Release v0.30.1 (#804)

This PR prepares the release `v0.30.1`.
(Please merge it before releasing draft)

.github/CODEOWNERS

@@ -1 +1 @@
-* @kvaps
+* @kvaps @lllamnyp

.github/workflows/pre-commit.yml

@@ -1,7 +1,12 @@
 name: Pre-Commit Checks
 
-on: [push, pull_request]
-
+on:
+  push:
+    branches:
+      - main
+  pull_request:
+    paths-ignore:
+      - '**.md'
 jobs:
   pre-commit:
     runs-on: ubuntu-22.04

.github/workflows/pull-requests-release.yaml

@@ -0,0 +1,96 @@
+name: Releasing PR
+
+on:
+  pull_request:
+    types: [labeled, opened, synchronize, reopened, closed]
+
+jobs:
+  verify:
+    name: Test Release
+    runs-on: [self-hosted]
+    permissions:
+      contents: read
+      packages: write
+
+    if: |
+      contains(github.event.pull_request.labels.*.name, 'ok-to-test') &&
+      contains(github.event.pull_request.labels.*.name, 'release') &&
+      github.event.action != 'closed'
+
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v4
+        with:
+          fetch-depth: 0
+          fetch-tags: true
+
+      - name: Login to GitHub Container Registry
+        uses: docker/login-action@v3
+        with:
+          username: ${{ github.repository_owner }}
+          password: ${{ secrets.GITHUB_TOKEN }}
+          registry: ghcr.io
+
+      - name: Run tests
+        run: make test
+
+  finalize:
+    name: Finalize Release
+    runs-on: [self-hosted]
+    permissions:
+      contents: write
+  
+    if: |
+      github.event.pull_request.merged == true &&
+      contains(github.event.pull_request.labels.*.name, 'release')
+  
+    steps:
+      - name: Extract tag from branch name
+        id: get_tag
+        uses: actions/github-script@v7
+        with:
+          script: |
+            const branch = context.payload.pull_request.head.ref;
+            const match = branch.match(/^release-(\d+\.\d+\.\d+(?:[-\w\.]+)?)$/);
+  
+            if (!match) {
+              core.setFailed(`Branch '${branch}' does not match expected format 'release-X.Y.Z[-suffix]'`);
+            } else {
+              const tag = match[1];
+              core.setOutput('tag', tag);
+              console.log(`✅ Extracted tag: ${tag}`);
+            }
+  
+      - name: Checkout repo
+        uses: actions/checkout@v4
+        with:
+          fetch-depth: 0
+  
+      - name: Create tag on merged commit
+        run: |
+          git tag ${{ steps.get_tag.outputs.tag }} ${{ github.sha }}
+          git push origin ${{ steps.get_tag.outputs.tag }}
+  
+      - name: Publish draft release
+        uses: actions/github-script@v7
+        with:
+          script: |
+            const tag = '${{ steps.get_tag.outputs.tag }}';
+            const releases = await github.rest.repos.listReleases({
+              owner: context.repo.owner,
+              repo: context.repo.repo
+            });
+  
+            const release = releases.data.find(r => r.tag_name === tag && r.draft);
+            if (!release) {
+              throw new Error(`Draft release with tag ${tag} not found`);
+            }
+  
+            await github.rest.repos.updateRelease({
+              owner: context.repo.owner,
+              repo: context.repo.repo,
+              release_id: release.id,
+              draft: false
+            });
+  
+            console.log(`✅ Published release for ${tag}`);

.github/workflows/pull-requests.yaml

@@ -0,0 +1,39 @@
+name: Pull Request
+
+on:
+  pull_request:
+    types: [labeled, opened, synchronize, reopened]
+
+jobs:
+  e2e:
+    name: Build and Test
+    runs-on: [self-hosted]
+    permissions:
+      contents: read
+      packages: write
+
+    if: |
+      contains(github.event.pull_request.labels.*.name, 'ok-to-test') &&
+      !contains(github.event.pull_request.labels.*.name, 'release')
+
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v4
+        with:
+          fetch-depth: 0
+          fetch-tags: true
+
+      - name: Login to GitHub Container Registry
+        uses: docker/login-action@v3
+        with:
+          username: ${{ github.repository_owner }}
+          password: ${{ secrets.GITHUB_TOKEN }}
+          registry: ghcr.io
+
+      - name: make build
+        run: |
+          make build
+
+      - name: make test
+        run: |
+          make test

.github/workflows/tags.yaml

@@ -0,0 +1,162 @@
+name: Versioned Tag
+
+on:
+  push:
+    tags:
+      - 'v*.*.*'
+
+jobs:
+  prepare-release:
+    name: Prepare Release
+    runs-on: [self-hosted]
+    permissions:
+      contents: write
+      packages: write
+      pull-requests: write
+
+    steps:
+      - name: Check if release already exists
+        id: check_release
+        uses: actions/github-script@v7
+        with:
+          script: |
+            const tag = context.ref.replace('refs/tags/', '');
+            const releases = await github.rest.repos.listReleases({
+              owner: context.repo.owner,
+              repo: context.repo.repo
+            });
+
+            const existing = releases.data.find(r => r.tag_name === tag && !r.draft);
+            if (existing) {
+              core.setOutput('skip', 'true');
+            } else {
+              core.setOutput('skip', 'false');
+            }
+
+      - name: Skip if release already exists
+        if: steps.check_release.outputs.skip == 'true'
+        run: echo "Release already exists, skipping workflow."
+
+      - name: Checkout code
+        if: steps.check_release.outputs.skip == 'false'
+        uses: actions/checkout@v4
+        with:
+          fetch-depth: 0
+          fetch-tags: true
+
+      - name: Login to GitHub Container Registry
+        if: steps.check_release.outputs.skip == 'false'
+        uses: docker/login-action@v3
+        with:
+          username: ${{ github.repository_owner }}
+          password: ${{ secrets.GITHUB_TOKEN }}
+          registry: ghcr.io
+
+      - name: Build
+        if: steps.check_release.outputs.skip == 'false'
+        run: make build
+
+      - name: Commit release artifacts
+        if: steps.check_release.outputs.skip == 'false'
+        env:
+          GIT_AUTHOR_NAME: ${{ github.actor }}
+          GIT_AUTHOR_EMAIL: ${{ github.actor }}@users.noreply.github.com
+        run: |
+          git config user.name "$GIT_AUTHOR_NAME"
+          git config user.email "$GIT_AUTHOR_EMAIL"
+          git add .
+          git commit -m "Prepare release ${GITHUB_REF#refs/tags/}" -s || echo "No changes to commit"
+
+      - name: Create release branch
+        if: steps.check_release.outputs.skip == 'false'
+        run: |
+          BRANCH_NAME="release-${GITHUB_REF#refs/tags/v}"
+          git branch -f "$BRANCH_NAME"
+          git push origin "$BRANCH_NAME" --force
+
+      - name: Create pull request if not exists
+        if: steps.check_release.outputs.skip == 'false'
+        uses: actions/github-script@v7
+        with:
+          script: |
+            const version = context.ref.replace('refs/tags/v', '');
+            const branch = `release-${version}`;
+            const base = 'main';
+      
+            const prs = await github.rest.pulls.list({
+              owner: context.repo.owner,
+              repo: context.repo.repo,
+              head: `${context.repo.owner}:${branch}`,
+              base
+            });
+      
+            if (prs.data.length === 0) {
+              const newPr = await github.rest.pulls.create({
+                owner: context.repo.owner,
+                repo: context.repo.repo,
+                head: branch,
+                base: base,
+                title: `Release v${version}`,
+                body:
+                  `This PR prepares the release \`v${version}\`.\n` +
+                  `(Please merge it before releasing draft)`,
+                draft: false
+              });
+      
+              console.log(`Created pull request #${newPr.data.number} from ${branch} to ${base}`);
+      
+              await github.rest.issues.addLabels({
+                owner: context.repo.owner,
+                repo: context.repo.repo,
+                issue_number: newPr.data.number,
+                labels: ['release']
+              });
+      
+            } else {
+              console.log(`Pull request already exists from ${branch} to ${base}`);
+            }
+
+      - name: Create or reuse draft release
+        if: steps.check_release.outputs.skip == 'false'
+        id: create_release
+        uses: actions/github-script@v7
+        with:
+          script: |
+            const tag = context.ref.replace('refs/tags/', '');
+            const releases = await github.rest.repos.listReleases({
+              owner: context.repo.owner,
+              repo: context.repo.repo
+            });
+
+            let release = releases.data.find(r => r.tag_name === tag);
+            if (!release) {
+              release = await github.rest.repos.createRelease({
+                owner: context.repo.owner,
+                repo: context.repo.repo,
+                tag_name: tag,
+                name: `${tag}`,
+                draft: true,
+                prerelease: false
+              });
+            }
+            core.setOutput('upload_url', release.upload_url);
+
+      - name: Build assets
+        if: steps.check_release.outputs.skip == 'false'
+        run: make assets
+        env:
+          GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+
+      - name: Upload assets
+        if: steps.check_release.outputs.skip == 'false'
+        run: make upload_assets VERSION=${GITHUB_REF#refs/tags/}
+        env:
+          GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+
+      - name: Delete pushed tag
+        if: steps.check_release.outputs.skip == 'false'
+        run: |
+          git push --delete origin ${GITHUB_REF#refs/tags/}
+
+      - name: Run tests
+        run: make test

ADOPTERS.md

@@ -13,8 +13,8 @@ but it means a lot to us.
 
 To add your organization to this list, you can either:
 
-- [open a pull request](https://github.com/aenix-io/cozystack/pulls) to directly update this file, or
-- [edit this file](https://github.com/aenix-io/cozystack/blob/main/ADOPTERS.md) directly in GitHub
+- [open a pull request](https://github.com/cozystack/cozystack/pulls) to directly update this file, or
+- [edit this file](https://github.com/cozystack/cozystack/blob/main/ADOPTERS.md) directly in GitHub
 
 Feel free to ask in the Slack chat if you any questions and/or require
 assistance with updating this list.
@@ -28,4 +28,5 @@ This list is sorted in chronological order, based on the submission date.
 | [Ænix](https://aenix.io/) | @kvaps | 2024-02-14 | Ænix provides consulting services for cloud providers and uses Cozystack as the main tool for organizing managed services for them. |
 | [Mediatech](https://mediatech.dev/) | @ugenk | 2024-05-01 | We're developing and hosting software for our and our custmer services. We're using cozystack as a kubernetes distribution for that. |
 | [Bootstack](https://bootstack.app/) | @mrkhachaturov | 2024-08-01| At Bootstack, we utilize a Kubernetes operator specifically designed to simplify and streamline cloud infrastructure creation.|
-| [gohost](https://gohost.kz/) | @karabass_off | 2024-02-01| Our company has been working in the market of Kazakhstan for more than 15 years, providing clients with a standard set of services: VPS/VDC, IaaS, shared hosting, etc. Now we are expanding the lineup by introducing Bare Metal Kubenetes cluster under Cozystack management.|
+| [gohost](https://gohost.kz/) | @karabass_off | 2024-02-01 | Our company has been working in the market of Kazakhstan for more than 15 years, providing clients with a standard set of services: VPS/VDC, IaaS, shared hosting, etc. Now we are expanding the lineup by introducing Bare Metal Kubenetes cluster under Cozystack management. |
+| [Urmanac](https://urmanac.com) | @kingdonb | 2024-12-04 | Urmanac is the future home of a hosting platform for the knowledge base of a community of personal server enthusiasts. We use Cozystack to provide support services for web sites hosted using both conventional deployments and on SpinKube, with WASM. |

CONTRIBUTING.md

@@ -6,13 +6,13 @@ As you get started, you are in the best position to give us feedbacks on areas o
 
 * Problems found while setting up the development environment
 * Gaps in our documentation
-* Bugs in our Github actions
+* Bugs in our GitHub actions
 
-First, though, it is important that you read the [code of conduct](CODE_OF_CONDUCT.md).
+First, though, it is important that you read the [CNCF Code of Conduct](https://github.com/cncf/foundation/blob/master/code-of-conduct.md).
 
 The guidelines below are a starting point. We don't want to limit your
 creativity, passion, and initiative. If you think there's a better way, please
-feel free to bring it up in a Github discussion, or open a pull request. We're
+feel free to bring it up in a GitHub discussion, or open a pull request. We're
 certain there are always better ways to do things, we just need to start some
 constructive dialogue!
 
@@ -23,9 +23,9 @@ We welcome many types of contributions including:
 * New features
 * Builds, CI/CD
 * Bug fixes
-* [Documentation](https://github.com/aenix-io/cozystack-website/tree/main)
+* [Documentation](https://GitHub.com/cozystack/cozystack-website/tree/main)
 * Issue Triage
-* Answering questions on Slack or Github Discussions
+* Answering questions on Slack or GitHub Discussions
 * Web design
 * Communications / Social Media / Blog Posts
 * Events participation
@@ -34,7 +34,7 @@ We welcome many types of contributions including:
 ## Ask for Help
 
 The best way to reach us with a question when contributing is to drop a line in
-our [Telegram channel](https://t.me/cozystack), or start a new Github discussion.
+our [Telegram channel](https://t.me/cozystack), or start a new GitHub discussion.
 
 ## Raising Issues
 

GOVERNANCE.md

@@ -0,0 +1,91 @@
+# Cozystack Governance
+
+This document defines the governance structure of the Cozystack community, outlining how members collaborate to achieve shared goals.
+
+## Overview
+
+**Cozystack**, a Cloud Native Computing Foundation (CNCF) project, is committed
+to building an open, inclusive, productive, and self-governing open source
+community focused on building a high-quality open source PaaS and framework for building clouds.
+
+## Code Repositories
+
+The following code repositories are governed by the Cozystack community and
+maintained under the `cozystack` namespace:
+
+* **[Cozystack](https://github.com/cozystack/cozystack):** Main Cozystack codebase
+* **[website](https://github.com/cozystack/website):** Cozystack website and documentation sources
+* **[Talm](https://github.com/cozystack/talm):** Tool for managing Talos Linux the GitOps way
+* **[cozy-proxy](https://github.com/cozystack/cozy-proxy):** A simple kube-proxy addon for 1:1 NAT services in Kubernetes with NFT backend
+* **[cozystack-telemetry-server](https://github.com/cozystack/cozystack-telemetry-server):** Cozystack telemetry
+* **[talos-bootstrap](https://github.com/cozystack/talos-bootstrap):** An interactive Talos Linux installer
+* **[talos-meta-tool](https://github.com/cozystack/talos-meta-tool):** Tool for writing network metadata into META partition
+
+## Community Roles
+
+* **Users:** Members that engage with the Cozystack community via any medium, including Slack, Telegram, GitHub, and mailing lists.
+* **Contributors:** Members contributing to the projects by contributing and reviewing code, writing documentation,
+  responding to issues, participating in proposal discussions, and so on.
+* **Directors:** Non-technical project leaders.
+* **Maintainers**: Technical project leaders.
+
+## Contributors
+
+Cozystack is for everyone. Anyone can become a Cozystack contributor simply by
+contributing to the project, whether through code, documentation, blog posts,
+community management, or other means.
+As with all Cozystack community members, contributors are expected to follow the
+[Cozystack Code of Conduct](https://github.com/cozystack/cozystack/blob/main/CODE_OF_CONDUCT.md).
+
+All contributions to Cozystack code, documentation, or other components in the
+Cozystack GitHub organisation must follow the 
+[contributing guidelines](https://github.com/cozystack/cozystack/blob/main/CONTRIBUTING.md).
+Whether these contributions are merged into the project is the prerogative of the maintainers.
+
+## Directors
+
+Directors are responsible for non-technical leadership functions within the project.
+This includes representing Cozystack and its maintainers to the community, to the press, 
+and to the outside world; interfacing with CNCF and other governance entities;
+and participating in project decision-making processes when appropriate.
+
+Directors are elected by a majority vote of the maintainers.
+
+## Maintainers
+
+Maintainers have the right to merge code into the project.
+Anyone can become a Cozystack maintainer (see "Becoming a maintainer" below).
+
+### Expectations
+
+Cozystack maintainers are expected to:
+
+* Review pull requests, triage issues, and fix bugs in their areas of
+  expertise, ensuring that all changes go through the project's code review
+  and integration processes.
+* Monitor cncf-cozystack-* emails, the Cozystack Slack channels in Kubernetes
+  and CNCF Slack workspaces, Telegram groups, and help out when possible.
+* Rapidly respond to any time-sensitive security release processes.
+* Attend Cozystack community meetings.
+
+If a maintainer is no longer interested in or cannot perform the duties
+listed above, they should move themselves to emeritus status.
+If necessary, this can also occur through the decision-making process outlined below.
+
+### Becoming a Maintainer
+
+Anyone can become a Cozystack maintainer. Maintainers should be extremely
+proficient in cloud native technologies and/or Go; have relevant domain expertise; 
+have the time and ability to meet the maintainer's expectations above; 
+and demonstrate the ability to work with the existing maintainers and project processes.
+
+To become a maintainer, start by expressing interest to existing maintainers.
+Existing maintainers will then ask you to demonstrate the qualifications above
+by contributing PRs, doing code reviews, and other such tasks under their guidance.
+After several months of working together, maintainers will decide whether to grant maintainer status.
+
+## Project Decision-making Process
+
+Ideally, all project decisions are resolved by consensus of maintainers and directors.
+If this is not possible, a vote will be called.
+The voting process is a simple majority in which each maintainer and director receives one vote.

MAINTAINERS.md

@@ -1,7 +1,12 @@
 # The Cozystack Maintainers
 
-| Maintainer | GitHub Username | Company |
-| ---------- | --------------- | ------- |
-| Andrei Kvapil | [@kvaps](https://github.com/kvaps) | Ænix |
-| George Gaál | [@gecube](https://github.com/gecube) | Ænix |
-| Eduard Generalov | [@egeneralov](https://github.com/egeneralov) | Ænix |
+| Maintainer | GitHub Username | Company |          Responsibility           |
+| ---------- | --------------- | ------- | --------------------------------- |
+| Andrei Kvapil | [@kvaps](https://github.com/kvaps) | Ænix | Core Maintainer |
+| George Gaál | [@gecube](https://github.com/gecube) | Ænix | DevOps Practices in Platform, Developers Advocate |
+| Kingdon Barrett | [@kingdonb](https://github.com/kingdonb) | Urmanac | FluxCD and flux-operator |
+| Timofei Larkin | [@lllamnyp](https://github.com/lllamnyp) | 3commas | Etcd-operator Lead |
+| Artem Bortnikov | [@aobort](https://github.com/aobort) | Timescale | Etcd-operator Lead |
+| Andrei Gumilev | [@chumkaska](https://github.com/chumkaska) | Ænix | Platform Documentation |
+| Timur Tukaev | [@tym83](https://github.com/tym83) | Ænix | Cozystack Website, Marketing, Community Management |
+| Kirill Klinchenkov | [@klinch0](https://github.com/klinch0) | Ænix | Core Maintainer |

Makefile

@@ -1,14 +1,24 @@
 .PHONY: manifests repos assets
 
-build:
+build-deps:
+	@command -V find docker skopeo jq gh helm > /dev/null
+	@yq --version | grep -q "mikefarah" || (echo "mikefarah/yq is required" && exit 1)
+	@tar --version | grep -q GNU || (echo "GNU tar is required" && exit 1)
+	@sed --version | grep -q GNU || (echo "GNU sed is required" && exit 1)
+	@awk --version | grep -q GNU || (echo "GNU awk is required" && exit 1)
+
+build: build-deps
 	make -C packages/apps/http-cache image
 	make -C packages/apps/postgres image
 	make -C packages/apps/mysql image
 	make -C packages/apps/clickhouse image
 	make -C packages/apps/kubernetes image
+	make -C packages/extra/monitoring image
 	make -C packages/system/cozystack-api image
+	make -C packages/system/cozystack-controller image
 	make -C packages/system/cilium image
 	make -C packages/system/kubeovn image
+	make -C packages/system/kubeovn-webhook image
 	make -C packages/system/dashboard image
 	make -C packages/system/kamaji image
 	make -C packages/system/bucket image
@@ -16,10 +26,6 @@ build:
 	make -C packages/core/installer image
 	make manifests
 
-manifests:
-	(cd packages/core/installer/; helm template -n cozy-installer installer .) > manifests/cozystack-installer.yaml
-	sed -i 's|@sha256:[^"]\+||' manifests/cozystack-installer.yaml
-
 repos:
 	rm -rf _out
 	make -C packages/apps check-version-map
@@ -30,10 +36,21 @@ repos:
 	mkdir -p _out/logos
 	cp ./packages/apps/*/logos/*.svg ./packages/extra/*/logos/*.svg _out/logos/
 
+
+manifests:
+	mkdir -p _out/assets
+	(cd packages/core/installer/; helm template -n cozy-installer installer .) > _out/assets/cozystack-installer.yaml
+
 assets:
 	make -C packages/core/installer/ assets
 
 test:
 	make -C packages/core/testing apply
 	make -C packages/core/testing test
-	make -C packages/core/testing test-applications
+	#make -C packages/core/testing test-applications
+
+generate:
+	hack/update-codegen.sh
+
+upload_assets: manifests
+	hack/upload-assets.sh

README.md

@@ -2,30 +2,31 @@
 ![Cozystack](img/cozystack-logo-white.svg#gh-dark-mode-only)
 
 [![Open Source](https://img.shields.io/badge/Open-Source-brightgreen)](https://opensource.org/)
-[![Apache-2.0 License](https://img.shields.io/github/license/aenix-io/cozystack)](https://opensource.org/licenses/)
-[![Support](https://img.shields.io/badge/$-support-12a0df.svg?style=flat)](https://aenix.io/contact-us/#meet)
-[![Active](http://img.shields.io/badge/Status-Active-green.svg)](https://aenix.io/cozystack/)
-[![GitHub Release](https://img.shields.io/github/release/aenix-io/cozystack.svg?style=flat)](https://github.com/aenix-io/cozystack)
-[![GitHub Commit](https://img.shields.io/github/commit-activity/y/aenix-io/cozystack)](https://github.com/aenix-io/cozystack) 
+[![Apache-2.0 License](https://img.shields.io/github/license/cozystack/cozystack)](https://opensource.org/licenses/)
+[![Support](https://img.shields.io/badge/$-support-12a0df.svg?style=flat)](https://cozystack.io/support/)
+[![Active](http://img.shields.io/badge/Status-Active-green.svg)](https://github.com/cozystack/cozystack)
+[![GitHub Release](https://img.shields.io/github/release/cozystack/cozystack.svg?style=flat)](https://github.com/cozystack/cozystack/releases/latest)
+[![GitHub Commit](https://img.shields.io/github/commit-activity/y/cozystack/cozystack)](https://github.com/cozystack/cozystack/graphs/contributors) 
 
 # Cozystack
 
 **Cozystack** is a free PaaS platform and framework for building clouds.
 
-With Cozystack, you can transform your bunch of servers into an intelligent system with a simple REST API for spawning Kubernetes clusters, Database-as-a-Service, virtual machines, load balancers, HTTP caching services, and other services with ease.
+With Cozystack, you can transform a bunch of servers into an intelligent system with a simple REST API for spawning Kubernetes clusters,
+Database-as-a-Service, virtual machines, load balancers, HTTP caching services, and other services with ease.
 
-You can use Cozystack to build your own cloud or to provide a cost-effective development environments.  
+Use Cozystack to build your own cloud or provide a cost-effective development environment.  
 
 ## Use-Cases
 
-* [**Using Cozystack to build public cloud**](https://cozystack.io/docs/use-cases/public-cloud/)  
-You can use Cozystack as backend for a public cloud
+* [**Using Cozystack to build a public cloud**](https://cozystack.io/docs/guides/use-cases/public-cloud/)  
+You can use Cozystack as a backend for a public cloud
 
-* [**Using Cozystack to build private cloud**](https://cozystack.io/docs/use-cases/private-cloud/)  
-You can use Cozystack as platform to build a private cloud powered by Infrastructure-as-Code approach
+* [**Using Cozystack to build a private cloud**](https://cozystack.io/docs/guides/use-cases/private-cloud/)  
+You can use Cozystack as a platform to build a private cloud powered by Infrastructure-as-Code approach
 
-* [**Using Cozystack as Kubernetes distribution**](https://cozystack.io/docs/use-cases/kubernetes-distribution/)  
-You can use Cozystack as Kubernetes distribution for Bare Metal
+* [**Using Cozystack as a Kubernetes distribution**](https://cozystack.io/docs/guides/use-cases/kubernetes-distribution/)  
+You can use Cozystack as a Kubernetes distribution for Bare Metal
 
 ## Screenshot
 
@@ -33,32 +34,32 @@ You can use Cozystack as Kubernetes distribution for Bare Metal
 
 ## Documentation
 
-The documentation is located on official [cozystack.io](https://cozystack.io) website.
+The documentation is located on the [cozystack.io](https://cozystack.io) website.
 
-Read [Get Started](https://cozystack.io/docs/get-started/) section for a quick start.
+Read the [Getting Started](https://cozystack.io/docs/getting-started/) section for a quick start.
 
-If you encounter any difficulties, start with the [troubleshooting guide](https://cozystack.io/docs/troubleshooting/), and work your way through the process that we've outlined.
+If you encounter any difficulties, start with the [troubleshooting guide](https://cozystack.io/docs/operations/troubleshooting/) and work your way through the process that we've outlined.
 
 ## Versioning
 
 Versioning adheres to the [Semantic Versioning](http://semver.org/) principles.  
-A full list of the available releases is available in the GitHub repository's [Release](https://github.com/aenix-io/cozystack/releases) section.
+A full list of the available releases is available in the GitHub repository's [Release](https://github.com/cozystack/cozystack/releases) section.
 
-- [Roadmap](https://github.com/orgs/aenix-io/projects/2)
+- [Roadmap](https://cozystack.io/docs/roadmap/)
 
 ## Contributions
 
 Contributions are highly appreciated and very welcomed!
 
-In case of bugs, please, check if the issue has been already opened by checking the [GitHub Issues](https://github.com/aenix-io/cozystack/issues) section.
-In case it isn't, you can open a new one: a detailed report will help us to replicate it, assess it, and work on a fix.
+In case of bugs, please check if the issue has already been opened by checking the [GitHub Issues](https://github.com/cozystack/cozystack/issues) section.
+If it isn't, you can open a new one. A detailed report will help us replicate it, assess it, and work on a fix.
 
-You can express your intention in working on the fix on your own.
+You can express your intention to on the fix on your own.
 Commits are used to generate the changelog, and their author will be referenced in it.
 
-In case of **Feature Requests** please use the [Discussion's Feature Request section](https://github.com/aenix-io/cozystack/discussions/categories/feature-requests).
+If you have **Feature Requests** please use the [Discussion's Feature Request section](https://github.com/cozystack/cozystack/discussions/categories/feature-requests).
 
-You can join our weekly community meetings (just add this events to your [Google Calendar](https://calendar.google.com/calendar?cid=ZTQzZDIxZTVjOWI0NWE5NWYyOGM1ZDY0OWMyY2IxZTFmNDMzZTJlNjUzYjU2ZGJiZGE3NGNhMzA2ZjBkMGY2OEBncm91cC5jYWxlbmRhci5nb29nbGUuY29t) or [iCal](https://calendar.google.com/calendar/ical/e43d21e5c9b45a95f28c5d649c2cb1e1f433e2e653b56dbbda74ca306f0d0f68%40group.calendar.google.com/public/basic.ics)) or [Telegram group](https://t.me/cozystack).
+You are welcome to join our weekly community meetings (just add this events to your [Google Calendar](https://calendar.google.com/calendar?cid=ZTQzZDIxZTVjOWI0NWE5NWYyOGM1ZDY0OWMyY2IxZTFmNDMzZTJlNjUzYjU2ZGJiZGE3NGNhMzA2ZjBkMGY2OEBncm91cC5jYWxlbmRhci5nb29nbGUuY29t) or [iCal](https://calendar.google.com/calendar/ical/e43d21e5c9b45a95f28c5d649c2cb1e1f433e2e653b56dbbda74ca306f0d0f68%40group.calendar.google.com/public/basic.ics)) or [Telegram group](https://t.me/cozystack).
 
 ## License
 
@@ -67,8 +68,4 @@ The code is provided as-is with no warranties.
 
 ## Commercial Support
 
-[**Ænix**](https://aenix.io) offers enterprise-grade support, available 24/7.
-
-We provide all types of assistance, including consultations, development of missing features, design, assistance with installation, and integration.
-
-[Contact us](https://aenix.io/contact/)
+A list of companies providing commercial support for this project can be found on [official site](https://cozystack.io/support/).

api/api-rules/cozystack_api_violation_exceptions.list

@@ -1,4 +1,4 @@
-API rule violation: list_type_missing,github.com/aenix.io/cozystack/pkg/apis/apps/v1alpha1,ApplicationStatus,Conditions
+API rule violation: list_type_missing,github.com/cozystack/cozystack/pkg/apis/apps/v1alpha1,ApplicationStatus,Conditions
 API rule violation: names_match,k8s.io/apiextensions-apiserver/pkg/apis/apiextensions/v1,JSONSchemaProps,Ref
 API rule violation: names_match,k8s.io/apiextensions-apiserver/pkg/apis/apiextensions/v1,JSONSchemaProps,Schema
 API rule violation: names_match,k8s.io/apiextensions-apiserver/pkg/apis/apiextensions/v1,JSONSchemaProps,XEmbeddedResource

api/v1alpha1/groupversion_info.go

@@ -0,0 +1,36 @@
+/*
+Copyright 2025.
+
+Licensed under the Apache License, Version 2.0 (the "License");
+you may not use this file except in compliance with the License.
+You may obtain a copy of the License at
+
+    http://www.apache.org/licenses/LICENSE-2.0
+
+Unless required by applicable law or agreed to in writing, software
+distributed under the License is distributed on an "AS IS" BASIS,
+WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+See the License for the specific language governing permissions and
+limitations under the License.
+*/
+
+// Package v1alpha1 contains API Schema definitions for the  v1alpha1 API group.
+// +kubebuilder:object:generate=true
+// +groupName=cozystack.io
+package v1alpha1
+
+import (
+	"k8s.io/apimachinery/pkg/runtime/schema"
+	"sigs.k8s.io/controller-runtime/pkg/scheme"
+)
+
+var (
+	// GroupVersion is group version used to register these objects.
+	GroupVersion = schema.GroupVersion{Group: "cozystack.io", Version: "v1alpha1"}
+
+	// SchemeBuilder is used to add go types to the GroupVersionKind scheme.
+	SchemeBuilder = &scheme.Builder{GroupVersion: GroupVersion}
+
+	// AddToScheme adds the types in this group-version to the given scheme.
+	AddToScheme = SchemeBuilder.AddToScheme
+)

api/v1alpha1/workload_types.go

@@ -0,0 +1,70 @@
+/*
+Copyright 2025.
+
+Licensed under the Apache License, Version 2.0 (the "License");
+you may not use this file except in compliance with the License.
+You may obtain a copy of the License at
+
+    http://www.apache.org/licenses/LICENSE-2.0
+
+Unless required by applicable law or agreed to in writing, software
+distributed under the License is distributed on an "AS IS" BASIS,
+WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+See the License for the specific language governing permissions and
+limitations under the License.
+*/
+
+package v1alpha1
+
+import (
+	"k8s.io/apimachinery/pkg/api/resource"
+	metav1 "k8s.io/apimachinery/pkg/apis/meta/v1"
+)
+
+// WorkloadStatus defines the observed state of Workload
+type WorkloadStatus struct {
+	// Kind represents the type of workload (redis, postgres, etc.)
+	// +required
+	Kind string `json:"kind"`
+
+	// Type represents the specific role of the workload (redis, sentinel, etc.)
+	// If not specified, defaults to Kind
+	// +optional
+	Type string `json:"type,omitempty"`
+
+	// Resources specifies the compute resources allocated to this workload
+	// +required
+	Resources map[string]resource.Quantity `json:"resources"`
+
+	// Operational indicates if all pods of the workload are ready
+	// +optional
+	Operational bool `json:"operational"`
+}
+
+// +kubebuilder:object:root=true
+// +kubebuilder:printcolumn:name="Kind",type="string",JSONPath=".status.kind"
+// +kubebuilder:printcolumn:name="Type",type="string",JSONPath=".status.type"
+// +kubebuilder:printcolumn:name="CPU",type="string",JSONPath=".status.resources.cpu"
+// +kubebuilder:printcolumn:name="Memory",type="string",JSONPath=".status.resources.memory"
+// +kubebuilder:printcolumn:name="Operational",type="boolean",JSONPath=`.status.operational`
+
+// Workload is the Schema for the workloads API
+type Workload struct {
+	metav1.TypeMeta   `json:",inline"`
+	metav1.ObjectMeta `json:"metadata,omitempty"`
+
+	Status WorkloadStatus `json:"status,omitempty"`
+}
+
+// +kubebuilder:object:root=true
+
+// WorkloadList contains a list of Workload
+type WorkloadList struct {
+	metav1.TypeMeta `json:",inline"`
+	metav1.ListMeta `json:"metadata,omitempty"`
+	Items           []Workload `json:"items"`
+}
+
+func init() {
+	SchemeBuilder.Register(&Workload{}, &WorkloadList{})
+}

api/v1alpha1/workloadmonitor_types.go

@@ -0,0 +1,91 @@
+package v1alpha1
+
+import (
+	metav1 "k8s.io/apimachinery/pkg/apis/meta/v1"
+)
+
+// WorkloadMonitorSpec defines the desired state of WorkloadMonitor
+type WorkloadMonitorSpec struct {
+	// Selector is a label selector to find workloads to monitor
+	// +required
+	Selector map[string]string `json:"selector"`
+
+	// Kind specifies the kind of the workload
+	// +optional
+	Kind string `json:"kind,omitempty"`
+
+	// Type specifies the type of the workload
+	// +optional
+	Type string `json:"type,omitempty"`
+
+	// Version specifies the version of the workload
+	// +optional
+	Version string `json:"version,omitempty"`
+
+	// MinReplicas specifies the minimum number of replicas that should be available
+	// +kubebuilder:validation:Minimum=0
+	// +optional
+	MinReplicas *int32 `json:"minReplicas,omitempty"`
+
+	// Replicas is the desired number of replicas
+	// If not specified, will use observedReplicas as the target
+	// +kubebuilder:validation:Minimum=0
+	// +optional
+	Replicas *int32 `json:"replicas,omitempty"`
+}
+
+// WorkloadMonitorStatus defines the observed state of WorkloadMonitor
+type WorkloadMonitorStatus struct {
+	// Operational indicates if the workload meets all operational requirements
+	// +optional
+	Operational *bool `json:"operational,omitempty"`
+
+	// AvailableReplicas is the number of ready replicas
+	// +optional
+	AvailableReplicas int32 `json:"availableReplicas"`
+
+	// ObservedReplicas is the total number of pods observed
+	// +optional
+	ObservedReplicas int32 `json:"observedReplicas"`
+}
+
+// +kubebuilder:object:root=true
+// +kubebuilder:subresource:status
+// +kubebuilder:printcolumn:name="Kind",type="string",JSONPath=".spec.kind"
+// +kubebuilder:printcolumn:name="Type",type="string",JSONPath=".spec.type"
+// +kubebuilder:printcolumn:name="Version",type="string",JSONPath=".spec.version"
+// +kubebuilder:printcolumn:name="Replicas",type="integer",JSONPath=".spec.replicas"
+// +kubebuilder:printcolumn:name="MinReplicas",type="integer",JSONPath=".spec.minReplicas"
+// +kubebuilder:printcolumn:name="Available",type="integer",JSONPath=".status.availableReplicas"
+// +kubebuilder:printcolumn:name="Observed",type="integer",JSONPath=".status.observedReplicas"
+// +kubebuilder:printcolumn:name="Operational",type="boolean",JSONPath=".status.operational"
+
+// WorkloadMonitor is the Schema for the workloadmonitors API
+type WorkloadMonitor struct {
+	metav1.TypeMeta   `json:",inline"`
+	metav1.ObjectMeta `json:"metadata,omitempty"`
+
+	Spec   WorkloadMonitorSpec   `json:"spec,omitempty"`
+	Status WorkloadMonitorStatus `json:"status,omitempty"`
+}
+
+// +kubebuilder:object:root=true
+
+// WorkloadMonitorList contains a list of WorkloadMonitor
+type WorkloadMonitorList struct {
+	metav1.TypeMeta `json:",inline"`
+	metav1.ListMeta `json:"metadata,omitempty"`
+	Items           []WorkloadMonitor `json:"items"`
+}
+
+func init() {
+	SchemeBuilder.Register(&WorkloadMonitor{}, &WorkloadMonitorList{})
+}
+
+// GetSelector returns the label selector from metadata
+func (w *WorkloadMonitor) GetSelector() map[string]string {
+	return w.Spec.Selector
+}
+
+// Selector specifies the label selector for workloads
+type Selector map[string]string

api/v1alpha1/zz_generated.deepcopy.go

@@ -0,0 +1,238 @@
+//go:build !ignore_autogenerated
+
+/*
+Copyright 2025 The Cozystack Authors.
+
+Licensed under the Apache License, Version 2.0 (the "License");
+you may not use this file except in compliance with the License.
+You may obtain a copy of the License at
+
+    http://www.apache.org/licenses/LICENSE-2.0
+
+Unless required by applicable law or agreed to in writing, software
+distributed under the License is distributed on an "AS IS" BASIS,
+WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+See the License for the specific language governing permissions and
+limitations under the License.
+*/
+
+// Code generated by controller-gen. DO NOT EDIT.
+
+package v1alpha1
+
+import (
+	"k8s.io/apimachinery/pkg/api/resource"
+	runtime "k8s.io/apimachinery/pkg/runtime"
+)
+
+// DeepCopyInto is an autogenerated deepcopy function, copying the receiver, writing into out. in must be non-nil.
+func (in Selector) DeepCopyInto(out *Selector) {
+	{
+		in := &in
+		*out = make(Selector, len(*in))
+		for key, val := range *in {
+			(*out)[key] = val
+		}
+	}
+}
+
+// DeepCopy is an autogenerated deepcopy function, copying the receiver, creating a new Selector.
+func (in Selector) DeepCopy() Selector {
+	if in == nil {
+		return nil
+	}
+	out := new(Selector)
+	in.DeepCopyInto(out)
+	return *out
+}
+
+// DeepCopyInto is an autogenerated deepcopy function, copying the receiver, writing into out. in must be non-nil.
+func (in *Workload) DeepCopyInto(out *Workload) {
+	*out = *in
+	out.TypeMeta = in.TypeMeta
+	in.ObjectMeta.DeepCopyInto(&out.ObjectMeta)
+	in.Status.DeepCopyInto(&out.Status)
+}
+
+// DeepCopy is an autogenerated deepcopy function, copying the receiver, creating a new Workload.
+func (in *Workload) DeepCopy() *Workload {
+	if in == nil {
+		return nil
+	}
+	out := new(Workload)
+	in.DeepCopyInto(out)
+	return out
+}
+
+// DeepCopyObject is an autogenerated deepcopy function, copying the receiver, creating a new runtime.Object.
+func (in *Workload) DeepCopyObject() runtime.Object {
+	if c := in.DeepCopy(); c != nil {
+		return c
+	}
+	return nil
+}
+
+// DeepCopyInto is an autogenerated deepcopy function, copying the receiver, writing into out. in must be non-nil.
+func (in *WorkloadList) DeepCopyInto(out *WorkloadList) {
+	*out = *in
+	out.TypeMeta = in.TypeMeta
+	in.ListMeta.DeepCopyInto(&out.ListMeta)
+	if in.Items != nil {
+		in, out := &in.Items, &out.Items
+		*out = make([]Workload, len(*in))
+		for i := range *in {
+			(*in)[i].DeepCopyInto(&(*out)[i])
+		}
+	}
+}
+
+// DeepCopy is an autogenerated deepcopy function, copying the receiver, creating a new WorkloadList.
+func (in *WorkloadList) DeepCopy() *WorkloadList {
+	if in == nil {
+		return nil
+	}
+	out := new(WorkloadList)
+	in.DeepCopyInto(out)
+	return out
+}
+
+// DeepCopyObject is an autogenerated deepcopy function, copying the receiver, creating a new runtime.Object.
+func (in *WorkloadList) DeepCopyObject() runtime.Object {
+	if c := in.DeepCopy(); c != nil {
+		return c
+	}
+	return nil
+}
+
+// DeepCopyInto is an autogenerated deepcopy function, copying the receiver, writing into out. in must be non-nil.
+func (in *WorkloadMonitor) DeepCopyInto(out *WorkloadMonitor) {
+	*out = *in
+	out.TypeMeta = in.TypeMeta
+	in.ObjectMeta.DeepCopyInto(&out.ObjectMeta)
+	in.Spec.DeepCopyInto(&out.Spec)
+	in.Status.DeepCopyInto(&out.Status)
+}
+
+// DeepCopy is an autogenerated deepcopy function, copying the receiver, creating a new WorkloadMonitor.
+func (in *WorkloadMonitor) DeepCopy() *WorkloadMonitor {
+	if in == nil {
+		return nil
+	}
+	out := new(WorkloadMonitor)
+	in.DeepCopyInto(out)
+	return out
+}
+
+// DeepCopyObject is an autogenerated deepcopy function, copying the receiver, creating a new runtime.Object.
+func (in *WorkloadMonitor) DeepCopyObject() runtime.Object {
+	if c := in.DeepCopy(); c != nil {
+		return c
+	}
+	return nil
+}
+
+// DeepCopyInto is an autogenerated deepcopy function, copying the receiver, writing into out. in must be non-nil.
+func (in *WorkloadMonitorList) DeepCopyInto(out *WorkloadMonitorList) {
+	*out = *in
+	out.TypeMeta = in.TypeMeta
+	in.ListMeta.DeepCopyInto(&out.ListMeta)
+	if in.Items != nil {
+		in, out := &in.Items, &out.Items
+		*out = make([]WorkloadMonitor, len(*in))
+		for i := range *in {
+			(*in)[i].DeepCopyInto(&(*out)[i])
+		}
+	}
+}
+
+// DeepCopy is an autogenerated deepcopy function, copying the receiver, creating a new WorkloadMonitorList.
+func (in *WorkloadMonitorList) DeepCopy() *WorkloadMonitorList {
+	if in == nil {
+		return nil
+	}
+	out := new(WorkloadMonitorList)
+	in.DeepCopyInto(out)
+	return out
+}
+
+// DeepCopyObject is an autogenerated deepcopy function, copying the receiver, creating a new runtime.Object.
+func (in *WorkloadMonitorList) DeepCopyObject() runtime.Object {
+	if c := in.DeepCopy(); c != nil {
+		return c
+	}
+	return nil
+}
+
+// DeepCopyInto is an autogenerated deepcopy function, copying the receiver, writing into out. in must be non-nil.
+func (in *WorkloadMonitorSpec) DeepCopyInto(out *WorkloadMonitorSpec) {
+	*out = *in
+	if in.Selector != nil {
+		in, out := &in.Selector, &out.Selector
+		*out = make(map[string]string, len(*in))
+		for key, val := range *in {
+			(*out)[key] = val
+		}
+	}
+	if in.MinReplicas != nil {
+		in, out := &in.MinReplicas, &out.MinReplicas
+		*out = new(int32)
+		**out = **in
+	}
+	if in.Replicas != nil {
+		in, out := &in.Replicas, &out.Replicas
+		*out = new(int32)
+		**out = **in
+	}
+}
+
+// DeepCopy is an autogenerated deepcopy function, copying the receiver, creating a new WorkloadMonitorSpec.
+func (in *WorkloadMonitorSpec) DeepCopy() *WorkloadMonitorSpec {
+	if in == nil {
+		return nil
+	}
+	out := new(WorkloadMonitorSpec)
+	in.DeepCopyInto(out)
+	return out
+}
+
+// DeepCopyInto is an autogenerated deepcopy function, copying the receiver, writing into out. in must be non-nil.
+func (in *WorkloadMonitorStatus) DeepCopyInto(out *WorkloadMonitorStatus) {
+	*out = *in
+	if in.Operational != nil {
+		in, out := &in.Operational, &out.Operational
+		*out = new(bool)
+		**out = **in
+	}
+}
+
+// DeepCopy is an autogenerated deepcopy function, copying the receiver, creating a new WorkloadMonitorStatus.
+func (in *WorkloadMonitorStatus) DeepCopy() *WorkloadMonitorStatus {
+	if in == nil {
+		return nil
+	}
+	out := new(WorkloadMonitorStatus)
+	in.DeepCopyInto(out)
+	return out
+}
+
+// DeepCopyInto is an autogenerated deepcopy function, copying the receiver, writing into out. in must be non-nil.
+func (in *WorkloadStatus) DeepCopyInto(out *WorkloadStatus) {
+	*out = *in
+	if in.Resources != nil {
+		in, out := &in.Resources, &out.Resources
+		*out = make(map[string]resource.Quantity, len(*in))
+		for key, val := range *in {
+			(*out)[key] = val.DeepCopy()
+		}
+	}
+}
+
+// DeepCopy is an autogenerated deepcopy function, copying the receiver, creating a new WorkloadStatus.
+func (in *WorkloadStatus) DeepCopy() *WorkloadStatus {
+	if in == nil {
+		return nil
+	}
+	out := new(WorkloadStatus)
+	in.DeepCopyInto(out)
+	return out
+}

cmd/cozystack-api/main.go

@@ -19,7 +19,7 @@ package main
 import (
 	"os"
 
-	"github.com/aenix.io/cozystack/pkg/cmd/server"
+	"github.com/cozystack/cozystack/pkg/cmd/server"
 	genericapiserver "k8s.io/apiserver/pkg/server"
 	"k8s.io/component-base/cli"
 )

cmd/cozystack-assets-server/main.go

@@ -0,0 +1,29 @@
+package main
+
+import (
+	"flag"
+	"log"
+	"net/http"
+	"path/filepath"
+)
+
+func main() {
+	addr := flag.String("address", ":8123", "Address to listen on")
+	dir := flag.String("dir", "/cozystack/assets", "Directory to serve files from")
+	flag.Parse()
+
+	absDir, err := filepath.Abs(*dir)
+	if err != nil {
+		log.Fatalf("Error getting absolute path for %s: %v", *dir, err)
+	}
+
+	fs := http.FileServer(http.Dir(absDir))
+	http.Handle("/", fs)
+
+	log.Printf("Server starting on %s, serving directory %s", *addr, absDir)
+
+	err = http.ListenAndServe(*addr, nil)
+	if err != nil {
+		log.Fatalf("Server failed to start: %v", err)
+	}
+}

cmd/cozystack-controller/main.go

@@ -0,0 +1,219 @@
+/*
+Copyright 2025.
+
+Licensed under the Apache License, Version 2.0 (the "License");
+you may not use this file except in compliance with the License.
+You may obtain a copy of the License at
+
+    http://www.apache.org/licenses/LICENSE-2.0
+
+Unless required by applicable law or agreed to in writing, software
+distributed under the License is distributed on an "AS IS" BASIS,
+WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+See the License for the specific language governing permissions and
+limitations under the License.
+*/
+
+package main
+
+import (
+	"crypto/tls"
+	"flag"
+	"os"
+	"time"
+
+	// Import all Kubernetes client auth plugins (e.g. Azure, GCP, OIDC, etc.)
+	// to ensure that exec-entrypoint and run can make use of them.
+	_ "k8s.io/client-go/plugin/pkg/client/auth"
+
+	"k8s.io/apimachinery/pkg/runtime"
+	utilruntime "k8s.io/apimachinery/pkg/util/runtime"
+	clientgoscheme "k8s.io/client-go/kubernetes/scheme"
+	ctrl "sigs.k8s.io/controller-runtime"
+	"sigs.k8s.io/controller-runtime/pkg/healthz"
+	"sigs.k8s.io/controller-runtime/pkg/log/zap"
+	"sigs.k8s.io/controller-runtime/pkg/metrics/filters"
+	metricsserver "sigs.k8s.io/controller-runtime/pkg/metrics/server"
+	"sigs.k8s.io/controller-runtime/pkg/webhook"
+
+	cozystackiov1alpha1 "github.com/cozystack/cozystack/api/v1alpha1"
+	"github.com/cozystack/cozystack/internal/controller"
+	"github.com/cozystack/cozystack/internal/telemetry"
+	// +kubebuilder:scaffold:imports
+)
+
+var (
+	scheme   = runtime.NewScheme()
+	setupLog = ctrl.Log.WithName("setup")
+)
+
+func init() {
+	utilruntime.Must(clientgoscheme.AddToScheme(scheme))
+
+	utilruntime.Must(cozystackiov1alpha1.AddToScheme(scheme))
+	// +kubebuilder:scaffold:scheme
+}
+
+func main() {
+	var metricsAddr string
+	var enableLeaderElection bool
+	var probeAddr string
+	var secureMetrics bool
+	var enableHTTP2 bool
+	var disableTelemetry bool
+	var telemetryEndpoint string
+	var telemetryInterval string
+	var cozystackVersion string
+	var tlsOpts []func(*tls.Config)
+	flag.StringVar(&metricsAddr, "metrics-bind-address", "0", "The address the metrics endpoint binds to. "+
+		"Use :8443 for HTTPS or :8080 for HTTP, or leave as 0 to disable the metrics service.")
+	flag.StringVar(&probeAddr, "health-probe-bind-address", ":8081", "The address the probe endpoint binds to.")
+	flag.BoolVar(&enableLeaderElection, "leader-elect", false,
+		"Enable leader election for controller manager. "+
+			"Enabling this will ensure there is only one active controller manager.")
+	flag.BoolVar(&secureMetrics, "metrics-secure", true,
+		"If set, the metrics endpoint is served securely via HTTPS. Use --metrics-secure=false to use HTTP instead.")
+	flag.BoolVar(&enableHTTP2, "enable-http2", false,
+		"If set, HTTP/2 will be enabled for the metrics and webhook servers")
+	flag.BoolVar(&disableTelemetry, "disable-telemetry", false,
+		"Disable telemetry collection")
+	flag.StringVar(&telemetryEndpoint, "telemetry-endpoint", "https://telemetry.cozystack.io",
+		"Endpoint for sending telemetry data")
+	flag.StringVar(&telemetryInterval, "telemetry-interval", "15m",
+		"Interval between telemetry data collection (e.g. 15m, 1h)")
+	flag.StringVar(&cozystackVersion, "cozystack-version", "unknown",
+		"Version of Cozystack")
+	opts := zap.Options{
+		Development: false,
+	}
+	opts.BindFlags(flag.CommandLine)
+	flag.Parse()
+
+	// Parse telemetry interval
+	interval, err := time.ParseDuration(telemetryInterval)
+	if err != nil {
+		setupLog.Error(err, "invalid telemetry interval")
+		os.Exit(1)
+	}
+
+	// Configure telemetry
+	telemetryConfig := telemetry.Config{
+		Disabled:         disableTelemetry,
+		Endpoint:         telemetryEndpoint,
+		Interval:         interval,
+		CozystackVersion: cozystackVersion,
+	}
+
+	ctrl.SetLogger(zap.New(zap.UseFlagOptions(&opts)))
+
+	// if the enable-http2 flag is false (the default), http/2 should be disabled
+	// due to its vulnerabilities. More specifically, disabling http/2 will
+	// prevent from being vulnerable to the HTTP/2 Stream Cancellation and
+	// Rapid Reset CVEs. For more information see:
+	// - https://github.com/advisories/GHSA-qppj-fm5r-hxr3
+	// - https://github.com/advisories/GHSA-4374-p667-p6c8
+	disableHTTP2 := func(c *tls.Config) {
+		setupLog.Info("disabling http/2")
+		c.NextProtos = []string{"http/1.1"}
+	}
+
+	if !enableHTTP2 {
+		tlsOpts = append(tlsOpts, disableHTTP2)
+	}
+
+	webhookServer := webhook.NewServer(webhook.Options{
+		TLSOpts: tlsOpts,
+	})
+
+	// Metrics endpoint is enabled in 'config/default/kustomization.yaml'. The Metrics options configure the server.
+	// More info:
+	// - https://pkg.go.dev/sigs.k8s.io/controller-runtime@v0.19.1/pkg/metrics/server
+	// - https://book.kubebuilder.io/reference/metrics.html
+	metricsServerOptions := metricsserver.Options{
+		BindAddress:   metricsAddr,
+		SecureServing: secureMetrics,
+		TLSOpts:       tlsOpts,
+	}
+
+	if secureMetrics {
+		// FilterProvider is used to protect the metrics endpoint with authn/authz.
+		// These configurations ensure that only authorized users and service accounts
+		// can access the metrics endpoint. The RBAC are configured in 'config/rbac/kustomization.yaml'. More info:
+		// https://pkg.go.dev/sigs.k8s.io/controller-runtime@v0.19.1/pkg/metrics/filters#WithAuthenticationAndAuthorization
+		metricsServerOptions.FilterProvider = filters.WithAuthenticationAndAuthorization
+
+		// TODO(user): If CertDir, CertName, and KeyName are not specified, controller-runtime will automatically
+		// generate self-signed certificates for the metrics server. While convenient for development and testing,
+		// this setup is not recommended for production.
+	}
+
+	mgr, err := ctrl.NewManager(ctrl.GetConfigOrDie(), ctrl.Options{
+		Scheme:                 scheme,
+		Metrics:                metricsServerOptions,
+		WebhookServer:          webhookServer,
+		HealthProbeBindAddress: probeAddr,
+		LeaderElection:         enableLeaderElection,
+		LeaderElectionID:       "19a0338c.cozystack.io",
+		// LeaderElectionReleaseOnCancel defines if the leader should step down voluntarily
+		// when the Manager ends. This requires the binary to immediately end when the
+		// Manager is stopped, otherwise, this setting is unsafe. Setting this significantly
+		// speeds up voluntary leader transitions as the new leader don't have to wait
+		// LeaseDuration time first.
+		//
+		// In the default scaffold provided, the program ends immediately after
+		// the manager stops, so would be fine to enable this option. However,
+		// if you are doing or is intended to do any operation such as perform cleanups
+		// after the manager stops then its usage might be unsafe.
+		// LeaderElectionReleaseOnCancel: true,
+	})
+	if err != nil {
+		setupLog.Error(err, "unable to start manager")
+		os.Exit(1)
+	}
+
+	if err = (&controller.WorkloadMonitorReconciler{
+		Client: mgr.GetClient(),
+		Scheme: mgr.GetScheme(),
+	}).SetupWithManager(mgr); err != nil {
+		setupLog.Error(err, "unable to create controller", "controller", "WorkloadMonitor")
+		os.Exit(1)
+	}
+
+	if err = (&controller.WorkloadReconciler{
+		Client: mgr.GetClient(),
+		Scheme: mgr.GetScheme(),
+	}).SetupWithManager(mgr); err != nil {
+		setupLog.Error(err, "unable to create controller", "controller", "Workload")
+		os.Exit(1)
+	}
+
+	// +kubebuilder:scaffold:builder
+
+	if err := mgr.AddHealthzCheck("healthz", healthz.Ping); err != nil {
+		setupLog.Error(err, "unable to set up health check")
+		os.Exit(1)
+	}
+	if err := mgr.AddReadyzCheck("readyz", healthz.Ping); err != nil {
+		setupLog.Error(err, "unable to set up ready check")
+		os.Exit(1)
+	}
+
+	// Initialize telemetry collector
+	collector, err := telemetry.NewCollector(mgr.GetClient(), &telemetryConfig, mgr.GetConfig())
+	if err != nil {
+		setupLog.V(1).Error(err, "unable to create telemetry collector, telemetry will be disabled")
+	}
+
+	if collector != nil {
+		if err := mgr.Add(collector); err != nil {
+			setupLog.Error(err, "unable to set up telemetry collector")
+			setupLog.V(1).Error(err, "unable to set up telemetry collector, continuing without telemetry")
+		}
+	}
+
+	setupLog.Info("starting manager")
+	if err := mgr.Start(ctrl.SetupSignalHandler()); err != nil {
+		setupLog.Error(err, "problem running manager")
+		os.Exit(1)
+	}
+}

go.mod

@@ -1,22 +1,27 @@
 // This is a generated file. Do not edit directly.
 
-module github.com/aenix.io/cozystack
+module github.com/cozystack/cozystack
 
 go 1.23.0
 
 require (
-	github.com/emicklei/go-restful/v3 v3.11.0
+	github.com/fluxcd/helm-controller/api v1.1.0
 	github.com/google/gofuzz v1.2.0
+	github.com/onsi/ginkgo/v2 v2.19.0
+	github.com/onsi/gomega v1.33.1
 	github.com/spf13/cobra v1.8.1
 	github.com/stretchr/testify v1.9.0
+	gopkg.in/yaml.v2 v2.4.0
+	k8s.io/api v0.31.2
 	k8s.io/apiextensions-apiserver v0.31.2
 	k8s.io/apimachinery v0.31.2
 	k8s.io/apiserver v0.31.2
 	k8s.io/client-go v0.31.2
-	k8s.io/code-generator v0.31.2
 	k8s.io/component-base v0.31.2
+	k8s.io/klog/v2 v2.130.1
 	k8s.io/kube-openapi v0.0.0-20240827152857-f7e401e7b4c2
 	k8s.io/utils v0.0.0-20240711033017-18e509b52bc8
+	sigs.k8s.io/controller-runtime v0.19.0
 	sigs.k8s.io/structured-merge-diff/v4 v4.4.1
 )
 
@@ -31,23 +36,27 @@ require (
 	github.com/coreos/go-semver v0.3.1 // indirect
 	github.com/coreos/go-systemd/v22 v22.5.0 // indirect
 	github.com/davecgh/go-spew v1.1.2-0.20180830191138-d8f796af33cc // indirect
+	github.com/emicklei/go-restful/v3 v3.11.0 // indirect
+	github.com/evanphx/json-patch/v5 v5.9.0 // indirect
 	github.com/felixge/httpsnoop v1.0.4 // indirect
-	github.com/fluxcd/helm-controller/api v1.1.0 // indirect
 	github.com/fluxcd/pkg/apis/kustomize v1.6.1 // indirect
 	github.com/fluxcd/pkg/apis/meta v1.6.1 // indirect
 	github.com/fsnotify/fsnotify v1.7.0 // indirect
 	github.com/fxamacker/cbor/v2 v2.7.0 // indirect
 	github.com/go-logr/logr v1.4.2 // indirect
 	github.com/go-logr/stdr v1.2.2 // indirect
+	github.com/go-logr/zapr v1.3.0 // indirect
 	github.com/go-openapi/jsonpointer v0.21.0 // indirect
 	github.com/go-openapi/jsonreference v0.20.2 // indirect
 	github.com/go-openapi/swag v0.23.0 // indirect
+	github.com/go-task/slim-sprig/v3 v3.0.0 // indirect
 	github.com/gogo/protobuf v1.3.2 // indirect
 	github.com/golang/groupcache v0.0.0-20210331224755-41bb18bfe9da // indirect
 	github.com/golang/protobuf v1.5.4 // indirect
 	github.com/google/cel-go v0.21.0 // indirect
 	github.com/google/gnostic-models v0.6.8 // indirect
 	github.com/google/go-cmp v0.6.0 // indirect
+	github.com/google/pprof v0.0.0-20240727154555-813a5fbdbec8 // indirect
 	github.com/google/uuid v1.6.0 // indirect
 	github.com/grpc-ecosystem/go-grpc-prometheus v1.2.0 // indirect
 	github.com/grpc-ecosystem/grpc-gateway/v2 v2.20.0 // indirect
@@ -84,7 +93,6 @@ require (
 	go.uber.org/zap v1.27.0 // indirect
 	golang.org/x/crypto v0.28.0 // indirect
 	golang.org/x/exp v0.0.0-20240719175910-8a7402abbf56 // indirect
-	golang.org/x/mod v0.21.0 // indirect
 	golang.org/x/net v0.30.0 // indirect
 	golang.org/x/oauth2 v0.23.0 // indirect
 	golang.org/x/sync v0.8.0 // indirect
@@ -93,6 +101,7 @@ require (
 	golang.org/x/text v0.19.0 // indirect
 	golang.org/x/time v0.7.0 // indirect
 	golang.org/x/tools v0.26.0 // indirect
+	gomodules.xyz/jsonpatch/v2 v2.4.0 // indirect
 	google.golang.org/genproto/googleapis/api v0.0.0-20240528184218-531527333157 // indirect
 	google.golang.org/genproto/googleapis/rpc v0.0.0-20240701130421-f6361c86f094 // indirect
 	google.golang.org/grpc v1.65.0 // indirect
@@ -100,14 +109,9 @@ require (
 	gopkg.in/evanphx/json-patch.v4 v4.12.0 // indirect
 	gopkg.in/inf.v0 v0.9.1 // indirect
 	gopkg.in/natefinch/lumberjack.v2 v2.2.1 // indirect
-	gopkg.in/yaml.v2 v2.4.0 // indirect
 	gopkg.in/yaml.v3 v3.0.1 // indirect
-	k8s.io/api v0.31.2 // indirect
-	k8s.io/gengo/v2 v2.0.0-20240911193312-2b36238f13e9 // indirect
-	k8s.io/klog/v2 v2.130.1 // indirect
 	k8s.io/kms v0.31.2 // indirect
 	sigs.k8s.io/apiserver-network-proxy/konnectivity-client v0.31.0 // indirect
-	sigs.k8s.io/controller-runtime v0.19.0 // indirect
 	sigs.k8s.io/json v0.0.0-20241010143419-9aa6b5e7a4b3 // indirect
 	sigs.k8s.io/yaml v1.4.0 // indirect
 )

go.sum

@@ -26,6 +26,10 @@ github.com/dustin/go-humanize v1.0.1 h1:GzkhY7T5VNhEkwH0PVJgjz+fX1rhBrR7pRT3mDkp
 github.com/dustin/go-humanize v1.0.1/go.mod h1:Mu1zIs6XwVuF/gI1OepvI0qD18qycQx+mFykh5fBlto=
 github.com/emicklei/go-restful/v3 v3.11.0 h1:rAQeMHw1c7zTmncogyy8VvRZwtkmkZ4FxERmMY4rD+g=
 github.com/emicklei/go-restful/v3 v3.11.0/go.mod h1:6n3XBCmQQb25CM2LCACGz8ukIrRry+4bhvbpWn3mrbc=
+github.com/evanphx/json-patch v0.5.2 h1:xVCHIVMUu1wtM/VkR9jVZ45N3FhZfYMMYGorLCR8P3k=
+github.com/evanphx/json-patch v0.5.2/go.mod h1:ZWS5hhDbVDyob71nXKNL0+PWn6ToqBHMikGIFbs31qQ=
+github.com/evanphx/json-patch/v5 v5.9.0 h1:kcBlZQbplgElYIlo/n1hJbls2z/1awpXxpRi0/FOJfg=
+github.com/evanphx/json-patch/v5 v5.9.0/go.mod h1:VNkHZ/282BpEyt/tObQO8s5CMPmYYq14uClGH4abBuQ=
 github.com/felixge/httpsnoop v1.0.4 h1:NFTV2Zj1bL4mc9sqWACXbQFVBBg2W3GPvqp8/ESS2Wg=
 github.com/felixge/httpsnoop v1.0.4/go.mod h1:m8KPJKqk1gH5J9DgRY2ASl2lWCfGKXixSwevea8zH2U=
 github.com/fluxcd/helm-controller/api v1.1.0 h1:NS5Wm3U6Kv4w7Cw2sDOV++vf2ecGfFV00x1+2Y3QcOY=
@@ -214,8 +218,6 @@ golang.org/x/exp v0.0.0-20240719175910-8a7402abbf56 h1:2dVuKD2vS7b0QIHQbpyTISPd0
 golang.org/x/exp v0.0.0-20240719175910-8a7402abbf56/go.mod h1:M4RDyNAINzryxdtnbRXRL/OHtkFuWGRjvuhBJpk2IlY=
 golang.org/x/mod v0.2.0/go.mod h1:s0Qsj1ACt9ePp/hMypM3fl4fZqREWJwdYDEqhRiZZUA=
 golang.org/x/mod v0.3.0/go.mod h1:s0Qsj1ACt9ePp/hMypM3fl4fZqREWJwdYDEqhRiZZUA=
-golang.org/x/mod v0.21.0 h1:vvrHzRwRfVKSiLrG+d4FMl/Qi4ukBCE6kZlTUkDYRT0=
-golang.org/x/mod v0.21.0/go.mod h1:6SkKJ3Xj0I0BrPOZoBy3bdMptDDU9oJrpohJ3eWZ1fY=
 golang.org/x/net v0.0.0-20190404232315-eb5bcb51f2a3/go.mod h1:t9HGtf8HONx5eT2rtn7q6eTqICYqUVnKs3thJo3Qplg=
 golang.org/x/net v0.0.0-20190620200207-3b0461eec859/go.mod h1:z5CRVTTTmAJ677TzLLGU+0bjPO0LkuOLi4/5GtJWs/s=
 golang.org/x/net v0.0.0-20200226121028-0de0cce0169b/go.mod h1:z5CRVTTTmAJ677TzLLGU+0bjPO0LkuOLi4/5GtJWs/s=
@@ -252,6 +254,8 @@ golang.org/x/xerrors v0.0.0-20190717185122-a985d3407aa7/go.mod h1:I/5z698sn9Ka8T
 golang.org/x/xerrors v0.0.0-20191011141410-1b5146add898/go.mod h1:I/5z698sn9Ka8TeJc9MKroUUfqBBauWjQqLJ2OPfmY0=
 golang.org/x/xerrors v0.0.0-20191204190536-9bdfabe68543/go.mod h1:I/5z698sn9Ka8TeJc9MKroUUfqBBauWjQqLJ2OPfmY0=
 golang.org/x/xerrors v0.0.0-20200804184101-5ec99f83aff1/go.mod h1:I/5z698sn9Ka8TeJc9MKroUUfqBBauWjQqLJ2OPfmY0=
+gomodules.xyz/jsonpatch/v2 v2.4.0 h1:Ci3iUJyx9UeRx7CeFN8ARgGbkESwJK+KB9lLcWxY/Zw=
+gomodules.xyz/jsonpatch/v2 v2.4.0/go.mod h1:AH3dM2RI6uoBZxn3LVrfvJ3E0/9dG4cSrbuBJT4moAY=
 google.golang.org/genproto v0.0.0-20230822172742-b8732ec3820d h1:VBu5YqKPv6XiJ199exd8Br+Aetz+o08F+PLMnwJQHAY=
 google.golang.org/genproto v0.0.0-20230822172742-b8732ec3820d/go.mod h1:yZTlhN0tQnXo3h00fuXNCxJdLdIdnVFVBaRJ5LWBbw4=
 google.golang.org/genproto/googleapis/api v0.0.0-20240528184218-531527333157 h1:7whR9kGa5LUwFtpLm2ArCEejtnxlGeLbAyjFY8sGNFw=
@@ -287,12 +291,8 @@ k8s.io/apiserver v0.31.2 h1:VUzOEUGRCDi6kX1OyQ801m4A7AUPglpsmGvdsekmcI4=
 k8s.io/apiserver v0.31.2/go.mod h1:o3nKZR7lPlJqkU5I3Ove+Zx3JuoFjQobGX1Gctw6XuE=
 k8s.io/client-go v0.31.2 h1:Y2F4dxU5d3AQj+ybwSMqQnpZH9F30//1ObxOKlTI9yc=
 k8s.io/client-go v0.31.2/go.mod h1:NPa74jSVR/+eez2dFsEIHNa+3o09vtNaWwWwb1qSxSs=
-k8s.io/code-generator v0.31.2 h1:xLWxG0HEpMSHfcM//3u3Ro2Hmc6AyyLINQS//Z2GEOI=
-k8s.io/code-generator v0.31.2/go.mod h1:eEQHXgBU/m7LDaToDoiz3t97dUUVyOblQdwOr8rivqc=
 k8s.io/component-base v0.31.2 h1:Z1J1LIaC0AV+nzcPRFqfK09af6bZ4D1nAOpWsy9owlA=
 k8s.io/component-base v0.31.2/go.mod h1:9PeyyFN/drHjtJZMCTkSpQJS3U9OXORnHQqMLDz0sUQ=
-k8s.io/gengo/v2 v2.0.0-20240911193312-2b36238f13e9 h1:si3PfKm8dDYxgfbeA6orqrtLkvvIeH8UqffFJDl0bz4=
-k8s.io/gengo/v2 v2.0.0-20240911193312-2b36238f13e9/go.mod h1:EJykeLsmFC60UQbYJezXkEsG2FLrt0GPNkU5iK5GWxU=
 k8s.io/klog/v2 v2.130.1 h1:n9Xl7H1Xvksem4KFG4PYbdQCQxqc/tTUyrgXaOhHSzk=
 k8s.io/klog/v2 v2.130.1/go.mod h1:3Jpz1GvMt720eyJH1ckRHK1EDfpxISzJ7I9OYgaDtPE=
 k8s.io/kms v0.31.2 h1:pyx7l2qVOkClzFMIWMVF/FxsSkgd+OIGH7DecpbscJI=

hack/boilerplate.go.txt

@@ -1,5 +1,5 @@
 /*
-Copyright 2024 The Cozystack Authors.
+Copyright 2025 The Cozystack Authors.
 
 Licensed under the Apache License, Version 2.0 (the "License");
 you may not use this file except in compliance with the License.

hack/download-dashboards.sh

@@ -21,7 +21,7 @@ fix_d8() {
 }
 
 swap_pvc_overview() {
- jq '(.panels[] | select(.title=="PVC Detailed") | .panels[] | select(.title=="Overview")) as $a | del(.panels[] | select(.title=="PVC Detailed").panels[] | select(.title=="Overview")) | ( (.panels[] | select(.title=="PVC Detailed"))) as $b | del( .panels[] | select(.title=="PVC Detailed")) | (.panels[.panels|length]=($a|.gridPos.y=$b.gridPos.y)) | (.panels[.panels|length]=($b|.gridPos.y=$a.gridPos.y))' 
+ jq '(.panels[] | select(.title=="PVC Detailed") | .panels[] | select(.title=="Overview")) as $a | del(.panels[] | select(.title=="PVC Detailed").panels[] | select(.title=="Overview")) | ( (.panels[] | select(.title=="PVC Detailed"))) as $b | del( .panels[] | select(.title=="PVC Detailed")) | (.panels[.panels|length]=($a|.gridPos.y=$b.gridPos.y)) | (.panels[.panels|length]=($b|.gridPos.y=$a.gridPos.y))'
 }
 
 deprectaed_remove_faq() {
@@ -68,7 +68,7 @@ modules/402-ingress-nginx/monitoring/grafana-dashboards/ingress-nginx/namespace/
 modules/402-ingress-nginx/monitoring/grafana-dashboards/ingress-nginx/vhost/vhost_detail.json
 modules/402-ingress-nginx/monitoring/grafana-dashboards/ingress-nginx/vhost/vhosts.json
 modules/340-monitoring-kubernetes-control-plane/monitoring/grafana-dashboards/kubernetes-cluster/control-plane-status.json
-modules/340-monitoring-kubernetes-control-plane/monitoring/grafana-dashboards/kubernetes-cluster/kube-etcd3.json                #TODO
+modules/340-monitoring-kubernetes-control-plane/monitoring/grafana-dashboards/kubernetes-cluster/kube-etcd.json                #TODO
 modules/340-monitoring-kubernetes-control-plane/monitoring/grafana-dashboards/kubernetes-cluster/deprecated-resources.json
 modules/340-monitoring-kubernetes/monitoring/grafana-dashboards//kubernetes-cluster/nodes/ntp.json                              #TODO
 modules/340-monitoring-kubernetes/monitoring/grafana-dashboards//kubernetes-cluster/nodes/nodes.json
@@ -78,6 +78,10 @@ modules/340-monitoring-kubernetes/monitoring/grafana-dashboards//main/pod.json
 modules/340-monitoring-kubernetes/monitoring/grafana-dashboards//main/namespace/namespaces.json
 modules/340-monitoring-kubernetes/monitoring/grafana-dashboards//main/namespace/namespace.json
 modules/340-monitoring-kubernetes/monitoring/grafana-dashboards//main/capacity-planning/capacity-planning.json
+modules/340-monitoring-kubernetes/monitoring/grafana-dashboards//flux/flux-control-plane.json
+modules/340-monitoring-kubernetes/monitoring/grafana-dashboards//flux/flux-stats.json
+modules/340-monitoring-kubernetes/monitoring/grafana-dashboards//kafka/strimzi-kafka.json
+modules/340-monitoring-kubernetes/monitoring/grafana-dashboards//goldpinger/goldpinger.json
 EOT
 
 
@@ -109,4 +113,3 @@ done <<\EOT
 	https://raw.githubusercontent.com/dotdc/grafana-dashboards-kubernetes/master/dashboards/k8s-views-namespaces.json
 	https://raw.githubusercontent.com/dotdc/grafana-dashboards-kubernetes/master/dashboards/k8s-views-pods.json
 EOT
-

hack/e2e.sh

@@ -60,7 +60,7 @@ done
 
 # Prepare system drive
 if [ ! -f nocloud-amd64.raw ]; then
-  wget https://github.com/aenix-io/cozystack/releases/latest/download/nocloud-amd64.raw.xz -O nocloud-amd64.raw.xz
+  wget https://github.com/cozystack/cozystack/releases/latest/download/nocloud-amd64.raw.xz -O nocloud-amd64.raw.xz
   rm -f nocloud-amd64.raw
   xz --decompress nocloud-amd64.raw.xz
 fi
@@ -84,7 +84,7 @@ done
 
 # Start VMs
 for i in 1 2 3; do
-  qemu-system-x86_64 -machine type=pc,accel=kvm -cpu host -smp 4 -m 8192 \
+  qemu-system-x86_64 -machine type=pc,accel=kvm -cpu host -smp 8 -m 16384 \
     -device virtio-net,netdev=net0,mac=52:54:00:12:34:5$i -netdev tap,id=net0,ifname=cozy-srv$i,script=no,downscript=no \
     -drive file=srv$i/system.img,if=virtio,format=raw \
     -drive file=srv$i/seed.img,if=virtio,format=raw \
@@ -113,8 +113,11 @@ machine:
         - usermode_helper=disabled
     - name: zfs
     - name: spl
-  install:
-    image: ghcr.io/aenix-io/cozystack/talos:v1.8.3
+  registries:
+    mirrors:
+      docker.io:
+        endpoints:
+        - https://mirror.gcr.io
   files:
   - content: |
       [plugins]
@@ -142,6 +145,9 @@ EOT
 
 cat > patch-controlplane.yaml <<\EOT
 machine:
+  nodeLabels:
+    node.kubernetes.io/exclude-from-external-load-balancers:
+      $patch: delete
   network:
     interfaces:
     - interface: eth0
@@ -228,6 +234,7 @@ sleep 5
 kubectl get hr -A | awk 'NR>1 {print "kubectl wait --timeout=15m --for=condition=ready -n " $1 " hr/" $2 " &"} END{print "wait"}' | sh -x
 
 # Wait for Cluster-API providers
+timeout 30 sh -c 'until kubectl get deploy -n cozy-cluster-api capi-controller-manager capi-kamaji-controller-manager capi-kubeadm-bootstrap-controller-manager capi-operator-cluster-api-operator capk-controller-manager; do sleep 1; done'
 kubectl wait deploy --timeout=30s --for=condition=available -n cozy-cluster-api capi-controller-manager capi-kamaji-controller-manager capi-kubeadm-bootstrap-controller-manager capi-operator-cluster-api-operator capk-controller-manager
 
 # Wait for linstor controller
@@ -296,6 +303,9 @@ spec:
   avoidBuggyIPs: false
 EOT
 
+# Wait for cozystack-api
+kubectl wait --for=condition=Available apiservices v1alpha1.apps.cozystack.io --timeout=2m
+
 kubectl patch -n tenant-root tenants.apps.cozystack.io root --type=merge -p '{"spec":{
   "host": "example.org",
   "ingress": true,
@@ -308,7 +318,12 @@ kubectl patch -n tenant-root tenants.apps.cozystack.io root --type=merge -p '{"s
 timeout 60 sh -c 'until kubectl get hr -n tenant-root etcd ingress monitoring tenant-root; do sleep 1; done'
 
 # Wait for HelmReleases be installed
-kubectl wait --timeout=2m --for=condition=ready -n tenant-root hr etcd ingress monitoring tenant-root
+kubectl wait --timeout=2m --for=condition=ready -n tenant-root hr etcd ingress tenant-root
+
+if ! kubectl wait --timeout=2m --for=condition=ready -n tenant-root hr monitoring; then
+  flux reconcile hr monitoring -n tenant-root --force
+  kubectl wait --timeout=2m --for=condition=ready -n tenant-root hr monitoring
+fi
 
 kubectl patch -n tenant-root ingresses.apps.cozystack.io ingress --type=merge -p '{"spec":{
   "dashboard": true
@@ -322,8 +337,8 @@ kubectl wait --timeout=5m --for=condition=available -n tenant-root deploy root-i
 kubectl wait --timeout=5m --for=jsonpath=.status.readyReplicas=3 -n tenant-root sts etcd
 
 # Wait for Victoria metrics
-kubectl wait --timeout=5m --for=jsonpath=.status.updateStatus=operational -n tenant-root vmalert/vmalert-longterm vmalert/vmalert-shortterm vmalertmanager/alertmanager
-kubectl wait --timeout=5m --for=jsonpath=.status.status=operational -n tenant-root vlogs/generic
+kubectl wait --timeout=5m --for=jsonpath=.status.updateStatus=operational -n tenant-root vmalert/vmalert-shortterm vmalertmanager/alertmanager
+kubectl wait --timeout=5m --for=jsonpath=.status.updateStatus=operational -n tenant-root vlogs/generic
 kubectl wait --timeout=5m --for=jsonpath=.status.clusterStatus=operational -n tenant-root vmcluster/shortterm vmcluster/longterm
 
 # Wait for grafana

hack/gen_versions_map.sh

@@ -1,12 +1,13 @@
 #!/bin/sh
 set -e
+
 file=versions_map
+
 charts=$(find . -mindepth 2 -maxdepth 2 -name Chart.yaml | awk 'sub("/Chart.yaml", "")')
 
-# <chart> <version> <commit> 
 new_map=$(
   for chart in $charts; do
-    awk '/^name:/ {chart=$2} /^version:/ {version=$2} END{printf "%s %s %s\n", chart, version, "HEAD"}' $chart/Chart.yaml
+    awk '/^name:/ {chart=$2} /^version:/ {version=$2} END{printf "%s %s %s\n", chart, version, "HEAD"}' "$chart/Chart.yaml"
   done
 )
 
@@ -15,47 +16,46 @@ if [ ! -f "$file" ] || [ ! -s "$file" ]; then
   exit 0
 fi
 
-miss_map=$(echo "$new_map" | awk 'NR==FNR { new_map[$1 " " $2] = $3; next } { if (!($1 " " $2 in new_map)) print $1, $2, $3}' - $file)
+miss_map=$(echo "$new_map" | awk 'NR==FNR { nm[$1 " " $2] = $3; next } { if (!($1 " " $2 in nm)) print $1, $2, $3}' - "$file")
+
+# search accross all tags sorted by version
+search_commits=$(git ls-remote --tags origin | awk -F/ '$3 ~ /v[0-9]+.[0-9]+.[0-9]+/ {print}' | sort -k2,2 -rV | awk '{print $1}')
 
 resolved_miss_map=$(
-  echo "$miss_map" | while read chart version commit; do
-    if [ "$commit" = HEAD ]; then
-      line=$(awk '/^version:/ {print NR; exit}' "./$chart/Chart.yaml")
-      change_commit=$(git --no-pager blame -L"$line",+1 -- "$chart/Chart.yaml" | awk '{print $1}')
-       
-      if [ "$change_commit" = "00000000" ]; then
-        # Not committed yet, use previous commit
-        line=$(git show HEAD:"./$chart/Chart.yaml" | awk '/^version:/ {print NR; exit}')
-        commit=$(git --no-pager blame -L"$line",+1 HEAD -- "$chart/Chart.yaml" | awk '{print $1}')
-        if [ $(echo $commit | cut -c1) = "^" ]; then
-          # Previous commit not exists
-          commit=$(echo $commit | cut -c2-)
-        fi
-      else
-        # Committed, but version_map wasn't updated
-        line=$(git show HEAD:"./$chart/Chart.yaml" | awk '/^version:/ {print NR; exit}')
-        change_commit=$(git --no-pager blame -L"$line",+1 HEAD -- "$chart/Chart.yaml" | awk '{print $1}')
-        if [ $(echo $change_commit | cut -c1) = "^" ]; then
-          # Previous commit not exists
-          commit=$(echo $change_commit | cut -c2-)
-        else
-          commit=$(git describe --always "$change_commit~1")
-        fi
+  echo "$miss_map" | while read -r chart version commit; do
+    # if version is found in HEAD, it's HEAD
+    if [ $(awk '$1 == "version:" {print $2}' ./${chart}/Chart.yaml) = "${version}" ]; then
+      echo "$chart $version HEAD"
+      continue
+    fi
+
+    # if commit is not HEAD, check if it's valid
+    if [ $commit != "HEAD" ]; then
+      if [ $(git show "${commit}:./${chart}/Chart.yaml" 2>/dev/null | awk '$1 == "version:" {print $2}') != "${version}" ]; then
+        echo "Commit $commit for $chart $version is not valid" >&2
+        exit 1
       fi
 
-      # Check if the commit belongs to the main branch
-      if ! git merge-base --is-ancestor "$commit" main; then
-        # Find the closest parent commit that belongs to main
-        commit_in_main=$(git log --pretty=format:"%h" main -- "$chart" | head -n 1)
-        if [ -n "$commit_in_main" ]; then
-          commit="$commit_in_main"
-        else
-          # No valid commit found in main branch for $chart, skipping..."
-          continue
-        fi
-      fi
+      commit=$(git rev-parse --short "$commit")
+      echo "$chart $version $commit"
+      continue
     fi
-    echo "$chart $version $commit"
+
+    # if commit is HEAD, but version is not found in HEAD, check all tags
+    found_tag=""
+    for tag in $search_commits; do
+      if [ $(git show "${tag}:./${chart}/Chart.yaml" 2>/dev/null | awk '$1 == "version:" {print $2}') = "${version}" ]; then
+        found_tag=$(git rev-parse --short "${tag}")
+        break
+      fi
+    done
+    
+    if [ -z "$found_tag" ]; then
+      echo "Can't find $chart $version in any version tag, removing it" >&2
+      continue
+    fi
+    
+    echo "$chart $version $found_tag"
   done
 )
 

hack/update-codegen.sh

@@ -22,6 +22,7 @@ SCRIPT_ROOT=$(dirname "${BASH_SOURCE[0]}")/..
 CODEGEN_PKG=${CODEGEN_PKG:-$(cd "${SCRIPT_ROOT}"; ls -d -1 ./vendor/k8s.io/code-generator 2>/dev/null || echo ../code-generator)}
 API_KNOWN_VIOLATIONS_DIR="${API_KNOWN_VIOLATIONS_DIR:-"${SCRIPT_ROOT}/api/api-rules"}"
 UPDATE_API_KNOWN_VIOLATIONS="${UPDATE_API_KNOWN_VIOLATIONS:-true}"
+CONTROLLER_GEN="go run sigs.k8s.io/controller-tools/cmd/controller-gen@v0.16.4"
 
 source "${CODEGEN_PKG}/kube_codegen.sh"
 
@@ -46,3 +47,6 @@ kube::codegen::gen_openapi \
     ${update_report:+"${update_report}"} \
     --boilerplate "${SCRIPT_ROOT}/hack/boilerplate.go.txt" \
     "${SCRIPT_ROOT}/pkg/apis"
+
+$CONTROLLER_GEN object:headerFile="hack/boilerplate.go.txt" paths="./api/..."
+$CONTROLLER_GEN rbac:roleName=manager-role crd paths="./api/..." output:crd:artifacts:config=packages/system/cozystack-controller/templates/crds

hack/upload-assets.sh

@@ -0,0 +1,11 @@
+#!/bin/bash
+set -xe
+
+version=${VERSION:-$(git describe --tags)}
+
+gh release upload --clobber $version _out/assets/cozystack-installer.yaml
+gh release upload --clobber $version _out/assets/metal-amd64.iso
+gh release upload --clobber $version _out/assets/metal-amd64.raw.xz
+gh release upload --clobber $version _out/assets/nocloud-amd64.raw.xz
+gh release upload --clobber $version _out/assets/kernel-amd64
+gh release upload --clobber $version _out/assets/initramfs-metal-amd64.xz

internal/controller/suite_test.go

@@ -0,0 +1,96 @@
+/*
+Copyright 2025.
+
+Licensed under the Apache License, Version 2.0 (the "License");
+you may not use this file except in compliance with the License.
+You may obtain a copy of the License at
+
+    http://www.apache.org/licenses/LICENSE-2.0
+
+Unless required by applicable law or agreed to in writing, software
+distributed under the License is distributed on an "AS IS" BASIS,
+WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+See the License for the specific language governing permissions and
+limitations under the License.
+*/
+
+package controller
+
+import (
+	"context"
+	"fmt"
+	"path/filepath"
+	"runtime"
+	"testing"
+
+	. "github.com/onsi/ginkgo/v2"
+	. "github.com/onsi/gomega"
+
+	"k8s.io/client-go/kubernetes/scheme"
+	"k8s.io/client-go/rest"
+	"sigs.k8s.io/controller-runtime/pkg/client"
+	"sigs.k8s.io/controller-runtime/pkg/envtest"
+	logf "sigs.k8s.io/controller-runtime/pkg/log"
+	"sigs.k8s.io/controller-runtime/pkg/log/zap"
+
+	cozystackiov1alpha1 "github.com/cozystack/cozystack/api/v1alpha1"
+	// +kubebuilder:scaffold:imports
+)
+
+// These tests use Ginkgo (BDD-style Go testing framework). Refer to
+// http://onsi.github.io/ginkgo/ to learn more about Ginkgo.
+
+var cfg *rest.Config
+var k8sClient client.Client
+var testEnv *envtest.Environment
+var ctx context.Context
+var cancel context.CancelFunc
+
+func TestControllers(t *testing.T) {
+	RegisterFailHandler(Fail)
+
+	RunSpecs(t, "Controller Suite")
+}
+
+var _ = BeforeSuite(func() {
+	logf.SetLogger(zap.New(zap.WriteTo(GinkgoWriter), zap.UseDevMode(true)))
+
+	ctx, cancel = context.WithCancel(context.TODO())
+
+	By("bootstrapping test environment")
+	testEnv = &envtest.Environment{
+		CRDDirectoryPaths:     []string{filepath.Join("..", "..", "config", "crd", "bases")},
+		ErrorIfCRDPathMissing: true,
+
+		// The BinaryAssetsDirectory is only required if you want to run the tests directly
+		// without call the makefile target test. If not informed it will look for the
+		// default path defined in controller-runtime which is /usr/local/kubebuilder/.
+		// Note that you must have the required binaries setup under the bin directory to perform
+		// the tests directly. When we run make test it will be setup and used automatically.
+		BinaryAssetsDirectory: filepath.Join("..", "..", "bin", "k8s",
+			fmt.Sprintf("1.31.0-%s-%s", runtime.GOOS, runtime.GOARCH)),
+	}
+
+	var err error
+	// cfg is defined in this file globally.
+	cfg, err = testEnv.Start()
+	Expect(err).NotTo(HaveOccurred())
+	Expect(cfg).NotTo(BeNil())
+
+	err = cozystackiov1alpha1.AddToScheme(scheme.Scheme)
+	Expect(err).NotTo(HaveOccurred())
+
+	// +kubebuilder:scaffold:scheme
+
+	k8sClient, err = client.New(cfg, client.Options{Scheme: scheme.Scheme})
+	Expect(err).NotTo(HaveOccurred())
+	Expect(k8sClient).NotTo(BeNil())
+
+})
+
+var _ = AfterSuite(func() {
+	By("tearing down the test environment")
+	cancel()
+	err := testEnv.Stop()
+	Expect(err).NotTo(HaveOccurred())
+})

internal/controller/workload_controller.go

@@ -0,0 +1,87 @@
+package controller
+
+import (
+	"context"
+	"strings"
+
+	corev1 "k8s.io/api/core/v1"
+	apierrors "k8s.io/apimachinery/pkg/api/errors"
+	"k8s.io/apimachinery/pkg/runtime"
+	"k8s.io/apimachinery/pkg/types"
+	ctrl "sigs.k8s.io/controller-runtime"
+	"sigs.k8s.io/controller-runtime/pkg/client"
+	"sigs.k8s.io/controller-runtime/pkg/log"
+
+	cozyv1alpha1 "github.com/cozystack/cozystack/api/v1alpha1"
+)
+
+// WorkloadMonitorReconciler reconciles a WorkloadMonitor object
+type WorkloadReconciler struct {
+	client.Client
+	Scheme *runtime.Scheme
+}
+
+func (r *WorkloadReconciler) Reconcile(ctx context.Context, req ctrl.Request) (ctrl.Result, error) {
+	logger := log.FromContext(ctx)
+	w := &cozyv1alpha1.Workload{}
+	err := r.Get(ctx, req.NamespacedName, w)
+	if err != nil {
+		if apierrors.IsNotFound(err) {
+			return ctrl.Result{}, nil
+		}
+		logger.Error(err, "Unable to fetch Workload")
+		return ctrl.Result{}, err
+	}
+
+	// it's being deleted, nothing to handle
+	if w.DeletionTimestamp != nil {
+		return ctrl.Result{}, nil
+	}
+
+	t := getMonitoredObject(w)
+	err = r.Get(ctx, types.NamespacedName{Name: t.GetName(), Namespace: t.GetNamespace()}, t)
+
+	// found object, nothing to do
+	if err == nil {
+		return ctrl.Result{}, nil
+	}
+
+	// error getting object but not 404 -- requeue
+	if !apierrors.IsNotFound(err) {
+		logger.Error(err, "failed to get dependent object", "kind", t.GetObjectKind(), "dependent-object-name", t.GetName())
+		return ctrl.Result{}, err
+	}
+
+	err = r.Delete(ctx, w)
+	if err != nil {
+		logger.Error(err, "failed to delete workload")
+	}
+	return ctrl.Result{}, err
+}
+
+// SetupWithManager registers our controller with the Manager and sets up watches.
+func (r *WorkloadReconciler) SetupWithManager(mgr ctrl.Manager) error {
+	return ctrl.NewControllerManagedBy(mgr).
+		// Watch WorkloadMonitor objects
+		For(&cozyv1alpha1.Workload{}).
+		Complete(r)
+}
+
+func getMonitoredObject(w *cozyv1alpha1.Workload) client.Object {
+	if strings.HasPrefix(w.Name, "pvc-") {
+		obj := &corev1.PersistentVolumeClaim{}
+		obj.Name = strings.TrimPrefix(w.Name, "pvc-")
+		obj.Namespace = w.Namespace
+		return obj
+	}
+	if strings.HasPrefix(w.Name, "svc-") {
+		obj := &corev1.Service{}
+		obj.Name = strings.TrimPrefix(w.Name, "svc-")
+		obj.Namespace = w.Namespace
+		return obj
+	}
+	obj := &corev1.Pod{}
+	obj.Name = w.Name
+	obj.Namespace = w.Namespace
+	return obj
+}

internal/controller/workloadmonitor_controller.go

@@ -0,0 +1,424 @@
+package controller
+
+import (
+	"context"
+	"encoding/json"
+	"fmt"
+	"sort"
+
+	apierrors "k8s.io/apimachinery/pkg/api/errors"
+	"k8s.io/apimachinery/pkg/runtime"
+	"k8s.io/apimachinery/pkg/types"
+	"k8s.io/utils/pointer"
+	ctrl "sigs.k8s.io/controller-runtime"
+	"sigs.k8s.io/controller-runtime/pkg/client"
+	"sigs.k8s.io/controller-runtime/pkg/handler"
+	"sigs.k8s.io/controller-runtime/pkg/log"
+	"sigs.k8s.io/controller-runtime/pkg/reconcile"
+
+	corev1 "k8s.io/api/core/v1"
+	"k8s.io/apimachinery/pkg/api/resource"
+	metav1 "k8s.io/apimachinery/pkg/apis/meta/v1"
+
+	cozyv1alpha1 "github.com/cozystack/cozystack/api/v1alpha1"
+)
+
+// WorkloadMonitorReconciler reconciles a WorkloadMonitor object
+type WorkloadMonitorReconciler struct {
+	client.Client
+	Scheme *runtime.Scheme
+}
+
+// +kubebuilder:rbac:groups=cozystack.io,resources=workloadmonitors,verbs=get;list;watch;create;update;patch;delete
+// +kubebuilder:rbac:groups=cozystack.io,resources=workloadmonitors/status,verbs=get;update;patch
+// +kubebuilder:rbac:groups=cozystack.io,resources=workloads,verbs=get;list;watch;create;update;patch;delete
+// +kubebuilder:rbac:groups=cozystack.io,resources=workloads/status,verbs=get;update;patch
+// +kubebuilder:rbac:groups=core,resources=pods,verbs=get;list;watch
+// +kubebuilder:rbac:groups=core,resources=persistentvolumeclaims,verbs=get;list;watch
+
+// isServiceReady checks if the service has an external IP bound
+func (r *WorkloadMonitorReconciler) isServiceReady(svc *corev1.Service) bool {
+	return len(svc.Status.LoadBalancer.Ingress) > 0
+}
+
+// isPVCReady checks if the PVC is bound
+func (r *WorkloadMonitorReconciler) isPVCReady(pvc *corev1.PersistentVolumeClaim) bool {
+	return pvc.Status.Phase == corev1.ClaimBound
+}
+
+// isPodReady checks if the Pod is in the Ready condition.
+func (r *WorkloadMonitorReconciler) isPodReady(pod *corev1.Pod) bool {
+	for _, c := range pod.Status.Conditions {
+		if c.Type == corev1.PodReady && c.Status == corev1.ConditionTrue {
+			return true
+		}
+	}
+	return false
+}
+
+// updateOwnerReferences adds the given monitor as a new owner reference to the object if not already present.
+// It then sorts the owner references to enforce a consistent order.
+func updateOwnerReferences(obj metav1.Object, monitor client.Object) {
+	// Retrieve current owner references
+	owners := obj.GetOwnerReferences()
+
+	// Check if current monitor is already in owner references
+	var alreadyOwned bool
+	for _, ownerRef := range owners {
+		if ownerRef.UID == monitor.GetUID() {
+			alreadyOwned = true
+			break
+		}
+	}
+
+	runtimeObj, ok := monitor.(runtime.Object)
+	if !ok {
+		return
+	}
+	gvk := runtimeObj.GetObjectKind().GroupVersionKind()
+
+	// If not already present, add new owner reference without controller flag
+	if !alreadyOwned {
+		newOwnerRef := metav1.OwnerReference{
+			APIVersion: gvk.GroupVersion().String(),
+			Kind:       gvk.Kind,
+			Name:       monitor.GetName(),
+			UID:        monitor.GetUID(),
+			// Set Controller to false to avoid conflict as multiple controllers are not allowed
+			Controller:         pointer.BoolPtr(false),
+			BlockOwnerDeletion: pointer.BoolPtr(true),
+		}
+		owners = append(owners, newOwnerRef)
+	}
+
+	// Sort owner references to enforce a consistent order by UID
+	sort.SliceStable(owners, func(i, j int) bool {
+		return owners[i].UID < owners[j].UID
+	})
+
+	// Update the owner references of the object
+	obj.SetOwnerReferences(owners)
+}
+
+// reconcileServiceForMonitor creates or updates a Workload object for the given Service and WorkloadMonitor.
+func (r *WorkloadMonitorReconciler) reconcileServiceForMonitor(
+	ctx context.Context,
+	monitor *cozyv1alpha1.WorkloadMonitor,
+	svc corev1.Service,
+) error {
+	logger := log.FromContext(ctx)
+	workload := &cozyv1alpha1.Workload{
+		ObjectMeta: metav1.ObjectMeta{
+			Name:      fmt.Sprintf("svc-%s", svc.Name),
+			Namespace: svc.Namespace,
+		},
+	}
+
+	resources := make(map[string]resource.Quantity)
+
+	q := resource.MustParse("0")
+
+	for _, ing := range svc.Status.LoadBalancer.Ingress {
+		if ing.IP != "" {
+			q.Add(resource.MustParse("1"))
+		}
+	}
+
+	resources["public-ips"] = q
+
+	_, err := ctrl.CreateOrUpdate(ctx, r.Client, workload, func() error {
+		// Update owner references with the new monitor
+		updateOwnerReferences(workload.GetObjectMeta(), monitor)
+
+		workload.Labels = svc.Labels
+
+		// Fill Workload status fields:
+		workload.Status.Kind = monitor.Spec.Kind
+		workload.Status.Type = monitor.Spec.Type
+		workload.Status.Resources = resources
+		workload.Status.Operational = r.isServiceReady(&svc)
+
+		return nil
+	})
+	if err != nil {
+		logger.Error(err, "Failed to CreateOrUpdate Workload", "workload", workload.Name)
+		return err
+	}
+
+	return nil
+}
+
+// reconcilePVCForMonitor creates or updates a Workload object for the given PVC and WorkloadMonitor.
+func (r *WorkloadMonitorReconciler) reconcilePVCForMonitor(
+	ctx context.Context,
+	monitor *cozyv1alpha1.WorkloadMonitor,
+	pvc corev1.PersistentVolumeClaim,
+) error {
+	logger := log.FromContext(ctx)
+	workload := &cozyv1alpha1.Workload{
+		ObjectMeta: metav1.ObjectMeta{
+			Name:      fmt.Sprintf("pvc-%s", pvc.Name),
+			Namespace: pvc.Namespace,
+		},
+	}
+
+	resources := make(map[string]resource.Quantity)
+
+	for resourceName, resourceQuantity := range pvc.Status.Capacity {
+		resources[resourceName.String()] = resourceQuantity
+	}
+
+	_, err := ctrl.CreateOrUpdate(ctx, r.Client, workload, func() error {
+		// Update owner references with the new monitor
+		updateOwnerReferences(workload.GetObjectMeta(), monitor)
+
+		workload.Labels = pvc.Labels
+
+		// Fill Workload status fields:
+		workload.Status.Kind = monitor.Spec.Kind
+		workload.Status.Type = monitor.Spec.Type
+		workload.Status.Resources = resources
+		workload.Status.Operational = r.isPVCReady(&pvc)
+
+		return nil
+	})
+	if err != nil {
+		logger.Error(err, "Failed to CreateOrUpdate Workload", "workload", workload.Name)
+		return err
+	}
+
+	return nil
+}
+
+// reconcilePodForMonitor creates or updates a Workload object for the given Pod and WorkloadMonitor.
+func (r *WorkloadMonitorReconciler) reconcilePodForMonitor(
+	ctx context.Context,
+	monitor *cozyv1alpha1.WorkloadMonitor,
+	pod corev1.Pod,
+) error {
+	logger := log.FromContext(ctx)
+
+	// Combine both init containers and normal containers to sum resources properly
+	combinedContainers := append(pod.Spec.InitContainers, pod.Spec.Containers...)
+
+	// totalResources will store the sum of all container resource limits
+	totalResources := make(map[string]resource.Quantity)
+
+	// Iterate over all containers to aggregate their Limits
+	for _, container := range combinedContainers {
+		for name, qty := range container.Resources.Limits {
+			if existing, exists := totalResources[name.String()]; exists {
+				existing.Add(qty)
+				totalResources[name.String()] = existing
+			} else {
+				totalResources[name.String()] = qty.DeepCopy()
+			}
+		}
+	}
+
+	// If annotation "workload.cozystack.io/resources" is present, parse and merge
+	if resourcesStr, ok := pod.Annotations["workload.cozystack.io/resources"]; ok {
+		annRes := map[string]string{}
+		if err := json.Unmarshal([]byte(resourcesStr), &annRes); err != nil {
+			logger.Error(err, "Failed to parse resources annotation", "pod", pod.Name)
+		} else {
+			for k, v := range annRes {
+				parsed, err := resource.ParseQuantity(v)
+				if err != nil {
+					logger.Error(err, "Failed to parse resource quantity from annotation", "key", k, "value", v)
+					continue
+				}
+				totalResources[k] = parsed
+			}
+		}
+	}
+
+	workload := &cozyv1alpha1.Workload{
+		ObjectMeta: metav1.ObjectMeta{
+			Name:      pod.Name,
+			Namespace: pod.Namespace,
+		},
+	}
+
+	_, err := ctrl.CreateOrUpdate(ctx, r.Client, workload, func() error {
+		// Update owner references with the new monitor
+		updateOwnerReferences(workload.GetObjectMeta(), monitor)
+
+		// Copy labels from the Pod if needed
+		workload.Labels = pod.Labels
+
+		// Fill Workload status fields:
+		workload.Status.Kind = monitor.Spec.Kind
+		workload.Status.Type = monitor.Spec.Type
+		workload.Status.Resources = totalResources
+		workload.Status.Operational = r.isPodReady(&pod)
+
+		return nil
+	})
+	if err != nil {
+		logger.Error(err, "Failed to CreateOrUpdate Workload", "workload", workload.Name)
+		return err
+	}
+
+	return nil
+}
+
+// Reconcile is the main reconcile loop.
+// 1. It reconciles WorkloadMonitor objects themselves (create/update/delete).
+// 2. It also reconciles Pod events mapped to WorkloadMonitor via label selector.
+func (r *WorkloadMonitorReconciler) Reconcile(ctx context.Context, req ctrl.Request) (ctrl.Result, error) {
+	logger := log.FromContext(ctx)
+
+	// Fetch the WorkloadMonitor object if it exists
+	monitor := &cozyv1alpha1.WorkloadMonitor{}
+	err := r.Get(ctx, req.NamespacedName, monitor)
+	if err != nil {
+		// If the resource is not found, it may be a Pod event (mapFunc).
+		if apierrors.IsNotFound(err) {
+			return ctrl.Result{}, nil
+		}
+		logger.Error(err, "Unable to fetch WorkloadMonitor")
+		return ctrl.Result{}, err
+	}
+
+	// List Pods that match the WorkloadMonitor's selector
+	podList := &corev1.PodList{}
+	if err := r.List(
+		ctx,
+		podList,
+		client.InNamespace(monitor.Namespace),
+		client.MatchingLabels(monitor.Spec.Selector),
+	); err != nil {
+		logger.Error(err, "Unable to list Pods for WorkloadMonitor", "monitor", monitor.Name)
+		return ctrl.Result{}, err
+	}
+
+	var observedReplicas, availableReplicas int32
+
+	// For each matching Pod, reconcile the corresponding Workload
+	for _, pod := range podList.Items {
+		observedReplicas++
+		if err := r.reconcilePodForMonitor(ctx, monitor, pod); err != nil {
+			logger.Error(err, "Failed to reconcile Workload for Pod", "pod", pod.Name)
+			continue
+		}
+		if r.isPodReady(&pod) {
+			availableReplicas++
+		}
+	}
+
+	pvcList := &corev1.PersistentVolumeClaimList{}
+	if err := r.List(
+		ctx,
+		pvcList,
+		client.InNamespace(monitor.Namespace),
+		client.MatchingLabels(monitor.Spec.Selector),
+	); err != nil {
+		logger.Error(err, "Unable to list PVCs for WorkloadMonitor", "monitor", monitor.Name)
+		return ctrl.Result{}, err
+	}
+
+	for _, pvc := range pvcList.Items {
+		if err := r.reconcilePVCForMonitor(ctx, monitor, pvc); err != nil {
+			logger.Error(err, "Failed to reconcile Workload for PVC", "PVC", pvc.Name)
+			continue
+		}
+	}
+
+	svcList := &corev1.ServiceList{}
+	if err := r.List(
+		ctx,
+		svcList,
+		client.InNamespace(monitor.Namespace),
+		client.MatchingLabels(monitor.Spec.Selector),
+	); err != nil {
+		logger.Error(err, "Unable to list Services for WorkloadMonitor", "monitor", monitor.Name)
+		return ctrl.Result{}, err
+	}
+
+	for _, svc := range svcList.Items {
+		if svc.Spec.Type != corev1.ServiceTypeLoadBalancer {
+			continue
+		}
+		if err := r.reconcileServiceForMonitor(ctx, monitor, svc); err != nil {
+			logger.Error(err, "Failed to reconcile Workload for Service", "Service", svc.Name)
+			continue
+		}
+	}
+
+	// Update WorkloadMonitor status based on observed pods
+	monitor.Status.ObservedReplicas = observedReplicas
+	monitor.Status.AvailableReplicas = availableReplicas
+
+	// Default to operational = true, but check MinReplicas if set
+	monitor.Status.Operational = pointer.Bool(true)
+	if monitor.Spec.MinReplicas != nil && availableReplicas < *monitor.Spec.MinReplicas {
+		monitor.Status.Operational = pointer.Bool(false)
+	}
+
+	// Update the WorkloadMonitor status in the cluster
+	if err := r.Status().Update(ctx, monitor); err != nil {
+		logger.Error(err, "Unable to update WorkloadMonitor status", "monitor", monitor.Name)
+		return ctrl.Result{}, err
+	}
+
+	// Return without requeue if we want purely event-driven reconciliations
+	return ctrl.Result{}, nil
+}
+
+// SetupWithManager registers our controller with the Manager and sets up watches.
+func (r *WorkloadMonitorReconciler) SetupWithManager(mgr ctrl.Manager) error {
+	return ctrl.NewControllerManagedBy(mgr).
+		// Watch WorkloadMonitor objects
+		For(&cozyv1alpha1.WorkloadMonitor{}).
+		// Also watch Pod objects and map them back to WorkloadMonitor if labels match
+		Watches(
+			&corev1.Pod{},
+			handler.EnqueueRequestsFromMapFunc(mapObjectToMonitor(&corev1.Pod{}, r.Client)),
+		).
+		// Watch PVCs as well
+		Watches(
+			&corev1.PersistentVolumeClaim{},
+			handler.EnqueueRequestsFromMapFunc(mapObjectToMonitor(&corev1.PersistentVolumeClaim{}, r.Client)),
+		).
+		// Watch for changes to Workload objects we create (owned by WorkloadMonitor)
+		Owns(&cozyv1alpha1.Workload{}).
+		Complete(r)
+}
+
+func mapObjectToMonitor[T client.Object](_ T, c client.Client) func(ctx context.Context, obj client.Object) []reconcile.Request {
+	return func(ctx context.Context, obj client.Object) []reconcile.Request {
+		concrete, ok := obj.(T)
+		if !ok {
+			return nil
+		}
+
+		var monitorList cozyv1alpha1.WorkloadMonitorList
+		// List all WorkloadMonitors in the same namespace
+		if err := c.List(ctx, &monitorList, client.InNamespace(concrete.GetNamespace())); err != nil {
+			return nil
+		}
+
+		labels := concrete.GetLabels()
+		// Match each monitor's selector with the Pod's labels
+		var requests []reconcile.Request
+		for _, m := range monitorList.Items {
+			matches := true
+			for k, v := range m.Spec.Selector {
+				if labelVal, exists := labels[k]; !exists || labelVal != v {
+					matches = false
+					break
+				}
+			}
+			if matches {
+				requests = append(requests, reconcile.Request{
+					NamespacedName: types.NamespacedName{
+						Namespace: m.Namespace,
+						Name:      m.Name,
+					},
+				})
+			}
+		}
+		return requests
+	}
+}

internal/telemetry/collector.go

@@ -0,0 +1,292 @@
+package telemetry
+
+import (
+	"bytes"
+	"context"
+	"fmt"
+	"net/http"
+	"strings"
+	"time"
+
+	corev1 "k8s.io/api/core/v1"
+	"k8s.io/apimachinery/pkg/api/resource"
+	"k8s.io/apimachinery/pkg/types"
+	"k8s.io/client-go/discovery"
+	"k8s.io/client-go/rest"
+	"sigs.k8s.io/controller-runtime/pkg/client"
+	"sigs.k8s.io/controller-runtime/pkg/log"
+
+	cozyv1alpha1 "github.com/cozystack/cozystack/api/v1alpha1"
+)
+
+// Collector handles telemetry data collection and sending
+type Collector struct {
+	client          client.Client
+	discoveryClient discovery.DiscoveryInterface
+	config          *Config
+	ticker          *time.Ticker
+	stopCh          chan struct{}
+}
+
+// NewCollector creates a new telemetry collector
+func NewCollector(client client.Client, config *Config, kubeConfig *rest.Config) (*Collector, error) {
+	discoveryClient, err := discovery.NewDiscoveryClientForConfig(kubeConfig)
+	if err != nil {
+		return nil, fmt.Errorf("failed to create discovery client: %w", err)
+	}
+	return &Collector{
+		client:          client,
+		discoveryClient: discoveryClient,
+		config:          config,
+	}, nil
+}
+
+// Start implements manager.Runnable
+func (c *Collector) Start(ctx context.Context) error {
+	if c.config.Disabled {
+		return nil
+	}
+
+	c.ticker = time.NewTicker(c.config.Interval)
+	c.stopCh = make(chan struct{})
+
+	// Initial collection
+	c.collect(ctx)
+
+	for {
+		select {
+		case <-ctx.Done():
+			c.ticker.Stop()
+			close(c.stopCh)
+			return nil
+		case <-c.ticker.C:
+			c.collect(ctx)
+		}
+	}
+}
+
+// NeedLeaderElection implements manager.LeaderElectionRunnable
+func (c *Collector) NeedLeaderElection() bool {
+	// Only run telemetry collector on the leader
+	return true
+}
+
+// Stop halts telemetry collection
+func (c *Collector) Stop() {
+	close(c.stopCh)
+}
+
+// getSizeGroup returns the exponential size group for PVC
+func getSizeGroup(size resource.Quantity) string {
+	gb := size.Value() / (1024 * 1024 * 1024)
+	switch {
+	case gb <= 1:
+		return "1Gi"
+	case gb <= 5:
+		return "5Gi"
+	case gb <= 10:
+		return "10Gi"
+	case gb <= 25:
+		return "25Gi"
+	case gb <= 50:
+		return "50Gi"
+	case gb <= 100:
+		return "100Gi"
+	case gb <= 250:
+		return "250Gi"
+	case gb <= 500:
+		return "500Gi"
+	case gb <= 1024:
+		return "1Ti"
+	case gb <= 2048:
+		return "2Ti"
+	case gb <= 5120:
+		return "5Ti"
+	default:
+		return "10Ti"
+	}
+}
+
+// collect gathers and sends telemetry data
+func (c *Collector) collect(ctx context.Context) {
+	logger := log.FromContext(ctx).V(1)
+
+	// Get cluster ID from kube-system namespace
+	var kubeSystemNS corev1.Namespace
+	if err := c.client.Get(ctx, types.NamespacedName{Name: "kube-system"}, &kubeSystemNS); err != nil {
+		logger.Info(fmt.Sprintf("Failed to get kube-system namespace: %v", err))
+		return
+	}
+
+	clusterID := string(kubeSystemNS.UID)
+
+	var cozystackCM corev1.ConfigMap
+	if err := c.client.Get(ctx, types.NamespacedName{Namespace: "cozy-system", Name: "cozystack"}, &cozystackCM); err != nil {
+		logger.Info(fmt.Sprintf("Failed to get cozystack configmap in cozy-system namespace: %v", err))
+		return
+	}
+
+	oidcEnabled := cozystackCM.Data["oidc-enabled"]
+	bundle := cozystackCM.Data["bundle-name"]
+	bundleEnable := cozystackCM.Data["bundle-enable"]
+	bundleDisable := cozystackCM.Data["bundle-disable"]
+
+	// Get Kubernetes version from nodes
+	var nodeList corev1.NodeList
+	if err := c.client.List(ctx, &nodeList); err != nil {
+		logger.Info(fmt.Sprintf("Failed to list nodes: %v", err))
+		return
+	}
+
+	// Create metrics buffer
+	var metrics strings.Builder
+
+	// Add Cozystack info metric
+	if len(nodeList.Items) > 0 {
+		k8sVersion, _ := c.discoveryClient.ServerVersion()
+		metrics.WriteString(fmt.Sprintf(
+			"cozy_cluster_info{cozystack_version=\"%s\",kubernetes_version=\"%s\",oidc_enabled=\"%s\",bundle_name=\"%s\",bunde_enable=\"%s\",bunde_disable=\"%s\"} 1\n",
+			c.config.CozystackVersion,
+			k8sVersion,
+			oidcEnabled,
+			bundle,
+			bundleEnable,
+			bundleDisable,
+		))
+	}
+
+	// Collect node metrics
+	nodeOSCount := make(map[string]int)
+	for _, node := range nodeList.Items {
+		key := fmt.Sprintf("%s (%s)", node.Status.NodeInfo.OperatingSystem, node.Status.NodeInfo.OSImage)
+		nodeOSCount[key] = nodeOSCount[key] + 1
+	}
+
+	for osKey, count := range nodeOSCount {
+		metrics.WriteString(fmt.Sprintf(
+			"cozy_nodes_count{os=\"%s\",kernel=\"%s\"} %d\n",
+			osKey,
+			nodeList.Items[0].Status.NodeInfo.KernelVersion,
+			count,
+		))
+	}
+
+	// Collect LoadBalancer services metrics
+	var serviceList corev1.ServiceList
+	if err := c.client.List(ctx, &serviceList); err != nil {
+		logger.Info(fmt.Sprintf("Failed to list Services: %v", err))
+	} else {
+		lbCount := 0
+		for _, svc := range serviceList.Items {
+			if svc.Spec.Type == corev1.ServiceTypeLoadBalancer {
+				lbCount++
+			}
+		}
+		metrics.WriteString(fmt.Sprintf("cozy_loadbalancers_count %d\n", lbCount))
+	}
+
+	// Count tenant namespaces
+	var nsList corev1.NamespaceList
+	if err := c.client.List(ctx, &nsList); err != nil {
+		logger.Info(fmt.Sprintf("Failed to list Namespaces: %v", err))
+	} else {
+		tenantCount := 0
+		for _, ns := range nsList.Items {
+			if strings.HasPrefix(ns.Name, "tenant-") {
+				tenantCount++
+			}
+		}
+		metrics.WriteString(fmt.Sprintf("cozy_tenants_count %d\n", tenantCount))
+	}
+
+	// Collect PV metrics grouped by driver and size
+	var pvList corev1.PersistentVolumeList
+	if err := c.client.List(ctx, &pvList); err != nil {
+		logger.Info(fmt.Sprintf("Failed to list PVs: %v", err))
+	} else {
+		// Map to store counts by size and driver
+		pvMetrics := make(map[string]map[string]int)
+
+		for _, pv := range pvList.Items {
+			if capacity, ok := pv.Spec.Capacity[corev1.ResourceStorage]; ok {
+				sizeGroup := getSizeGroup(capacity)
+
+				// Get the CSI driver name
+				driver := "unknown"
+				if pv.Spec.CSI != nil {
+					driver = pv.Spec.CSI.Driver
+				} else if pv.Spec.HostPath != nil {
+					driver = "hostpath"
+				} else if pv.Spec.NFS != nil {
+					driver = "nfs"
+				}
+
+				// Initialize nested map if needed
+				if _, exists := pvMetrics[sizeGroup]; !exists {
+					pvMetrics[sizeGroup] = make(map[string]int)
+				}
+
+				// Increment count for this size/driver combination
+				pvMetrics[sizeGroup][driver]++
+			}
+		}
+
+		// Write metrics
+		for size, drivers := range pvMetrics {
+			for driver, count := range drivers {
+				metrics.WriteString(fmt.Sprintf(
+					"cozy_pvs_count{driver=\"%s\",size=\"%s\"} %d\n",
+					driver,
+					size,
+					count,
+				))
+			}
+		}
+	}
+
+	// Collect workload metrics
+	var monitorList cozyv1alpha1.WorkloadMonitorList
+	if err := c.client.List(ctx, &monitorList); err != nil {
+		logger.Info(fmt.Sprintf("Failed to list WorkloadMonitors: %v", err))
+		return
+	}
+
+	for _, monitor := range monitorList.Items {
+		metrics.WriteString(fmt.Sprintf(
+			"cozy_workloads_count{uid=\"%s\",kind=\"%s\",type=\"%s\",version=\"%s\"} %d\n",
+			monitor.UID,
+			monitor.Spec.Kind,
+			monitor.Spec.Type,
+			monitor.Spec.Version,
+			monitor.Status.ObservedReplicas,
+		))
+	}
+
+	// Send metrics
+	if err := c.sendMetrics(clusterID, metrics.String()); err != nil {
+		logger.Info(fmt.Sprintf("Failed to send metrics: %v", err))
+	}
+}
+
+// sendMetrics sends collected metrics to the configured endpoint
+func (c *Collector) sendMetrics(clusterID, metrics string) error {
+	req, err := http.NewRequest("POST", c.config.Endpoint, bytes.NewBufferString(metrics))
+	if err != nil {
+		return fmt.Errorf("failed to create request: %w", err)
+	}
+
+	req.Header.Set("Content-Type", "text/plain")
+	req.Header.Set("X-Cluster-ID", clusterID)
+
+	resp, err := http.DefaultClient.Do(req)
+	if err != nil {
+		return fmt.Errorf("failed to send request: %w", err)
+	}
+	defer resp.Body.Close()
+
+	if resp.StatusCode != http.StatusOK {
+		return fmt.Errorf("unexpected status code: %d", resp.StatusCode)
+	}
+
+	return nil
+}

internal/telemetry/config.go

@@ -0,0 +1,27 @@
+package telemetry
+
+import (
+	"time"
+)
+
+// Config holds telemetry configuration
+type Config struct {
+	// Disable telemetry collection if set to true
+	Disabled bool
+	// Endpoint to send telemetry data to
+	Endpoint string
+	// Interval between telemetry data collection
+	Interval time.Duration
+	// CozystackVersion represents the current version of Cozystack
+	CozystackVersion string
+}
+
+// DefaultConfig returns default telemetry configuration
+func DefaultConfig() *Config {
+	return &Config{
+		Disabled:         false,
+		Endpoint:         "https://telemetry.cozystack.io",
+		Interval:         15 * time.Minute,
+		CozystackVersion: "unknown",
+	}
+}

manifests/cozystack-installer.yaml

@@ -1,105 +0,0 @@
----
-# Source: cozy-installer/templates/cozystack.yaml
-apiVersion: v1
-kind: Namespace
-metadata:
-  name: cozy-system
-  labels:
-    pod-security.kubernetes.io/enforce: privileged
----
-# Source: cozy-installer/templates/cozystack.yaml
-apiVersion: v1
-kind: ServiceAccount
-metadata:
-  name: cozystack
-  namespace: cozy-system
----
-# Source: cozy-installer/templates/cozystack.yaml
-apiVersion: rbac.authorization.k8s.io/v1
-kind: ClusterRoleBinding
-metadata:
-  name: cozystack
-subjects:
-- kind: ServiceAccount
-  name: cozystack
-  namespace: cozy-system
-roleRef:
-  kind: ClusterRole
-  name: cluster-admin
-  apiGroup: rbac.authorization.k8s.io
----
-# Source: cozy-installer/templates/cozystack.yaml
-apiVersion: v1
-kind: Service
-metadata:
-  name: cozystack
-  namespace: cozy-system
-spec:
-  ports:
-  - name: http
-    port: 80
-    targetPort: 8123
-  selector:
-    app: cozystack
-  type: ClusterIP
----
-# Source: cozy-installer/templates/cozystack.yaml
-apiVersion: apps/v1
-kind: Deployment
-metadata:
-  name: cozystack
-  namespace: cozy-system
-spec:
-  replicas: 1
-  selector:
-    matchLabels:
-      app: cozystack
-  strategy:
-    type: RollingUpdate
-    rollingUpdate:
-      maxSurge: 0
-      maxUnavailable: 1
-  template:
-    metadata:
-      labels:
-        app: cozystack
-    spec:
-      hostNetwork: true
-      serviceAccountName: cozystack
-      containers:
-      - name: cozystack
-        image: "ghcr.io/aenix-io/cozystack/cozystack:v0.19.0"
-        env:
-        - name: KUBERNETES_SERVICE_HOST
-          value: localhost
-        - name: KUBERNETES_SERVICE_PORT
-          value: "7445"
-        - name: K8S_AWAIT_ELECTION_ENABLED
-          value: "1"
-        - name: K8S_AWAIT_ELECTION_NAME
-          value: cozystack
-        - name: K8S_AWAIT_ELECTION_LOCK_NAME
-          value: cozystack
-        - name: K8S_AWAIT_ELECTION_LOCK_NAMESPACE
-          value: cozy-system
-        - name: K8S_AWAIT_ELECTION_IDENTITY
-          valueFrom:
-            fieldRef:
-              fieldPath: metadata.name
-      - name: darkhttpd
-        image: "ghcr.io/aenix-io/cozystack/cozystack:v0.19.0"
-        command:
-        - /usr/bin/darkhttpd
-        - /cozystack/assets
-        - --port
-        - "8123"
-        ports:
-        - name: http
-          containerPort: 8123
-      tolerations:
-      - key: "node.kubernetes.io/not-ready"
-        operator: "Exists"
-        effect: "NoSchedule"
-      - key: "node.cilium.io/agent-not-ready"
-        operator: "Exists"
-        effect: "NoSchedule"

packages/apps/clickhouse/Chart.yaml

@@ -16,7 +16,7 @@ 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: 0.6.1
+version: 0.7.0
 
 # 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

packages/apps/clickhouse/Makefile

@@ -14,6 +14,7 @@ image:
 		--cache-to type=inline \
 		--metadata-file images/clickhouse-backup.json \
 		--push=$(PUSH) \
+		--label "org.opencontainers.image.source=https://github.com/cozystack/cozystack" \
 		--load=$(LOAD)
 	echo "$(REGISTRY)/clickhouse-backup:$(call settag,$(CLICKHOUSE_BACKUP_TAG))@$$(yq e '."containerimage.digest"' images/clickhouse-backup.json -o json -r)" \
 		> images/clickhouse-backup.tag

packages/apps/clickhouse/README.md

@@ -36,13 +36,15 @@ more details:
 
 ### Backup parameters
 
-| Name                     | Description                                    | Value                                                  |
-| ------------------------ | ---------------------------------------------- | ------------------------------------------------------ |
-| `backup.enabled`         | Enable pereiodic backups                       | `false`                                                |
-| `backup.s3Region`        | The AWS S3 region where backups are stored     | `us-east-1`                                            |
-| `backup.s3Bucket`        | The S3 bucket used for storing backups         | `s3.example.org/clickhouse-backups`                    |
-| `backup.schedule`        | Cron schedule for automated backups            | `0 2 * * *`                                            |
-| `backup.cleanupStrategy` | The strategy for cleaning up old backups       | `--keep-last=3 --keep-daily=3 --keep-within-weekly=1m` |
-| `backup.s3AccessKey`     | The access key for S3, used for authentication | `oobaiRus9pah8PhohL1ThaeTa4UVa7gu`                     |
-| `backup.s3SecretKey`     | The secret key for S3, used for authentication | `ju3eum4dekeich9ahM1te8waeGai0oog`                     |
-| `backup.resticPassword`  | The password for Restic backup encryption      | `ChaXoveekoh6eigh4siesheeda2quai0`                     |
+| Name                     | Description                                                                                                                                                                                                       | Value                                                  |
+| ------------------------ | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------ |
+| `backup.enabled`         | Enable pereiodic backups                                                                                                                                                                                          | `false`                                                |
+| `backup.s3Region`        | The AWS S3 region where backups are stored                                                                                                                                                                        | `us-east-1`                                            |
+| `backup.s3Bucket`        | The S3 bucket used for storing backups                                                                                                                                                                            | `s3.example.org/clickhouse-backups`                    |
+| `backup.schedule`        | Cron schedule for automated backups                                                                                                                                                                               | `0 2 * * *`                                            |
+| `backup.cleanupStrategy` | The strategy for cleaning up old backups                                                                                                                                                                          | `--keep-last=3 --keep-daily=3 --keep-within-weekly=1m` |
+| `backup.s3AccessKey`     | The access key for S3, used for authentication                                                                                                                                                                    | `oobaiRus9pah8PhohL1ThaeTa4UVa7gu`                     |
+| `backup.s3SecretKey`     | The secret key for S3, used for authentication                                                                                                                                                                    | `ju3eum4dekeich9ahM1te8waeGai0oog`                     |
+| `backup.resticPassword`  | The password for Restic backup encryption                                                                                                                                                                         | `ChaXoveekoh6eigh4siesheeda2quai0`                     |
+| `resources`              | Resources                                                                                                                                                                                                         | `{}`                                                   |
+| `resourcesPreset`        | Set container resources according to one common preset (allowed values: none, nano, micro, small, medium, large, xlarge, 2xlarge). This is ignored if resources is set (resources is recommended for production). | `nano`                                                 |

packages/apps/clickhouse/images/clickhouse-backup.tag

@@ -1 +1 @@
-ghcr.io/aenix-io/cozystack/clickhouse-backup:0.6.1@sha256:3f76662144e31acf75f9495879da0c358a6729d08cfa0a4721cf495ff9a4c659
+ghcr.io/cozystack/cozystack/clickhouse-backup:0.7.0@sha256:3faf7a4cebf390b9053763107482de175aa0fdb88c1e77424fd81100b1c3a205

packages/apps/clickhouse/templates/_resources.tpl

@@ -0,0 +1,50 @@
+{{/*
+Copyright Broadcom, Inc. All Rights Reserved.
+SPDX-License-Identifier: APACHE-2.0
+*/}}
+
+{{/* vim: set filetype=mustache: */}}
+
+{{/*
+Return a resource request/limit object based on a given preset.
+These presets are for basic testing and not meant to be used in production
+{{ include "resources.preset" (dict "type" "nano") -}}
+*/}}
+{{- define "resources.preset" -}}
+{{/* The limits are the requests increased by 50% (except ephemeral-storage and xlarge/2xlarge sizes)*/}}
+{{- $presets := dict 
+  "nano" (dict 
+      "requests" (dict "cpu" "100m" "memory" "128Mi" "ephemeral-storage" "50Mi")
+      "limits" (dict "cpu" "150m" "memory" "192Mi" "ephemeral-storage" "2Gi")
+   )
+  "micro" (dict 
+      "requests" (dict "cpu" "250m" "memory" "256Mi" "ephemeral-storage" "50Mi")
+      "limits" (dict "cpu" "375m" "memory" "384Mi" "ephemeral-storage" "2Gi")
+   )
+  "small" (dict 
+      "requests" (dict "cpu" "500m" "memory" "512Mi" "ephemeral-storage" "50Mi")
+      "limits" (dict "cpu" "750m" "memory" "768Mi" "ephemeral-storage" "2Gi")
+   )
+  "medium" (dict 
+      "requests" (dict "cpu" "500m" "memory" "1024Mi" "ephemeral-storage" "50Mi")
+      "limits" (dict "cpu" "750m" "memory" "1536Mi" "ephemeral-storage" "2Gi")
+   )
+  "large" (dict 
+      "requests" (dict "cpu" "1.0" "memory" "2048Mi" "ephemeral-storage" "50Mi")
+      "limits" (dict "cpu" "1.5" "memory" "3072Mi" "ephemeral-storage" "2Gi")
+   )
+  "xlarge" (dict 
+      "requests" (dict "cpu" "1.0" "memory" "3072Mi" "ephemeral-storage" "50Mi")
+      "limits" (dict "cpu" "3.0" "memory" "6144Mi" "ephemeral-storage" "2Gi")
+   )
+  "2xlarge" (dict 
+      "requests" (dict "cpu" "1.0" "memory" "3072Mi" "ephemeral-storage" "50Mi")
+      "limits" (dict "cpu" "6.0" "memory" "12288Mi" "ephemeral-storage" "2Gi")
+   )
+ }}
+{{- if hasKey $presets .type -}}
+{{- index $presets .type | toYaml -}}
+{{- else -}}
+{{- printf "ERROR: Preset key '%s' invalid. Allowed values are %s" .type (join "," (keys $presets)) | fail -}}
+{{- end -}}
+{{- end -}}

packages/apps/clickhouse/templates/clickhouse.yaml

@@ -121,6 +121,11 @@ spec:
           containers:
             - name: clickhouse
               image: clickhouse/clickhouse-server:24.9.2.42
+              {{- if .Values.resources }}
+              resources: {{- toYaml .Values.resources | nindent 16 }}
+              {{- else if ne .Values.resourcesPreset "none" }}
+              resources: {{- include "resources.preset" (dict "type" .Values.resourcesPreset "Release" .Release) | nindent 16 }}
+              {{- end }}
               volumeMounts:
                 - name: data-volume-template
                   mountPath: /var/lib/clickhouse

packages/apps/clickhouse/templates/dashboard-resourcemap.yaml

@@ -17,3 +17,10 @@ rules:
   resourceNames:
   - {{ .Release.Name }}-credentials
   verbs: ["get", "list", "watch"]
+- apiGroups:
+  - cozystack.io
+  resources:
+  - workloadmonitors
+  resourceNames:
+  - {{ .Release.Name }}
+  verbs: ["get", "list", "watch"]

packages/apps/clickhouse/templates/workloadmonitor.yaml

@@ -0,0 +1,13 @@
+---
+apiVersion: cozystack.io/v1alpha1
+kind: WorkloadMonitor
+metadata:
+  name: {{ $.Release.Name }}
+spec:
+  replicas: {{ .Values.replicas }}
+  minReplicas: 1
+  kind: clickhouse
+  type: clickhouse
+  selector:
+    clickhouse.altinity.com/chi: {{ $.Release.Name }}
+  version: {{ $.Chart.Version }}

packages/apps/clickhouse/values.schema.json

@@ -76,6 +76,16 @@
                     "default": "ChaXoveekoh6eigh4siesheeda2quai0"
                 }
             }
+        },
+        "resources": {
+            "type": "object",
+            "description": "Resources",
+            "default": {}
+        },
+        "resourcesPreset": {
+            "type": "string",
+            "description": "Set container resources according to one common preset (allowed values: none, nano, micro, small, medium, large, xlarge, 2xlarge). This is ignored if resources is set (resources is recommended for production).",
+            "default": "nano"
         }
     }
 }

packages/apps/clickhouse/values.yaml

@@ -46,3 +46,16 @@ backup:
   s3AccessKey: oobaiRus9pah8PhohL1ThaeTa4UVa7gu
   s3SecretKey: ju3eum4dekeich9ahM1te8waeGai0oog
   resticPassword: ChaXoveekoh6eigh4siesheeda2quai0
+
+## @param resources Resources
+resources: {}
+ # resources:
+ #   limits:
+ #     cpu: 4000m
+ #     memory: 4Gi
+ #   requests:
+ #     cpu: 100m
+ #     memory: 512Mi
+ 
+## @param resourcesPreset Set container resources according to one common preset (allowed values: none, nano, micro, small, medium, large, xlarge, 2xlarge). This is ignored if resources is set (resources is recommended for production).
+resourcesPreset: "nano"

packages/apps/ferretdb/Chart.yaml

@@ -16,7 +16,7 @@ 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: 0.4.1
+version: 0.5.0
 
 # 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

packages/apps/ferretdb/README.md

@@ -21,15 +21,17 @@
 
 ### Backup parameters
 
-| Name                     | Description                                    | Value                                                  |
-| ------------------------ | ---------------------------------------------- | ------------------------------------------------------ |
-| `backup.enabled`         | Enable pereiodic backups                       | `false`                                                |
-| `backup.s3Region`        | The AWS S3 region where backups are stored     | `us-east-1`                                            |
-| `backup.s3Bucket`        | The S3 bucket used for storing backups         | `s3.example.org/postgres-backups`                      |
-| `backup.schedule`        | Cron schedule for automated backups            | `0 2 * * *`                                            |
-| `backup.cleanupStrategy` | The strategy for cleaning up old backups       | `--keep-last=3 --keep-daily=3 --keep-within-weekly=1m` |
-| `backup.s3AccessKey`     | The access key for S3, used for authentication | `oobaiRus9pah8PhohL1ThaeTa4UVa7gu`                     |
-| `backup.s3SecretKey`     | The secret key for S3, used for authentication | `ju3eum4dekeich9ahM1te8waeGai0oog`                     |
-| `backup.resticPassword`  | The password for Restic backup encryption      | `ChaXoveekoh6eigh4siesheeda2quai0`                     |
+| Name                     | Description                                                                                                                                                                                                       | Value                                                  |
+| ------------------------ | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------ |
+| `backup.enabled`         | Enable pereiodic backups                                                                                                                                                                                          | `false`                                                |
+| `backup.s3Region`        | The AWS S3 region where backups are stored                                                                                                                                                                        | `us-east-1`                                            |
+| `backup.s3Bucket`        | The S3 bucket used for storing backups                                                                                                                                                                            | `s3.example.org/postgres-backups`                      |
+| `backup.schedule`        | Cron schedule for automated backups                                                                                                                                                                               | `0 2 * * *`                                            |
+| `backup.cleanupStrategy` | The strategy for cleaning up old backups                                                                                                                                                                          | `--keep-last=3 --keep-daily=3 --keep-within-weekly=1m` |
+| `backup.s3AccessKey`     | The access key for S3, used for authentication                                                                                                                                                                    | `oobaiRus9pah8PhohL1ThaeTa4UVa7gu`                     |
+| `backup.s3SecretKey`     | The secret key for S3, used for authentication                                                                                                                                                                    | `ju3eum4dekeich9ahM1te8waeGai0oog`                     |
+| `backup.resticPassword`  | The password for Restic backup encryption                                                                                                                                                                         | `ChaXoveekoh6eigh4siesheeda2quai0`                     |
+| `resources`              | Resources                                                                                                                                                                                                         | `{}`                                                   |
+| `resourcesPreset`        | Set container resources according to one common preset (allowed values: none, nano, micro, small, medium, large, xlarge, 2xlarge). This is ignored if resources is set (resources is recommended for production). | `nano`                                                 |
 
 

packages/apps/ferretdb/images/postgres-backup.tag

@@ -1 +1 @@
-ghcr.io/aenix-io/cozystack/postgres-backup:0.7.1@sha256:034a480a119986da8a8e0532f09f66c58ed919e18612987b1a847fe8a59b6f3c
+ghcr.io/cozystack/cozystack/postgres-backup:0.10.0@sha256:10179ed56457460d95cd5708db2a00130901255fa30c4dd76c65d2ef5622b61f

packages/apps/ferretdb/templates/_resources.tpl

@@ -0,0 +1,50 @@
+{{/*
+Copyright Broadcom, Inc. All Rights Reserved.
+SPDX-License-Identifier: APACHE-2.0
+*/}}
+
+{{/* vim: set filetype=mustache: */}}
+
+{{/*
+Return a resource request/limit object based on a given preset.
+These presets are for basic testing and not meant to be used in production
+{{ include "resources.preset" (dict "type" "nano") -}}
+*/}}
+{{- define "resources.preset" -}}
+{{/* The limits are the requests increased by 50% (except ephemeral-storage and xlarge/2xlarge sizes)*/}}
+{{- $presets := dict 
+  "nano" (dict 
+      "requests" (dict "cpu" "100m" "memory" "128Mi" "ephemeral-storage" "50Mi")
+      "limits" (dict "cpu" "150m" "memory" "192Mi" "ephemeral-storage" "2Gi")
+   )
+  "micro" (dict 
+      "requests" (dict "cpu" "250m" "memory" "256Mi" "ephemeral-storage" "50Mi")
+      "limits" (dict "cpu" "375m" "memory" "384Mi" "ephemeral-storage" "2Gi")
+   )
+  "small" (dict 
+      "requests" (dict "cpu" "500m" "memory" "512Mi" "ephemeral-storage" "50Mi")
+      "limits" (dict "cpu" "750m" "memory" "768Mi" "ephemeral-storage" "2Gi")
+   )
+  "medium" (dict 
+      "requests" (dict "cpu" "500m" "memory" "1024Mi" "ephemeral-storage" "50Mi")
+      "limits" (dict "cpu" "750m" "memory" "1536Mi" "ephemeral-storage" "2Gi")
+   )
+  "large" (dict 
+      "requests" (dict "cpu" "1.0" "memory" "2048Mi" "ephemeral-storage" "50Mi")
+      "limits" (dict "cpu" "1.5" "memory" "3072Mi" "ephemeral-storage" "2Gi")
+   )
+  "xlarge" (dict 
+      "requests" (dict "cpu" "1.0" "memory" "3072Mi" "ephemeral-storage" "50Mi")
+      "limits" (dict "cpu" "3.0" "memory" "6144Mi" "ephemeral-storage" "2Gi")
+   )
+  "2xlarge" (dict 
+      "requests" (dict "cpu" "1.0" "memory" "3072Mi" "ephemeral-storage" "50Mi")
+      "limits" (dict "cpu" "6.0" "memory" "12288Mi" "ephemeral-storage" "2Gi")
+   )
+ }}
+{{- if hasKey $presets .type -}}
+{{- index $presets .type | toYaml -}}
+{{- else -}}
+{{- printf "ERROR: Preset key '%s' invalid. Allowed values are %s" .type (join "," (keys $presets)) | fail -}}
+{{- end -}}
+{{- end -}}

packages/apps/ferretdb/templates/dashboard-resourcemap.yaml

@@ -17,3 +17,10 @@ rules:
   resourceNames:
   - {{ .Release.Name }}-credentials
   verbs: ["get", "list", "watch"]
+- apiGroups:
+  - cozystack.io
+  resources:
+  - workloadmonitors
+  resourceNames:
+  - {{ .Release.Name }}
+  verbs: ["get", "list", "watch"]

packages/apps/ferretdb/templates/postgres.yaml

@@ -6,10 +6,20 @@ metadata:
 spec:
   instances: {{ .Values.replicas }}
   enableSuperuserAccess: true
-
+  {{- $configMap := lookup "v1" "ConfigMap" "cozy-system" "cozystack-scheduling" }}
+  {{- if $configMap }}
+  {{- $rawConstraints := get $configMap.data "globalAppTopologySpreadConstraints" }}
+  {{- if $rawConstraints }}
+  {{- $rawConstraints | fromYaml | toYaml | nindent 2 }}
+  {{- end }}
+  {{- end }}
   minSyncReplicas: {{ .Values.quorum.minSyncReplicas }}
   maxSyncReplicas: {{ .Values.quorum.maxSyncReplicas }}
-
+  {{- if .Values.resources }}
+  resources: {{- toYaml .Values.resources | nindent 4 }}
+  {{- else if ne .Values.resourcesPreset "none" }}
+  resources: {{- include "resources.preset" (dict "type" .Values.resourcesPreset "Release" .Release) | nindent 4 }}
+  {{- end }}
   monitoring:
     enablePodMonitor: true
 

packages/apps/ferretdb/templates/workloadmonitor.yaml

@@ -0,0 +1,13 @@
+---
+apiVersion: cozystack.io/v1alpha1
+kind: WorkloadMonitor
+metadata:
+  name: {{ $.Release.Name }}
+spec:
+  replicas: {{ .Values.replicas }}
+  minReplicas: 1
+  kind: ferretdb
+  type: ferretdb
+  selector:
+    app: {{ $.Release.Name }}
+  version: {{ $.Chart.Version }}

packages/apps/ferretdb/values.schema.json

@@ -81,6 +81,16 @@
                     "default": "ChaXoveekoh6eigh4siesheeda2quai0"
                 }
             }
+        },
+        "resources": {
+            "type": "object",
+            "description": "Resources",
+            "default": {}
+        },
+        "resourcesPreset": {
+            "type": "string",
+            "description": "Set container resources according to one common preset (allowed values: none, nano, micro, small, medium, large, xlarge, 2xlarge). This is ignored if resources is set (resources is recommended for production).",
+            "default": "nano"
         }
     }
 }

packages/apps/ferretdb/values.yaml

@@ -48,3 +48,16 @@ backup:
   s3AccessKey: oobaiRus9pah8PhohL1ThaeTa4UVa7gu
   s3SecretKey: ju3eum4dekeich9ahM1te8waeGai0oog
   resticPassword: ChaXoveekoh6eigh4siesheeda2quai0
+
+## @param resources Resources
+resources: {}
+ # resources:
+ #   limits:
+ #     cpu: 4000m
+ #     memory: 4Gi
+ #   requests:
+ #     cpu: 100m
+ #     memory: 512Mi
+ 
+## @param resourcesPreset Set container resources according to one common preset (allowed values: none, nano, micro, small, medium, large, xlarge, 2xlarge). This is ignored if resources is set (resources is recommended for production).
+resourcesPreset: "nano"

packages/apps/http-cache/Chart.yaml

@@ -16,7 +16,7 @@ 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: 0.3.1
+version: 0.4.0
 
 # 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

packages/apps/http-cache/Makefile

@@ -13,6 +13,7 @@ image-nginx:
 		--cache-to type=inline \
 		--metadata-file images/nginx-cache.json \
 		--push=$(PUSH) \
+		--label "org.opencontainers.image.source=https://github.com/cozystack/cozystack" \
 		--load=$(LOAD)
 	echo "$(REGISTRY)/nginx-cache:$(call settag,$(NGINX_CACHE_TAG))@$$(yq e '."containerimage.digest"' images/nginx-cache.json -o json -r)" \
 		> images/nginx-cache.tag

packages/apps/http-cache/README.md

@@ -60,13 +60,17 @@ VTS module shows wrong upstream resonse time
 
 ### Common parameters
 
-| Name               | Description                                     | Value   |
-| ------------------ | ----------------------------------------------- | ------- |
-| `external`         | Enable external access from outside the cluster | `false` |
-| `size`             | Persistent Volume size                          | `10Gi`  |
-| `storageClass`     | StorageClass used to store the data             | `""`    |
-| `haproxy.replicas` | Number of HAProxy replicas                      | `2`     |
-| `nginx.replicas`   | Number of Nginx replicas                        | `2`     |
+| Name                      | Description                                                                                                                                                                                                       | Value   |
+| ------------------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ------- |
+| `external`                | Enable external access from outside the cluster                                                                                                                                                                   | `false` |
+| `size`                    | Persistent Volume size                                                                                                                                                                                            | `10Gi`  |
+| `storageClass`            | StorageClass used to store the data                                                                                                                                                                               | `""`    |
+| `haproxy.replicas`        | Number of HAProxy replicas                                                                                                                                                                                        | `2`     |
+| `nginx.replicas`          | Number of Nginx replicas                                                                                                                                                                                          | `2`     |
+| `haproxy.resources`       | Resources                                                                                                                                                                                                         | `{}`    |
+| `haproxy.resourcesPreset` | Set container resources according to one common preset (allowed values: none, nano, micro, small, medium, large, xlarge, 2xlarge). This is ignored if resources is set (resources is recommended for production). | `nano`  |
+| `nginx.resources`         | Resources                                                                                                                                                                                                         | `{}`    |
+| `nginx.resourcesPreset`   | Set container resources according to one common preset (allowed values: none, nano, micro, small, medium, large, xlarge, 2xlarge). This is ignored if resources is set (resources is recommended for production). | `nano`  |
 
 ### Configuration parameters
 

packages/apps/http-cache/images/nginx-cache.tag

@@ -1 +1 @@
-ghcr.io/aenix-io/cozystack/nginx-cache:0.3.1@sha256:3030c5b58dcb38dab3892fb1b4241381fc04707b2aa66550ef446231077add6e
+ghcr.io/cozystack/cozystack/nginx-cache:0.4.0@sha256:bef7344da098c4dc400a9e20ffad10ac991df67d09a30026207454abbc91f28b

packages/apps/http-cache/templates/_resources.tpl

@@ -0,0 +1,50 @@
+{{/*
+Copyright Broadcom, Inc. All Rights Reserved.
+SPDX-License-Identifier: APACHE-2.0
+*/}}
+
+{{/* vim: set filetype=mustache: */}}
+
+{{/*
+Return a resource request/limit object based on a given preset.
+These presets are for basic testing and not meant to be used in production
+{{ include "resources.preset" (dict "type" "nano") -}}
+*/}}
+{{- define "resources.preset" -}}
+{{/* The limits are the requests increased by 50% (except ephemeral-storage and xlarge/2xlarge sizes)*/}}
+{{- $presets := dict 
+  "nano" (dict 
+      "requests" (dict "cpu" "100m" "memory" "128Mi" "ephemeral-storage" "50Mi")
+      "limits" (dict "cpu" "150m" "memory" "192Mi" "ephemeral-storage" "2Gi")
+   )
+  "micro" (dict 
+      "requests" (dict "cpu" "250m" "memory" "256Mi" "ephemeral-storage" "50Mi")
+      "limits" (dict "cpu" "375m" "memory" "384Mi" "ephemeral-storage" "2Gi")
+   )
+  "small" (dict 
+      "requests" (dict "cpu" "500m" "memory" "512Mi" "ephemeral-storage" "50Mi")
+      "limits" (dict "cpu" "750m" "memory" "768Mi" "ephemeral-storage" "2Gi")
+   )
+  "medium" (dict 
+      "requests" (dict "cpu" "500m" "memory" "1024Mi" "ephemeral-storage" "50Mi")
+      "limits" (dict "cpu" "750m" "memory" "1536Mi" "ephemeral-storage" "2Gi")
+   )
+  "large" (dict 
+      "requests" (dict "cpu" "1.0" "memory" "2048Mi" "ephemeral-storage" "50Mi")
+      "limits" (dict "cpu" "1.5" "memory" "3072Mi" "ephemeral-storage" "2Gi")
+   )
+  "xlarge" (dict 
+      "requests" (dict "cpu" "1.0" "memory" "3072Mi" "ephemeral-storage" "50Mi")
+      "limits" (dict "cpu" "3.0" "memory" "6144Mi" "ephemeral-storage" "2Gi")
+   )
+  "2xlarge" (dict 
+      "requests" (dict "cpu" "1.0" "memory" "3072Mi" "ephemeral-storage" "50Mi")
+      "limits" (dict "cpu" "6.0" "memory" "12288Mi" "ephemeral-storage" "2Gi")
+   )
+ }}
+{{- if hasKey $presets .type -}}
+{{- index $presets .type | toYaml -}}
+{{- else -}}
+{{- printf "ERROR: Preset key '%s' invalid. Allowed values are %s" .type (join "," (keys $presets)) | fail -}}
+{{- end -}}
+{{- end -}}

packages/apps/http-cache/templates/haproxy/deployment.yaml

@@ -33,6 +33,11 @@ spec:
       containers:
       - image: haproxy:latest
         name: haproxy
+        {{- if .Values.haproxy.resources }}
+        resources: {{- toYaml .Values.haproxy.resources | nindent 10 }}
+        {{- else if ne .Values.haproxy.resourcesPreset "none" }}
+        resources: {{- include "resources.preset" (dict "type" .Values.haproxy.resourcesPreset "Release" .Release) | nindent 10 }}
+        {{- end }}
         ports:
         - containerPort: 8080
           name: http

packages/apps/http-cache/templates/nginx/deployment.yaml

@@ -52,6 +52,11 @@ spec:
       shareProcessNamespace: true
       containers:
       - name: nginx
+        {{- if $.Values.nginx.resources }}
+        resources: {{- toYaml $.Values.nginx.resources | nindent 10 }}
+        {{- else if ne $.Values.nginx.resourcesPreset "none" }}
+        resources: {{- include "resources.preset" (dict "type" $.Values.nginx.resourcesPreset "Release" $.Release) | nindent 10 }}
+        {{- end }}
         image: "{{ $.Files.Get "images/nginx-cache.tag" | trim }}"
         readinessProbe:
           httpGet:
@@ -83,6 +88,13 @@ spec:
       - name: reloader
         image: "{{ $.Files.Get "images/nginx-cache.tag" | trim }}"
         command: ["/usr/bin/nginx-reloader.sh"]
+        resources:
+          limits:
+            cpu: 50m
+            memory: 50Mi
+          requests:
+            cpu: 50m
+            memory: 50Mi
         #command: ["sleep", "infinity"]
         volumeMounts:
         - mountPath: /etc/nginx/nginx.conf

packages/apps/http-cache/values.schema.json

@@ -24,6 +24,16 @@
                     "type": "number",
                     "description": "Number of HAProxy replicas",
                     "default": 2
+                },
+                "resources": {
+                    "type": "object",
+                    "description": "Resources",
+                    "default": {}
+                },
+                "resourcesPreset": {
+                    "type": "string",
+                    "description": "Set container resources according to one common preset (allowed values: none, nano, micro, small, medium, large, xlarge, 2xlarge). This is ignored if resources is set (resources is recommended for production).",
+                    "default": "nano"
                 }
             }
         },
@@ -34,6 +44,16 @@
                     "type": "number",
                     "description": "Number of Nginx replicas",
                     "default": 2
+                },
+                "resources": {
+                    "type": "object",
+                    "description": "Resources",
+                    "default": {}
+                },
+                "resourcesPreset": {
+                    "type": "string",
+                    "description": "Set container resources according to one common preset (allowed values: none, nano, micro, small, medium, large, xlarge, 2xlarge). This is ignored if resources is set (resources is recommended for production).",
+                    "default": "nano"
                 }
             }
         },

packages/apps/http-cache/values.yaml

@@ -12,8 +12,32 @@ size: 10Gi
 storageClass: ""
 haproxy:
   replicas: 2
+  ## @param haproxy.resources Resources
+  resources: {}
+  # resources:
+  #   limits:
+  #     cpu: 4000m
+  #     memory: 4Gi
+  #   requests:
+  #     cpu: 100m
+  #     memory: 512Mi
+  
+  ## @param haproxy.resourcesPreset Set container resources according to one common preset (allowed values: none, nano, micro, small, medium, large, xlarge, 2xlarge). This is ignored if resources is set (resources is recommended for production).
+  resourcesPreset: "nano"
 nginx:
   replicas: 2
+  ## @param nginx.resources Resources
+  resources: {}
+  # resources:
+  #   limits:
+  #     cpu: 4000m
+  #     memory: 4Gi
+  #   requests:
+  #     cpu: 100m
+  #     memory: 512Mi
+  
+  ## @param nginx.resourcesPreset Set container resources according to one common preset (allowed values: none, nano, micro, small, medium, large, xlarge, 2xlarge). This is ignored if resources is set (resources is recommended for production).
+  resourcesPreset: "nano"
 
 ## @section Configuration parameters
 

packages/apps/kafka/Chart.yaml

@@ -16,7 +16,7 @@ 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: 0.3.1
+version: 0.5.0
 
 # 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

packages/apps/kafka/README.md

@@ -4,15 +4,19 @@
 
 ### Common parameters
 
-| Name                     | Description                                     | Value   |
-| ------------------------ | ----------------------------------------------- | ------- |
-| `external`               | Enable external access from outside the cluster | `false` |
-| `kafka.size`             | Persistent Volume size for Kafka                | `10Gi`  |
-| `kafka.replicas`         | Number of Kafka replicas                        | `3`     |
-| `kafka.storageClass`     | StorageClass used to store the Kafka data       | `""`    |
-| `zookeeper.size`         | Persistent Volume size for ZooKeeper            | `5Gi`   |
-| `zookeeper.replicas`     | Number of ZooKeeper replicas                    | `3`     |
-| `zookeeper.storageClass` | StorageClass used to store the ZooKeeper data   | `""`    |
+| Name                        | Description                                                                                                                                                                                                       | Value   |
+| --------------------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ------- |
+| `external`                  | Enable external access from outside the cluster                                                                                                                                                                   | `false` |
+| `kafka.size`                | Persistent Volume size for Kafka                                                                                                                                                                                  | `10Gi`  |
+| `kafka.replicas`            | Number of Kafka replicas                                                                                                                                                                                          | `3`     |
+| `kafka.storageClass`        | StorageClass used to store the Kafka data                                                                                                                                                                         | `""`    |
+| `zookeeper.size`            | Persistent Volume size for ZooKeeper                                                                                                                                                                              | `5Gi`   |
+| `zookeeper.replicas`        | Number of ZooKeeper replicas                                                                                                                                                                                      | `3`     |
+| `zookeeper.storageClass`    | StorageClass used to store the ZooKeeper data                                                                                                                                                                     | `""`    |
+| `kafka.resources`           | Resources                                                                                                                                                                                                         | `{}`    |
+| `kafka.resourcesPreset`     | Set container resources according to one common preset (allowed values: none, nano, micro, small, medium, large, xlarge, 2xlarge). This is ignored if resources is set (resources is recommended for production). | `nano`  |
+| `zookeeper.resources`       | Resources                                                                                                                                                                                                         | `{}`    |
+| `zookeeper.resourcesPreset` | Set container resources according to one common preset (allowed values: none, nano, micro, small, medium, large, xlarge, 2xlarge). This is ignored if resources is set (resources is recommended for production). | `nano`  |
 
 ### Configuration parameters
 

packages/apps/kafka/templates/_resources.tpl

@@ -0,0 +1,50 @@
+{{/*
+Copyright Broadcom, Inc. All Rights Reserved.
+SPDX-License-Identifier: APACHE-2.0
+*/}}
+
+{{/* vim: set filetype=mustache: */}}
+
+{{/*
+Return a resource request/limit object based on a given preset.
+These presets are for basic testing and not meant to be used in production
+{{ include "resources.preset" (dict "type" "nano") -}}
+*/}}
+{{- define "resources.preset" -}}
+{{/* The limits are the requests increased by 50% (except ephemeral-storage and xlarge/2xlarge sizes)*/}}
+{{- $presets := dict 
+  "nano" (dict 
+      "requests" (dict "cpu" "100m" "memory" "128Mi" "ephemeral-storage" "50Mi")
+      "limits" (dict "cpu" "150m" "memory" "192Mi" "ephemeral-storage" "2Gi")
+   )
+  "micro" (dict 
+      "requests" (dict "cpu" "250m" "memory" "256Mi" "ephemeral-storage" "50Mi")
+      "limits" (dict "cpu" "375m" "memory" "384Mi" "ephemeral-storage" "2Gi")
+   )
+  "small" (dict 
+      "requests" (dict "cpu" "500m" "memory" "512Mi" "ephemeral-storage" "50Mi")
+      "limits" (dict "cpu" "750m" "memory" "768Mi" "ephemeral-storage" "2Gi")
+   )
+  "medium" (dict 
+      "requests" (dict "cpu" "500m" "memory" "1024Mi" "ephemeral-storage" "50Mi")
+      "limits" (dict "cpu" "750m" "memory" "1536Mi" "ephemeral-storage" "2Gi")
+   )
+  "large" (dict 
+      "requests" (dict "cpu" "1.0" "memory" "2048Mi" "ephemeral-storage" "50Mi")
+      "limits" (dict "cpu" "1.5" "memory" "3072Mi" "ephemeral-storage" "2Gi")
+   )
+  "xlarge" (dict 
+      "requests" (dict "cpu" "1.0" "memory" "3072Mi" "ephemeral-storage" "50Mi")
+      "limits" (dict "cpu" "3.0" "memory" "6144Mi" "ephemeral-storage" "2Gi")
+   )
+  "2xlarge" (dict 
+      "requests" (dict "cpu" "1.0" "memory" "3072Mi" "ephemeral-storage" "50Mi")
+      "limits" (dict "cpu" "6.0" "memory" "12288Mi" "ephemeral-storage" "2Gi")
+   )
+ }}
+{{- if hasKey $presets .type -}}
+{{- index $presets .type | toYaml -}}
+{{- else -}}
+{{- printf "ERROR: Preset key '%s' invalid. Allowed values are %s" .type (join "," (keys $presets)) | fail -}}
+{{- end -}}
+{{- end -}}

packages/apps/kafka/templates/dashboard-resourcemap.yaml

@@ -17,3 +17,11 @@ rules:
   resourceNames:
   - {{ .Release.Name }}-clients-ca
   verbs: ["get", "list", "watch"]
+- apiGroups:
+  - cozystack.io
+  resources:
+  - workloadmonitors
+  resourceNames:
+  - {{ .Release.Name }}
+  - {{ $.Release.Name }}-zookeeper
+  verbs: ["get", "list", "watch"]

packages/apps/kafka/templates/kafka.yaml

@@ -8,6 +8,11 @@ metadata:
 spec:
   kafka:
     replicas: {{ .Values.kafka.replicas }}
+    {{- if .Values.kafka.resources }}
+    resources: {{- toYaml .Values.kafka.resources | nindent 6 }}
+    {{- else if ne .Values.kafka.resourcesPreset "none" }}
+    resources: {{- include "resources.preset" (dict "type" .Values.kafka.resourcesPreset "Release" .Release) | nindent 6 }}
+    {{- end }}
     listeners:
       - name: plain
         port: 9092
@@ -57,8 +62,19 @@ spec:
         class: {{ . }}
         {{- end }}
         deleteClaim: true
+    metricsConfig:
+      type: jmxPrometheusExporter
+      valueFrom:
+        configMapKeyRef:
+          name: {{ .Release.Name }}-metrics
+          key: kafka-metrics-config.yml
   zookeeper:
     replicas: {{ .Values.zookeeper.replicas }}
+    {{- if .Values.zookeeper.resources }}
+    resources: {{- toYaml .Values.zookeeper.resources | nindent 6 }}
+    {{- else if ne .Values.zookeeper.resourcesPreset "none" }}
+    resources: {{- include "resources.preset" (dict "type" .Values.zookeeper.resourcesPreset "Release" .Release) | nindent 6 }}
+    {{- end }}
     storage:
       type: persistent-claim
       {{- with .Values.zookeeper.size }}
@@ -68,6 +84,12 @@ spec:
       class: {{ . }}
       {{- end }}
       deleteClaim: false
+    metricsConfig:
+      type: jmxPrometheusExporter
+      valueFrom:
+        configMapKeyRef:
+          name: {{ .Release.Name }}-metrics
+          key: kafka-metrics-config.yml
   entityOperator:
     topicOperator: {}
     userOperator: {}

packages/apps/kafka/templates/metrics-configmap.yaml

@@ -0,0 +1,198 @@
+kind: ConfigMap
+apiVersion: v1
+metadata:
+  name: {{ .Release.Name }}-metrics
+data:
+  kafka-metrics-config.yml: |
+    # See https://github.com/prometheus/jmx_exporter for more info about JMX Prometheus Exporter metrics
+    lowercaseOutputName: true
+    rules:
+    # Special cases and very specific rules
+    - pattern: kafka.server<type=(.+), name=(.+), clientId=(.+), topic=(.+), partition=(.*)><>Value
+      name: kafka_server_$1_$2
+      type: GAUGE
+      labels:
+        clientId: "$3"
+        topic: "$4"
+        partition: "$5"
+    - pattern: kafka.server<type=(.+), name=(.+), clientId=(.+), brokerHost=(.+), brokerPort=(.+)><>Value
+      name: kafka_server_$1_$2
+      type: GAUGE
+      labels:
+        clientId: "$3"
+        broker: "$4:$5"
+    - pattern: kafka.server<type=(.+), cipher=(.+), protocol=(.+), listener=(.+), networkProcessor=(.+)><>connections
+      name: kafka_server_$1_connections_tls_info
+      type: GAUGE
+      labels:
+        cipher: "$2"
+        protocol: "$3"
+        listener: "$4"
+        networkProcessor: "$5"
+    - pattern: kafka.server<type=(.+), clientSoftwareName=(.+), clientSoftwareVersion=(.+), listener=(.+), networkProcessor=(.+)><>connections
+      name: kafka_server_$1_connections_software
+      type: GAUGE
+      labels:
+        clientSoftwareName: "$2"
+        clientSoftwareVersion: "$3"
+        listener: "$4"
+        networkProcessor: "$5"
+    - pattern: "kafka.server<type=(.+), listener=(.+), networkProcessor=(.+)><>(.+-total):"
+      name: kafka_server_$1_$4
+      type: COUNTER
+      labels:
+        listener: "$2"
+        networkProcessor: "$3"
+    - pattern: "kafka.server<type=(.+), listener=(.+), networkProcessor=(.+)><>(.+):"
+      name: kafka_server_$1_$4
+      type: GAUGE
+      labels:
+        listener: "$2"
+        networkProcessor: "$3"
+    - pattern: kafka.server<type=(.+), listener=(.+), networkProcessor=(.+)><>(.+-total)
+      name: kafka_server_$1_$4
+      type: COUNTER
+      labels:
+        listener: "$2"
+        networkProcessor: "$3"
+    - pattern: kafka.server<type=(.+), listener=(.+), networkProcessor=(.+)><>(.+)
+      name: kafka_server_$1_$4
+      type: GAUGE
+      labels:
+        listener: "$2"
+        networkProcessor: "$3"
+    # Some percent metrics use MeanRate attribute
+    # Ex) kafka.server<type=(KafkaRequestHandlerPool), name=(RequestHandlerAvgIdlePercent)><>MeanRate
+    - pattern: kafka.(\w+)<type=(.+), name=(.+)Percent\w*><>MeanRate
+      name: kafka_$1_$2_$3_percent
+      type: GAUGE
+    # Generic gauges for percents
+    - pattern: kafka.(\w+)<type=(.+), name=(.+)Percent\w*><>Value
+      name: kafka_$1_$2_$3_percent
+      type: GAUGE
+    - pattern: kafka.(\w+)<type=(.+), name=(.+)Percent\w*, (.+)=(.+)><>Value
+      name: kafka_$1_$2_$3_percent
+      type: GAUGE
+      labels:
+        "$4": "$5"
+    # Generic per-second counters with 0-2 key/value pairs
+    - pattern: kafka.(\w+)<type=(.+), name=(.+)PerSec\w*, (.+)=(.+), (.+)=(.+)><>Count
+      name: kafka_$1_$2_$3_total
+      type: COUNTER
+      labels:
+        "$4": "$5"
+        "$6": "$7"
+    - pattern: kafka.(\w+)<type=(.+), name=(.+)PerSec\w*, (.+)=(.+)><>Count
+      name: kafka_$1_$2_$3_total
+      type: COUNTER
+      labels:
+        "$4": "$5"
+    - pattern: kafka.(\w+)<type=(.+), name=(.+)PerSec\w*><>Count
+      name: kafka_$1_$2_$3_total
+      type: COUNTER
+    # Generic gauges with 0-2 key/value pairs
+    - pattern: kafka.(\w+)<type=(.+), name=(.+), (.+)=(.+), (.+)=(.+)><>Value
+      name: kafka_$1_$2_$3
+      type: GAUGE
+      labels:
+        "$4": "$5"
+        "$6": "$7"
+    - pattern: kafka.(\w+)<type=(.+), name=(.+), (.+)=(.+)><>Value
+      name: kafka_$1_$2_$3
+      type: GAUGE
+      labels:
+        "$4": "$5"
+    - pattern: kafka.(\w+)<type=(.+), name=(.+)><>Value
+      name: kafka_$1_$2_$3
+      type: GAUGE
+    # Emulate Prometheus 'Summary' metrics for the exported 'Histogram's.
+    # Note that these are missing the '_sum' metric!
+    - pattern: kafka.(\w+)<type=(.+), name=(.+), (.+)=(.+), (.+)=(.+)><>Count
+      name: kafka_$1_$2_$3_count
+      type: COUNTER
+      labels:
+        "$4": "$5"
+        "$6": "$7"
+    - pattern: kafka.(\w+)<type=(.+), name=(.+), (.+)=(.*), (.+)=(.+)><>(\d+)thPercentile
+      name: kafka_$1_$2_$3
+      type: GAUGE
+      labels:
+        "$4": "$5"
+        "$6": "$7"
+        quantile: "0.$8"
+    - pattern: kafka.(\w+)<type=(.+), name=(.+), (.+)=(.+)><>Count
+      name: kafka_$1_$2_$3_count
+      type: COUNTER
+      labels:
+        "$4": "$5"
+    - pattern: kafka.(\w+)<type=(.+), name=(.+), (.+)=(.*)><>(\d+)thPercentile
+      name: kafka_$1_$2_$3
+      type: GAUGE
+      labels:
+        "$4": "$5"
+        quantile: "0.$6"
+    - pattern: kafka.(\w+)<type=(.+), name=(.+)><>Count
+      name: kafka_$1_$2_$3_count
+      type: COUNTER
+    - pattern: kafka.(\w+)<type=(.+), name=(.+)><>(\d+)thPercentile
+      name: kafka_$1_$2_$3
+      type: GAUGE
+      labels:
+        quantile: "0.$4"
+    # KRaft overall related metrics
+    # distinguish between always increasing COUNTER (total and max) and variable GAUGE (all others) metrics
+    - pattern: "kafka.server<type=raft-metrics><>(.+-total|.+-max):"
+      name: kafka_server_raftmetrics_$1
+      type: COUNTER
+    - pattern: "kafka.server<type=raft-metrics><>(current-state): (.+)"
+      name: kafka_server_raftmetrics_$1
+      value: 1
+      type: UNTYPED
+      labels:
+        $1: "$2"
+    - pattern: "kafka.server<type=raft-metrics><>(.+):"
+      name: kafka_server_raftmetrics_$1
+      type: GAUGE
+    # KRaft "low level" channels related metrics
+    # distinguish between always increasing COUNTER (total and max) and variable GAUGE (all others) metrics
+    - pattern: "kafka.server<type=raft-channel-metrics><>(.+-total|.+-max):"
+      name: kafka_server_raftchannelmetrics_$1
+      type: COUNTER
+    - pattern: "kafka.server<type=raft-channel-metrics><>(.+):"
+      name: kafka_server_raftchannelmetrics_$1
+      type: GAUGE
+    # Broker metrics related to fetching metadata topic records in KRaft mode
+    - pattern: "kafka.server<type=broker-metadata-metrics><>(.+):"
+      name: kafka_server_brokermetadatametrics_$1
+      type: GAUGE
+  zookeeper-metrics-config.yml: |
+    # See https://github.com/prometheus/jmx_exporter for more info about JMX Prometheus Exporter metrics
+    lowercaseOutputName: true
+    rules:
+    # replicated Zookeeper
+    - pattern: "org.apache.ZooKeeperService<name0=ReplicatedServer_id(\\d+)><>(\\w+)"
+      name: "zookeeper_$2"
+      type: GAUGE
+    - pattern: "org.apache.ZooKeeperService<name0=ReplicatedServer_id(\\d+), name1=replica.(\\d+)><>(\\w+)"
+      name: "zookeeper_$3"
+      type: GAUGE
+      labels:
+        replicaId: "$2"
+    - pattern: "org.apache.ZooKeeperService<name0=ReplicatedServer_id(\\d+), name1=replica.(\\d+), name2=(\\w+)><>(Packets\\w+)"
+      name: "zookeeper_$4"
+      type: COUNTER
+      labels:
+        replicaId: "$2"
+        memberType: "$3"
+    - pattern: "org.apache.ZooKeeperService<name0=ReplicatedServer_id(\\d+), name1=replica.(\\d+), name2=(\\w+)><>(\\w+)"
+      name: "zookeeper_$4"
+      type: GAUGE
+      labels:
+        replicaId: "$2"
+        memberType: "$3"
+    - pattern: "org.apache.ZooKeeperService<name0=ReplicatedServer_id(\\d+), name1=replica.(\\d+), name2=(\\w+), name3=(\\w+)><>(\\w+)"
+      name: "zookeeper_$4_$5"
+      type: GAUGE
+      labels:
+        replicaId: "$2"
+        memberType: "$3"

packages/apps/kafka/templates/podscrape.yaml

@@ -0,0 +1,40 @@
+apiVersion: operator.victoriametrics.com/v1beta1
+kind: VMPodScrape
+metadata:
+  name: {{ .Release.Name }}
+spec:
+  podMetricsEndpoints:
+    - port: tcp-prometheus
+      scheme: http
+      relabelConfigs:
+      - separator: ;
+        regex: __meta_kubernetes_pod_label_(strimzi_io_.+)
+        replacement: $1
+        action: labelmap
+      - sourceLabels: [__meta_kubernetes_namespace]
+        separator: ;
+        regex: (.*)
+        targetLabel: namespace
+        replacement: $1
+        action: replace
+      - sourceLabels: [__meta_kubernetes_pod_name]
+        separator: ;
+        regex: (.*)
+        targetLabel: pod
+        replacement: $1
+        action: replace
+      - sourceLabels: [__meta_kubernetes_pod_node_name]
+        separator: ;
+        regex: (.*)
+        targetLabel: node
+        replacement: $1
+        action: replace
+      - sourceLabels: [__meta_kubernetes_pod_host_ip]
+        separator: ;
+        regex: (.*)
+        targetLabel: node_ip
+        replacement: $1
+        action: replace
+  selector:
+    matchLabels:
+      app.kubernetes.io/instance: {{ .Release.Name }}

packages/apps/kafka/templates/workloadmonitor.yaml

@@ -0,0 +1,30 @@
+---
+apiVersion: cozystack.io/v1alpha1
+kind: WorkloadMonitor
+metadata:
+  name: {{ $.Release.Name }}
+spec:
+  replicas: {{ .Values.replicas }}
+  minReplicas: 1
+  kind: kafka
+  type: kafka
+  selector:
+    app.kubernetes.io/instance: {{ $.Release.Name }}
+    app.kubernetes.io/name: kafka
+  version: {{ $.Chart.Version }}
+
+---
+
+apiVersion: cozystack.io/v1alpha1
+kind: WorkloadMonitor
+metadata:
+  name: {{ $.Release.Name }}-zookeeper
+spec:
+  replicas: {{ .Values.replicas }}
+  minReplicas: 1
+  kind: kafka
+  type: zookeeper
+  selector:
+    app.kubernetes.io/instance: {{ $.Release.Name }}
+    app.kubernetes.io/name: zookeeper
+  version: {{ $.Chart.Version }}

packages/apps/kafka/values.schema.json

@@ -24,6 +24,16 @@
                     "type": "string",
                     "description": "StorageClass used to store the Kafka data",
                     "default": ""
+                },
+                "resources": {
+                    "type": "object",
+                    "description": "Resources",
+                    "default": {}
+                },
+                "resourcesPreset": {
+                    "type": "string",
+                    "description": "Set container resources according to one common preset (allowed values: none, nano, micro, small, medium, large, xlarge, 2xlarge). This is ignored if resources is set (resources is recommended for production).",
+                    "default": "nano"
                 }
             }
         },
@@ -44,6 +54,16 @@
                     "type": "string",
                     "description": "StorageClass used to store the ZooKeeper data",
                     "default": ""
+                },
+                "resources": {
+                    "type": "object",
+                    "description": "Resources",
+                    "default": {}
+                },
+                "resourcesPreset": {
+                    "type": "string",
+                    "description": "Set container resources according to one common preset (allowed values: none, nano, micro, small, medium, large, xlarge, 2xlarge). This is ignored if resources is set (resources is recommended for production).",
+                    "default": "nano"
                 }
             }
         },

packages/apps/kafka/values.yaml

@@ -14,10 +14,35 @@ kafka:
   size: 10Gi
   replicas: 3
   storageClass: ""
+  ## @param kafka.resources Resources
+  resources: {}
+  # resources:
+  #   limits:
+  #     cpu: 4000m
+  #     memory: 4Gi
+  #   requests:
+  #     cpu: 100m
+  #     memory: 512Mi
+  
+  ## @param kafka.resourcesPreset Set container resources according to one common preset (allowed values: none, nano, micro, small, medium, large, xlarge, 2xlarge). This is ignored if resources is set (resources is recommended for production).
+  resourcesPreset: "nano"
+
 zookeeper:
   size: 5Gi
   replicas: 3
   storageClass: ""
+  ## @param zookeeper.resources Resources
+  resources: {}
+  # resources:
+  #   limits:
+  #     cpu: 4000m
+  #     memory: 4Gi
+  #   requests:
+  #     cpu: 100m
+  #     memory: 512Mi
+  
+  ## @param zookeeper.resourcesPreset Set container resources according to one common preset (allowed values: none, nano, micro, small, medium, large, xlarge, 2xlarge). This is ignored if resources is set (resources is recommended for production).
+  resourcesPreset: "nano"
 
 ## @section Configuration parameters
 

packages/apps/kubernetes/Chart.yaml

@@ -16,7 +16,7 @@ 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: 0.14.0
+version: 0.17.1
 
 # 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

packages/apps/kubernetes/Makefile

@@ -18,6 +18,7 @@ image-ubuntu-container-disk:
 		--cache-to type=inline \
 		--metadata-file images/ubuntu-container-disk.json \
 		--push=$(PUSH) \
+		--label "org.opencontainers.image.source=https://github.com/cozystack/cozystack" \
 		--load=$(LOAD)
 	echo "$(REGISTRY)/ubuntu-container-disk:$(call settag,$(UBUNTU_CONTAINER_DISK_TAG))@$$(yq e '."containerimage.digest"' images/ubuntu-container-disk.json -o json -r)" \
 		> images/ubuntu-container-disk.tag
@@ -32,6 +33,7 @@ image-kubevirt-cloud-provider:
 		--cache-to type=inline \
 		--metadata-file images/kubevirt-cloud-provider.json \
 		--push=$(PUSH) \
+		--label "org.opencontainers.image.source=https://github.com/cozystack/cozystack" \
 		--load=$(LOAD)
 	echo "$(REGISTRY)/kubevirt-cloud-provider:$(call settag,$(KUBERNETES_PKG_TAG))@$$(yq e '."containerimage.digest"' images/kubevirt-cloud-provider.json -o json -r)" \
 		> images/kubevirt-cloud-provider.tag
@@ -46,6 +48,7 @@ image-kubevirt-csi-driver:
 		--cache-to type=inline \
 		--metadata-file images/kubevirt-csi-driver.json \
 		--push=$(PUSH) \
+		--label "org.opencontainers.image.source=https://github.com/cozystack/cozystack" \
 		--load=$(LOAD)
 	echo "$(REGISTRY)/kubevirt-csi-driver:$(call settag,$(KUBERNETES_PKG_TAG))@$$(yq e '."containerimage.digest"' images/kubevirt-csi-driver.json -o json -r)" \
 		> images/kubevirt-csi-driver.tag
@@ -61,6 +64,7 @@ image-cluster-autoscaler:
 		--cache-to type=inline \
 		--metadata-file images/cluster-autoscaler.json \
 		--push=$(PUSH) \
+		--label "org.opencontainers.image.source=https://github.com/cozystack/cozystack" \
 		--load=$(LOAD)
 	echo "$(REGISTRY)/cluster-autoscaler:$(call settag,$(KUBERNETES_PKG_TAG))@$$(yq e '."containerimage.digest"' images/cluster-autoscaler.json -o json -r)" \
 		> images/cluster-autoscaler.tag

packages/apps/kubernetes/images/cluster-autoscaler.tag

@@ -1 +1 @@
-ghcr.io/aenix-io/cozystack/cluster-autoscaler:0.14.0@sha256:c80c305a7c0ff5d64664eea9aefc9a2e68c3bd500cf341d820ef8dd460f3174b
+ghcr.io/cozystack/cozystack/cluster-autoscaler:0.17.1@sha256:85371c6aabf5a7fea2214556deac930c600e362f92673464fe2443784e2869c3

packages/apps/kubernetes/images/cluster-autoscaler/Dockerfile

@@ -1,12 +1,14 @@
 # Source: https://raw.githubusercontent.com/kubernetes/autoscaler/refs/heads/master/cluster-autoscaler/Dockerfile.amd64
-ARG builder_image=docker.io/library/golang:1.22.5
+ARG builder_image=docker.io/library/golang:1.23.4
 ARG BASEIMAGE=gcr.io/distroless/static:nonroot-amd64
 FROM ${builder_image} AS builder
 RUN git clone https://github.com/kubernetes/autoscaler /src/autoscaler \
  && cd /src/autoscaler/cluster-autoscaler \
- && git checkout cluster-autoscaler-1.31.0
+ && git checkout cluster-autoscaler-1.32.0
 
 WORKDIR /src/autoscaler/cluster-autoscaler
+COPY fix-downscale.diff /fix-downscale.diff
+RUN git apply /fix-downscale.diff
 RUN make build
 
 FROM $BASEIMAGE

packages/apps/kubernetes/images/cluster-autoscaler/fix-downscale.diff

@@ -0,0 +1,13 @@
+diff --git a/cluster-autoscaler/cloudprovider/clusterapi/clusterapi_unstructured.go b/cluster-autoscaler/cloudprovider/clusterapi/clusterapi_unstructured.go
+index 4eec0e4bf..f28fd9241 100644
+--- a/cluster-autoscaler/cloudprovider/clusterapi/clusterapi_unstructured.go
++++ b/cluster-autoscaler/cloudprovider/clusterapi/clusterapi_unstructured.go
+@@ -106,8 +106,6 @@ func (r unstructuredScalableResource) Replicas() (int, error) {
+ 
+ func (r unstructuredScalableResource) SetSize(nreplicas int) error {
+ 	switch {
+-	case nreplicas > r.maxSize:
+-		return fmt.Errorf("size increase too large - desired:%d max:%d", nreplicas, r.maxSize)
+ 	case nreplicas < r.minSize:
+ 		return fmt.Errorf("size decrease too large - desired:%d min:%d", nreplicas, r.minSize)
+ 	}

packages/apps/kubernetes/images/kubevirt-cloud-provider.tag

@@ -1 +1 @@
-ghcr.io/aenix-io/cozystack/kubevirt-cloud-provider:0.14.0@sha256:55b78220b60773eefb7b7d3451d7ab9fe89fb6b989e8fe2ae214aab164f00293
+ghcr.io/cozystack/cozystack/kubevirt-cloud-provider:0.17.1@sha256:795d8e1ef4b2b0df2aa1e09d96cd13476ebb545b4bf4b5779b7547a70ef64cf9

packages/apps/kubernetes/images/kubevirt-cloud-provider/Dockerfile

@@ -3,13 +3,13 @@ FROM --platform=linux/amd64 golang:1.20.6 AS builder
 
 RUN git clone https://github.com/kubevirt/cloud-provider-kubevirt /go/src/kubevirt.io/cloud-provider-kubevirt \
  && cd /go/src/kubevirt.io/cloud-provider-kubevirt \
- && git checkout adbd6c27468b86b020cf38490e84f124ef24ab62
+ && git checkout 443a1fe
 
 WORKDIR /go/src/kubevirt.io/cloud-provider-kubevirt
 
-# see: https://github.com/kubevirt/cloud-provider-kubevirt/pull/291
+# see: https://github.com/kubevirt/cloud-provider-kubevirt/pull/335
 ADD patches /patches
-RUN git apply /patches/external-traffic-policy-local.diff
+RUN git apply /patches/*.diff
 RUN go get 'k8s.io/endpointslice/util@v0.28' 'k8s.io/apiserver@v0.28'
 RUN go mod tidy
 RUN go mod vendor

packages/apps/kubernetes/images/kubevirt-cloud-provider/patches/341.diff

@@ -0,0 +1,689 @@
+diff --git a/.golangci.yml b/.golangci.yml
+index cf72a41a2..1c9237e83 100644
+--- a/.golangci.yml
++++ b/.golangci.yml
+@@ -122,3 +122,9 @@ linters:
+   # - testpackage
+   # - revive
+   # - wsl
++issues:
++  exclude-rules:
++    - filename: "kubevirteps_controller_test.go"
++      linters:
++        - govet
++      text: "declaration of \"err\" shadows"
+diff --git a/cmd/kubevirt-cloud-controller-manager/kubevirteps.go b/cmd/kubevirt-cloud-controller-manager/kubevirteps.go
+index 74166b5d9..4e744f8de 100644
+--- a/cmd/kubevirt-cloud-controller-manager/kubevirteps.go
++++ b/cmd/kubevirt-cloud-controller-manager/kubevirteps.go
+@@ -101,7 +101,18 @@ func startKubevirtCloudController(
+ 
+ 	klog.Infof("Setting up kubevirtEPSController")
+ 
+-	kubevirtEPSController := kubevirteps.NewKubevirtEPSController(tenantClient, infraClient, infraDynamic, kubevirtCloud.Namespace())
++	clusterName := ccmConfig.ComponentConfig.KubeCloudShared.ClusterName
++	if clusterName == "" {
++		klog.Fatalf("Required flag --cluster-name is missing")
++	}
++
++	kubevirtEPSController := kubevirteps.NewKubevirtEPSController(
++		tenantClient,
++		infraClient,
++		infraDynamic,
++		kubevirtCloud.Namespace(),
++		clusterName,
++	)
+ 
+ 	klog.Infof("Initializing kubevirtEPSController")
+ 
+diff --git a/pkg/controller/kubevirteps/kubevirteps_controller.go b/pkg/controller/kubevirteps/kubevirteps_controller.go
+index 6f6e3d322..b56882c12 100644
+--- a/pkg/controller/kubevirteps/kubevirteps_controller.go
++++ b/pkg/controller/kubevirteps/kubevirteps_controller.go
+@@ -54,10 +54,10 @@ type Controller struct {
+ 	infraDynamic dynamic.Interface
+ 	infraFactory informers.SharedInformerFactory
+ 
+-	infraNamespace string
+-	queue          workqueue.RateLimitingInterface
+-	maxRetries     int
+-
++	infraNamespace       string
++	clusterName          string
++	queue                workqueue.RateLimitingInterface
++	maxRetries           int
+ 	maxEndPointsPerSlice int
+ }
+ 
+@@ -65,8 +65,9 @@ func NewKubevirtEPSController(
+ 	tenantClient kubernetes.Interface,
+ 	infraClient kubernetes.Interface,
+ 	infraDynamic dynamic.Interface,
+-	infraNamespace string) *Controller {
+-
++	infraNamespace string,
++	clusterName string,
++) *Controller {
+ 	tenantFactory := informers.NewSharedInformerFactory(tenantClient, 0)
+ 	infraFactory := informers.NewSharedInformerFactoryWithOptions(infraClient, 0, informers.WithNamespace(infraNamespace))
+ 	queue := workqueue.NewRateLimitingQueue(workqueue.DefaultControllerRateLimiter())
+@@ -79,6 +80,7 @@ func NewKubevirtEPSController(
+ 		infraDynamic:         infraDynamic,
+ 		infraFactory:         infraFactory,
+ 		infraNamespace:       infraNamespace,
++		clusterName:          clusterName,
+ 		queue:                queue,
+ 		maxRetries:           25,
+ 		maxEndPointsPerSlice: 100,
+@@ -320,22 +322,30 @@ func (c *Controller) processNextItem(ctx context.Context) bool {
+ 
+ // getInfraServiceFromTenantEPS returns the Service in the infra cluster that is associated with the given tenant endpoint slice.
+ func (c *Controller) getInfraServiceFromTenantEPS(ctx context.Context, slice *discovery.EndpointSlice) (*v1.Service, error) {
+-	infraServices, err := c.infraClient.CoreV1().Services(c.infraNamespace).List(ctx,
+-		metav1.ListOptions{LabelSelector: fmt.Sprintf("%s=%s,%s=%s", kubevirt.TenantServiceNameLabelKey, slice.Labels["kubernetes.io/service-name"],
+-			kubevirt.TenantServiceNamespaceLabelKey, slice.Namespace)})
++	tenantServiceName := slice.Labels[discovery.LabelServiceName]
++	tenantServiceNamespace := slice.Namespace
++
++	labelSelector := fmt.Sprintf(
++		"%s=%s,%s=%s,%s=%s",
++		kubevirt.TenantServiceNameLabelKey, tenantServiceName,
++		kubevirt.TenantServiceNamespaceLabelKey, tenantServiceNamespace,
++		kubevirt.TenantClusterNameLabelKey, c.clusterName,
++	)
++
++	svcList, err := c.infraClient.CoreV1().Services(c.infraNamespace).List(ctx, metav1.ListOptions{
++		LabelSelector: labelSelector,
++	})
+ 	if err != nil {
+-		klog.Errorf("Failed to get Service in Infra for EndpointSlice %s in namespace %s: %v", slice.Name, slice.Namespace, err)
++		klog.Errorf("Failed to get Service in Infra for EndpointSlice %s in namespace %s: %v", slice.Name, tenantServiceNamespace, err)
+ 		return nil, err
+ 	}
+-	if len(infraServices.Items) > 1 {
+-		// This should never be possible, only one service should exist for a given tenant endpoint slice
+-		klog.Errorf("Multiple services found for tenant endpoint slice %s in namespace %s", slice.Name, slice.Namespace)
++	if len(svcList.Items) > 1 {
++		klog.Errorf("Multiple services found for tenant endpoint slice %s in namespace %s", slice.Name, tenantServiceNamespace)
+ 		return nil, errors.New("multiple services found for tenant endpoint slice")
+ 	}
+-	if len(infraServices.Items) == 1 {
+-		return &infraServices.Items[0], nil
++	if len(svcList.Items) == 1 {
++		return &svcList.Items[0], nil
+ 	}
+-	// No service found, possible if service is deleted.
+ 	return nil, nil
+ }
+ 
+@@ -363,16 +373,27 @@ func (c *Controller) getTenantEPSFromInfraService(ctx context.Context, svc *v1.S
+ // getInfraEPSFromInfraService returns the EndpointSlices in the infra cluster that are associated with the given infra service.
+ func (c *Controller) getInfraEPSFromInfraService(ctx context.Context, svc *v1.Service) ([]*discovery.EndpointSlice, error) {
+ 	var infraEPSSlices []*discovery.EndpointSlice
+-	klog.Infof("Searching for endpoints on infra cluster for service %s in namespace %s.", svc.Name, svc.Namespace)
+-	result, err := c.infraClient.DiscoveryV1().EndpointSlices(svc.Namespace).List(ctx,
+-		metav1.ListOptions{LabelSelector: fmt.Sprintf("%s=%s", discovery.LabelServiceName, svc.Name)})
++
++	klog.Infof("Searching for EndpointSlices in infra cluster for service %s/%s", svc.Namespace, svc.Name)
++
++	labelSelector := fmt.Sprintf(
++		"%s=%s,%s=%s",
++		discovery.LabelServiceName, svc.Name,
++		kubevirt.TenantClusterNameLabelKey, c.clusterName,
++	)
++
++	result, err := c.infraClient.DiscoveryV1().EndpointSlices(svc.Namespace).List(ctx, metav1.ListOptions{
++		LabelSelector: labelSelector,
++	})
+ 	if err != nil {
+ 		klog.Errorf("Failed to get EndpointSlices for Service %s in namespace %s: %v", svc.Name, svc.Namespace, err)
+ 		return nil, err
+ 	}
++
+ 	for _, eps := range result.Items {
+ 		infraEPSSlices = append(infraEPSSlices, &eps)
+ 	}
++
+ 	return infraEPSSlices, nil
+ }
+ 
+@@ -382,74 +403,117 @@ func (c *Controller) reconcile(ctx context.Context, r *Request) error {
+ 		return errors.New("could not cast object to service")
+ 	}
+ 
++	// Skip services not managed by this controller (missing required labels)
+ 	if service.Labels[kubevirt.TenantServiceNameLabelKey] == "" ||
+ 		service.Labels[kubevirt.TenantServiceNamespaceLabelKey] == "" ||
+ 		service.Labels[kubevirt.TenantClusterNameLabelKey] == "" {
+-		klog.Infof("This LoadBalancer Service: %s is not managed by the %s. Skipping.", service.Name, ControllerName)
++		klog.Infof("Service %s is not managed by this controller. Skipping.", service.Name)
++		return nil
++	}
++
++	// Skip services for other clusters
++	if service.Labels[kubevirt.TenantClusterNameLabelKey] != c.clusterName {
++		klog.Infof("Skipping Service %s: cluster label %q doesn't match our clusterName %q", service.Name, service.Labels[kubevirt.TenantClusterNameLabelKey], c.clusterName)
+ 		return nil
+ 	}
++
+ 	klog.Infof("Reconciling: %v", service.Name)
+ 
++	/*
++	   1) Check if Service in the infra cluster is actually present.
++	      If it's not found, mark it as 'deleted' so that we don't create new slices.
++	*/
+ 	serviceDeleted := false
+-	svc, err := c.infraFactory.Core().V1().Services().Lister().Services(c.infraNamespace).Get(service.Name)
++	infraSvc, err := c.infraFactory.Core().V1().Services().Lister().Services(c.infraNamespace).Get(service.Name)
+ 	if err != nil {
+-		klog.Infof("Service %s in namespace %s is deleted.", service.Name, service.Namespace)
++		// The Service is not present in the infra lister => treat as deleted
++		klog.Infof("Service %s in namespace %s is deleted (or not found).", service.Name, service.Namespace)
+ 		serviceDeleted = true
+ 	} else {
+-		service = svc
++		// Use the actual object from the lister, so we have the latest state
++		service = infraSvc
+ 	}
+ 
++	/*
++	   2) Get all existing EndpointSlices in the infra cluster that belong to this LB Service.
++	      We'll decide which of them should be updated or deleted.
++	*/
+ 	infraExistingEpSlices, err := c.getInfraEPSFromInfraService(ctx, service)
+ 	if err != nil {
+ 		return err
+ 	}
+ 
+-	// At this point we have the current state of the 3 main objects we are interested in:
+-	// 1. The Service in the infra cluster, the one created by the KubevirtCloudController.
+-	// 2. The EndpointSlices in the tenant cluster, created for the tenant cluster's Service.
+-	// 3. The EndpointSlices in the infra cluster, managed by this controller.
+-
+ 	slicesToDelete := []*discovery.EndpointSlice{}
+ 	slicesByAddressType := make(map[discovery.AddressType][]*discovery.EndpointSlice)
+ 
++	// For example, if the service is single-stack IPv4 => only AddressTypeIPv4
++	// or if dual-stack => IPv4 and IPv6, etc.
+ 	serviceSupportedAddressesTypes := getAddressTypesForService(service)
+-	// If the services switched to a different address type, we need to delete the old ones, because it's immutable.
+-	// If the services switched to a different externalTrafficPolicy, we need to delete the old ones.
++
++	/*
++	   3) Determine which slices to delete, and which to pass on to the normal
++	      "reconcileByAddressType" logic.
++
++	      - If 'serviceDeleted' is true OR service.Spec.Selector != nil, we remove them.
++	      - Also, if the slice's address type is unsupported by the Service, we remove it.
++	*/
+ 	for _, eps := range infraExistingEpSlices {
+-		if service.Spec.Selector != nil || serviceDeleted {
+-			klog.Infof("Added for deletion EndpointSlice %s in namespace %s because it has a selector", eps.Name, eps.Namespace)
+-			// to be sure we don't delete any slice that is not managed by us
++		// If service is deleted or has a non-nil selector => remove slices
++		if serviceDeleted || service.Spec.Selector != nil {
++			/*
++			   Only remove if it is clearly labeled as managed by us:
++			   we do not want to accidentally remove slices that are not
++			   created by this controller.
++			*/
+ 			if c.managedByController(eps) {
++				klog.Infof("Added for deletion EndpointSlice %s in namespace %s because service is deleted or has a selector",
++					eps.Name, eps.Namespace)
+ 				slicesToDelete = append(slicesToDelete, eps)
+ 			}
+ 			continue
+ 		}
++
++		// If the Service does not support this slice's AddressType => remove
+ 		if !serviceSupportedAddressesTypes.Has(eps.AddressType) {
+-			klog.Infof("Added for deletion EndpointSlice %s in namespace %s because it has an unsupported address type: %v", eps.Name, eps.Namespace, eps.AddressType)
++			klog.Infof("Added for deletion EndpointSlice %s in namespace %s because it has an unsupported address type: %v",
++				eps.Name, eps.Namespace, eps.AddressType)
+ 			slicesToDelete = append(slicesToDelete, eps)
+ 			continue
+ 		}
++
++		/*
++		   Otherwise, this slice is potentially still valid for the given AddressType,
++		   we'll send it to reconcileByAddressType for final merging and updates.
++		*/
+ 		slicesByAddressType[eps.AddressType] = append(slicesByAddressType[eps.AddressType], eps)
+ 	}
+ 
+-	if !serviceDeleted {
+-		// Get tenant's endpoint slices for this service
++	/*
++	   4) If the Service was NOT deleted and has NO selector (i.e., it's a "no-selector" LB Service),
++	      we proceed to handle creation and updates. That means:
++	      - Gather Tenant's EndpointSlices
++	      - Reconcile them by each AddressType
++	*/
++	if !serviceDeleted && service.Spec.Selector == nil {
+ 		tenantEpSlices, err := c.getTenantEPSFromInfraService(ctx, service)
+ 		if err != nil {
+ 			return err
+ 		}
+ 
+-		// Reconcile the EndpointSlices for each address type e.g. ipv4, ipv6
++		// For each addressType (ipv4, ipv6, etc.) reconcile the infra slices
+ 		for addressType := range serviceSupportedAddressesTypes {
+ 			existingSlices := slicesByAddressType[addressType]
+-			err := c.reconcileByAddressType(service, tenantEpSlices, existingSlices, addressType)
+-			if err != nil {
++			if err := c.reconcileByAddressType(service, tenantEpSlices, existingSlices, addressType); err != nil {
+ 				return err
+ 			}
+ 		}
+ 	}
+ 
+-	// Delete the EndpointSlices that are no longer needed
++	/*
++	   5) Perform the actual deletion of all slices we flagged.
++	      In many cases (serviceDeleted or .Spec.Selector != nil),
++	      we end up with only "delete" actions and no new slice creation.
++	*/
+ 	for _, eps := range slicesToDelete {
+ 		err := c.infraClient.DiscoveryV1().EndpointSlices(eps.Namespace).Delete(context.TODO(), eps.Name, metav1.DeleteOptions{})
+ 		if err != nil {
+@@ -474,11 +538,11 @@ func (c *Controller) reconcileByAddressType(service *v1.Service, tenantSlices []
+ 	// Create the desired port configuration
+ 	var desiredPorts []discovery.EndpointPort
+ 
+-	for _, port := range service.Spec.Ports {
++	for i := range service.Spec.Ports {
+ 		desiredPorts = append(desiredPorts, discovery.EndpointPort{
+-			Port:     &port.TargetPort.IntVal,
+-			Protocol: &port.Protocol,
+-			Name:     &port.Name,
++			Port:     &service.Spec.Ports[i].TargetPort.IntVal,
++			Protocol: &service.Spec.Ports[i].Protocol,
++			Name:     &service.Spec.Ports[i].Name,
+ 		})
+ 	}
+ 
+@@ -588,55 +652,114 @@ func ownedBy(endpointSlice *discovery.EndpointSlice, svc *v1.Service) bool {
+ 	return false
+ }
+ 
+-func (c *Controller) finalize(service *v1.Service, slicesToCreate []*discovery.EndpointSlice, slicesToUpdate []*discovery.EndpointSlice, slicesToDelete []*discovery.EndpointSlice) error {
+-	// If there are slices to delete and slices to create, make them as update
+-	for i := 0; i < len(slicesToDelete); {
++func (c *Controller) finalize(
++	service *v1.Service,
++	slicesToCreate []*discovery.EndpointSlice,
++	slicesToUpdate []*discovery.EndpointSlice,
++	slicesToDelete []*discovery.EndpointSlice,
++) error {
++	/*
++	   We try to turn a "delete + create" pair into a single "update" operation
++	   if the original slice (slicesToDelete[i]) has the same address type as
++	   the first slice in slicesToCreate, and is owned by the same Service.
++
++	   However, we must re-check the lengths of slicesToDelete and slicesToCreate
++	   within the loop to avoid an out-of-bounds index in slicesToCreate.
++	*/
++
++	i := 0
++	for i < len(slicesToDelete) {
++		// If there is nothing to create, break early
+ 		if len(slicesToCreate) == 0 {
+ 			break
+ 		}
+-		if slicesToDelete[i].AddressType == slicesToCreate[0].AddressType && ownedBy(slicesToDelete[i], service) {
+-			slicesToCreate[0].Name = slicesToDelete[i].Name
++
++		sd := slicesToDelete[i]
++		sc := slicesToCreate[0] // We can safely do this now, because len(slicesToCreate) > 0
++
++		// If the address type matches, and the slice is owned by the same Service,
++		// then instead of deleting sd and creating sc, we'll transform it into an update:
++		// we rename sc with sd's name, remove sd from the delete list, remove sc from the create list,
++		// and add sc to the update list.
++		if sd.AddressType == sc.AddressType && ownedBy(sd, service) {
++			sliceToUpdate := sc
++			sliceToUpdate.Name = sd.Name
++
++			// Remove the first element from slicesToCreate
+ 			slicesToCreate = slicesToCreate[1:]
+-			slicesToUpdate = append(slicesToUpdate, slicesToCreate[0])
++
++			// Remove the slice from slicesToDelete
+ 			slicesToDelete = append(slicesToDelete[:i], slicesToDelete[i+1:]...)
++
++			// Now add the renamed slice to the list of slices we want to update
++			slicesToUpdate = append(slicesToUpdate, sliceToUpdate)
++
++			/*
++			   Do not increment i here, because we've just removed an element from
++			   slicesToDelete. The next slice to examine is now at the same index i.
++			*/
+ 		} else {
++			// If they don't match, move on to the next slice in slicesToDelete.
+ 			i++
+ 		}
+ 	}
+ 
+-	// Create the new slices if service is not marked for deletion
++	/*
++	   If the Service is not being deleted, create all remaining slices in slicesToCreate.
++	   (If the Service has a DeletionTimestamp, it means it is going away, so we do not
++	   want to create new EndpointSlices.)
++	*/
+ 	if service.DeletionTimestamp == nil {
+ 		for _, slice := range slicesToCreate {
+-			createdSlice, err := c.infraClient.DiscoveryV1().EndpointSlices(slice.Namespace).Create(context.TODO(), slice, metav1.CreateOptions{})
++			createdSlice, err := c.infraClient.DiscoveryV1().EndpointSlices(slice.Namespace).Create(
++				context.TODO(),
++				slice,
++				metav1.CreateOptions{},
++			)
+ 			if err != nil {
+-				klog.Errorf("Failed to create EndpointSlice %s in namespace %s: %v", slice.Name, slice.Namespace, err)
++				klog.Errorf("Failed to create EndpointSlice %s in namespace %s: %v",
++					slice.Name, slice.Namespace, err)
++				// If the namespace is terminating, it's safe to ignore the error.
+ 				if k8serrors.HasStatusCause(err, v1.NamespaceTerminatingCause) {
+-					return nil
++					continue
+ 				}
+ 				return err
+ 			}
+-			klog.Infof("Created EndpointSlice %s in namespace %s", createdSlice.Name, createdSlice.Namespace)
++			klog.Infof("Created EndpointSlice %s in namespace %s",
++				createdSlice.Name, createdSlice.Namespace)
+ 		}
+ 	}
+ 
+-	// Update slices
++	// Update slices that are in the slicesToUpdate list.
+ 	for _, slice := range slicesToUpdate {
+-		_, err := c.infraClient.DiscoveryV1().EndpointSlices(slice.Namespace).Update(context.TODO(), slice, metav1.UpdateOptions{})
++		_, err := c.infraClient.DiscoveryV1().EndpointSlices(slice.Namespace).Update(
++			context.TODO(),
++			slice,
++			metav1.UpdateOptions{},
++		)
+ 		if err != nil {
+-			klog.Errorf("Failed to update EndpointSlice %s in namespace %s: %v", slice.Name, slice.Namespace, err)
++			klog.Errorf("Failed to update EndpointSlice %s in namespace %s: %v",
++				slice.Name, slice.Namespace, err)
+ 			return err
+ 		}
+-		klog.Infof("Updated EndpointSlice %s in namespace %s", slice.Name, slice.Namespace)
++		klog.Infof("Updated EndpointSlice %s in namespace %s",
++			slice.Name, slice.Namespace)
+ 	}
+ 
+-	// Delete slices
++	// Finally, delete slices that are in slicesToDelete and are no longer needed.
+ 	for _, slice := range slicesToDelete {
+-		err := c.infraClient.DiscoveryV1().EndpointSlices(slice.Namespace).Delete(context.TODO(), slice.Name, metav1.DeleteOptions{})
++		err := c.infraClient.DiscoveryV1().EndpointSlices(slice.Namespace).Delete(
++			context.TODO(),
++			slice.Name,
++			metav1.DeleteOptions{},
++		)
+ 		if err != nil {
+-			klog.Errorf("Failed to delete EndpointSlice %s in namespace %s: %v", slice.Name, slice.Namespace, err)
++			klog.Errorf("Failed to delete EndpointSlice %s in namespace %s: %v",
++				slice.Name, slice.Namespace, err)
+ 			return err
+ 		}
+-		klog.Infof("Deleted EndpointSlice %s in namespace %s", slice.Name, slice.Namespace)
++		klog.Infof("Deleted EndpointSlice %s in namespace %s",
++			slice.Name, slice.Namespace)
+ 	}
+ 
+ 	return nil
+diff --git a/pkg/controller/kubevirteps/kubevirteps_controller_test.go b/pkg/controller/kubevirteps/kubevirteps_controller_test.go
+index 1fb86e25f..14d92d340 100644
+--- a/pkg/controller/kubevirteps/kubevirteps_controller_test.go
++++ b/pkg/controller/kubevirteps/kubevirteps_controller_test.go
+@@ -13,6 +13,7 @@ import (
+ 	"k8s.io/apimachinery/pkg/runtime"
+ 	"k8s.io/apimachinery/pkg/runtime/schema"
+ 	"k8s.io/apimachinery/pkg/util/intstr"
++	"k8s.io/apimachinery/pkg/util/sets"
+ 	dfake "k8s.io/client-go/dynamic/fake"
+ 	"k8s.io/client-go/kubernetes/fake"
+ 	"k8s.io/client-go/testing"
+@@ -189,7 +190,7 @@ func setupTestKubevirtEPSController() *testKubevirtEPSController {
+ 		}: "VirtualMachineInstanceList",
+ 	})
+ 
+-	controller := NewKubevirtEPSController(tenantClient, infraClient, infraDynamic, "test")
++	controller := NewKubevirtEPSController(tenantClient, infraClient, infraDynamic, "test", "test-cluster")
+ 
+ 	err := controller.Init()
+ 	if err != nil {
+@@ -686,5 +687,229 @@ var _ = g.Describe("KubevirtEPSController", g.Ordered, func() {
+ 				return false, err
+ 			}).Should(BeTrue(), "EndpointSlice in infra cluster should be recreated by the controller after deletion")
+ 		})
++
++		g.It("Should correctly handle multiple unique ports in EndpointSlice", func() {
++			// Create a VMI in the infra cluster
++			createAndAssertVMI("worker-0-test", "ip-10-32-5-13", "123.45.67.89")
++
++			// Create an EndpointSlice in the tenant cluster
++			createAndAssertTenantSlice("test-epslice", "tenant-service-name", discoveryv1.AddressTypeIPv4,
++				*createPort("http", 80, v1.ProtocolTCP),
++				[]discoveryv1.Endpoint{*createEndpoint("123.45.67.89", "worker-0-test", true, true, false)})
++
++			// Define multiple ports for the Service
++			servicePorts := []v1.ServicePort{
++				{
++					Name:       "client",
++					Protocol:   v1.ProtocolTCP,
++					Port:       10001,
++					TargetPort: intstr.FromInt(30396),
++					NodePort:   30396,
++				},
++				{
++					Name:       "dashboard",
++					Protocol:   v1.ProtocolTCP,
++					Port:       8265,
++					TargetPort: intstr.FromInt(31003),
++					NodePort:   31003,
++				},
++				{
++					Name:       "metrics",
++					Protocol:   v1.ProtocolTCP,
++					Port:       8080,
++					TargetPort: intstr.FromInt(30452),
++					NodePort:   30452,
++				},
++			}
++
++			createAndAssertInfraServiceLB("infra-multiport-service", "tenant-service-name", "test-cluster",
++				servicePorts[0], v1.ServiceExternalTrafficPolicyLocal)
++
++			svc, err := testVals.infraClient.CoreV1().Services(infraNamespace).Get(context.TODO(), "infra-multiport-service", metav1.GetOptions{})
++			Expect(err).To(BeNil())
++
++			svc.Spec.Ports = servicePorts
++			_, err = testVals.infraClient.CoreV1().Services(infraNamespace).Update(context.TODO(), svc, metav1.UpdateOptions{})
++			Expect(err).To(BeNil())
++
++			var epsListMultiPort *discoveryv1.EndpointSliceList
++
++			Eventually(func() (bool, error) {
++				epsListMultiPort, err = testVals.infraClient.DiscoveryV1().EndpointSlices(infraNamespace).List(context.TODO(), metav1.ListOptions{})
++				if len(epsListMultiPort.Items) != 1 {
++					return false, err
++				}
++
++				createdSlice := epsListMultiPort.Items[0]
++				expectedPortNames := []string{"client", "dashboard", "metrics"}
++				foundPortNames := []string{}
++
++				for _, port := range createdSlice.Ports {
++					if port.Name != nil {
++						foundPortNames = append(foundPortNames, *port.Name)
++					}
++				}
++
++				if len(foundPortNames) != len(expectedPortNames) {
++					return false, err
++				}
++
++				portSet := sets.NewString(foundPortNames...)
++				expectedPortSet := sets.NewString(expectedPortNames...)
++				return portSet.Equal(expectedPortSet), err
++			}).Should(BeTrue(), "EndpointSlice should contain all unique ports from the Service without duplicates")
++		})
++
++		g.It("Should not panic when Service changes to have a non-nil selector, causing EndpointSlice deletion with no new slices to create", func() {
++			createAndAssertVMI("worker-0-test", "ip-10-32-5-13", "123.45.67.89")
++			createAndAssertTenantSlice("test-epslice", "tenant-service-name", discoveryv1.AddressTypeIPv4,
++				*createPort("http", 80, v1.ProtocolTCP),
++				[]discoveryv1.Endpoint{*createEndpoint("123.45.67.89", "worker-0-test", true, true, false)})
++			createAndAssertInfraServiceLB("infra-service-no-selector", "tenant-service-name", "test-cluster",
++				v1.ServicePort{
++					Name:       "web",
++					Port:       80,
++					NodePort:   31900,
++					Protocol:   v1.ProtocolTCP,
++					TargetPort: intstr.IntOrString{IntVal: 30390},
++				},
++				v1.ServiceExternalTrafficPolicyLocal,
++			)
++
++			// Wait for the controller to create an EndpointSlice in the infra cluster.
++			var epsList *discoveryv1.EndpointSliceList
++			var err error
++			Eventually(func() (bool, error) {
++				epsList, err = testVals.infraClient.DiscoveryV1().EndpointSlices(infraNamespace).
++					List(context.TODO(), metav1.ListOptions{})
++				if err != nil {
++					return false, err
++				}
++				// Wait exactly 1 slice
++				if len(epsList.Items) == 1 {
++					return true, nil
++				}
++				return false, nil
++			}).Should(BeTrue(), "Controller should create an EndpointSlice in infra cluster for the LB service")
++
++			svcWithSelector, err := testVals.infraClient.CoreV1().Services(infraNamespace).
++				Get(context.TODO(), "infra-service-no-selector", metav1.GetOptions{})
++			Expect(err).To(BeNil())
++
++			// Let's set any selector to run the slice deletion logic
++			svcWithSelector.Spec.Selector = map[string]string{"test": "selector-added"}
++			_, err = testVals.infraClient.CoreV1().Services(infraNamespace).
++				Update(context.TODO(), svcWithSelector, metav1.UpdateOptions{})
++			Expect(err).To(BeNil())
++
++			Eventually(func() (bool, error) {
++				epsList, err = testVals.infraClient.DiscoveryV1().EndpointSlices(infraNamespace).
++					List(context.TODO(), metav1.ListOptions{})
++				if err != nil {
++					return false, err
++				}
++				// We expect that after the update service.EndpointSlice will become 0
++				if len(epsList.Items) == 0 {
++					return true, nil
++				}
++				return false, nil
++			}).Should(BeTrue(), "Existing EndpointSlice should be removed because Service now has a selector")
++		})
++
++		g.It("Should remove EndpointSlices and not recreate them when a previously no-selector Service obtains a selector", func() {
++			testVals.infraClient.Fake.PrependReactor("create", "endpointslices", func(action testing.Action) (bool, runtime.Object, error) {
++				createAction := action.(testing.CreateAction)
++				slice := createAction.GetObject().(*discoveryv1.EndpointSlice)
++				if slice.Name == "" && slice.GenerateName != "" {
++					slice.Name = slice.GenerateName + "-fake001"
++				}
++				return false, slice, nil
++			})
++
++			createAndAssertVMI("worker-0-test", "ip-10-32-5-13", "123.45.67.89")
++
++			createAndAssertTenantSlice("test-epslice", "tenant-service-name", discoveryv1.AddressTypeIPv4,
++				*createPort("http", 80, v1.ProtocolTCP),
++				[]discoveryv1.Endpoint{
++					*createEndpoint("123.45.67.89", "worker-0-test", true, true, false),
++				},
++			)
++
++			noSelectorSvcName := "svc-without-selector"
++			svc := &v1.Service{
++				ObjectMeta: metav1.ObjectMeta{
++					Name:      noSelectorSvcName,
++					Namespace: infraNamespace,
++					Labels: map[string]string{
++						kubevirt.TenantServiceNameLabelKey:      "tenant-service-name",
++						kubevirt.TenantServiceNamespaceLabelKey: tenantNamespace,
++						kubevirt.TenantClusterNameLabelKey:      "test-cluster",
++					},
++				},
++				Spec: v1.ServiceSpec{
++					Ports: []v1.ServicePort{
++						{
++							Name:       "web",
++							Port:       80,
++							NodePort:   31900,
++							Protocol:   v1.ProtocolTCP,
++							TargetPort: intstr.IntOrString{IntVal: 30390},
++						},
++					},
++					Type:                  v1.ServiceTypeLoadBalancer,
++					ExternalTrafficPolicy: v1.ServiceExternalTrafficPolicyLocal,
++				},
++			}
++
++			_, err := testVals.infraClient.CoreV1().Services(infraNamespace).Create(context.TODO(), svc, metav1.CreateOptions{})
++			Expect(err).To(BeNil())
++
++			Eventually(func() (bool, error) {
++				epsList, err := testVals.infraClient.DiscoveryV1().EndpointSlices(infraNamespace).
++					List(context.TODO(), metav1.ListOptions{})
++				if err != nil {
++					return false, err
++				}
++				return len(epsList.Items) == 1, nil
++			}).Should(BeTrue(), "Controller should create an EndpointSlice in infra cluster for the no-selector LB service")
++
++			svcWithSelector, err := testVals.infraClient.CoreV1().Services(infraNamespace).Get(
++				context.TODO(), noSelectorSvcName, metav1.GetOptions{})
++			Expect(err).To(BeNil())
++
++			svcWithSelector.Spec.Selector = map[string]string{"app": "test-value"}
++			_, err = testVals.infraClient.CoreV1().Services(infraNamespace).
++				Update(context.TODO(), svcWithSelector, metav1.UpdateOptions{})
++			Expect(err).To(BeNil())
++
++			Eventually(func() (bool, error) {
++				epsList, err := testVals.infraClient.DiscoveryV1().EndpointSlices(infraNamespace).
++					List(context.TODO(), metav1.ListOptions{})
++				if err != nil {
++					return false, err
++				}
++				return len(epsList.Items) == 0, nil
++			}).Should(BeTrue(), "All EndpointSlices should be removed after Service acquires a selector (no new slices created)")
++		})
++
++		g.It("Should ignore Services from a different cluster", func() {
++			// Create a Service with cluster label "other-cluster"
++			svc := createInfraServiceLB("infra-service-conflict", "tenant-service-name", "other-cluster",
++				v1.ServicePort{Name: "web", Port: 80, NodePort: 31900, Protocol: v1.ProtocolTCP, TargetPort: intstr.IntOrString{IntVal: 30390}},
++				v1.ServiceExternalTrafficPolicyLocal)
++			_, err := testVals.infraClient.CoreV1().Services(infraNamespace).Create(context.TODO(), svc, metav1.CreateOptions{})
++			Expect(err).To(BeNil())
++
++			// The controller should ignore this Service, so no EndpointSlice should be created.
++			Eventually(func() (bool, error) {
++				epsList, err := testVals.infraClient.DiscoveryV1().EndpointSlices(infraNamespace).List(context.TODO(), metav1.ListOptions{})
++				if err != nil {
++					return false, err
++				}
++				// Expect zero slices since cluster label does not match "test-cluster"
++				return len(epsList.Items) == 0, nil
++			}).Should(BeTrue(), "Services with a different cluster label should be ignored")
++		})
++
+ 	})
+ })

packages/apps/kubernetes/images/kubevirt-csi-driver.tag

@@ -1 +1 @@
-ghcr.io/aenix-io/cozystack/kubevirt-csi-driver:0.14.0@sha256:bc61dba787ca79f9b8d7288a631cbaecf8de9f87b6a2ad44e1513f730362621f
+ghcr.io/cozystack/cozystack/kubevirt-csi-driver:0.17.1@sha256:d1346d59224e6d2d07f1551af918ed31e57ba84b750122c1aeceaf9b33dd2271

packages/apps/kubernetes/images/ubuntu-container-disk.tag

@@ -1 +1 @@
-ghcr.io/aenix-io/cozystack/ubuntu-container-disk:v1.30.1@sha256:8258747003f40f0f8dd54317e52e98baf4674c5ac14ad851ac6b2871d29e4b2d
+ghcr.io/cozystack/cozystack/ubuntu-container-disk:v1.30.1@sha256:07392e7a87a3d4ef1c86c1b146e6c5de5c2b524aed5a53bf48870dc8a296f99a

packages/apps/kubernetes/templates/_resources.tpl

@@ -0,0 +1,50 @@
+{{/*
+Copyright Broadcom, Inc. All Rights Reserved.
+SPDX-License-Identifier: APACHE-2.0
+*/}}
+
+{{/* vim: set filetype=mustache: */}}
+
+{{/*
+Return a resource request/limit object based on a given preset.
+These presets are for basic testing and not meant to be used in production
+{{ include "resources.preset" (dict "type" "nano") -}}
+*/}}
+{{- define "resources.preset" -}}
+{{/* The limits are the requests increased by 50% (except ephemeral-storage and xlarge/2xlarge sizes)*/}}
+{{- $presets := dict 
+  "nano" (dict 
+      "requests" (dict "cpu" "100m" "memory" "128Mi" "ephemeral-storage" "50Mi")
+      "limits" (dict "cpu" "150m" "memory" "192Mi" "ephemeral-storage" "2Gi")
+   )
+  "micro" (dict 
+      "requests" (dict "cpu" "250m" "memory" "256Mi" "ephemeral-storage" "50Mi")
+      "limits" (dict "cpu" "375m" "memory" "384Mi" "ephemeral-storage" "2Gi")
+   )
+  "small" (dict 
+      "requests" (dict "cpu" "500m" "memory" "512Mi" "ephemeral-storage" "50Mi")
+      "limits" (dict "cpu" "750m" "memory" "768Mi" "ephemeral-storage" "2Gi")
+   )
+  "medium" (dict 
+      "requests" (dict "cpu" "500m" "memory" "1024Mi" "ephemeral-storage" "50Mi")
+      "limits" (dict "cpu" "750m" "memory" "1536Mi" "ephemeral-storage" "2Gi")
+   )
+  "large" (dict 
+      "requests" (dict "cpu" "1.0" "memory" "2048Mi" "ephemeral-storage" "50Mi")
+      "limits" (dict "cpu" "1.5" "memory" "3072Mi" "ephemeral-storage" "2Gi")
+   )
+  "xlarge" (dict 
+      "requests" (dict "cpu" "1.0" "memory" "3072Mi" "ephemeral-storage" "50Mi")
+      "limits" (dict "cpu" "3.0" "memory" "6144Mi" "ephemeral-storage" "2Gi")
+   )
+  "2xlarge" (dict 
+      "requests" (dict "cpu" "1.0" "memory" "3072Mi" "ephemeral-storage" "50Mi")
+      "limits" (dict "cpu" "6.0" "memory" "12288Mi" "ephemeral-storage" "2Gi")
+   )
+ }}
+{{- if hasKey $presets .type -}}
+{{- index $presets .type | toYaml -}}
+{{- else -}}
+{{- printf "ERROR: Preset key '%s' invalid. Allowed values are %s" .type (join "," (keys $presets)) | fail -}}
+{{- end -}}
+{{- end -}}

packages/apps/kubernetes/templates/cluster-autoscaler/deployment.yaml

@@ -26,10 +26,23 @@ spec:
       containers:
       - image: "{{ $.Files.Get "images/cluster-autoscaler.tag" | trim }}"
         name: cluster-autoscaler
+        resources:
+          limits:
+            cpu: 512m
+            memory: 512Mi
+          requests:
+            cpu: 125m
+            memory: 128Mi
         command:
         - /cluster-autoscaler
         args:
         - --cloud-provider=clusterapi
+        - --enforce-node-group-min-size=true
+        - --ignore-daemonsets-utilization=true
+        - --ignore-mirror-pods-utilization=true
+        - --scale-down-unneeded-time=30s
+        - --scan-interval=25s
+        - --force-delete-unregistered-nodes=true
         - --kubeconfig=/etc/kubernetes/kubeconfig/super-admin.svc
         - --clusterapi-cloud-config-authoritative
         - --node-group-auto-discovery=clusterapi:namespace={{ .Release.Namespace }},clusterName={{ .Release.Name }}

packages/apps/kubernetes/templates/cluster.yaml

@@ -29,6 +29,7 @@ spec:
             {{- range .group.roles }}
             node-role.kubernetes.io/{{ . }}: ""
             {{- end }}
+            cluster.x-k8s.io/deployment-name: {{ $.Release.Name }}-{{ .groupName }}
         spec:
           domain:
             {{- if and .group.resources .group.resources.cpu }}
@@ -101,12 +102,37 @@ metadata:
   annotations:
     kamaji.clastix.io/kubeconfig-secret-key: "super-admin.svc"
 spec:
+  apiServer:
+    {{- if .Values.kamajiControlPlane.apiServer.resources }}
+    resources: {{- toYaml .Values.kamajiControlPlane.apiServer.resources | nindent 6 }}
+    {{- else if ne .Values.kamajiControlPlane.apiServer.resourcesPreset "none" }}
+    resources: {{- include "resources.preset" (dict "type" .Values.kamajiControlPlane.apiServer.resourcesPreset "Release" .Release) | nindent 6 }}
+    {{- end }}
+  controllerManager:
+    {{- if .Values.kamajiControlPlane.controllerManager.resources }}
+    resources: {{- toYaml .Values.kamajiControlPlane.controllerManager.resources | nindent 6 }}
+    {{- else if ne .Values.kamajiControlPlane.controllerManager.resourcesPreset "none" }}
+    resources: {{- include "resources.preset" (dict "type" .Values.kamajiControlPlane.controllerManager.resourcesPreset "Release" .Release) | nindent 6 }}
+    {{- end }}
+  scheduler:
+    {{- if .Values.kamajiControlPlane.scheduler.resources }}
+    resources: {{- toYaml .Values.kamajiControlPlane.scheduler.resources | nindent 6 }}
+    {{- else if ne .Values.kamajiControlPlane.scheduler.resourcesPreset "none" }}
+    resources: {{- include "resources.preset" (dict "type" .Values.kamajiControlPlane.scheduler.resourcesPreset "Release" .Release) | nindent 6 }}
+    {{- end }}
   dataStoreName: "{{ $etcd }}"
   addons:
     coreDNS:
       dnsServiceIPs:
       - 10.95.0.10
-    konnectivity: {}
+    konnectivity:
+      server:
+        port: 8132
+        {{- if .Values.kamajiControlPlane.addons.konnectivity.server.resources }}
+        resources: {{- toYaml .Values.kamajiControlPlane.addons.konnectivity.server.resources | nindent 10 }}
+        {{- else if ne .Values.kamajiControlPlane.addons.konnectivity.server.resourcesPreset "none" }}
+        resources: {{- include "resources.preset" (dict "type" .Values.kamajiControlPlane.addons.konnectivity.server.resourcesPreset "Release" .Release) | nindent 10 }}
+        {{- end }}
   kubelet:
     cgroupfs: systemd
     preferredAddressTypes:
@@ -117,7 +143,7 @@ spec:
     ingress:
       extraAnnotations:
         nginx.ingress.kubernetes.io/ssl-passthrough: "true"
-      hostname: {{ .Values.host | default (printf "%s.%s" .Release.Name $host) }}:443
+      hostname: {{ .Values.host | default (printf "%s.%s" .Release.Name $host) }}
       className: "{{ $ingress }}"
   deployment:
     podAdditionalMetadata:
@@ -126,6 +152,21 @@ spec:
   replicas: 2
   version: 1.30.1
 ---
+apiVersion: cozystack.io/v1alpha1
+kind: WorkloadMonitor
+metadata:
+  name: {{ .Release.Name }}
+  namespace: {{ .Release.Namespace }}
+spec:
+  replicas: 2
+  minReplicas: 1
+  kind: kubernetes
+  type: control-plane
+  selector:
+    kamaji.clastix.io/component: deployment
+    kamaji.clastix.io/name: {{ .Release.Name }}
+  version: {{ $.Chart.Version }}
+---
 apiVersion: infrastructure.cluster.x-k8s.io/v1alpha1
 kind: KubevirtCluster
 metadata:
@@ -172,6 +213,7 @@ spec:
 ---
 {{- $context := deepCopy $ }}
 {{- $_ := set $context "group" $group }}
+{{- $_ := set $context "groupName" $groupName }}
 {{- $kubevirtmachinetemplate := include "kubevirtmachinetemplate" $context }}
 {{- $kubevirtmachinetemplateHash := $kubevirtmachinetemplate | sha256sum | trunc 6 }}
 {{- $kubevirtmachinetemplateName := printf "%s-%s-%s" $.Release.Name $groupName $kubevirtmachinetemplateHash }}
@@ -233,7 +275,7 @@ spec:
         apiVersion: infrastructure.cluster.x-k8s.io/v1alpha1
         kind: KubevirtMachineTemplate
         name: {{ $.Release.Name }}-{{ $groupName }}-{{ $kubevirtmachinetemplateHash }}
-        namespace: default
+        namespace: {{ $.Release.Namespace }}
       version: v1.30.1
 ---
 apiVersion: cluster.x-k8s.io/v1beta1
@@ -255,6 +297,21 @@ spec:
   - type: Ready
     status: "False"
     timeout: 300s
+---
+apiVersion: cozystack.io/v1alpha1
+kind: WorkloadMonitor
+metadata:
+  name: {{ $.Release.Name }}-{{ $groupName }}
+  namespace: {{ $.Release.Namespace }}
+spec:
+  minReplicas: {{ $group.minReplicas }}
+  kind: kubernetes
+  type: worker
+  selector:
+    cluster.x-k8s.io/cluster-name: {{ $.Release.Name }}
+    cluster.x-k8s.io/deployment-name: {{ $.Release.Name }}-{{ $groupName }}
+    cluster.x-k8s.io/role: worker
+  version: {{ $.Chart.Version }}
 {{- end }}
 ---
 {{- /*

packages/apps/kubernetes/templates/csi/deploy.yaml

@@ -63,11 +63,21 @@ spec:
               mountPath: /etc/kubernetes/kubeconfig
               readOnly: true
           resources:
+            limits:
+              cpu: 512m
+              memory: 512Mi
             requests:
-              memory: 50Mi
-              cpu: 10m
+              cpu: 125m
+              memory: 128Mi
         - name: csi-provisioner
           image: quay.io/openshift/origin-csi-external-provisioner:latest
+          resources:
+            limits:
+              cpu: 512m
+              memory: 512Mi
+            requests:
+              cpu: 125m
+              memory: 128Mi
           args:
             - "--csi-address=$(ADDRESS)"
             - "--default-fstype=ext4"
@@ -102,9 +112,12 @@ spec:
               mountPath: /etc/kubernetes/kubeconfig
               readOnly: true
           resources:
+            limits:
+              cpu: 512m
+              memory: 512Mi
             requests:
-              memory: 50Mi
-              cpu: 10m
+              cpu: 125m
+              memory: 128Mi
         - name: csi-liveness-probe
           image: quay.io/openshift/origin-csi-livenessprobe:latest
           args:
@@ -115,9 +128,12 @@ spec:
             - name: socket-dir
               mountPath: /csi
           resources:
+            limits:
+              cpu: 512m
+              memory: 512Mi
             requests:
-              memory: 50Mi
-              cpu: 10m
+              cpu: 125m
+              memory: 128Mi
       volumes:
         - name: socket-dir
           emptyDir: {}

packages/apps/kubernetes/templates/dashboard-resourcemap.yaml

@@ -24,3 +24,13 @@ rules:
   resourceNames:
   - {{ .Release.Name }}
   verbs: ["get", "list", "watch"]
+- apiGroups:
+  - cozystack.io
+  resources:
+  - workloadmonitors
+  resourceNames:
+  - {{ .Release.Name }}
+  {{- range $groupName, $group := .Values.nodeGroups }}
+  - {{ $.Release.Name }}-{{ $groupName }}
+  {{- end }}
+  verbs: ["get", "list", "watch"]

packages/apps/kubernetes/templates/helmreleases/cert-manager-crds.yaml

@@ -18,7 +18,8 @@ spec:
         namespace: cozy-system
   kubeConfig:
     secretRef:
-      name: {{ .Release.Name }}-kubeconfig
+      name: {{ .Release.Name }}-admin-kubeconfig
+      key: super-admin.svc
   targetNamespace: cozy-cert-manager-crds
   storageNamespace: cozy-cert-manager-crds
   install:

packages/apps/kubernetes/templates/helmreleases/cert-manager.yaml

@@ -19,7 +19,8 @@ spec:
         namespace: cozy-system
   kubeConfig:
     secretRef:
-      name: {{ .Release.Name }}-kubeconfig
+      name: {{ .Release.Name }}-admin-kubeconfig
+      key: super-admin.svc
   targetNamespace: cozy-cert-manager
   storageNamespace: cozy-cert-manager
   install:

packages/apps/kubernetes/templates/helmreleases/cilium.yaml

@@ -18,7 +18,8 @@ spec:
         namespace: cozy-system
   kubeConfig:
     secretRef:
-      name: {{ .Release.Name }}-kubeconfig
+      name: {{ .Release.Name }}-admin-kubeconfig
+      key: super-admin.svc
   targetNamespace: cozy-cilium
   storageNamespace: cozy-cilium
   install:

packages/apps/kubernetes/templates/helmreleases/csi.yaml

@@ -18,7 +18,8 @@ spec:
         namespace: cozy-system
   kubeConfig:
     secretRef:
-      name: {{ .Release.Name }}-kubeconfig
+      name: {{ .Release.Name }}-admin-kubeconfig
+      key: super-admin.svc
   targetNamespace: cozy-csi
   storageNamespace: cozy-csi
   install: