_check, zpages]
+      pipelines:
+        metrics:
+          receivers: [otlp, prometheus]
+          processors: [batch]
+          exporters: [clickhousemetricswrite]

deploy/kubernetes/platform/templates/otel-collector-metrics/otel-collector-metrics-deployment.yaml

@@ -0,0 +1,72 @@
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: otel-collector-metrics
+  labels:
+    app: opentelemetry
+    component: otel-collector-metrics
+spec:
+  selector:
+    matchLabels:
+      app: opentelemetry
+      component: otel-collector-metrics
+  minReadySeconds: 5
+  progressDeadlineSeconds: 120
+  replicas: 1 #TODO - adjust this to your own requirements
+  template:
+    metadata:
+      labels:
+        app: opentelemetry
+        component: otel-collector-metrics
+    spec:
+      containers:
+      - command:
+          - "/otelcontribcol"
+          - "--config=/conf/otel-collector-metrics-config.yaml"
+#           Memory Ballast size should be max 1/3 to 1/2 of memory.
+          - "--mem-ballast-size-mib=683"
+        image: signoz/otelcontribcol:0.4.2
+        name: otel-collector
+        resources:
+          limits:
+            cpu: 1
+            memory: 2Gi
+          requests:
+            cpu: 200m
+            memory: 400Mi
+        ports:
+        - containerPort: 55679 # Default endpoint for ZPages.
+        - containerPort: 55680 # Default endpoint for OpenTelemetry receiver.
+        - containerPort: 55681 # Default endpoint for OpenTelemetry HTTP/1.0 receiver.
+        - containerPort: 4317 # Default endpoint for OpenTelemetry GRPC receiver.
+        - containerPort: 14250 # Default endpoint for Jaeger GRPC receiver.
+        - containerPort: 14268 # Default endpoint for Jaeger HTTP receiver.
+        - containerPort: 9411 # Default endpoint for Zipkin receiver.
+        - containerPort: 8888  # Default endpoint for querying metrics.
+        volumeMounts:
+        - name: otel-collector-metrics-config-vol
+          mountPath: /conf
+#        - name: otel-collector-secrets
+#          mountPath: /secrets
+        livenessProbe:
+          httpGet:
+            path: /
+            port: 13133 # Health Check extension default port.
+        readinessProbe:
+          httpGet:
+            path: /
+            port: 13133 # Health Check extension default port.
+      volumes:
+        - configMap:
+            name: otel-collector-metrics-conf
+            items:
+              - key: otel-collector-metrics-config
+                path: otel-collector-metrics-config.yaml
+          name: otel-collector-metrics-config-vol
+#        - secret:
+#            name: otel-collector-secrets
+#            items:
+#              - key: cert.pem
+#                path: cert.pem
+#              - key: key.pem
+#                path: key.pem

deploy/kubernetes/platform/templates/otel-collector-metrics/otel-collector-metrics-service.yaml

@@ -0,0 +1,31 @@
+apiVersion: v1
+kind: Service
+metadata:
+  name: otel-collector-metrics
+  labels:
+    app: opentelemetry
+    component: otel-collector-metrics
+spec:
+  ports:
+  - name: otlp # Default endpoint for OpenTelemetry receiver.
+    port: 55680
+    protocol: TCP
+    targetPort: 55680
+  - name: otlp-http-legacy # Default endpoint for OpenTelemetry receiver.
+    port: 55681
+    protocol: TCP
+    targetPort: 55681
+  - name: otlp-grpc # Default endpoint for OpenTelemetry receiver.
+    port: 4317
+    protocol: TCP
+    targetPort: 4317
+  - name: jaeger-grpc # Default endpoing for Jaeger gRPC receiver
+    port: 14250
+  - name: jaeger-thrift-http # Default endpoint for Jaeger HTTP receiver.
+    port: 14268
+  - name: zipkin # Default endpoint for Zipkin receiver.
+    port: 9411
+  - name: metrics # Default endpoint for querying metrics.
+    port: 8888
+  selector:
+    component: otel-collector-metrics

deploy/kubernetes/platform/templates/otel-collector/otel-collector-config.yaml

@@ -0,0 +1,67 @@
+apiVersion: v1
+kind: ConfigMap
+metadata:
+  name: otel-collector-conf
+  labels:
+    app: opentelemetry
+    component: otel-collector-conf
+data:
+  otel-collector-config: |
+    receivers:
+      otlp/spanmetrics:
+        protocols:
+          grpc:
+            endpoint: "localhost:12345"
+      otlp:
+        protocols:
+          grpc:
+          http:
+      jaeger:
+        protocols:
+          grpc:
+          thrift_http:
+    processors:
+      batch:
+        send_batch_size: 1000
+        timeout: 10s
+      signozspanmetrics/prometheus:
+        metrics_exporter: prometheus
+        latency_histogram_buckets: [100us, 1ms, 2ms, 6ms, 10ms, 50ms, 100ms, 250ms, 500ms, 1000ms, 1400ms, 2000ms, 5s, 10s, 20s, 40s, 60s ]
+      memory_limiter:
+        # Same as --mem-ballast-size-mib CLI argument
+        ballast_size_mib: 683
+        # 80% of maximum memory up to 2G
+        limit_mib: 1500
+        # 25% of limit up to 2G
+        spike_limit_mib: 512
+        check_interval: 5s
+      # queued_retry:
+      #   num_workers: 4
+      #   queue_size: 100
+      #   retry_on_failure: true
+    extensions:
+      health_check: {}
+      zpages: {}
+    exporters:
+      clickhouse:
+        datasource: tcp://signoz-clickhouse:9000?username=clickhouse_operator&password=clickhouse_operator_password
+      clickhousemetricswrite:
+        endpoint: tcp://signoz-clickhouse:9000/?database=signoz_metrics&username=clickhouse_operator&password=clickhouse_operator_password
+        resource_to_telemetry_conversion:
+          enabled: true
+      prometheus:
+        endpoint: "0.0.0.0:8889"
+    service:
+      extensions: [health_check, zpages]
+      pipelines:
+        traces:
+          receivers: [jaeger, otlp]
+          processors: [signozspanmetrics/prometheus, batch]
+          exporters: [clickhouse]
+        metrics:
+          receivers: [otlp]
+          processors: [batch]
+          exporters: [clickhousemetricswrite]
+        metrics/spanmetrics:
+          receivers: [otlp/spanmetrics]
+          exporters: [prometheus]

deploy/kubernetes/platform/templates/otel-collector/otel-collector-deployment.yaml

@@ -21,11 +21,11 @@ spec:
     spec:
       containers:
       - command:
-          - "/otelcol"
+          - "/otelcontribcol"
           - "--config=/conf/otel-collector-config.yaml"
 #           Memory Ballast size should be max 1/3 to 1/2 of memory.
           - "--mem-ballast-size-mib=683"
-        image: otel/opentelemetry-collector:0.18.0
+        image: signoz/otelcontribcol:0.4.2
         name: otel-collector
         resources:
           limits:
@@ -43,6 +43,7 @@ spec:
         - containerPort: 14268 # Default endpoint for Jaeger HTTP receiver.
         - containerPort: 9411 # Default endpoint for Zipkin receiver.
         - containerPort: 8888  # Default endpoint for querying metrics.
+        - containerPort: 8889  # Default endpoint for prometheus exported metrics.
         volumeMounts:
         - name: otel-collector-config-vol
           mountPath: /conf

deploy/kubernetes/platform/templates/otel-collector/otel-collector-service.yaml

@@ -27,5 +27,7 @@ spec:
     port: 9411
   - name: metrics # Default endpoint for querying metrics.
     port: 8888
+  - name: prometheus-metrics # Default endpoint for querying prometheus metrics.
+    port: 8889
   selector:
     component: otel-collector

deploy/kubernetes/platform/values.yaml

@@ -1,51 +1,15 @@
 zookeeper:
-    autopurge:
-        purgeInterval: 1
-
-kafka:
-    zookeeper:
-        enabled: false
-    externalZookeeper:
-        servers: ["signoz-zookeeper:2181"]
-    zookeeperConnectionTimeoutMs: 6000
-
-druid:
-    image:
-        tag: 0.21.1-rc2
-
-    configVars:
-
-        # To store data on local disks attached
-        druid_extensions_loadList: '["druid-histogram", "druid-datasketches", "druid-lookups-cached-global", "postgresql-metadata-storage", "druid-kafka-indexing-service"]'
-        druid_storage_type: local
-
-
-        # # To store data in S3
-        # druid_extensions_loadList: '["druid-histogram", "druid-datasketches", "druid-lookups-cached-global", "postgresql-metadata-storage", "druid-kafka-indexing-service", "druid-s3-extensions"]'
-        # druid_storage_type: s3
-        # druid_storage_bucket: signoz-druid
-        # druid_storage_baseKey: baseKey
-        # AWS_ACCESS_KEY_ID: <your secret id>
-        # AWS_SECRET_ACCESS_KEY: <your secret key>
-        # AWS_REGION: <your region>
-
-    historical:
-        persistence:
-            size: "20Gi"
-
-    zkHosts: "signoz-zookeeper:2181"
-
-    zookeeper:
-        enabled: false
-
-flattener-processor:
-    configVars:
-        KAFKA_BROKER: signoz-kafka:9092
-        KAFKA_INPUT_TOPIC: otlp_spans
-        KAFKA_OUTPUT_TOPIC: flattened_spans
+  autopurge:
+    purgeInterval: 1
 
 query-service:
-    configVars:
-        DruidClientUrl: http://signoz-druid-router:8888
-        DruidDatasource: flattened_spans
-        STORAGE: druid
+  configVars:
+    ClickHouseUrl: http://signoz-clickhouse:9000?username=clickhouse_operator&password=clickhouse_operator_password
+    STORAGE: clickhouse
+
+cloud: aws
+
+clickhouseOperator:
+  enabled: true
+  storage: 20Gi
+  serviceType: ClusterIP

frontend/.eslintignore

@@ -0,0 +1,2 @@
+node_modules
+build

frontend/.eslintrc.js

@@ -0,0 +1,63 @@
+module.exports = {
+	env: {
+		browser: true,
+		es2021: true,
+		node: true,
+	},
+	extends: [
+		'eslint:recommended',
+		'plugin:react/recommended',
+		'plugin:@typescript-eslint/recommended',
+		'plugin:@typescript-eslint/eslint-recommended',
+		'plugin:prettier/recommended',
+	],
+	parser: '@typescript-eslint/parser',
+	parserOptions: {
+		ecmaFeatures: {
+			jsx: true,
+		},
+		ecmaVersion: 12,
+		sourceType: 'module',
+	},
+	plugins: [
+		'react',
+		'@typescript-eslint',
+		'simple-import-sort',
+		'react-hooks',
+		'prettier',
+	],
+	settings: {
+		react: {
+			version: 'latest',
+		},
+	},
+	rules: {
+		'react/jsx-filename-extension': [
+			'error',
+			{
+				extensions: ['.tsx', '.js', '.jsx'],
+			},
+		],
+		'react/prop-types': 'off',
+		'@typescript-eslint/explicit-function-return-type': 'error',
+		'@typescript-eslint/no-var-requires': 0,
+		'react/no-array-index-key': 2,
+		'linebreak-style': ['error', process.platform === 'win32' ? 'windows' : 'unix'],
+
+		// simple sort error
+		'simple-import-sort/imports': 'error',
+		'simple-import-sort/exports': 'error',
+
+		// hooks
+		'react-hooks/rules-of-hooks': 'error',
+		'react-hooks/exhaustive-deps': 'warn',
+
+		'prettier/prettier': [
+			'error',
+			{},
+			{
+				usePrettierrc: true,
+			},
+		],
+	},
+};

frontend/.prettierrc.json

@@ -2,6 +2,7 @@
 	"trailingComma": "all",
 	"useTabs": true,
 	"tabWidth": 1,
-	"singleQuote": false,
-	"jsxSingleQuote": false
+	"singleQuote": true,
+	"jsxSingleQuote": false,
+	"semi": true
 }

frontend/__mocks__/cssMock.ts

@@ -0,0 +1 @@
+export default {};

frontend/bundlesize.config.json

@@ -0,0 +1,8 @@
+{
+	"files": [
+		{
+			"path": "./build/**.js",
+			"maxSize": "1.2MB"
+		}
+	]
+}

frontend/cypress.json

@@ -0,0 +1,3 @@
+{
+	"video": false
+}

frontend/cypress/CustomFunctions/Login.ts

@@ -0,0 +1,47 @@
+const Login = ({ email, name }: LoginProps): void => {
+	const emailInput = cy.findByPlaceholderText('mike@netflix.com');
+
+	emailInput.then((emailInput) => {
+		const element = emailInput[0];
+		// element is present
+		expect(element).not.undefined;
+		expect(element.nodeName).to.be.equal('INPUT');
+	});
+	emailInput.type(email).then((inputElements) => {
+		const inputElement = inputElements[0];
+		const inputValue = inputElement.getAttribute('value');
+		expect(inputValue).to.be.equals(email);
+	});
+
+	const firstNameInput = cy.findByPlaceholderText('Mike');
+	firstNameInput.then((firstNameInput) => {
+		const element = firstNameInput[0];
+		// element is present
+		expect(element).not.undefined;
+		expect(element.nodeName).to.be.equal('INPUT');
+	});
+
+	firstNameInput.type(name).then((inputElements) => {
+		const inputElement = inputElements[0];
+		const inputValue = inputElement.getAttribute('value');
+		expect(inputValue).to.be.equals(name);
+	});
+
+	const gettingStartedButton = cy.findByText('Get Started');
+	gettingStartedButton.click();
+
+	cy
+		.intercept('POST', '/api/v1/user?email*', {
+			statusCode: 200,
+		})
+		.as('defaultUser');
+
+	cy.wait('@defaultUser');
+};
+
+export interface LoginProps {
+	email: string;
+	name: string;
+}
+
+export default Login;

frontend/cypress/CustomFunctions/checkRouteDefaultGlobalTimeOptions.ts

@@ -0,0 +1,49 @@
+import {
+	getDefaultOption,
+	getOptions,
+} from 'container/Header/DateTimeSelection/config';
+// import { AppState } from 'store/reducers';
+
+const CheckRouteDefaultGlobalTimeOptions = ({
+	route,
+}: CheckRouteDefaultGlobalTimeOptionsProps): void => {
+	cy.visit(Cypress.env('baseUrl') + route);
+
+	const allOptions = getOptions(route);
+
+	const defaultValue = getDefaultOption(route);
+
+	const defaultSelectedOption = allOptions.find((e) => e.value === defaultValue);
+
+	expect(defaultSelectedOption).not.undefined;
+
+	cy
+		.findAllByTestId('dropDown')
+		.find('span')
+		.then((el) => {
+			const elements = el.get();
+
+			const item = elements[1];
+
+			expect(defaultSelectedOption?.label).to.be.equals(
+				item.innerText,
+				'Default option is not matching',
+			);
+		});
+
+	// cy
+	// 	.window()
+	// 	.its('store')
+	// 	.invoke('getState')
+	// 	.then((e: AppState) => {
+	// 		const { globalTime } = e;
+	// 		const { maxTime, minTime } = globalTime;
+	// 		// @TODO match the global min time and max time according to the selected option
+	// 	});
+};
+
+export interface CheckRouteDefaultGlobalTimeOptionsProps {
+	route: string;
+}
+
+export default CheckRouteDefaultGlobalTimeOptions;

frontend/cypress/fixtures/defaultAllChannels.json

@@ -0,0 +1,21 @@
+{
+	"data": [
+		{
+			"created_at": 1638083159246,
+			"data": "{}",
+			"id": 1,
+			"name": "First Channels",
+			"type": "slack",
+			"updated_at": 1638083159246
+		},
+		{
+			"created_at": 1638083159246,
+			"data": "{}",
+			"id": 2,
+			"name": "Second Channels",
+			"type": "Slack",
+			"updated_at": 1638083159246
+		}
+	],
+	"message": "Success"
+}