Release v0.31.0 (#1003)

This PR prepares the release `v0.31.0`.

.github/CODEOWNERS

@@ -1 +1 @@
-* @kvaps
+* @kvaps @lllamnyp @klinch0

.github/workflows/backport.yaml

@@ -0,0 +1,53 @@
+name: Automatic Backport
+
+on:
+  pull_request_target:
+    types: [closed]   # fires when PR is closed (merged)
+
+concurrency:
+  group: backport-${{ github.workflow }}-${{ github.event.pull_request.number }}
+  cancel-in-progress: true
+
+permissions:
+  contents: write
+  pull-requests: write
+
+jobs:
+  backport:
+    if: |
+      github.event.pull_request.merged == true &&
+      contains(github.event.pull_request.labels.*.name, 'backport')
+    runs-on: [self-hosted]
+
+    steps:
+      # 1. Decide which maintenance branch should receive the back‑port
+      - name: Determine target maintenance branch
+        id: target
+        uses: actions/github-script@v7
+        with:
+          script: |
+            let rel;
+            try {
+              rel = await github.rest.repos.getLatestRelease({
+                owner: context.repo.owner,
+                repo: context.repo.repo
+              });
+            } catch (e) {
+              core.setFailed('No existing releases found; cannot determine backport target.');
+              return;
+            }
+            const [maj, min] = rel.data.tag_name.replace(/^v/, '').split('.');
+            const branch = `release-${maj}.${min}`;
+            core.setOutput('branch', branch);
+            console.log(`Latest release ${rel.data.tag_name}; backporting to ${branch}`);
+      # 2. Checkout (required by backport‑action)
+      - name: Checkout repository
+        uses: actions/checkout@v4
+
+      # 3. Create the back‑port pull request
+      - name: Create back‑port PR
+        uses: korthout/backport-action@v3
+        with:
+          github_token: ${{ secrets.GITHUB_TOKEN }}
+          label_pattern: '' # don't read labels for targets
+          target_branches: ${{ steps.target.outputs.branch }}

.github/workflows/pre-commit.yml

@@ -1,6 +1,12 @@
 name: Pre-Commit Checks
 
-on: [push, pull_request]
+on:
+  pull_request:
+    types: [labeled, opened, synchronize, reopened]
+
+concurrency:
+  group: pre-commit-${{ github.workflow }}-${{ github.event.pull_request.number }}
+  cancel-in-progress: true
 
 jobs:
   pre-commit:
@@ -8,6 +14,9 @@ jobs:
     steps:
       - name: Checkout code
         uses: actions/checkout@v3
+        with:
+          fetch-depth: 0
+          fetch-tags: true
 
       - name: Set up Python
         uses: actions/setup-python@v4

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

@@ -0,0 +1,197 @@
+name: Releasing PR
+
+on:
+  pull_request:
+    types: [labeled, opened, synchronize, reopened, closed]
+
+concurrency:
+  group: pull-requests-release-${{ github.workflow }}-${{ github.event.pull_request.number }}
+  cancel-in-progress: true
+
+jobs:
+  verify:
+    name: Test Release
+    runs-on: [self-hosted]
+    permissions:
+      contents: read
+      packages: write
+
+    # Run only when the PR carries the "release" label and not closed.
+    if: |
+      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: ${{ secrets.GITHUB_TOKEN }}
+          registry: ghcr.io
+
+      - name: Run tests
+        run: make test
+
+  finalize:
+    name: Finalize Release
+    runs-on: [self-hosted]
+    permissions:
+      contents: write
+
+    if: |
+      github.event.pull_request.merged == true &&
+      contains(github.event.pull_request.labels.*.name, 'release')
+
+    steps:
+      # Extract tag from branch name  (branch = release-X.Y.Z*)
+      - name: Extract tag from branch name
+        id: get_tag
+        uses: actions/github-script@v7
+        with:
+          script: |
+            const branch = context.payload.pull_request.head.ref;
+            const m = branch.match(/^release-(\d+\.\d+\.\d+(?:[-\w\.]+)?)$/);
+            if (!m) {
+              core.setFailed(`Branch '${branch}' does not match 'release-X.Y.Z[-suffix]'`);
+              return;
+            }
+            const tag = `v${m[1]}`;
+            core.setOutput('tag', tag);
+            console.log(`✅ Tag to publish: ${tag}`);
+
+      # Checkout repo & create / push annotated tag
+      - name: Checkout repo
+        uses: actions/checkout@v4
+        with:
+          fetch-depth: 0
+
+      - name: Create tag on merge commit
+        run: |
+          git tag -f ${{ steps.get_tag.outputs.tag }} ${{ github.sha }}
+          git push -f origin ${{ steps.get_tag.outputs.tag }}
+
+      # Ensure maintenance branch release-X.Y
+      - name: Ensure maintenance branch release-X.Y
+        uses: actions/github-script@v7
+        with:
+          github-token: ${{ secrets.GH_PAT }}
+          script: |
+            const tag = '${{ steps.get_tag.outputs.tag }}';  // e.g. v0.1.3 or v0.1.3-rc3
+            const match = tag.match(/^v(\d+)\.(\d+)\.\d+(?:[-\w\.]+)?$/);
+            if (!match) {
+              core.setFailed(`❌ tag '${tag}' must match 'vX.Y.Z' or 'vX.Y.Z-suffix'`);
+              return;
+            }
+            const line = `${match[1]}.${match[2]}`;
+            const branch = `release-${line}`;
+
+            // Get main branch commit for the tag
+            const ref = await github.rest.git.getRef({
+              owner: context.repo.owner,
+              repo:  context.repo.repo,
+              ref:   `tags/${tag}`
+            });
+
+            const commitSha = ref.data.object.sha;
+
+            try {
+              await github.rest.repos.getBranch({
+                owner: context.repo.owner,
+                repo: context.repo.repo,
+                branch
+              });
+           
+              await github.rest.git.updateRef({
+                owner: context.repo.owner,
+                repo: context.repo.repo,
+                ref: `heads/${branch}`,
+                sha: commitSha,
+                force: true
+              });
+              console.log(`🔁 Force-updated '${branch}' to ${commitSha}`);
+            } catch (err) {
+              if (err.status === 404) {
+                await github.rest.git.createRef({
+                  owner: context.repo.owner,
+                  repo: context.repo.repo,
+                  ref: `refs/heads/${branch}`,
+                  sha: commitSha
+                });
+                console.log(`✅ Created branch '${branch}' at ${commitSha}`);
+              } else {
+                console.error('Unexpected error --', err);
+                core.setFailed(`Unexpected error creating/updating branch: ${err.message}`);
+                throw err;
+              }
+            }
+
+      # Get the latest published release
+      - name: Get the latest published release
+        id: latest_release
+        uses: actions/github-script@v7
+        with:
+          script: |
+            try {
+              const rel = await github.rest.repos.getLatestRelease({
+                owner: context.repo.owner,
+                repo:  context.repo.repo
+              });
+              core.setOutput('tag', rel.data.tag_name);
+            } catch (_) {
+              core.setOutput('tag', '');
+            }
+
+      # Compare current tag vs latest using semver-utils
+      - name: Semver compare
+        id: semver
+        uses: madhead/semver-utils@v4.3.0
+        with:
+          version:    ${{ steps.get_tag.outputs.tag }}
+          compare-to: ${{ steps.latest_release.outputs.tag }}
+
+      # Derive flags: prerelease?  make_latest?
+      - name: Calculate publish flags
+        id: flags
+        uses: actions/github-script@v7
+        with:
+          script: |
+            const tag = '${{ steps.get_tag.outputs.tag }}';              // v0.31.5-rc.1
+            const m = tag.match(/^v(\d+\.\d+\.\d+)(-(?:alpha|beta|rc)\.\d+)?$/);
+            if (!m) {
+              core.setFailed(`❌ tag '${tag}' must match 'vX.Y.Z' or 'vX.Y.Z-(alpha|beta|rc).N'`);
+              return;
+            }
+            const version = m[1] + (m[2] ?? '');                         // 0.31.5-rc.1
+            const isRc    = Boolean(m[2]);
+            core.setOutput('is_rc',      isRc);
+            const outdated = '${{ steps.semver.outputs.comparison-result }}' === '<';
+            core.setOutput('make_latest', isRc || outdated ? 'false' : 'legacy');
+
+      # Publish draft release with correct flags
+      - name: Publish draft release
+        uses: actions/github-script@v7
+        with:
+          script: |
+            const tag = '${{ steps.get_tag.outputs.tag }}';
+            const releases = await github.rest.repos.listReleases({
+              owner: context.repo.owner,
+              repo:  context.repo.repo
+            });
+            const draft = releases.data.find(r => r.tag_name === tag && r.draft);
+            if (!draft) throw new Error(`Draft release for ${tag} not found`);
+            await github.rest.repos.updateRelease({
+              owner:       context.repo.owner,
+              repo:        context.repo.repo,
+              release_id:  draft.id,
+              draft:       false,
+              prerelease:  ${{ steps.flags.outputs.is_rc }},
+              make_latest: '${{ steps.flags.outputs.make_latest }}'
+            });
+
+            console.log(`🚀 Published release for ${tag}`);

.github/workflows/pull-requests.yaml

@@ -0,0 +1,41 @@
+name: Pull Request
+
+on:
+  pull_request:
+    types: [labeled, opened, synchronize, reopened]
+
+concurrency:
+  group: pull-requests-${{ github.workflow }}-${{ github.event.pull_request.number }}
+  cancel-in-progress: true
+
+jobs:
+  e2e:
+    name: Build and Test
+    runs-on: [self-hosted]
+    permissions:
+      contents: read
+      packages: write
+
+    # Never run when the PR carries the "release" label.
+    if: |
+      !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: Build
+        run: make build
+
+      - name: Test
+        run: make test

.github/workflows/tags.yaml

@@ -0,0 +1,228 @@
+name: Versioned Tag
+
+on:
+  push:
+    tags:
+      - 'v*.*.*'          # vX.Y.Z
+      - 'v*.*.*-rc.*'     # vX.Y.Z-rc.N
+      - 'v*.*.*-beta.*'   # vX.Y.Z-beta.N
+      - 'v*.*.*-alpha.*'  # vX.Y.Z-alpha.N
+
+concurrency:
+  group: tags-${{ github.workflow }}-${{ github.ref }}
+  cancel-in-progress: true
+
+jobs:
+  prepare-release:
+    name: Prepare Release
+    runs-on: [self-hosted]
+    permissions:
+      contents: write
+      packages: write
+      pull-requests: write
+      actions: write
+
+    steps:
+      # Check if a non-draft release with this tag already exists
+      - 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 exists = releases.data.some(r => r.tag_name === tag && !r.draft);
+            core.setOutput('skip', exists);
+            console.log(exists ? `Release ${tag} already published` : `No published release ${tag}`);
+
+      # If a published release already exists, skip the rest of the workflow
+      - name: Skip if release already exists
+        if: steps.check_release.outputs.skip == 'true'
+        run: echo "Release already exists, skipping workflow."
+
+      # Parse tag meta-data (rc?, maintenance line, etc.)
+      - name: Parse tag
+        if: steps.check_release.outputs.skip == 'false'
+        id: tag
+        uses: actions/github-script@v7
+        with:
+          script: |
+            const ref = context.ref.replace('refs/tags/', '');           // e.g. v0.31.5-rc.1
+            const m = ref.match(/^v(\d+\.\d+\.\d+)(-(?:alpha|beta|rc)\.\d+)?$/);        // ['0.31.5', '-rc.1' | '-beta.1' | …]
+            if (!m) {
+              core.setFailed(`❌ tag '${ref}' must match 'vX.Y.Z' or 'vX.Y.Z-(alpha|beta|rc).N'`);
+              return;
+            }
+            const version = m[1] + (m[2] ?? '');                         // 0.31.5-rc.1
+            const isRc    = Boolean(m[2]);
+            const [maj, min] = m[1].split('.');
+            core.setOutput('tag',     ref);                              // v0.31.5-rc.1
+            core.setOutput('version', version);                          // 0.31.5-rc.1
+            core.setOutput('is_rc',   isRc);                             // true
+            core.setOutput('line',    `${maj}.${min}`);                  // 0.31
+
+      # Detect base branch (main or release-X.Y) the tag was pushed from
+      - name: Get base branch
+        if: steps.check_release.outputs.skip == 'false'
+        id: get_base
+        uses: actions/github-script@v7
+        with:
+          script: |
+            const baseRef = context.payload.base_ref;
+            if (!baseRef) {
+              core.setFailed(`❌ base_ref is empty. Push the tag via 'git push origin HEAD:refs/tags/<tag>'.`);
+              return;
+            }
+            const branch = baseRef.replace('refs/heads/', '');
+            const ok     = branch === 'main' || /^release-\d+\.\d+$/.test(branch);
+            if (!ok) {
+              core.setFailed(`❌ Tagged commit must belong to 'main' or 'release-X.Y'. Got '${branch}'`);
+              return;
+            }
+            core.setOutput('branch', branch);
+
+      # Checkout & login once
+      - name: Checkout code
+        if: steps.check_release.outputs.skip == 'false'
+        uses: actions/checkout@v4
+        with:
+          fetch-depth: 0
+          fetch-tags:  true
+
+      - name: Login to GHCR
+        if: steps.check_release.outputs.skip == 'false'
+        uses: docker/login-action@v3
+        with:
+          username: ${{ github.repository_owner }}
+          password: ${{ secrets.GITHUB_TOKEN }}
+          registry: ghcr.io
+
+      # Build project artifacts
+      - name: Build
+        if: steps.check_release.outputs.skip == 'false'
+        run: make build
+
+      # Commit built artifacts
+      - name: Commit release artifacts
+        if: steps.check_release.outputs.skip == 'false'
+        run: |
+          git config user.name  "github-actions"
+          git config user.email "github-actions@github.com"
+          git add .
+          git commit -m "Prepare release ${GITHUB_REF#refs/tags/}" -s || echo "No changes to commit"
+          git push origin HEAD || true
+
+      # Get `latest_version` from latest published release 
+      - name: Get latest published release
+        if: steps.check_release.outputs.skip == 'false'
+        id: latest_release
+        uses: actions/github-script@v7
+        with:
+          script: |
+            try {
+              const rel = await github.rest.repos.getLatestRelease({
+                owner: context.repo.owner,
+                repo:  context.repo.repo
+              });
+              core.setOutput('tag', rel.data.tag_name);
+            } catch (_) {
+              core.setOutput('tag', '');
+            }
+
+      # Compare tag (A) with latest (B)
+      - name: Semver compare
+        if: steps.check_release.outputs.skip == 'false'
+        id: semver
+        uses: madhead/semver-utils@v4.3.0
+        with:
+          version:     ${{ steps.tag.outputs.tag }}            # A
+          compare-to:  ${{ steps.latest_release.outputs.tag }} # B
+
+      # Create or reuse DRAFT GitHub Release
+      - name: Create / reuse draft release
+        if: steps.check_release.outputs.skip == 'false'
+        id: release
+        uses: actions/github-script@v7
+        with:
+          script: |
+            const tag        = '${{ steps.tag.outputs.tag }}';
+            const isRc       = ${{ steps.tag.outputs.is_rc }};
+            const outdated   = '${{ steps.semver.outputs.comparison-result }}' === '<';
+            const makeLatest = outdated ? false : 'legacy';
+            const releases   = await github.rest.repos.listReleases({
+              owner: context.repo.owner,
+              repo:  context.repo.repo
+            });
+            let rel          = releases.data.find(r => r.tag_name === tag);
+            if (!rel) {
+              rel = await github.rest.repos.createRelease({
+                owner: context.repo.owner,
+                repo:  context.repo.repo,
+                tag_name:    tag,
+                name:        tag,
+                draft:       true,
+                prerelease:  isRc,
+                make_latest: makeLatest
+              });
+              console.log(`Draft release created for ${tag}`);
+            } else {
+              console.log(`Re-using existing release ${tag}`);
+            }
+            core.setOutput('upload_url', rel.upload_url);
+
+      # Build + upload assets (optional)
+      - name: Build & upload assets
+        if: steps.check_release.outputs.skip == 'false'
+        run: |
+          make assets
+          make upload_assets VERSION=${{ steps.tag.outputs.tag }}
+        env:
+          GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+
+      # Create release-X.Y.Z branch and push (force-update)
+      - name: Create release branch
+        if: steps.check_release.outputs.skip == 'false'
+        run: |
+          BRANCH="release-${GITHUB_REF#refs/tags/v}"
+          git branch -f "$BRANCH"
+          git push -f origin "$BRANCH"
+
+      # Create pull request into original base branch (if absent)
+      - 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 base    = '${{ steps.get_base.outputs.branch }}';
+            const head    = `release-${version}`;
+
+            const prs = await github.rest.pulls.list({
+              owner: context.repo.owner,
+              repo:  context.repo.repo,
+              head:  `${context.repo.owner}:${head}`,
+              base
+            });
+            if (prs.data.length === 0) {
+              const pr = await github.rest.pulls.create({
+                owner: context.repo.owner,
+                repo:  context.repo.repo,
+                head,
+                base,
+                title: `Release v${version}`,
+                body:  `This PR prepares the release \`v${version}\`.`,
+                draft: false
+              });
+              await github.rest.issues.addLabels({
+                owner: context.repo.owner,
+                repo:  context.repo.repo,
+                issue_number: pr.data.number,
+                labels: ['release']
+              });
+              console.log(`Created PR #${pr.data.number}`);
+            } else {
+              console.log(`PR already exists from ${head} to ${base}`);
+            }

.gitignore

@@ -1,6 +1,7 @@
 _out
 .git
 .idea
+.vscode
 
 # User-specific stuff
 .idea/**/workspace.xml
@@ -75,4 +76,4 @@ fabric.properties
 .idea/caches/build_file_checksums.ser
 
 .DS_Store
-**/.DS_Store
+**/.DS_Store

.pre-commit-config.yaml

@@ -18,6 +18,7 @@ repos:
               (cd "$dir" && make generate)
             fi
           done
+          git diff --color=always | cat
         '
       language: script
       files: ^.*$

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.

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

@@ -1,25 +1,32 @@
 .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/metallb image
 	make -C packages/system/kamaji image
 	make -C packages/system/bucket image
 	make -C packages/core/testing image
 	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 +37,20 @@ 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
+
+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 +1,230 @@
+/*
+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"
+
+	helmv2 "github.com/fluxcd/helm-controller/api/v2"
+	// +kubebuilder:scaffold:imports
+)
+
+var (
+	scheme   = runtime.NewScheme()
+	setupLog = ctrl.Log.WithName("setup")
+)
+
+func init() {
+	utilruntime.Must(clientgoscheme.AddToScheme(scheme))
+
+	utilruntime.Must(cozystackiov1alpha1.AddToScheme(scheme))
+	utilruntime.Must(helmv2.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", "WorkloadReconciler")
+		os.Exit(1)
+	}
+
+	if err = (&controller.TenantHelmReconciler{
+		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)
+	}
+}

dashboards/main/capacity-planning.json

@@ -450,7 +450,7 @@
             "uid": "$ds_prometheus"
           },
           "editorMode": "code",
-          "expr": "sum(sum by (node) (rate(container_cpu_usage_seconds_total{container!=\"POD\",container!=\"\",node=~\"$node\"}[$__rate_interval])))\n / sum(sum by (node) (avg_over_time(kube_node_status_allocatable{resource=\"cpu\",unit=\"core\",node=~\"$node\"}[$__rate_interval])))",
+          "expr": "sum(sum by (node) (rate(container_cpu_usage_seconds_total{container!=\"\",node=~\"$node\"}[$__rate_interval])))\n / sum(sum by (node) (avg_over_time(kube_node_status_allocatable{resource=\"cpu\",unit=\"core\",node=~\"$node\"}[$__rate_interval])))",
           "hide": false,
           "legendFormat": "Total",
           "range": true,
@@ -520,7 +520,7 @@
             "uid": "$ds_prometheus"
           },
           "editorMode": "code",
-          "expr": "sum(sum by (node) (container_memory_working_set_bytes:without_kmem{container!=\"POD\",container!=\"\",node=~\"$node\"})) / sum(sum by (node) (avg_over_time(kube_node_status_allocatable{resource=\"memory\",unit=\"byte\",node=~\"$node\"}[$__rate_interval])))",
+          "expr": "sum(sum by (node) (container_memory_working_set_bytes:without_kmem{container!=\"\",node=~\"$node\"})) / sum(sum by (node) (avg_over_time(kube_node_status_allocatable{resource=\"memory\",unit=\"byte\",node=~\"$node\"}[$__rate_interval])))",
           "hide": false,
           "legendFormat": "Total",
           "range": true,
@@ -590,7 +590,7 @@
             "uid": "$ds_prometheus"
           },
           "editorMode": "code",
-          "expr": "sum(sum by (node) (rate(container_cpu_usage_seconds_total{container!=\"POD\",container!=\"\",node=~\"$node\"}[$__rate_interval]))) / sum(sum by (node) (avg_over_time(kube_pod_container_resource_requests{resource=\"cpu\",unit=\"core\",node=~\"$node\"}[$__rate_interval])))",
+          "expr": "sum(sum by (node) (rate(container_cpu_usage_seconds_total{container!=\"\",node=~\"$node\"}[$__rate_interval]))) / sum(sum by (node) (avg_over_time(kube_pod_container_resource_requests{resource=\"cpu\",unit=\"core\",node=~\"$node\"}[$__rate_interval])))",
           "hide": false,
           "legendFormat": "Total",
           "range": true,
@@ -660,7 +660,7 @@
             "uid": "$ds_prometheus"
           },
           "editorMode": "code",
-          "expr": "sum(sum by (node) (container_memory_working_set_bytes:without_kmem{container!=\"POD\",container!=\"\",node=~\"$node\"} )) / sum(sum by (node) (avg_over_time(kube_pod_container_resource_requests{resource=\"memory\",node=~\"$node\"}[$__rate_interval])))",
+          "expr": "sum(sum by (node) (container_memory_working_set_bytes:without_kmem{container!=\"\",node=~\"$node\"} )) / sum(sum by (node) (avg_over_time(kube_pod_container_resource_requests{resource=\"memory\",node=~\"$node\"}[$__rate_interval])))",
           "hide": false,
           "legendFormat": "__auto",
           "range": true,
@@ -1128,7 +1128,7 @@
             "uid": "$ds_prometheus"
           },
           "editorMode": "code",
-          "expr": "sum by (node) (rate(container_cpu_usage_seconds_total{container!=\"POD\",container!=\"\",node=~\"$node\"}[$__rate_interval]) - on (namespace,pod,container,node) group_left avg by (namespace,pod,container, node)(kube_pod_container_resource_requests{resource=\"cpu\",node=~\"$node\"})) * -1 > 0\n",
+          "expr": "sum by (node) (rate(container_cpu_usage_seconds_total{container!=\"\",node=~\"$node\"}[$__rate_interval]) - on (namespace,pod,container,node) group_left avg by (namespace,pod,container, node)(kube_pod_container_resource_requests{resource=\"cpu\",node=~\"$node\"})) * -1 > 0\n",
           "format": "time_series",
           "hide": false,
           "intervalFactor": 1,
@@ -1143,7 +1143,7 @@
             "uid": "$ds_prometheus"
           },
           "editorMode": "code",
-          "expr": "sum(sum by (node) (rate(container_cpu_usage_seconds_total{container!=\"POD\",container!=\"\",node=~\"$node\"}[$__rate_interval]) - on (namespace,pod,container,node) group_left avg by (namespace,pod,container, node)(kube_pod_container_resource_requests{resource=\"cpu\",node=~\"$node\"})) * -1 > 0)",
+          "expr": "sum(sum by (node) (rate(container_cpu_usage_seconds_total{container!=\"\",node=~\"$node\"}[$__rate_interval]) - on (namespace,pod,container,node) group_left avg by (namespace,pod,container, node)(kube_pod_container_resource_requests{resource=\"cpu\",node=~\"$node\"})) * -1 > 0)",
           "hide": false,
           "legendFormat": "Total",
           "range": true,
@@ -1527,7 +1527,7 @@
             "uid": "$ds_prometheus"
           },
           "editorMode": "code",
-          "expr": "(sum by (node) (container_memory_working_set_bytes:without_kmem{container!=\"POD\",container!=\"\",node=~\"$node\"} ) - sum by (node) (kube_pod_container_resource_requests{resource=\"memory\",node=~\"$node\"})) * -1 > 0\n",
+          "expr": "(sum by (node) (container_memory_working_set_bytes:without_kmem{container!=\"\",node=~\"$node\"} ) - sum by (node) (kube_pod_container_resource_requests{resource=\"memory\",node=~\"$node\"})) * -1 > 0\n",
           "format": "time_series",
           "hide": false,
           "intervalFactor": 1,
@@ -1542,7 +1542,7 @@
             "uid": "$ds_prometheus"
           },
           "editorMode": "code",
-          "expr": "sum((sum by (node) (container_memory_working_set_bytes:without_kmem{container!=\"POD\",container!=\"\",node=~\"$node\"} ) - sum by (node) (kube_pod_container_resource_requests{resource=\"memory\",node=~\"$node\"})) * -1 > 0)",
+          "expr": "sum((sum by (node) (container_memory_working_set_bytes:without_kmem{container!=\"\",node=~\"$node\"} ) - sum by (node) (kube_pod_container_resource_requests{resource=\"memory\",node=~\"$node\"})) * -1 > 0)",
           "hide": false,
           "legendFormat": "Total",
           "range": true,
@@ -1909,7 +1909,7 @@
           },
           "editorMode": "code",
           "exemplar": false,
-          "expr": "topk(10, (sum by (namespace,pod,container)((rate(container_cpu_usage_seconds_total{namespace=~\"$namespace\",container!=\"POD\",container!=\"\",node=~\"$node\"}[$__rate_interval])) - on (namespace,pod,container) group_left avg by (namespace,pod,container)(kube_pod_container_resource_requests{resource=\"cpu\",node=~\"$node\"}))) * -1 > 0)\n",
+          "expr": "topk(10, (sum by (namespace,pod,container)((rate(container_cpu_usage_seconds_total{namespace=~\"$namespace\",container!=\"\",node=~\"$node\"}[$__rate_interval])) - on (namespace,pod,container) group_left avg by (namespace,pod,container)(kube_pod_container_resource_requests{resource=\"cpu\",node=~\"$node\"}))) * -1 > 0)\n",
           "format": "table",
           "instant": true,
           "range": false,
@@ -2037,7 +2037,7 @@
           },
           "editorMode": "code",
           "exemplar": false,
-          "expr": "topk(10, (sum by (namespace,container,pod) (container_memory_working_set_bytes:without_kmem{container!=\"POD\",container!=\"\",namespace=~\"$namespace\",node=~\"$node\"}) - on (namespace,pod,container) avg by (namespace,pod,container)(kube_pod_container_resource_requests{resource=\"memory\",namespace=~\"$namespace\",node=~\"$node\"})) * -1 >0)\n",
+          "expr": "topk(10, (sum by (namespace,container,pod) (container_memory_working_set_bytes:without_kmem{container!=\"\",namespace=~\"$namespace\",node=~\"$node\"}) - on (namespace,pod,container) avg by (namespace,pod,container)(kube_pod_container_resource_requests{resource=\"memory\",namespace=~\"$namespace\",node=~\"$node\"})) * -1 >0)\n",
           "format": "table",
           "instant": true,
           "range": false,
@@ -2160,7 +2160,7 @@
           },
           "editorMode": "code",
           "exemplar": false,
-          "expr": "topk(10, (sum by (namespace,pod,container)((rate(container_cpu_usage_seconds_total{namespace=~\"$namespace\",container!=\"POD\",container!=\"\",node=~\"$node\"}[$__rate_interval])) - on (namespace,pod,container) group_left avg by (namespace,pod,container)(kube_pod_container_resource_requests{resource=\"cpu\",node=~\"$node\"}))) > 0)\n",
+          "expr": "topk(10, (sum by (namespace,pod,container)((rate(container_cpu_usage_seconds_total{namespace=~\"$namespace\",container!=\"\",node=~\"$node\"}[$__rate_interval])) - on (namespace,pod,container) group_left avg by (namespace,pod,container)(kube_pod_container_resource_requests{resource=\"cpu\",node=~\"$node\"}))) > 0)\n",
           "format": "table",
           "instant": true,
           "range": false,
@@ -2288,7 +2288,7 @@
           },
           "editorMode": "code",
           "exemplar": false,
-          "expr": "topk(10, (sum by (namespace,container,pod) (container_memory_working_set_bytes:without_kmem{container!=\"POD\",container!=\"\",namespace=~\"$namespace\",node=~\"$node\"}) - on (namespace,pod,container) avg by (namespace,pod,container)(kube_pod_container_resource_requests{resource=\"memory\",namespace=~\"$namespace\",node=~\"$node\"})) >0)\n",
+          "expr": "topk(10, (sum by (namespace,container,pod) (container_memory_working_set_bytes:without_kmem{container!=\"\",namespace=~\"$namespace\",node=~\"$node\"}) - on (namespace,pod,container) avg by (namespace,pod,container)(kube_pod_container_resource_requests{resource=\"memory\",namespace=~\"$namespace\",node=~\"$node\"})) >0)\n",
           "format": "table",
           "instant": true,
           "range": false,

dashboards/main/controller.json

@@ -684,7 +684,7 @@
             "type": "prometheus",
             "uid": "${ds_prometheus}"
           },
-          "expr": "(\n  sum by (pod) (avg_over_time(kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller=\"$controller\", pod=~\"$pod\"}[$__range])) \n  * on (pod)\n  sum by (pod) (rate(container_cpu_usage_seconds_total{node=~\"$node\", container!=\"POD\", namespace=\"$namespace\", pod=~\"$pod\"}[$__range]))\n)\nor\nsum by (pod) (avg_over_time(kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller=\"$controller\", pod=~\"$pod\"}[$__range])  * 0)",
+          "expr": "(\n  sum by (pod) (avg_over_time(kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller=\"$controller\", pod=~\"$pod\"}[$__range])) \n  * on (pod)\n  sum by (pod) (rate(container_cpu_usage_seconds_total{node=~\"$node\", container!=\"\", namespace=\"$namespace\", pod=~\"$pod\"}[$__range]))\n)\nor\nsum by (pod) (avg_over_time(kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller=\"$controller\", pod=~\"$pod\"}[$__range])  * 0)",
           "format": "table",
           "hide": false,
           "instant": true,
@@ -710,7 +710,7 @@
             "type": "prometheus",
             "uid": "${ds_prometheus}"
           },
-          "expr": "sum by (pod)\n(\n  avg_over_time(kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller=\"$controller\", pod=~\"$pod\"}[$__range])\n  * on (controller_type, controller_name) group_left()\n  sum by (controller_type, controller_name) (avg_over_time(vpa_target_recommendation{container!=\"POD\", namespace=\"$namespace\", resource=\"cpu\"}[$__range]))\n)\nor\nsum by (pod) (avg_over_time(kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller=\"$controller\", pod=~\"$pod\"}[$__range]) * 0)",
+          "expr": "sum by (pod)\n(\n  avg_over_time(kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller=\"$controller\", pod=~\"$pod\"}[$__range])\n  * on (controller_type, controller_name) group_left()\n  sum by (controller_type, controller_name) (avg_over_time(vpa_target_recommendation{container!=\"\", namespace=\"$namespace\", resource=\"cpu\"}[$__range]))\n)\nor\nsum by (pod) (avg_over_time(kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller=\"$controller\", pod=~\"$pod\"}[$__range]) * 0)",
           "format": "table",
           "hide": false,
           "instant": true,
@@ -723,7 +723,7 @@
             "type": "prometheus",
             "uid": "${ds_prometheus}"
           },
-          "expr": "(\n  sum by (pod) (avg_over_time(kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller=\"$controller\", pod=~\"$pod\"}[$__range])) \n  * on (pod)\n  sum by (pod)\n  (\n    sum by (namespace, pod) (avg_over_time(kube_pod_container_resource_requests{resource=\"cpu\",unit=\"core\",node=~\"$node\", namespace=\"$namespace\", pod=~\"$pod\"}[$__range]))\n    -\n    sum by (namespace, pod) (rate(container_cpu_usage_seconds_total{node=~\"$node\", namespace=\"$namespace\", pod=~\"$pod\", container!=\"POD\"}[$__range]))\n  ) > 0\n)\nor\nsum by (pod) (avg_over_time(kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller=\"$controller\", pod=~\"$pod\"}[$__range]) * 0)",
+          "expr": "(\n  sum by (pod) (avg_over_time(kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller=\"$controller\", pod=~\"$pod\"}[$__range])) \n  * on (pod)\n  sum by (pod)\n  (\n    sum by (namespace, pod) (avg_over_time(kube_pod_container_resource_requests{resource=\"cpu\",unit=\"core\",node=~\"$node\", namespace=\"$namespace\", pod=~\"$pod\"}[$__range]))\n    -\n    sum by (namespace, pod) (rate(container_cpu_usage_seconds_total{node=~\"$node\", namespace=\"$namespace\", pod=~\"$pod\", container!=\"\"}[$__range]))\n  ) > 0\n)\nor\nsum by (pod) (avg_over_time(kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller=\"$controller\", pod=~\"$pod\"}[$__range]) * 0)",
           "format": "table",
           "hide": false,
           "instant": true,
@@ -736,7 +736,7 @@
             "type": "prometheus",
             "uid": "${ds_prometheus}"
           },
-          "expr": "(\n  sum by (pod) (avg_over_time(kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller=\"$controller\", pod=~\"$pod\"}[$__range])) \n  * on (pod)\n  sum by (pod) \n  (\n    (\n      (\n        sum by (namespace, pod) (rate(container_cpu_usage_seconds_total{node=~\"$node\", namespace=\"$namespace\", pod=~\"$pod\"}[$__range]))\n        -\n        sum by (namespace, pod) (avg_over_time(kube_pod_container_resource_requests{resource=\"cpu\",unit=\"core\",node=~\"$node\", namespace=\"$namespace\", pod=~\"$pod\", container!=\"POD\"}[$__range]))\n      ) or sum by (namespace, pod) (rate(container_cpu_usage_seconds_total{node=~\"$node\", namespace=\"$namespace\", pod=~\"$pod\", container!=\"POD\"}[$__range]))\n    ) > 0\n  )\n)\nor\nsum by (pod) (avg_over_time(kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller=\"$controller\", pod=~\"$pod\"}[$__range]) * 0)",
+          "expr": "(\n  sum by (pod) (avg_over_time(kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller=\"$controller\", pod=~\"$pod\"}[$__range])) \n  * on (pod)\n  sum by (pod) \n  (\n    (\n      (\n        sum by (namespace, pod) (rate(container_cpu_usage_seconds_total{node=~\"$node\", namespace=\"$namespace\", pod=~\"$pod\"}[$__range]))\n        -\n        sum by (namespace, pod) (avg_over_time(kube_pod_container_resource_requests{resource=\"cpu\",unit=\"core\",node=~\"$node\", namespace=\"$namespace\", pod=~\"$pod\", container!=\"\"}[$__range]))\n      ) or sum by (namespace, pod) (rate(container_cpu_usage_seconds_total{node=~\"$node\", namespace=\"$namespace\", pod=~\"$pod\", container!=\"\"}[$__range]))\n    ) > 0\n  )\n)\nor\nsum by (pod) (avg_over_time(kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller=\"$controller\", pod=~\"$pod\"}[$__range]) * 0)",
           "format": "table",
           "hide": false,
           "instant": true,
@@ -762,7 +762,7 @@
             "type": "prometheus",
             "uid": "${ds_prometheus}"
           },
-          "expr": "(\n  sum by (pod) (avg_over_time(kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller=\"$controller\", pod=~\"$pod\"}[$__range])) \n  * on (pod)\n  sum by (pod) (avg_over_time(container_memory_working_set_bytes:without_kmem{node=~\"$node\", container!=\"POD\", namespace=\"$namespace\", pod=~\"$pod\"}[$__range]))\n)\nor\nsum by (pod) (avg_over_time(kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller=\"$controller\", pod=~\"$pod\"}[$__range]) * 0)",
+          "expr": "(\n  sum by (pod) (avg_over_time(kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller=\"$controller\", pod=~\"$pod\"}[$__range])) \n  * on (pod)\n  sum by (pod) (avg_over_time(container_memory_working_set_bytes:without_kmem{node=~\"$node\", container!=\"\", namespace=\"$namespace\", pod=~\"$pod\"}[$__range]))\n)\nor\nsum by (pod) (avg_over_time(kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller=\"$controller\", pod=~\"$pod\"}[$__range]) * 0)",
           "format": "table",
           "instant": true,
           "intervalFactor": 1,
@@ -786,7 +786,7 @@
             "type": "prometheus",
             "uid": "${ds_prometheus}"
           },
-          "expr": "sum by (pod)\n(\n  avg_over_time(kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller=\"$controller\", pod=~\"$pod\"}[$__range])\n  * on (controller_type, controller_name) group_left()\n  sum by (controller_type, controller_name) (avg_over_time(vpa_target_recommendation{container!=\"POD\", namespace=\"$namespace\", resource=\"memory\"}[$__range]))\n)\nor\nsum by (pod) (avg_over_time(kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller=\"$controller\", pod=~\"$pod\"}[$__range]) * 0)",
+          "expr": "sum by (pod)\n(\n  avg_over_time(kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller=\"$controller\", pod=~\"$pod\"}[$__range])\n  * on (controller_type, controller_name) group_left()\n  sum by (controller_type, controller_name) (avg_over_time(vpa_target_recommendation{container!=\"\", namespace=\"$namespace\", resource=\"memory\"}[$__range]))\n)\nor\nsum by (pod) (avg_over_time(kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller=\"$controller\", pod=~\"$pod\"}[$__range]) * 0)",
           "format": "table",
           "instant": true,
           "intervalFactor": 1,
@@ -798,7 +798,7 @@
             "type": "prometheus",
             "uid": "${ds_prometheus}"
           },
-          "expr": "(\n  sum by (pod) (avg_over_time(kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller=\"$controller\", pod=~\"$pod\"}[$__range])) \n  * on (pod)\n  sum by (pod)\n  (\n    (\n      (\n        sum by (namespace, pod) (avg_over_time(kube_pod_container_resource_requests{resource=\"memory\",unit=\"byte\",node=~\"$node\", namespace=\"$namespace\", pod=~\"$pod\"}[$__range]))\n        -\n        sum by (namespace, pod) (avg_over_time(container_memory_working_set_bytes:without_kmem{node=~\"$node\", namespace=\"$namespace\", pod=~\"$pod\", container!=\"POD\"}[$__range]))\n      ) > 0\n    )\n  )\n)\nor\nsum by (pod) (avg_over_time(kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller=\"$controller\", pod=~\"$pod\"}[$__range]) * 0)",
+          "expr": "(\n  sum by (pod) (avg_over_time(kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller=\"$controller\", pod=~\"$pod\"}[$__range])) \n  * on (pod)\n  sum by (pod)\n  (\n    (\n      (\n        sum by (namespace, pod) (avg_over_time(kube_pod_container_resource_requests{resource=\"memory\",unit=\"byte\",node=~\"$node\", namespace=\"$namespace\", pod=~\"$pod\"}[$__range]))\n        -\n        sum by (namespace, pod) (avg_over_time(container_memory_working_set_bytes:without_kmem{node=~\"$node\", namespace=\"$namespace\", pod=~\"$pod\", container!=\"\"}[$__range]))\n      ) > 0\n    )\n  )\n)\nor\nsum by (pod) (avg_over_time(kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller=\"$controller\", pod=~\"$pod\"}[$__range]) * 0)",
           "format": "table",
           "instant": true,
           "intervalFactor": 1,
@@ -810,7 +810,7 @@
             "type": "prometheus",
             "uid": "${ds_prometheus}"
           },
-          "expr": "(\n  sum by (pod) (avg_over_time(kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller=\"$controller\", pod=~\"$pod\"}[$__range])) \n  * on (pod)\n  sum by (pod)\n  (\n    (\n      (\n        sum by (namespace, pod) (avg_over_time(container_memory_working_set_bytes:without_kmem{node=~\"$node\", namespace=\"$namespace\", pod=~\"$pod\"}[$__range]))\n        -\n        sum by (namespace, pod) (avg_over_time(kube_pod_container_resource_requests{resource=\"memory\",unit=\"byte\",node=~\"$node\", namespace=\"$namespace\", pod=~\"$pod\", container!=\"POD\"}[$__range]))\n      ) or sum by (namespace, pod) (avg_over_time(container_memory_working_set_bytes:without_kmem{node=~\"$node\", namespace=\"$namespace\", pod=~\"$pod\", container!=\"POD\"}[$__range]))\n    ) > 0\n  )\n)\nor\nsum by (pod) (avg_over_time(kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller=\"$controller\", pod=~\"$pod\"}[$__range]) * 0)",
+          "expr": "(\n  sum by (pod) (avg_over_time(kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller=\"$controller\", pod=~\"$pod\"}[$__range])) \n  * on (pod)\n  sum by (pod)\n  (\n    (\n      (\n        sum by (namespace, pod) (avg_over_time(container_memory_working_set_bytes:without_kmem{node=~\"$node\", namespace=\"$namespace\", pod=~\"$pod\"}[$__range]))\n        -\n        sum by (namespace, pod) (avg_over_time(kube_pod_container_resource_requests{resource=\"memory\",unit=\"byte\",node=~\"$node\", namespace=\"$namespace\", pod=~\"$pod\", container!=\"\"}[$__range]))\n      ) or sum by (namespace, pod) (avg_over_time(container_memory_working_set_bytes:without_kmem{node=~\"$node\", namespace=\"$namespace\", pod=~\"$pod\", container!=\"\"}[$__range]))\n    ) > 0\n  )\n)\nor\nsum by (pod) (avg_over_time(kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller=\"$controller\", pod=~\"$pod\"}[$__range]) * 0)",
           "format": "table",
           "instant": true,
           "intervalFactor": 1,
@@ -848,7 +848,7 @@
             "type": "prometheus",
             "uid": "${ds_prometheus}"
           },
-          "expr": "(\n  sum by (pod) (avg_over_time(kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller=\"$controller\", pod=~\"$pod\"}[$__range])) \n  * on (pod)\n  sum by (pod) (rate(container_fs_reads_total{node=~\"$node\", container!=\"POD\", namespace=\"$namespace\", pod=~\"$pod\"}[$__range]))\n)\nor\nsum by (pod) (avg_over_time(kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller=\"$controller\", pod=~\"$pod\"}[$__range]) * 0)",
+          "expr": "(\n  sum by (pod) (avg_over_time(kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller=\"$controller\", pod=~\"$pod\"}[$__range])) \n  * on (pod)\n  sum by (pod) (rate(container_fs_reads_total{node=~\"$node\", container!=\"\", namespace=\"$namespace\", pod=~\"$pod\"}[$__range]))\n)\nor\nsum by (pod) (avg_over_time(kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller=\"$controller\", pod=~\"$pod\"}[$__range]) * 0)",
           "format": "table",
           "instant": true,
           "intervalFactor": 1,
@@ -860,7 +860,7 @@
             "type": "prometheus",
             "uid": "${ds_prometheus}"
           },
-          "expr": "(\n  sum by (pod) (avg_over_time(kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller=\"$controller\", pod=~\"$pod\"}[$__range])) \n  * on (pod)\n  sum by (pod) (rate(container_fs_writes_total{node=~\"$node\", container!=\"POD\", namespace=\"$namespace\", pod=~\"$pod\"}[$__range]))\n)\nor\nsum by (pod) (avg_over_time(kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller=\"$controller\", pod=~\"$pod\"}[$__range]) * 0)",
+          "expr": "(\n  sum by (pod) (avg_over_time(kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller=\"$controller\", pod=~\"$pod\"}[$__range])) \n  * on (pod)\n  sum by (pod) (rate(container_fs_writes_total{node=~\"$node\", container!=\"\", namespace=\"$namespace\", pod=~\"$pod\"}[$__range]))\n)\nor\nsum by (pod) (avg_over_time(kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller=\"$controller\", pod=~\"$pod\"}[$__range]) * 0)",
           "format": "table",
           "instant": true,
           "intervalFactor": 1,
@@ -1315,7 +1315,7 @@
             "uid": "$ds_prometheus"
           },
           "editorMode": "code",
-          "expr": "sum by(pod) (\n  max(kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller=\"$controller\", pod=~\"$pod\"}) by(pod)\n  * on (pod)\n  sum by (pod) (rate(container_cpu_usage_seconds_total{node=~\"$node\", container!=\"POD\", pod=~\"$pod\", namespace=\"$namespace\"}[$__rate_interval]))\n)",
+          "expr": "sum by(pod) (\n  max(kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller=\"$controller\", pod=~\"$pod\"}) by(pod)\n  * on (pod)\n  sum by (pod) (rate(container_cpu_usage_seconds_total{node=~\"$node\", container!=\"\", pod=~\"$pod\", namespace=\"$namespace\"}[$__rate_interval]))\n)",
           "format": "time_series",
           "instant": false,
           "intervalFactor": 1,
@@ -1488,7 +1488,7 @@
             "uid": "$ds_prometheus"
           },
           "editorMode": "code",
-          "expr": "sum (\n  max(kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller=\"$controller\", pod=~\"$pod\"}) by(pod)\n  * on (pod)\n  sum by (pod) (rate(container_cpu_system_seconds_total{node=~\"$node\", container!=\"POD\", pod=~\"$pod\", namespace=\"$namespace\"}[$__rate_interval]))\n)",
+          "expr": "sum (\n  max(kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller=\"$controller\", pod=~\"$pod\"}) by(pod)\n  * on (pod)\n  sum by (pod) (rate(container_cpu_system_seconds_total{node=~\"$node\", container!=\"\", pod=~\"$pod\", namespace=\"$namespace\"}[$__rate_interval]))\n)",
           "format": "time_series",
           "interval": "",
           "intervalFactor": 1,
@@ -1502,7 +1502,7 @@
             "uid": "$ds_prometheus"
           },
           "editorMode": "code",
-          "expr": "sum (\n  max(kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller=\"$controller\", pod=~\"$pod\"}) by(pod)\n  * on (pod)\n  sum by (pod) (rate(container_cpu_user_seconds_total{node=~\"$node\", container!=\"POD\", pod=~\"$pod\", namespace=\"$namespace\"}[$__rate_interval]))\n)",
+          "expr": "sum (\n  max(kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller=\"$controller\", pod=~\"$pod\"}) by(pod)\n  * on (pod)\n  sum by (pod) (rate(container_cpu_user_seconds_total{node=~\"$node\", container!=\"\", pod=~\"$pod\", namespace=\"$namespace\"}[$__rate_interval]))\n)",
           "format": "time_series",
           "interval": "",
           "intervalFactor": 1,
@@ -1642,7 +1642,7 @@
             "uid": "$ds_prometheus"
           },
           "editorMode": "code",
-          "expr": "sum by (pod)\n  (\n    max(kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller=\"$controller\", pod=~\"$pod\"}) by(pod)\n    * on (pod)\n    sum by (pod) (\n      sum by(namespace, pod, container) (avg_over_time(kube_pod_container_resource_requests{resource=\"cpu\",unit=\"core\",node=~\"$node\", namespace=\"$namespace\", pod=~\"$pod\"}[$__rate_interval]))\n      -\n      sum by(namespace, pod, container) (rate(container_cpu_usage_seconds_total{node=~\"$node\", container!=\"POD\", namespace=\"$namespace\", pod=~\"$pod\"}[$__rate_interval]))\n    ) > 0\n  )",
+          "expr": "sum by (pod)\n  (\n    max(kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller=\"$controller\", pod=~\"$pod\"}) by(pod)\n    * on (pod)\n    sum by (pod) (\n      sum by(namespace, pod, container) (avg_over_time(kube_pod_container_resource_requests{resource=\"cpu\",unit=\"core\",node=~\"$node\", namespace=\"$namespace\", pod=~\"$pod\"}[$__rate_interval]))\n      -\n      sum by(namespace, pod, container) (rate(container_cpu_usage_seconds_total{node=~\"$node\", container!=\"\", namespace=\"$namespace\", pod=~\"$pod\"}[$__rate_interval]))\n    ) > 0\n  )",
           "format": "time_series",
           "intervalFactor": 1,
           "legendFormat": "{{ pod }}",
@@ -1779,7 +1779,7 @@
             "uid": "$ds_prometheus"
           },
           "editorMode": "code",
-          "expr": "    (\n  max(kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller=\"$controller\", pod=~\"$pod\"}) by(pod)\n  * on (pod)\n  sum by (pod) (\n    (\n      sum by(namespace, pod, container) (rate(container_cpu_usage_seconds_total{node=~\"$node\", namespace=\"$namespace\", pod=~\"$pod\"}[$__rate_interval]))\n      -\n      sum by(namespace, pod, container) (avg_over_time(kube_pod_container_resource_requests{resource=\"cpu\",unit=\"core\",node=~\"$node\", namespace=\"$namespace\", pod=~\"$pod\", container!=\"POD\"}[$__rate_interval]))\n    )\n    or\n    sum by(namespace, pod, container) (rate(container_cpu_usage_seconds_total{node=~\"$node\", namespace=\"$namespace\", pod=~\"$pod\"}[$__rate_interval]))\n  )\n) > 0",
+          "expr": "    (\n  max(kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller=\"$controller\", pod=~\"$pod\"}) by(pod)\n  * on (pod)\n  sum by (pod) (\n    (\n      sum by(namespace, pod, container) (rate(container_cpu_usage_seconds_total{node=~\"$node\", namespace=\"$namespace\", pod=~\"$pod\"}[$__rate_interval]))\n      -\n      sum by(namespace, pod, container) (avg_over_time(kube_pod_container_resource_requests{resource=\"cpu\",unit=\"core\",node=~\"$node\", namespace=\"$namespace\", pod=~\"$pod\", container!=\"\"}[$__rate_interval]))\n    )\n    or\n    sum by(namespace, pod, container) (rate(container_cpu_usage_seconds_total{node=~\"$node\", namespace=\"$namespace\", pod=~\"$pod\"}[$__rate_interval]))\n  )\n) > 0",
           "format": "time_series",
           "hide": false,
           "intervalFactor": 1,
@@ -2095,7 +2095,7 @@
           "repeatDirection": "h",
           "targets": [
             {
-              "expr": "sum by(pod) (rate(container_cpu_usage_seconds_total{node=~\"$node\", container!=\"POD\", pod=\"$pod\", namespace=\"$namespace\"}[$__rate_interval]))",
+              "expr": "sum by(pod) (rate(container_cpu_usage_seconds_total{node=~\"$node\", container!=\"\", pod=\"$pod\", namespace=\"$namespace\"}[$__rate_interval]))",
               "format": "time_series",
               "intervalFactor": 1,
               "legendFormat": "Usage",
@@ -2109,7 +2109,7 @@
               "refId": "D"
             },
             {
-              "expr": "sum by (pod)\n(\n  kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller=\"$controller\", pod=~\"$pod\"}\n  * on (controller_type, controller_name) group_left()\n  sum by (controller_type, controller_name) (avg_over_time(vpa_target_recommendation{container!=\"POD\", namespace=\"$namespace\", resource=\"cpu\"}[$__rate_interval]))\n)",
+              "expr": "sum by (pod)\n(\n  kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller=\"$controller\", pod=~\"$pod\"}\n  * on (controller_type, controller_name) group_left()\n  sum by (controller_type, controller_name) (avg_over_time(vpa_target_recommendation{container!=\"\", namespace=\"$namespace\", resource=\"cpu\"}[$__rate_interval]))\n)",
               "format": "time_series",
               "intervalFactor": 1,
               "legendFormat": "VPA Target",
@@ -2295,7 +2295,7 @@
                 "type": "prometheus",
                 "uid": "$ds_prometheus"
               },
-              "expr": "sum by(pod) (rate(container_cpu_system_seconds_total{node=~\"$node\", container!=\"POD\", pod=\"$pod\", namespace=\"$namespace\"}[$__rate_interval]))",
+              "expr": "sum by(pod) (rate(container_cpu_system_seconds_total{node=~\"$node\", container!=\"\", pod=\"$pod\", namespace=\"$namespace\"}[$__rate_interval]))",
               "format": "time_series",
               "intervalFactor": 1,
               "legendFormat": "System",
@@ -2306,7 +2306,7 @@
                 "type": "prometheus",
                 "uid": "$ds_prometheus"
               },
-              "expr": "sum by(pod) (rate(container_cpu_user_seconds_total{node=~\"$node\", container!=\"POD\", pod=\"$pod\", namespace=\"$namespace\"}[$__rate_interval]))",
+              "expr": "sum by(pod) (rate(container_cpu_user_seconds_total{node=~\"$node\", container!=\"\", pod=\"$pod\", namespace=\"$namespace\"}[$__rate_interval]))",
               "format": "time_series",
               "intervalFactor": 1,
               "legendFormat": "User",
@@ -2468,7 +2468,7 @@
             "uid": "$ds_prometheus"
           },
           "editorMode": "code",
-          "expr": "sum by(pod) (\n  max(kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller=\"$controller\", pod=~\"$pod\"}) by(pod)\n  * on (pod)\n  sum by (pod) (avg_over_time(container_memory_working_set_bytes:without_kmem{node=~\"$node\", container!=\"POD\", pod=~\"$pod\", namespace=\"$namespace\"}[$__rate_interval]))\n)",
+          "expr": "sum by(pod) (\n  max(kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller=\"$controller\", pod=~\"$pod\"}) by(pod)\n  * on (pod)\n  sum by (pod) (avg_over_time(container_memory_working_set_bytes:without_kmem{node=~\"$node\", container!=\"\", pod=~\"$pod\", namespace=\"$namespace\"}[$__rate_interval]))\n)",
           "format": "time_series",
           "intervalFactor": 1,
           "legendFormat": "{{ pod }}",
@@ -2653,7 +2653,7 @@
             "uid": "${ds_prometheus}"
           },
           "editorMode": "code",
-          "expr": "sum (\n  max(kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller=\"$controller\", pod=~\"$pod\"}) by(pod)\n  * on (pod)\n  sum by (pod) (avg_over_time(container_memory_rss{node=~\"$node\", namespace=\"$namespace\", pod=~\"$pod\", container!=\"POD\"}[$__rate_interval]))\n)",
+          "expr": "sum (\n  max(kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller=\"$controller\", pod=~\"$pod\"}) by(pod)\n  * on (pod)\n  sum by (pod) (avg_over_time(container_memory_rss{node=~\"$node\", namespace=\"$namespace\", pod=~\"$pod\", container!=\"\"}[$__rate_interval]))\n)",
           "format": "time_series",
           "intervalFactor": 1,
           "legendFormat": "RSS",
@@ -2666,7 +2666,7 @@
             "uid": "${ds_prometheus}"
           },
           "editorMode": "code",
-          "expr": "sum (\n  max(kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller=\"$controller\", pod=~\"$pod\"}) by(pod)\n  * on (pod)\n  sum by (pod) (avg_over_time(container_memory_cache{node=~\"$node\", namespace=\"$namespace\", pod=~\"$pod\", container!=\"POD\"}[$__rate_interval]))\n)",
+          "expr": "sum (\n  max(kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller=\"$controller\", pod=~\"$pod\"}) by(pod)\n  * on (pod)\n  sum by (pod) (avg_over_time(container_memory_cache{node=~\"$node\", namespace=\"$namespace\", pod=~\"$pod\", container!=\"\"}[$__rate_interval]))\n)",
           "format": "time_series",
           "intervalFactor": 1,
           "legendFormat": "Cache",
@@ -2679,7 +2679,7 @@
             "uid": "${ds_prometheus}"
           },
           "editorMode": "code",
-          "expr": "sum (\n  max(kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller=\"$controller\", pod=~\"$pod\"}) by(pod)\n  * on (pod)\n  sum by (pod) (avg_over_time(container_memory_swap{node=~\"$node\", namespace=\"$namespace\", pod=~\"$pod\", container!=\"POD\"}[$__rate_interval]))\n)",
+          "expr": "sum (\n  max(kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller=\"$controller\", pod=~\"$pod\"}) by(pod)\n  * on (pod)\n  sum by (pod) (avg_over_time(container_memory_swap{node=~\"$node\", namespace=\"$namespace\", pod=~\"$pod\", container!=\"\"}[$__rate_interval]))\n)",
           "format": "time_series",
           "intervalFactor": 1,
           "legendFormat": "Swap",
@@ -2692,7 +2692,7 @@
             "uid": "${ds_prometheus}"
           },
           "editorMode": "code",
-          "expr": "sum (\n  max(kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller=\"$controller\", pod=~\"$pod\"}) by(pod)\n  * on (pod)\n  sum by (pod) (avg_over_time(container_memory_working_set_bytes:without_kmem{node=~\"$node\", namespace=\"$namespace\", pod=~\"$pod\", container!=\"POD\"}[$__rate_interval]))\n)",
+          "expr": "sum (\n  max(kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller=\"$controller\", pod=~\"$pod\"}) by(pod)\n  * on (pod)\n  sum by (pod) (avg_over_time(container_memory_working_set_bytes:without_kmem{node=~\"$node\", namespace=\"$namespace\", pod=~\"$pod\", container!=\"\"}[$__rate_interval]))\n)",
           "format": "time_series",
           "intervalFactor": 1,
           "legendFormat": "Working set bytes without kmem",
@@ -2705,7 +2705,7 @@
             "uid": "${ds_prometheus}"
           },
           "editorMode": "code",
-          "expr": "sum (\n  max(kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller=\"$controller\", pod=~\"$pod\"}) by(pod)\n  * on (pod)\n  sum by (pod) (avg_over_time(container_memory:kmem{node=~\"$node\", namespace=\"$namespace\", pod=~\"$pod\", container!=\"POD\"}[$__rate_interval]))\n)",
+          "expr": "sum (\n  max(kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller=\"$controller\", pod=~\"$pod\"}) by(pod)\n  * on (pod)\n  sum by (pod) (avg_over_time(container_memory:kmem{node=~\"$node\", namespace=\"$namespace\", pod=~\"$pod\", container!=\"\"}[$__rate_interval]))\n)",
           "format": "time_series",
           "intervalFactor": 1,
           "legendFormat": "Kmem",
@@ -2837,7 +2837,7 @@
             "type": "prometheus",
             "uid": "$ds_prometheus"
           },
-          "expr": "(\n  kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller=\"$controller\", pod=~\"$pod\"}\n  * on (pod) group_left()\n  sum by (pod)\n    (\n      (\n        sum by (namespace, pod, container) (avg_over_time(kube_pod_container_resource_requests{resource=\"memory\",unit=\"byte\",node=~\"$node\", namespace=\"$namespace\"}[$__rate_interval]))\n        -\n        sum by (namespace, pod, container) (avg_over_time(container_memory_working_set_bytes:without_kmem{node=~\"$node\", namespace=\"$namespace\", container!=\"POD\"}[$__rate_interval]))\n      ) > 0\n    )\n)",
+          "expr": "(\n  kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller=\"$controller\", pod=~\"$pod\"}\n  * on (pod) group_left()\n  sum by (pod)\n    (\n      (\n        sum by (namespace, pod, container) (avg_over_time(kube_pod_container_resource_requests{resource=\"memory\",unit=\"byte\",node=~\"$node\", namespace=\"$namespace\"}[$__rate_interval]))\n        -\n        sum by (namespace, pod, container) (avg_over_time(container_memory_working_set_bytes:without_kmem{node=~\"$node\", namespace=\"$namespace\", container!=\"\"}[$__rate_interval]))\n      ) > 0\n    )\n)",
           "format": "time_series",
           "intervalFactor": 1,
           "legendFormat": "{{ pod }}",
@@ -2974,7 +2974,7 @@
             "type": "prometheus",
             "uid": "$ds_prometheus"
           },
-          "expr": "(\n  kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller=\"$controller\", pod=~\"$pod\"}\n  * on (pod) group_left()\n  sum by (pod)\n    (\n      (\n        (\n          sum by (namespace, pod, container) (avg_over_time(container_memory_working_set_bytes:without_kmem{node=~\"$node\", namespace=\"$namespace\"}[$__rate_interval]))\n          -\n          sum by (namespace, pod, container) (avg_over_time(kube_pod_container_resource_requests{resource=\"memory\",unit=\"byte\",node=~\"$node\", namespace=\"$namespace\", container!=\"POD\"}[$__rate_interval]))\n        ) or sum by (namespace, pod, container) (avg_over_time(container_memory_working_set_bytes:without_kmem{node=~\"$node\", namespace=\"$namespace\", container!=\"POD\"}[$__rate_interval]))\n      ) > 0\n    )\n)",
+          "expr": "(\n  kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller=\"$controller\", pod=~\"$pod\"}\n  * on (pod) group_left()\n  sum by (pod)\n    (\n      (\n        (\n          sum by (namespace, pod, container) (avg_over_time(container_memory_working_set_bytes:without_kmem{node=~\"$node\", namespace=\"$namespace\"}[$__rate_interval]))\n          -\n          sum by (namespace, pod, container) (avg_over_time(kube_pod_container_resource_requests{resource=\"memory\",unit=\"byte\",node=~\"$node\", namespace=\"$namespace\", container!=\"\"}[$__rate_interval]))\n        ) or sum by (namespace, pod, container) (avg_over_time(container_memory_working_set_bytes:without_kmem{node=~\"$node\", namespace=\"$namespace\", container!=\"\"}[$__rate_interval]))\n      ) > 0\n    )\n)",
           "format": "time_series",
           "intervalFactor": 1,
           "legendFormat": "{{ pod }}",
@@ -3290,56 +3290,56 @@
           "repeatDirection": "h",
           "targets": [
             {
-              "expr": "sum by (pod) (avg_over_time(container_memory_rss{node=~\"$node\", namespace=\"$namespace\", pod=~\"$pod\", container!=\"POD\"}[$__rate_interval]))",
+              "expr": "sum by (pod) (avg_over_time(container_memory_rss{node=~\"$node\", namespace=\"$namespace\", pod=~\"$pod\", container!=\"\"}[$__rate_interval]))",
               "format": "time_series",
               "intervalFactor": 1,
               "legendFormat": "RSS",
               "refId": "A"
             },
             {
-              "expr": "sum by (pod) (avg_over_time(container_memory_cache{node=~\"$node\", namespace=\"$namespace\", pod=~\"$pod\", container!=\"POD\"}[$__rate_interval]))",
+              "expr": "sum by (pod) (avg_over_time(container_memory_cache{node=~\"$node\", namespace=\"$namespace\", pod=~\"$pod\", container!=\"\"}[$__rate_interval]))",
               "format": "time_series",
               "intervalFactor": 1,
               "legendFormat": "Cache",
               "refId": "B"
             },
             {
-              "expr": "sum by (pod) (avg_over_time(container_memory_swap{node=~\"$node\", namespace=\"$namespace\", pod=~\"$pod\", container!=\"POD\"}[$__rate_interval]))",
+              "expr": "sum by (pod) (avg_over_time(container_memory_swap{node=~\"$node\", namespace=\"$namespace\", pod=~\"$pod\", container!=\"\"}[$__rate_interval]))",
               "format": "time_series",
               "intervalFactor": 1,
               "legendFormat": "Swap",
               "refId": "C"
             },
             {
-              "expr": "sum by (pod) (avg_over_time(container_memory_working_set_bytes:without_kmem{node=~\"$node\", namespace=\"$namespace\", pod=~\"$pod\", container!=\"POD\"}[$__rate_interval]))",
+              "expr": "sum by (pod) (avg_over_time(container_memory_working_set_bytes:without_kmem{node=~\"$node\", namespace=\"$namespace\", pod=~\"$pod\", container!=\"\"}[$__rate_interval]))",
               "format": "time_series",
               "intervalFactor": 1,
               "legendFormat": "Working set bytes without kmem",
               "refId": "D"
             },
             {
-              "expr": "sum by (pod)\n(\n  kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller=\"$controller\", pod=~\"$pod\"}\n  * on (controller_type, controller_name) group_left()\n  sum by (controller_type, controller_name) (avg_over_time(vpa_target_recommendation{namespace=\"$namespace\", container!=\"POD\", resource=\"memory\"}[$__rate_interval]))\n)",
+              "expr": "sum by (pod)\n(\n  kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller=\"$controller\", pod=~\"$pod\"}\n  * on (controller_type, controller_name) group_left()\n  sum by (controller_type, controller_name) (avg_over_time(vpa_target_recommendation{namespace=\"$namespace\", container!=\"\", resource=\"memory\"}[$__rate_interval]))\n)",
               "format": "time_series",
               "intervalFactor": 1,
               "legendFormat": "VPA Target",
               "refId": "E"
             },
             {
-              "expr": "sum by(pod) (avg_over_time(kube_pod_container_resource_limits{resource=\"memory\",unit=\"byte\",node=~\"$node\", namespace=\"$namespace\", pod=~\"$pod\", container!=\"POD\"}[$__rate_interval]))",
+              "expr": "sum by(pod) (avg_over_time(kube_pod_container_resource_limits{resource=\"memory\",unit=\"byte\",node=~\"$node\", namespace=\"$namespace\", pod=~\"$pod\", container!=\"\"}[$__rate_interval]))",
               "format": "time_series",
               "intervalFactor": 1,
               "legendFormat": "Limits",
               "refId": "F"
             },
             {
-              "expr": "sum by(pod) (avg_over_time(kube_pod_container_resource_requests{resource=\"memory\",unit=\"byte\",node=~\"$node\", namespace=\"$namespace\", pod=~\"$pod\", container!=\"POD\"}[$__rate_interval]))",
+              "expr": "sum by(pod) (avg_over_time(kube_pod_container_resource_requests{resource=\"memory\",unit=\"byte\",node=~\"$node\", namespace=\"$namespace\", pod=~\"$pod\", container!=\"\"}[$__rate_interval]))",
               "format": "time_series",
               "intervalFactor": 1,
               "legendFormat": "Requests",
               "refId": "G"
             },
             {
-              "expr": "sum by(pod) (avg_over_time(container_memory:kmem{node=~\"$node\", namespace=\"$namespace\", pod=~\"$pod\", container!=\"POD\"}[$__rate_interval]))",
+              "expr": "sum by(pod) (avg_over_time(container_memory:kmem{node=~\"$node\", namespace=\"$namespace\", pod=~\"$pod\", container!=\"\"}[$__rate_interval]))",
               "format": "time_series",
               "intervalFactor": 1,
               "legendFormat": "Kmem",
@@ -3834,7 +3834,7 @@
             "uid": "$ds_prometheus"
           },
           "editorMode": "code",
-          "expr": "sum by(pod) (\n  max(kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller=\"$controller\"}) by(pod)\n  * on (pod)\n  sum by (pod) (rate(container_fs_reads_total{node=~\"$node\", container!=\"POD\", pod=~\"$pod\", namespace=\"$namespace\"}[$__rate_interval]))\n)",
+          "expr": "sum by(pod) (\n  max(kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller=\"$controller\"}) by(pod)\n  * on (pod)\n  sum by (pod) (rate(container_fs_reads_total{node=~\"$node\", container!=\"\", pod=~\"$pod\", namespace=\"$namespace\"}[$__rate_interval]))\n)",
           "format": "time_series",
           "intervalFactor": 1,
           "legendFormat": "{{ pod }}",
@@ -3972,7 +3972,7 @@
             "uid": "$ds_prometheus"
           },
           "editorMode": "code",
-          "expr": "sum by(pod) (\n  max(kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller=\"$controller\"}) by(pod)\n  * on (pod)\n  sum by (pod) (rate(container_fs_writes_total{node=~\"$node\", container!=\"POD\", pod=~\"$pod\", namespace=\"$namespace\"}[$__rate_interval]))\n)",
+          "expr": "sum by(pod) (\n  max(kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller=\"$controller\"}) by(pod)\n  * on (pod)\n  sum by (pod) (rate(container_fs_writes_total{node=~\"$node\", container!=\"\", pod=~\"$pod\", namespace=\"$namespace\"}[$__rate_interval]))\n)",
           "format": "time_series",
           "intervalFactor": 1,
           "legendFormat": "{{ pod }}",

dashboards/main/namespace.json

@@ -656,7 +656,7 @@
             "type": "prometheus",
             "uid": "${ds_prometheus}"
           },
-          "expr": "sum by (controller) (avg_over_time(kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller_type=~\"$controller_type\", controller=~\"$controller\"}[$__range]) * on (pod) group_left() sum by (pod) (rate(container_cpu_usage_seconds_total{node=~\"$node\", namespace=\"$namespace\", container!=\"POD\"}[$__range])))\nor\ncount (avg_over_time(kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller_type=~\"$controller_type\", controller=~\"$controller\"}[$__range])) by (controller) * 0",
+          "expr": "sum by (controller) (avg_over_time(kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller_type=~\"$controller_type\", controller=~\"$controller\"}[$__range]) * on (pod) group_left() sum by (pod) (rate(container_cpu_usage_seconds_total{node=~\"$node\", namespace=\"$namespace\", container!=\"\"}[$__range])))\nor\ncount (avg_over_time(kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller_type=~\"$controller_type\", controller=~\"$controller\"}[$__range])) by (controller) * 0",
           "format": "table",
           "instant": true,
           "intervalFactor": 1,
@@ -680,7 +680,7 @@
             "type": "prometheus",
             "uid": "${ds_prometheus}"
           },
-          "expr": "sum by (controller)\n  (\n    avg_over_time(kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller_type=~\"$controller_type\", controller=~\"$controller\"}[$__range])\n    * on (controller_type, controller_name) group_left()\n    sum by(controller_type, controller_name) (avg_over_time(vpa_target_recommendation{container!=\"POD\",namespace=\"$namespace\", resource=\"cpu\"}[$__range]))\n  ) \nor\ncount (avg_over_time(kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller_type=~\"$controller_type\", controller=~\"$controller\"}[$__range])) by (controller) * 0",
+          "expr": "sum by (controller)\n  (\n    avg_over_time(kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller_type=~\"$controller_type\", controller=~\"$controller\"}[$__range])\n    * on (controller_type, controller_name) group_left()\n    sum by(controller_type, controller_name) (avg_over_time(vpa_target_recommendation{container!=\"\",namespace=\"$namespace\", resource=\"cpu\"}[$__range]))\n  ) \nor\ncount (avg_over_time(kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller_type=~\"$controller_type\", controller=~\"$controller\"}[$__range])) by (controller) * 0",
           "format": "table",
           "instant": true,
           "intervalFactor": 1,
@@ -692,7 +692,7 @@
             "type": "prometheus",
             "uid": "${ds_prometheus}"
           },
-          "expr": "sum by (controller)\n  (\n    avg_over_time(kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller_type=~\"$controller_type\", controller=~\"$controller\"}[$__range])\n    * on (namespace, pod) group_left()\n    sum by (namespace, pod)\n      (\n        (\n          sum by(namespace, pod, container) (avg_over_time(kube_pod_container_resource_requests{resource=\"cpu\",unit=\"core\",node=~\"$node\", namespace=\"$namespace\"}[$__range]))\n          -\n          sum by(namespace, pod, container) (rate(container_cpu_usage_seconds_total{node=~\"$node\", container!=\"POD\", namespace=\"$namespace\"}[$__range]))\n        ) > 0\n      )\n  )\nor\ncount (avg_over_time(kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller_type=~\"$controller_type\", controller=~\"$controller\"}[$__range])) by (controller) * 0",
+          "expr": "sum by (controller)\n  (\n    avg_over_time(kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller_type=~\"$controller_type\", controller=~\"$controller\"}[$__range])\n    * on (namespace, pod) group_left()\n    sum by (namespace, pod)\n      (\n        (\n          sum by(namespace, pod, container) (avg_over_time(kube_pod_container_resource_requests{resource=\"cpu\",unit=\"core\",node=~\"$node\", namespace=\"$namespace\"}[$__range]))\n          -\n          sum by(namespace, pod, container) (rate(container_cpu_usage_seconds_total{node=~\"$node\", container!=\"\", namespace=\"$namespace\"}[$__range]))\n        ) > 0\n      )\n  )\nor\ncount (avg_over_time(kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller_type=~\"$controller_type\", controller=~\"$controller\"}[$__range])) by (controller) * 0",
           "format": "table",
           "instant": true,
           "intervalFactor": 1,
@@ -704,7 +704,7 @@
             "type": "prometheus",
             "uid": "${ds_prometheus}"
           },
-          "expr": "sum by (controller)\n  (\n    avg_over_time(kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller_type=~\"$controller_type\", controller=~\"$controller\"}[$__range])\n    * on (namespace, pod) group_left()\n    sum by (namespace, pod)\n      (\n        (\n          (\n            sum by(namespace, pod, container) (rate(container_cpu_usage_seconds_total{node=~\"$node\", namespace=\"$namespace\"}[$__range]))\n            -\n            sum by(namespace, pod, container) (avg_over_time(kube_pod_container_resource_requests{resource=\"cpu\",unit=\"core\",node=~\"$node\", container!=\"POD\", namespace=\"$namespace\"}[$__range]))\n          ) or sum by(namespace, pod, container) (rate(container_cpu_usage_seconds_total{node=~\"$node\", container!=\"POD\", namespace=\"$namespace\"}[$__range]))\n        ) > 0\n      )\n  )\nor\ncount (avg_over_time(kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller_type=~\"$controller_type\", controller=~\"$controller\"}[$__range])) by (controller) * 0",
+          "expr": "sum by (controller)\n  (\n    avg_over_time(kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller_type=~\"$controller_type\", controller=~\"$controller\"}[$__range])\n    * on (namespace, pod) group_left()\n    sum by (namespace, pod)\n      (\n        (\n          (\n            sum by(namespace, pod, container) (rate(container_cpu_usage_seconds_total{node=~\"$node\", namespace=\"$namespace\"}[$__range]))\n            -\n            sum by(namespace, pod, container) (avg_over_time(kube_pod_container_resource_requests{resource=\"cpu\",unit=\"core\",node=~\"$node\", container!=\"\", namespace=\"$namespace\"}[$__range]))\n          ) or sum by(namespace, pod, container) (rate(container_cpu_usage_seconds_total{node=~\"$node\", container!=\"\", namespace=\"$namespace\"}[$__range]))\n        ) > 0\n      )\n  )\nor\ncount (avg_over_time(kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller_type=~\"$controller_type\", controller=~\"$controller\"}[$__range])) by (controller) * 0",
           "format": "table",
           "instant": true,
           "intervalFactor": 1,
@@ -728,7 +728,7 @@
             "type": "prometheus",
             "uid": "${ds_prometheus}"
           },
-          "expr": "sum by (controller) (avg_over_time(kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller_type=~\"$controller_type\", controller=~\"$controller\"}[$__range]) * on (pod) group_left() sum by (pod) (avg_over_time(container_memory_working_set_bytes:without_kmem{node=~\"$node\", namespace=\"$namespace\", container!=\"POD\"}[$__range])))\nor\ncount (avg_over_time(kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller_type=~\"$controller_type\", controller=~\"$controller\"}[$__range])) by (controller) * 0",
+          "expr": "sum by (controller) (avg_over_time(kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller_type=~\"$controller_type\", controller=~\"$controller\"}[$__range]) * on (pod) group_left() sum by (pod) (avg_over_time(container_memory_working_set_bytes:without_kmem{node=~\"$node\", namespace=\"$namespace\", container!=\"\"}[$__range])))\nor\ncount (avg_over_time(kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller_type=~\"$controller_type\", controller=~\"$controller\"}[$__range])) by (controller) * 0",
           "format": "table",
           "instant": true,
           "intervalFactor": 1,
@@ -740,7 +740,7 @@
             "type": "prometheus",
             "uid": "${ds_prometheus}"
           },
-          "expr": "sum by (controller)\n  (\n    avg_over_time(kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller_type=~\"$controller_type\", controller=~\"$controller\"}[$__range])\n    * on (pod) group_left()\n    sum by (namespace, pod)\n      (\n        avg_over_time(kube_pod_container_resource_requests{resource=\"memory\",unit=\"byte\",node=~\"$node\", namespace=\"$namespace\", container!=\"POD\"}[$__range])\n      )\n    )\n  or\n  count (avg_over_time(kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller_type=~\"$controller_type\", controller=~\"$controller\"}[$__range])) by (controller) * 0",
+          "expr": "sum by (controller)\n  (\n    avg_over_time(kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller_type=~\"$controller_type\", controller=~\"$controller\"}[$__range])\n    * on (pod) group_left()\n    sum by (namespace, pod)\n      (\n        avg_over_time(kube_pod_container_resource_requests{resource=\"memory\",unit=\"byte\",node=~\"$node\", namespace=\"$namespace\", container!=\"\"}[$__range])\n      )\n    )\n  or\n  count (avg_over_time(kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller_type=~\"$controller_type\", controller=~\"$controller\"}[$__range])) by (controller) * 0",
           "format": "table",
           "instant": true,
           "intervalFactor": 1,
@@ -752,7 +752,7 @@
             "type": "prometheus",
             "uid": "${ds_prometheus}"
           },
-          "expr": "sum by (controller)\n  (\n    avg_over_time(kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller_type=~\"$controller_type\", controller=~\"$controller\"}[$__range])\n    * on (controller_type, controller_name) group_left()\n    sum by(controller_type, controller_name) (avg_over_time(vpa_target_recommendation{container!=\"POD\",namespace=\"$namespace\", resource=\"memory\"}[$__range]))\n  ) \n  or  \ncount (avg_over_time(kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller_type=~\"$controller_type\", controller=~\"$controller\"}[$__range])) by (controller) * 0",
+          "expr": "sum by (controller)\n  (\n    avg_over_time(kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller_type=~\"$controller_type\", controller=~\"$controller\"}[$__range])\n    * on (controller_type, controller_name) group_left()\n    sum by(controller_type, controller_name) (avg_over_time(vpa_target_recommendation{container!=\"\",namespace=\"$namespace\", resource=\"memory\"}[$__range]))\n  ) \n  or  \ncount (avg_over_time(kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller_type=~\"$controller_type\", controller=~\"$controller\"}[$__range])) by (controller) * 0",
           "format": "table",
           "instant": true,
           "intervalFactor": 1,
@@ -764,7 +764,7 @@
             "type": "prometheus",
             "uid": "${ds_prometheus}"
           },
-          "expr": "sum by (controller)\n  (\n    avg_over_time(kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller_type=~\"$controller_type\", controller=~\"$controller\"}[$__range])\n    * on (namespace, pod) group_left()\n    sum by (namespace, pod)\n      (\n        (\n          sum by(namespace, pod, container) (avg_over_time(kube_pod_container_resource_requests{resource=\"memory\",unit=\"byte\",node=~\"$node\", namespace=\"$namespace\"}[$__range]))\n          -\n          sum by(namespace, pod, container) (avg_over_time(container_memory_working_set_bytes:without_kmem{node=~\"$node\", container!=\"POD\", namespace=\"$namespace\"}[$__range]))\n        ) > 0\n      )\n  )\nor\ncount (avg_over_time(kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller_type=~\"$controller_type\", controller=~\"$controller\"}[$__range])) by (controller) * 0",
+          "expr": "sum by (controller)\n  (\n    avg_over_time(kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller_type=~\"$controller_type\", controller=~\"$controller\"}[$__range])\n    * on (namespace, pod) group_left()\n    sum by (namespace, pod)\n      (\n        (\n          sum by(namespace, pod, container) (avg_over_time(kube_pod_container_resource_requests{resource=\"memory\",unit=\"byte\",node=~\"$node\", namespace=\"$namespace\"}[$__range]))\n          -\n          sum by(namespace, pod, container) (avg_over_time(container_memory_working_set_bytes:without_kmem{node=~\"$node\", container!=\"\", namespace=\"$namespace\"}[$__range]))\n        ) > 0\n      )\n  )\nor\ncount (avg_over_time(kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller_type=~\"$controller_type\", controller=~\"$controller\"}[$__range])) by (controller) * 0",
           "format": "table",
           "instant": true,
           "intervalFactor": 1,
@@ -776,7 +776,7 @@
             "type": "prometheus",
             "uid": "${ds_prometheus}"
           },
-          "expr": "sum by (controller)\n  (\n    avg_over_time(kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller_type=~\"$controller_type\", controller=~\"$controller\"}[$__range])\n    * on (namespace, pod) group_left()\n    sum by (namespace, pod)\n      (\n        (\n          (\n            sum by(namespace, pod, container) (avg_over_time(container_memory_working_set_bytes:without_kmem{node=~\"$node\", namespace=\"$namespace\"}[$__range]))\n            -\n            sum by(namespace, pod, container) (avg_over_time(kube_pod_container_resource_requests{resource=\"memory\",unit=\"byte\",node=~\"$node\", container!=\"POD\", namespace=\"$namespace\"}[$__range]))\n          ) or sum by(namespace, pod, container) (avg_over_time(container_memory_working_set_bytes:without_kmem{node=~\"$node\", container!=\"POD\", namespace=\"$namespace\"}[$__range]))\n        ) > 0\n      )\n  )\nor\ncount (avg_over_time(kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller_type=~\"$controller_type\", controller=~\"$controller\"}[$__range])) by (controller) * 0",
+          "expr": "sum by (controller)\n  (\n    avg_over_time(kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller_type=~\"$controller_type\", controller=~\"$controller\"}[$__range])\n    * on (namespace, pod) group_left()\n    sum by (namespace, pod)\n      (\n        (\n          (\n            sum by(namespace, pod, container) (avg_over_time(container_memory_working_set_bytes:without_kmem{node=~\"$node\", namespace=\"$namespace\"}[$__range]))\n            -\n            sum by(namespace, pod, container) (avg_over_time(kube_pod_container_resource_requests{resource=\"memory\",unit=\"byte\",node=~\"$node\", container!=\"\", namespace=\"$namespace\"}[$__range]))\n          ) or sum by(namespace, pod, container) (avg_over_time(container_memory_working_set_bytes:without_kmem{node=~\"$node\", container!=\"\", namespace=\"$namespace\"}[$__range]))\n        ) > 0\n      )\n  )\nor\ncount (avg_over_time(kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller_type=~\"$controller_type\", controller=~\"$controller\"}[$__range])) by (controller) * 0",
           "format": "table",
           "instant": true,
           "intervalFactor": 1,
@@ -814,7 +814,7 @@
             "type": "prometheus",
             "uid": "${ds_prometheus}"
           },
-          "expr": "sum by (controller) (avg_over_time(kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller_type=~\"$controller_type\", controller=~\"$controller\"}[$__range]) * on (pod) group_left() sum by (pod) (rate(container_fs_reads_total{node=~\"$node\", container!=\"POD\", namespace=\"$namespace\"}[$__range])))\nor\ncount (avg_over_time(kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller_type=~\"$controller_type\", controller=~\"$controller\"}[$__range])) by (controller) * 0",
+          "expr": "sum by (controller) (avg_over_time(kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller_type=~\"$controller_type\", controller=~\"$controller\"}[$__range]) * on (pod) group_left() sum by (pod) (rate(container_fs_reads_total{node=~\"$node\", container!=\"\", namespace=\"$namespace\"}[$__range])))\nor\ncount (avg_over_time(kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller_type=~\"$controller_type\", controller=~\"$controller\"}[$__range])) by (controller) * 0",
           "format": "table",
           "instant": true,
           "intervalFactor": 1,
@@ -826,7 +826,7 @@
             "type": "prometheus",
             "uid": "${ds_prometheus}"
           },
-          "expr": "sum by (controller) (avg_over_time(kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller_type=~\"$controller_type\", controller=~\"$controller\"}[$__range]) * on (pod) group_left() sum by (pod) (rate(container_fs_writes_total{node=~\"$node\", container!=\"POD\", namespace=\"$namespace\"}[$__range])))\nor\ncount (avg_over_time(kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller_type=~\"$controller_type\", controller=~\"$controller\"}[$__range])) by (controller) * 0",
+          "expr": "sum by (controller) (avg_over_time(kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller_type=~\"$controller_type\", controller=~\"$controller\"}[$__range]) * on (pod) group_left() sum by (pod) (rate(container_fs_writes_total{node=~\"$node\", container!=\"\", namespace=\"$namespace\"}[$__range])))\nor\ncount (avg_over_time(kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller_type=~\"$controller_type\", controller=~\"$controller\"}[$__range])) by (controller) * 0",
           "format": "table",
           "instant": true,
           "intervalFactor": 1,
@@ -877,7 +877,7 @@
             "type": "prometheus",
             "uid": "${ds_prometheus}"
           },
-          "expr": "sum by (controller) (avg_over_time(kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller_type=~\"$controller_type\", controller=~\"$controller\"}[$__range]) * on (pod) group_left() sum by (pod) (avg_over_time(container_memory:kmem{node=~\"$node\", namespace=\"$namespace\", container!=\"POD\"}[$__range])))\nor\ncount (avg_over_time(kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller_type=~\"$controller_type\", controller=~\"$controller\"}[$__range])) by (controller) * 0",
+          "expr": "sum by (controller) (avg_over_time(kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller_type=~\"$controller_type\", controller=~\"$controller\"}[$__range]) * on (pod) group_left() sum by (pod) (avg_over_time(container_memory:kmem{node=~\"$node\", namespace=\"$namespace\", container!=\"\"}[$__range])))\nor\ncount (avg_over_time(kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller_type=~\"$controller_type\", controller=~\"$controller\"}[$__range])) by (controller) * 0",
           "format": "table",
           "instant": true,
           "intervalFactor": 1,
@@ -1475,7 +1475,7 @@
             "type": "prometheus",
             "uid": "$ds_prometheus"
           },
-          "expr": "sum by (controller) (kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller_type=~\"$controller_type\", controller=~\"$controller\"} * on (pod) group_left() sum by (pod) (rate(container_cpu_usage_seconds_total{node=~\"$node\", namespace=\"$namespace\", container!=\"POD\"}[$__rate_interval])))",
+          "expr": "sum by (controller) (kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller_type=~\"$controller_type\", controller=~\"$controller\"} * on (pod) group_left() sum by (pod) (rate(container_cpu_usage_seconds_total{node=~\"$node\", namespace=\"$namespace\", container!=\"\"}[$__rate_interval])))",
           "format": "time_series",
           "intervalFactor": 1,
           "legendFormat": "{{ controller }}",
@@ -1646,7 +1646,7 @@
             "type": "prometheus",
             "uid": "$ds_prometheus"
           },
-          "expr": "sum (sum by (controller) (kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller_type=~\"$controller_type\", controller=~\"$controller\"} * on (pod) group_left() sum by (pod) (rate(container_cpu_system_seconds_total{node=~\"$node\", namespace=\"$namespace\", container!=\"POD\"}[$__rate_interval]))))",
+          "expr": "sum (sum by (controller) (kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller_type=~\"$controller_type\", controller=~\"$controller\"} * on (pod) group_left() sum by (pod) (rate(container_cpu_system_seconds_total{node=~\"$node\", namespace=\"$namespace\", container!=\"\"}[$__rate_interval]))))",
           "format": "time_series",
           "intervalFactor": 1,
           "legendFormat": "System",
@@ -1657,7 +1657,7 @@
             "type": "prometheus",
             "uid": "$ds_prometheus"
           },
-          "expr": "sum (sum by (controller) (kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller_type=~\"$controller_type\", controller=~\"$controller\"} * on (pod) group_left() sum by (pod) (rate(container_cpu_user_seconds_total{node=~\"$node\", namespace=\"$namespace\", container!=\"POD\"}[$__rate_interval]))))",
+          "expr": "sum (sum by (controller) (kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller_type=~\"$controller_type\", controller=~\"$controller\"} * on (pod) group_left() sum by (pod) (rate(container_cpu_user_seconds_total{node=~\"$node\", namespace=\"$namespace\", container!=\"\"}[$__rate_interval]))))",
           "format": "time_series",
           "intervalFactor": 1,
           "legendFormat": "User",
@@ -1798,7 +1798,7 @@
             "type": "prometheus",
             "uid": "$ds_prometheus"
           },
-          "expr": "sum by (controller)\n  (\n    kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller_type=~\"$controller_type\", controller=~\"$controller\"}\n    * on (namespace, pod) group_left()\n    sum by (namespace, pod)\n      (\n        (\n          sum by(namespace, pod, container) (avg_over_time(kube_pod_container_resource_requests{resource=\"cpu\",unit=\"core\",node=~\"$node\", namespace=\"$namespace\"}[$__rate_interval]))\n          -\n          sum by(namespace, pod, container) (rate(container_cpu_usage_seconds_total{node=~\"$node\", container!=\"POD\", namespace=\"$namespace\"}[$__rate_interval]))\n        ) > 0\n      )\n  )",
+          "expr": "sum by (controller)\n  (\n    kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller_type=~\"$controller_type\", controller=~\"$controller\"}\n    * on (namespace, pod) group_left()\n    sum by (namespace, pod)\n      (\n        (\n          sum by(namespace, pod, container) (avg_over_time(kube_pod_container_resource_requests{resource=\"cpu\",unit=\"core\",node=~\"$node\", namespace=\"$namespace\"}[$__rate_interval]))\n          -\n          sum by(namespace, pod, container) (rate(container_cpu_usage_seconds_total{node=~\"$node\", container!=\"\", namespace=\"$namespace\"}[$__rate_interval]))\n        ) > 0\n      )\n  )",
           "format": "time_series",
           "intervalFactor": 1,
           "legendFormat": "{{ controller }}",
@@ -1939,7 +1939,7 @@
             "type": "prometheus",
             "uid": "$ds_prometheus"
           },
-          "expr": "sum by (controller)\n  (\n    kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller_type=~\"$controller_type\", controller=~\"$controller\"}\n    * on (namespace, pod) group_left()\n    sum by (namespace, pod)\n      (\n        (\n          (\n            sum by(namespace, pod, container) (rate(container_cpu_usage_seconds_total{node=~\"$node\", namespace=\"$namespace\"}[$__rate_interval]))\n            -\n            sum by(namespace, pod, container) (avg_over_time(kube_pod_container_resource_requests{resource=\"cpu\",unit=\"core\",node=~\"$node\", container!=\"POD\", namespace=\"$namespace\"}[$__rate_interval]))\n          ) or sum by(namespace, pod, container) (rate(container_cpu_usage_seconds_total{node=~\"$node\", container!=\"POD\", namespace=\"$namespace\"}[$__rate_interval]))\n        ) > 0\n      )\n  )",
+          "expr": "sum by (controller)\n  (\n    kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller_type=~\"$controller_type\", controller=~\"$controller\"}\n    * on (namespace, pod) group_left()\n    sum by (namespace, pod)\n      (\n        (\n          (\n            sum by(namespace, pod, container) (rate(container_cpu_usage_seconds_total{node=~\"$node\", namespace=\"$namespace\"}[$__rate_interval]))\n            -\n            sum by(namespace, pod, container) (avg_over_time(kube_pod_container_resource_requests{resource=\"cpu\",unit=\"core\",node=~\"$node\", container!=\"\", namespace=\"$namespace\"}[$__rate_interval]))\n          ) or sum by(namespace, pod, container) (rate(container_cpu_usage_seconds_total{node=~\"$node\", container!=\"\", namespace=\"$namespace\"}[$__rate_interval]))\n        ) > 0\n      )\n  )",
           "format": "time_series",
           "instant": false,
           "intervalFactor": 1,
@@ -2257,28 +2257,28 @@
           "repeatDirection": "h",
           "targets": [
             {
-              "expr": "sum by (controller) (kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller=\"$controller\"} * on (pod) group_left() sum by (pod) (rate(container_cpu_usage_seconds_total{node=~\"$node\", namespace=\"$namespace\", container!=\"POD\"}[$__rate_interval])))",
+              "expr": "sum by (controller) (kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller=\"$controller\"} * on (pod) group_left() sum by (pod) (rate(container_cpu_usage_seconds_total{node=~\"$node\", namespace=\"$namespace\", container!=\"\"}[$__rate_interval])))",
               "format": "time_series",
               "intervalFactor": 1,
               "legendFormat": "Usage",
               "refId": "D"
             },
             {
-              "expr": "sum by (controller)\n  (\n    kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller=\"$controller\"}\n    * on (pod) group_left()\n    sum by(pod) (avg_over_time(kube_pod_container_resource_requests{resource=\"cpu\",unit=\"core\",node=~\"$node\", container!=\"POD\",namespace=\"$namespace\"}[$__rate_interval]))\n  )",
+              "expr": "sum by (controller)\n  (\n    kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller=\"$controller\"}\n    * on (pod) group_left()\n    sum by(pod) (avg_over_time(kube_pod_container_resource_requests{resource=\"cpu\",unit=\"core\",node=~\"$node\", container!=\"\",namespace=\"$namespace\"}[$__rate_interval]))\n  )",
               "format": "time_series",
               "intervalFactor": 1,
               "legendFormat": "Requests",
               "refId": "C"
             },
             {
-              "expr": "sum by (controller)\n  (\n    kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller=\"$controller\"}\n    * on (pod) group_left()\n    sum by(pod) (avg_over_time(kube_pod_container_resource_limits{resource=\"cpu\",unit=\"core\",node=~\"$node\", container!=\"POD\",namespace=\"$namespace\"}[$__rate_interval]))\n  )",
+              "expr": "sum by (controller)\n  (\n    kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller=\"$controller\"}\n    * on (pod) group_left()\n    sum by(pod) (avg_over_time(kube_pod_container_resource_limits{resource=\"cpu\",unit=\"core\",node=~\"$node\", container!=\"\",namespace=\"$namespace\"}[$__rate_interval]))\n  )",
               "format": "time_series",
               "intervalFactor": 1,
               "legendFormat": "Limits",
               "refId": "E"
             },
             {
-              "expr": "sum by (controller)\n  (\n    kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller=\"$controller\"}\n    * on (controller_type, controller_name) group_left()\n    sum by(controller_type, controller_name) (avg_over_time(vpa_target_recommendation{container!=\"POD\",namespace=\"$namespace\", resource=\"cpu\"}[$__rate_interval]))\n  )",
+              "expr": "sum by (controller)\n  (\n    kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller=\"$controller\"}\n    * on (controller_type, controller_name) group_left()\n    sum by(controller_type, controller_name) (avg_over_time(vpa_target_recommendation{container!=\"\",namespace=\"$namespace\", resource=\"cpu\"}[$__rate_interval]))\n  )",
               "format": "time_series",
               "intervalFactor": 1,
               "legendFormat": "VPA Target",
@@ -2458,7 +2458,7 @@
                 "type": "prometheus",
                 "uid": "$ds_prometheus"
               },
-              "expr": "sum by (controller) (kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller=\"$controller\"} * on (pod) group_left() sum by (pod) (rate(container_cpu_system_seconds_total{node=~\"$node\", namespace=\"$namespace\", container!=\"POD\"}[$__rate_interval])))",
+              "expr": "sum by (controller) (kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller=\"$controller\"} * on (pod) group_left() sum by (pod) (rate(container_cpu_system_seconds_total{node=~\"$node\", namespace=\"$namespace\", container!=\"\"}[$__rate_interval])))",
               "format": "time_series",
               "interval": "",
               "intervalFactor": 1,
@@ -2470,7 +2470,7 @@
                 "type": "prometheus",
                 "uid": "$ds_prometheus"
               },
-              "expr": "sum by (controller) (kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller=\"$controller\"} * on (pod) group_left() sum by (pod) (rate(container_cpu_user_seconds_total{node=~\"$node\", namespace=\"$namespace\", container!=\"POD\"}[$__rate_interval])))",
+              "expr": "sum by (controller) (kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller=\"$controller\"} * on (pod) group_left() sum by (pod) (rate(container_cpu_user_seconds_total{node=~\"$node\", namespace=\"$namespace\", container!=\"\"}[$__rate_interval])))",
               "format": "time_series",
               "intervalFactor": 1,
               "legendFormat": "User",
@@ -2622,7 +2622,7 @@
             "type": "prometheus",
             "uid": "$ds_prometheus"
           },
-          "expr": "sum by (controller)\n  (\n    kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller_type=~\"$controller_type\", controller=~\"$controller\"}\n    * on (pod) group_left()\n    sum by (pod) (avg_over_time(container_memory_working_set_bytes:without_kmem{node=~\"$node\", namespace=\"$namespace\", container!=\"POD\"}[$__rate_interval]))\n  )",
+          "expr": "sum by (controller)\n  (\n    kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller_type=~\"$controller_type\", controller=~\"$controller\"}\n    * on (pod) group_left()\n    sum by (pod) (avg_over_time(container_memory_working_set_bytes:without_kmem{node=~\"$node\", namespace=\"$namespace\", container!=\"\"}[$__rate_interval]))\n  )",
           "format": "time_series",
           "intervalFactor": 1,
           "legendFormat": "{{ controller }}",
@@ -2799,14 +2799,14 @@
       "pluginVersion": "8.5.13",
       "targets": [
         {
-          "expr": "sum\n  (\n    kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller_type=~\"$controller_type\", controller=~\"$controller\"}\n    * on (pod) group_left()\n    sum by (pod) (avg_over_time(container_memory_rss{node=~\"$node\", namespace=\"$namespace\", container!=\"POD\"}[$__rate_interval]))\n  )",
+          "expr": "sum\n  (\n    kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller_type=~\"$controller_type\", controller=~\"$controller\"}\n    * on (pod) group_left()\n    sum by (pod) (avg_over_time(container_memory_rss{node=~\"$node\", namespace=\"$namespace\", container!=\"\"}[$__rate_interval]))\n  )",
           "format": "time_series",
           "intervalFactor": 1,
           "legendFormat": "RSS",
           "refId": "A"
         },
         {
-          "expr": "sum \n  (\n    kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller_type=~\"$controller_type\", controller=~\"$controller\"}\n    * on (pod) group_left()\n    sum by (pod) (avg_over_time(container_memory_cache{node=~\"$node\", namespace=\"$namespace\", container!=\"POD\"}[$__rate_interval]))\n  )",
+          "expr": "sum \n  (\n    kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller_type=~\"$controller_type\", controller=~\"$controller\"}\n    * on (pod) group_left()\n    sum by (pod) (avg_over_time(container_memory_cache{node=~\"$node\", namespace=\"$namespace\", container!=\"\"}[$__rate_interval]))\n  )",
           "format": "time_series",
           "interval": "",
           "intervalFactor": 1,
@@ -2814,7 +2814,7 @@
           "refId": "B"
         },
         {
-          "expr": "sum \n  (\n    kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller_type=~\"$controller_type\", controller=~\"$controller\"}\n    * on (pod) group_left()\n    sum by (pod) (avg_over_time(container_memory_swap{node=~\"$node\", namespace=\"$namespace\", container!=\"POD\"}[$__rate_interval]))\n  )",
+          "expr": "sum \n  (\n    kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller_type=~\"$controller_type\", controller=~\"$controller\"}\n    * on (pod) group_left()\n    sum by (pod) (avg_over_time(container_memory_swap{node=~\"$node\", namespace=\"$namespace\", container!=\"\"}[$__rate_interval]))\n  )",
           "format": "time_series",
           "interval": "",
           "intervalFactor": 1,
@@ -2822,14 +2822,14 @@
           "refId": "C"
         },
         {
-          "expr": "sum \n  (\n    kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller_type=~\"$controller_type\", controller=~\"$controller\"}\n    * on (pod) group_left()\n    sum by (pod) (avg_over_time(container_memory_working_set_bytes:without_kmem{node=~\"$node\", namespace=\"$namespace\", container!=\"POD\"}[$__rate_interval]))\n  )",
+          "expr": "sum \n  (\n    kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller_type=~\"$controller_type\", controller=~\"$controller\"}\n    * on (pod) group_left()\n    sum by (pod) (avg_over_time(container_memory_working_set_bytes:without_kmem{node=~\"$node\", namespace=\"$namespace\", container!=\"\"}[$__rate_interval]))\n  )",
           "format": "time_series",
           "intervalFactor": 1,
           "legendFormat": "Working set bytes without kmem",
           "refId": "D"
         },
         {
-          "expr": "sum \n  (\n    kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller_type=~\"$controller_type\", controller=~\"$controller\"}\n    * on (pod) group_left()\n    sum by (pod) (avg_over_time(container_memory:kmem{node=~\"$node\", namespace=\"$namespace\", container!=\"POD\"}[$__rate_interval]))\n  )",
+          "expr": "sum \n  (\n    kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller_type=~\"$controller_type\", controller=~\"$controller\"}\n    * on (pod) group_left()\n    sum by (pod) (avg_over_time(container_memory:kmem{node=~\"$node\", namespace=\"$namespace\", container!=\"\"}[$__rate_interval]))\n  )",
           "format": "time_series",
           "intervalFactor": 1,
           "legendFormat": "Kmem",
@@ -2955,7 +2955,7 @@
             "type": "prometheus",
             "uid": "$ds_prometheus"
           },
-          "expr": "sum by (controller)\n  (\n    kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller_type=~\"$controller_type\", controller=~\"$controller\"}\n    * on (namespace, pod) group_left()\n    sum by (namespace, pod)\n      (\n        (\n          sum by(namespace, pod, container) (avg_over_time(kube_pod_container_resource_requests{resource=\"memory\",unit=\"byte\",node=~\"$node\", namespace=\"$namespace\"}[$__rate_interval]))\n          -\n          sum by(namespace, pod, container) (avg_over_time(container_memory_working_set_bytes:without_kmem{node=~\"$node\", container!=\"POD\", namespace=\"$namespace\"}[$__rate_interval]))\n        ) > 0\n      )\n  )",
+          "expr": "sum by (controller)\n  (\n    kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller_type=~\"$controller_type\", controller=~\"$controller\"}\n    * on (namespace, pod) group_left()\n    sum by (namespace, pod)\n      (\n        (\n          sum by(namespace, pod, container) (avg_over_time(kube_pod_container_resource_requests{resource=\"memory\",unit=\"byte\",node=~\"$node\", namespace=\"$namespace\"}[$__rate_interval]))\n          -\n          sum by(namespace, pod, container) (avg_over_time(container_memory_working_set_bytes:without_kmem{node=~\"$node\", container!=\"\", namespace=\"$namespace\"}[$__rate_interval]))\n        ) > 0\n      )\n  )",
           "format": "time_series",
           "intervalFactor": 1,
           "legendFormat": "{{ controller }}",
@@ -3091,7 +3091,7 @@
             "type": "prometheus",
             "uid": "$ds_prometheus"
           },
-          "expr": "sum by (controller)\n  (\n    kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller_type=~\"$controller_type\", controller=~\"$controller\"}\n    * on (namespace, pod) group_left()\n    sum by (namespace, pod)\n      (\n        (\n          (\n            sum by(namespace, pod, container) (avg_over_time(container_memory_working_set_bytes:without_kmem{node=~\"$node\", namespace=\"$namespace\"}[$__rate_interval]))\n            -\n            sum by(namespace, pod, container) (avg_over_time(kube_pod_container_resource_requests{resource=\"memory\",unit=\"byte\",node=~\"$node\", container!=\"POD\", namespace=\"$namespace\"}[$__rate_interval]))\n          )\n          or\n          (\n            sum by(namespace, pod, container) (avg_over_time(container_memory_working_set_bytes:without_kmem{node=~\"$node\", container!=\"POD\", namespace=\"$namespace\"}[$__rate_interval]))\n            +\n            sum by(namespace, pod, container) (avg_over_time(container_memory:kmem{node=~\"$node\", container!=\"POD\", namespace=\"$namespace\"}[$__rate_interval]))\n          )\n        ) > 0\n      )\n  )",
+          "expr": "sum by (controller)\n  (\n    kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller_type=~\"$controller_type\", controller=~\"$controller\"}\n    * on (namespace, pod) group_left()\n    sum by (namespace, pod)\n      (\n        (\n          (\n            sum by(namespace, pod, container) (avg_over_time(container_memory_working_set_bytes:without_kmem{node=~\"$node\", namespace=\"$namespace\"}[$__rate_interval]))\n            -\n            sum by(namespace, pod, container) (avg_over_time(kube_pod_container_resource_requests{resource=\"memory\",unit=\"byte\",node=~\"$node\", container!=\"\", namespace=\"$namespace\"}[$__rate_interval]))\n          )\n          or\n          (\n            sum by(namespace, pod, container) (avg_over_time(container_memory_working_set_bytes:without_kmem{node=~\"$node\", container!=\"\", namespace=\"$namespace\"}[$__rate_interval]))\n            +\n            sum by(namespace, pod, container) (avg_over_time(container_memory:kmem{node=~\"$node\", container!=\"\", namespace=\"$namespace\"}[$__rate_interval]))\n          )\n        ) > 0\n      )\n  )",
           "format": "time_series",
           "intervalFactor": 1,
           "legendFormat": "{{ controller }}",
@@ -3408,14 +3408,14 @@
           "repeatDirection": "h",
           "targets": [
             {
-              "expr": "sum \n  (\n    kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller=\"$controller\"}\n    * on (pod) group_left() \n    sum by (pod) (avg_over_time(container_memory_rss{node=~\"$node\", namespace=\"$namespace\", container!=\"POD\"}[$__rate_interval]))\n  )",
+              "expr": "sum \n  (\n    kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller=\"$controller\"}\n    * on (pod) group_left() \n    sum by (pod) (avg_over_time(container_memory_rss{node=~\"$node\", namespace=\"$namespace\", container!=\"\"}[$__rate_interval]))\n  )",
               "format": "time_series",
               "intervalFactor": 1,
               "legendFormat": "RSS",
               "refId": "A"
             },
             {
-              "expr": "sum\n  (\n    kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller=\"$controller\"} \n    * on (pod) group_left() \n    sum by (pod) (avg_over_time(container_memory_cache{node=~\"$node\", namespace=\"$namespace\", container!=\"POD\"}[$__rate_interval]))\n  )",
+              "expr": "sum\n  (\n    kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller=\"$controller\"} \n    * on (pod) group_left() \n    sum by (pod) (avg_over_time(container_memory_cache{node=~\"$node\", namespace=\"$namespace\", container!=\"\"}[$__rate_interval]))\n  )",
               "format": "time_series",
               "interval": "",
               "intervalFactor": 1,
@@ -3423,7 +3423,7 @@
               "refId": "B"
             },
             {
-              "expr": "sum \n  (\n    kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller=\"$controller\"}\n    * on (pod) group_left() \n    sum by (pod) (avg_over_time(container_memory_swap{node=~\"$node\", namespace=\"$namespace\", container!=\"POD\"}[$__rate_interval]))\n  )",
+              "expr": "sum \n  (\n    kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller=\"$controller\"}\n    * on (pod) group_left() \n    sum by (pod) (avg_over_time(container_memory_swap{node=~\"$node\", namespace=\"$namespace\", container!=\"\"}[$__rate_interval]))\n  )",
               "format": "time_series",
               "interval": "",
               "intervalFactor": 1,
@@ -3431,35 +3431,35 @@
               "refId": "C"
             },
             {
-              "expr": "sum \n  (\n    kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller=\"$controller\"}\n    * on (pod) group_left()\n    sum by (pod) (avg_over_time(container_memory_working_set_bytes:without_kmem{node=~\"$node\", namespace=\"$namespace\", container!=\"POD\"}[$__rate_interval]))\n  )",
+              "expr": "sum \n  (\n    kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller=\"$controller\"}\n    * on (pod) group_left()\n    sum by (pod) (avg_over_time(container_memory_working_set_bytes:without_kmem{node=~\"$node\", namespace=\"$namespace\", container!=\"\"}[$__rate_interval]))\n  )",
               "format": "time_series",
               "intervalFactor": 1,
               "legendFormat": "Working set bytes without kmem",
               "refId": "D"
             },
             {
-              "expr": "sum \n  (\n    kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller=\"$controller\"}\n    * on (pod) group_left()\n    sum by(pod) (avg_over_time(kube_pod_container_resource_requests{resource=\"memory\",unit=\"byte\",node=~\"$node\", container!=\"POD\",namespace=\"$namespace\"}[$__rate_interval]))\n  ) ",
+              "expr": "sum \n  (\n    kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller=\"$controller\"}\n    * on (pod) group_left()\n    sum by(pod) (avg_over_time(kube_pod_container_resource_requests{resource=\"memory\",unit=\"byte\",node=~\"$node\", container!=\"\",namespace=\"$namespace\"}[$__rate_interval]))\n  ) ",
               "format": "time_series",
               "intervalFactor": 1,
               "legendFormat": "Requests",
               "refId": "E"
             },
             {
-              "expr": "sum\n  (\n    kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller=\"$controller\"} \n    * on (pod) group_left() \n    sum by(pod) (avg_over_time(kube_pod_container_resource_limits{resource=\"memory\",unit=\"byte\",node=~\"$node\", container!=\"POD\",namespace=\"$namespace\"}[$__rate_interval]))\n  )",
+              "expr": "sum\n  (\n    kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller=\"$controller\"} \n    * on (pod) group_left() \n    sum by(pod) (avg_over_time(kube_pod_container_resource_limits{resource=\"memory\",unit=\"byte\",node=~\"$node\", container!=\"\",namespace=\"$namespace\"}[$__rate_interval]))\n  )",
               "format": "time_series",
               "intervalFactor": 1,
               "legendFormat": "Limits",
               "refId": "F"
             },
             {
-              "expr": "sum \n  (\n    kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller=\"$controller\"}\n    * on (controller_type, controller_name) group_left()\n    sum by(controller_type, controller_name) (avg_over_time(vpa_target_recommendation{container!=\"POD\",namespace=\"$namespace\", resource=\"memory\"}[$__rate_interval]))\n  )",
+              "expr": "sum \n  (\n    kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller=\"$controller\"}\n    * on (controller_type, controller_name) group_left()\n    sum by(controller_type, controller_name) (avg_over_time(vpa_target_recommendation{container!=\"\",namespace=\"$namespace\", resource=\"memory\"}[$__rate_interval]))\n  )",
               "format": "time_series",
               "intervalFactor": 1,
               "legendFormat": "VPA Target",
               "refId": "G"
             },
             {
-              "expr": "sum \n  (\n    kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller=\"$controller\"}\n    * on (pod) group_left()\n    sum by (pod) (avg_over_time(container_memory:kmem{node=~\"$node\", namespace=\"$namespace\", container!=\"POD\"}[$__rate_interval]))\n  )",
+              "expr": "sum \n  (\n    kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller=\"$controller\"}\n    * on (pod) group_left()\n    sum by (pod) (avg_over_time(container_memory:kmem{node=~\"$node\", namespace=\"$namespace\", container!=\"\"}[$__rate_interval]))\n  )",
               "format": "time_series",
               "intervalFactor": 1,
               "legendFormat": "Kmem",
@@ -3910,7 +3910,7 @@
             "type": "prometheus",
             "uid": "$ds_prometheus"
           },
-          "expr": "sum by (controller) (kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller_type=~\"$controller_type\", controller=~\"$controller\"} * on (pod) group_left() sum by (pod) (rate(container_fs_reads_total{node=~\"$node\", container!=\"POD\", namespace=\"$namespace\"}[$__rate_interval])))",
+          "expr": "sum by (controller) (kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller_type=~\"$controller_type\", controller=~\"$controller\"} * on (pod) group_left() sum by (pod) (rate(container_fs_reads_total{node=~\"$node\", container!=\"\", namespace=\"$namespace\"}[$__rate_interval])))",
           "format": "time_series",
           "intervalFactor": 1,
           "legendFormat": "{{ controller }}",
@@ -4049,7 +4049,7 @@
             "type": "prometheus",
             "uid": "$ds_prometheus"
           },
-          "expr": "sum by (controller) (kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller_type=~\"$controller_type\", controller=~\"$controller\"} * on (pod) group_left() sum by (pod) (rate(container_fs_writes_total{node=~\"$node\", container!=\"POD\", namespace=\"$namespace\"}[$__rate_interval])))",
+          "expr": "sum by (controller) (kube_controller_pod{node=~\"$node\", namespace=\"$namespace\", controller_type=~\"$controller_type\", controller=~\"$controller\"} * on (pod) group_left() sum by (pod) (rate(container_fs_writes_total{node=~\"$node\", container!=\"\", namespace=\"$namespace\"}[$__rate_interval])))",
           "format": "time_series",
           "intervalFactor": 1,
           "legendFormat": "{{ controller }}",

dashboards/main/namespaces.json

@@ -869,7 +869,7 @@
           "refId": "A"
         },
         {
-          "expr": "100 * count by (namespace) (\n  sum by (namespace, verticalpodautoscaler) (  \n    count by (namespace, controller_name, verticalpodautoscaler) (avg_over_time(vpa_target_recommendation{namespace=~\"$namespace\", container!=\"POD\"}[$__range]))\n    / on (controller_name, namespace) group_left\n    count by (namespace, controller_name) (avg_over_time(kube_controller_pod{namespace=~\"$namespace\"}[$__range]))\n  )\n) \n/ count by (namespace) (sum by (namespace, controller) (avg_over_time(kube_controller_pod{namespace=~\"$namespace\"}[$__range])))\nor\ncount (avg_over_time(kube_controller_pod{node=~\"$node\", namespace=~\"$namespace\"}[$__range])) by (namespace) * 0",
+          "expr": "100 * count by (namespace) (\n  sum by (namespace, verticalpodautoscaler) (  \n    count by (namespace, controller_name, verticalpodautoscaler) (avg_over_time(vpa_target_recommendation{namespace=~\"$namespace\", container!=\"\"}[$__range]))\n    / on (controller_name, namespace) group_left\n    count by (namespace, controller_name) (avg_over_time(kube_controller_pod{namespace=~\"$namespace\"}[$__range]))\n  )\n) \n/ count by (namespace) (sum by (namespace, controller) (avg_over_time(kube_controller_pod{namespace=~\"$namespace\"}[$__range])))\nor\ncount (avg_over_time(kube_controller_pod{node=~\"$node\", namespace=~\"$namespace\"}[$__range])) by (namespace) * 0",
           "format": "table",
           "hide": false,
           "instant": true,
@@ -878,7 +878,7 @@
           "refId": "B"
         },
         {
-          "expr": "sum by (namespace) (rate(container_cpu_usage_seconds_total{node=~\"$node\", namespace=~\"$namespace\", container!=\"POD\"}[$__range]))\nor\ncount (avg_over_time(kube_controller_pod{node=~\"$node\", namespace=~\"$namespace\"}[$__range])) by (namespace) * 0",
+          "expr": "sum by (namespace) (rate(container_cpu_usage_seconds_total{node=~\"$node\", namespace=~\"$namespace\", container!=\"\"}[$__range]))\nor\ncount (avg_over_time(kube_controller_pod{node=~\"$node\", namespace=~\"$namespace\"}[$__range])) by (namespace) * 0",
           "format": "table",
           "hide": false,
           "instant": true,
@@ -895,7 +895,7 @@
           "refId": "D"
         },
         {
-          "expr": "sum by (namespace)\n  (\n    (\n      sum by(namespace, pod, container) (avg_over_time(kube_pod_container_resource_requests{resource=\"cpu\",unit=\"core\",node=~\"$node\", namespace=~\"$namespace\"}[$__range]))\n      -\n      sum by(namespace, pod, container) (rate(container_cpu_usage_seconds_total{node=~\"$node\", container!=\"POD\", namespace=~\"$namespace\"}[$__range]))\n    ) > 0\n  )\nor count (avg_over_time(kube_controller_pod{node=~\"$node\", namespace=~\"$namespace\"}[$__range])) by (namespace) * 0",
+          "expr": "sum by (namespace)\n  (\n    (\n      sum by(namespace, pod, container) (avg_over_time(kube_pod_container_resource_requests{resource=\"cpu\",unit=\"core\",node=~\"$node\", namespace=~\"$namespace\"}[$__range]))\n      -\n      sum by(namespace, pod, container) (rate(container_cpu_usage_seconds_total{node=~\"$node\", container!=\"\", namespace=~\"$namespace\"}[$__range]))\n    ) > 0\n  )\nor count (avg_over_time(kube_controller_pod{node=~\"$node\", namespace=~\"$namespace\"}[$__range])) by (namespace) * 0",
           "format": "table",
           "instant": true,
           "intervalFactor": 1,
@@ -903,7 +903,7 @@
           "refId": "E"
         },
         {
-          "expr": "sum by (namespace)\n  (\n    (\n      (\n        sum by(namespace, pod, container) (rate(container_cpu_usage_seconds_total{node=~\"$node\", container!=\"POD\", namespace=~\"$namespace\"}[$__range]))\n        -\n        sum by(namespace, pod, container) (avg_over_time(kube_pod_container_resource_requests{resource=\"cpu\",unit=\"core\",node=~\"$node\", namespace=~\"$namespace\"}[$__range]))\n      ) or sum by(namespace, pod, container) (rate(container_cpu_usage_seconds_total{node=~\"$node\", container!=\"POD\", namespace=~\"$namespace\"}[$__range]))\n    )\n    > 0\n  )\nor count (avg_over_time(kube_controller_pod{node=~\"$node\", namespace=~\"$namespace\"}[$__range])) by (namespace) * 0",
+          "expr": "sum by (namespace)\n  (\n    (\n      (\n        sum by(namespace, pod, container) (rate(container_cpu_usage_seconds_total{node=~\"$node\", container!=\"\", namespace=~\"$namespace\"}[$__range]))\n        -\n        sum by(namespace, pod, container) (avg_over_time(kube_pod_container_resource_requests{resource=\"cpu\",unit=\"core\",node=~\"$node\", namespace=~\"$namespace\"}[$__range]))\n      ) or sum by(namespace, pod, container) (rate(container_cpu_usage_seconds_total{node=~\"$node\", container!=\"\", namespace=~\"$namespace\"}[$__range]))\n    )\n    > 0\n  )\nor count (avg_over_time(kube_controller_pod{node=~\"$node\", namespace=~\"$namespace\"}[$__range])) by (namespace) * 0",
           "format": "table",
           "instant": true,
           "intervalFactor": 1,
@@ -919,7 +919,7 @@
           "refId": "G"
         },
         {
-          "expr": "sum by (namespace) (avg_over_time(container_memory_working_set_bytes:without_kmem{node=~\"$node\", namespace=~\"$namespace\", container!=\"POD\"}[$__range]))\nor\ncount (avg_over_time(kube_controller_pod{node=~\"$node\", namespace=~\"$namespace\"}[$__range])) by (namespace) * 0",
+          "expr": "sum by (namespace) (avg_over_time(container_memory_working_set_bytes:without_kmem{node=~\"$node\", namespace=~\"$namespace\", container!=\"\"}[$__range]))\nor\ncount (avg_over_time(kube_controller_pod{node=~\"$node\", namespace=~\"$namespace\"}[$__range])) by (namespace) * 0",
           "format": "table",
           "instant": true,
           "intervalFactor": 1,
@@ -935,7 +935,7 @@
           "refId": "I"
         },
         {
-          "expr": "sum by (namespace)\n  (\n    (\n      sum by(namespace, pod, container) (avg_over_time(kube_pod_container_resource_requests{resource=\"memory\",unit=\"byte\",node=~\"$node\", namespace=~\"$namespace\"}[$__range]))\n      -\n      sum by(namespace, pod, container) (avg_over_time(container_memory_working_set_bytes:without_kmem{node=~\"$node\", container!=\"POD\", namespace=~\"$namespace\"}[$__range]))\n    ) > 0\n  )\nor\ncount(avg_over_time(kube_controller_pod{node=~\"$node\", namespace=~\"$namespace\"}[$__range])) by (namespace) * 0",
+          "expr": "sum by (namespace)\n  (\n    (\n      sum by(namespace, pod, container) (avg_over_time(kube_pod_container_resource_requests{resource=\"memory\",unit=\"byte\",node=~\"$node\", namespace=~\"$namespace\"}[$__range]))\n      -\n      sum by(namespace, pod, container) (avg_over_time(container_memory_working_set_bytes:without_kmem{node=~\"$node\", container!=\"\", namespace=~\"$namespace\"}[$__range]))\n    ) > 0\n  )\nor\ncount(avg_over_time(kube_controller_pod{node=~\"$node\", namespace=~\"$namespace\"}[$__range])) by (namespace) * 0",
           "format": "table",
           "instant": true,
           "intervalFactor": 1,
@@ -943,7 +943,7 @@
           "refId": "J"
         },
         {
-          "expr": "sum by (namespace)\n  (\n    (\n      (\n        sum by(namespace, pod, container) (avg_over_time(container_memory_working_set_bytes:without_kmem{node=~\"$node\", container!=\"POD\", namespace=~\"$namespace\"}[$__range]))\n        -\n        sum by(namespace, pod, container) (avg_over_time(kube_pod_container_resource_requests{resource=\"memory\",unit=\"byte\",node=~\"$node\", namespace=~\"$namespace\"}[$__range]))\n      ) or sum by(namespace, pod, container) (avg_over_time(container_memory_working_set_bytes:without_kmem{node=~\"$node\", container!=\"POD\", namespace=~\"$namespace\"}[$__range]))\n    )\n    > 0\n  )\nor count (avg_over_time(kube_controller_pod{node=~\"$node\", namespace=~\"$namespace\"}[$__range])) by (namespace) * 0",
+          "expr": "sum by (namespace)\n  (\n    (\n      (\n        sum by(namespace, pod, container) (avg_over_time(container_memory_working_set_bytes:without_kmem{node=~\"$node\", container!=\"\", namespace=~\"$namespace\"}[$__range]))\n        -\n        sum by(namespace, pod, container) (avg_over_time(kube_pod_container_resource_requests{resource=\"memory\",unit=\"byte\",node=~\"$node\", namespace=~\"$namespace\"}[$__range]))\n      ) or sum by(namespace, pod, container) (avg_over_time(container_memory_working_set_bytes:without_kmem{node=~\"$node\", container!=\"\", namespace=~\"$namespace\"}[$__range]))\n    )\n    > 0\n  )\nor count (avg_over_time(kube_controller_pod{node=~\"$node\", namespace=~\"$namespace\"}[$__range])) by (namespace) * 0",
           "format": "table",
           "instant": true,
           "intervalFactor": 1,
@@ -968,7 +968,7 @@
           "refId": "M"
         },
         {
-          "expr": "sum by (namespace) (rate(container_fs_reads_total{node=~\"$node\", namespace=~\"$namespace\", container!=\"POD\"}[$__range]))\nor\ncount (avg_over_time(kube_controller_pod{node=~\"$node\", namespace=~\"$namespace\"}[$__range])) by (namespace) * 0",
+          "expr": "sum by (namespace) (rate(container_fs_reads_total{node=~\"$node\", namespace=~\"$namespace\", container!=\"\"}[$__range]))\nor\ncount (avg_over_time(kube_controller_pod{node=~\"$node\", namespace=~\"$namespace\"}[$__range])) by (namespace) * 0",
           "format": "table",
           "hide": false,
           "instant": true,
@@ -977,7 +977,7 @@
           "refId": "N"
         },
         {
-          "expr": "sum by (namespace) (rate(container_fs_writes_total{node=~\"$node\", namespace=~\"$namespace\", container!=\"POD\"}[$__range]))\nor\ncount (avg_over_time(kube_controller_pod{node=~\"$node\", namespace=~\"$namespace\"}[$__range])) by (namespace) * 0",
+          "expr": "sum by (namespace) (rate(container_fs_writes_total{node=~\"$node\", namespace=~\"$namespace\", container!=\"\"}[$__range]))\nor\ncount (avg_over_time(kube_controller_pod{node=~\"$node\", namespace=~\"$namespace\"}[$__range])) by (namespace) * 0",
           "format": "table",
           "hide": false,
           "instant": true,
@@ -1449,7 +1449,7 @@
             "type": "prometheus",
             "uid": "$ds_prometheus"
           },
-          "expr": "sum by (namespace) (rate(container_cpu_usage_seconds_total{node=~\"$node\", namespace=~\"$namespace\", container!=\"POD\"}[$__rate_interval]))",
+          "expr": "sum by (namespace) (rate(container_cpu_usage_seconds_total{node=~\"$node\", namespace=~\"$namespace\", container!=\"\"}[$__rate_interval]))",
           "format": "time_series",
           "intervalFactor": 1,
           "legendFormat": "{{ namespace }}",
@@ -1616,7 +1616,7 @@
             "type": "prometheus",
             "uid": "$ds_prometheus"
           },
-          "expr": "sum (rate(container_cpu_system_seconds_total{node=~\"$node\", namespace=~\"$namespace\", container!=\"POD\"}[$__rate_interval]))",
+          "expr": "sum (rate(container_cpu_system_seconds_total{node=~\"$node\", namespace=~\"$namespace\", container!=\"\"}[$__rate_interval]))",
           "format": "time_series",
           "intervalFactor": 1,
           "legendFormat": "System",
@@ -1627,7 +1627,7 @@
             "type": "prometheus",
             "uid": "$ds_prometheus"
           },
-          "expr": "sum (rate(container_cpu_user_seconds_total{node=~\"$node\", namespace=~\"$namespace\", container!=\"POD\"}[$__rate_interval]))",
+          "expr": "sum (rate(container_cpu_user_seconds_total{node=~\"$node\", namespace=~\"$namespace\", container!=\"\"}[$__rate_interval]))",
           "format": "time_series",
           "intervalFactor": 1,
           "legendFormat": "User",
@@ -1764,7 +1764,7 @@
             "type": "prometheus",
             "uid": "$ds_prometheus"
           },
-          "expr": "sum by (namespace)\n  (\n    (\n      sum by(namespace, pod, container) (avg_over_time(kube_pod_container_resource_requests{resource=\"cpu\",unit=\"core\",node=~\"$node\", namespace=~\"$namespace\"}[$__rate_interval]))\n      -\n      sum by(namespace, pod, container) (rate(container_cpu_usage_seconds_total{node=~\"$node\", container!=\"POD\", namespace=~\"$namespace\"}[$__rate_interval]))\n    ) > 0\n  )",
+          "expr": "sum by (namespace)\n  (\n    (\n      sum by(namespace, pod, container) (avg_over_time(kube_pod_container_resource_requests{resource=\"cpu\",unit=\"core\",node=~\"$node\", namespace=~\"$namespace\"}[$__rate_interval]))\n      -\n      sum by(namespace, pod, container) (rate(container_cpu_usage_seconds_total{node=~\"$node\", container!=\"\", namespace=~\"$namespace\"}[$__rate_interval]))\n    ) > 0\n  )",
           "format": "time_series",
           "intervalFactor": 1,
           "legendFormat": "{{ namespace }}",
@@ -1901,7 +1901,7 @@
             "type": "prometheus",
             "uid": "$ds_prometheus"
           },
-          "expr": "sum by (namespace)\n  (\n    (\n      (\n        sum by(namespace, pod, container) (rate(container_cpu_usage_seconds_total{node=~\"$node\", container!=\"POD\", namespace=~\"$namespace\"}[$__rate_interval]))\n        -\n        sum by(namespace, pod, container) (avg_over_time(kube_pod_container_resource_requests{resource=\"cpu\",unit=\"core\",node=~\"$node\", namespace=~\"$namespace\"}[$__rate_interval]))\n      ) or sum by(namespace, pod, container) (rate(container_cpu_usage_seconds_total{node=~\"$node\", container!=\"POD\", namespace=~\"$namespace\"}[$__rate_interval]))\n    )\n    > 0\n  )",
+          "expr": "sum by (namespace)\n  (\n    (\n      (\n        sum by(namespace, pod, container) (rate(container_cpu_usage_seconds_total{node=~\"$node\", container!=\"\", namespace=~\"$namespace\"}[$__rate_interval]))\n        -\n        sum by(namespace, pod, container) (avg_over_time(kube_pod_container_resource_requests{resource=\"cpu\",unit=\"core\",node=~\"$node\", namespace=~\"$namespace\"}[$__rate_interval]))\n      ) or sum by(namespace, pod, container) (rate(container_cpu_usage_seconds_total{node=~\"$node\", container!=\"\", namespace=~\"$namespace\"}[$__rate_interval]))\n    )\n    > 0\n  )",
           "format": "time_series",
           "intervalFactor": 1,
           "legendFormat": "{{ namespace }}",
@@ -2210,7 +2210,7 @@
           "repeatDirection": "h",
           "targets": [
             {
-              "expr": "sum by (namespace) (rate(container_cpu_usage_seconds_total{node=~\"$node\", namespace=\"$namespace\", container!=\"POD\"}[$__rate_interval]))",
+              "expr": "sum by (namespace) (rate(container_cpu_usage_seconds_total{node=~\"$node\", namespace=\"$namespace\", container!=\"\"}[$__rate_interval]))",
               "format": "time_series",
               "interval": "",
               "intervalFactor": 1,
@@ -2218,21 +2218,21 @@
               "refId": "A"
             },
             {
-              "expr": "sum by (namespace) (avg_over_time(kube_pod_container_resource_requests{resource=\"cpu\",unit=\"core\",node=~\"$node\", container!=\"POD\", namespace=\"$namespace\"}[$__rate_interval])* on (uid) group_left(phase) kube_pod_status_phase{phase=\"Running\"})",
+              "expr": "sum by (namespace) (avg_over_time(kube_pod_container_resource_requests{resource=\"cpu\",unit=\"core\",node=~\"$node\", container!=\"\", namespace=\"$namespace\"}[$__rate_interval])* on (uid) group_left(phase) kube_pod_status_phase{phase=\"Running\"})",
               "format": "time_series",
               "intervalFactor": 1,
               "legendFormat": "Requests",
               "refId": "B"
             },
             {
-              "expr": "sum by (namespace) (avg_over_time(kube_pod_container_resource_limits{resource=\"cpu\",unit=\"core\",node=~\"$node\", container!=\"POD\", namespace=\"$namespace\"}[$__rate_interval])* on (uid) group_left(phase) kube_pod_status_phase{phase=\"Running\"})",
+              "expr": "sum by (namespace) (avg_over_time(kube_pod_container_resource_limits{resource=\"cpu\",unit=\"core\",node=~\"$node\", container!=\"\", namespace=\"$namespace\"}[$__rate_interval])* on (uid) group_left(phase) kube_pod_status_phase{phase=\"Running\"})",
               "format": "time_series",
               "intervalFactor": 1,
               "legendFormat": "Limits",
               "refId": "C"
             },
             {
-              "expr": "sum by (namespace) (avg_over_time(vpa_target_recommendation{container!=\"POD\", namespace=\"$namespace\", resource=\"cpu\"}[$__rate_interval]))",
+              "expr": "sum by (namespace) (avg_over_time(vpa_target_recommendation{container!=\"\", namespace=\"$namespace\", resource=\"cpu\"}[$__rate_interval]))",
               "format": "time_series",
               "intervalFactor": 1,
               "legendFormat": "VPA Target",
@@ -2407,7 +2407,7 @@
                 "type": "prometheus",
                 "uid": "$ds_prometheus"
               },
-              "expr": "sum by (namespace) (rate(container_cpu_system_seconds_total{node=~\"$node\", namespace=\"$namespace\", container!=\"POD\"}[$__rate_interval]))",
+              "expr": "sum by (namespace) (rate(container_cpu_system_seconds_total{node=~\"$node\", namespace=\"$namespace\", container!=\"\"}[$__rate_interval]))",
               "format": "time_series",
               "interval": "",
               "intervalFactor": 1,
@@ -2419,7 +2419,7 @@
                 "type": "prometheus",
                 "uid": "$ds_prometheus"
               },
-              "expr": "sum by (namespace) (rate(container_cpu_user_seconds_total{node=~\"$node\", namespace=\"$namespace\", container!=\"POD\"}[$__rate_interval]))",
+              "expr": "sum by (namespace) (rate(container_cpu_user_seconds_total{node=~\"$node\", namespace=\"$namespace\", container!=\"\"}[$__rate_interval]))",
               "format": "time_series",
               "intervalFactor": 1,
               "legendFormat": "User",
@@ -2572,7 +2572,7 @@
             "type": "prometheus",
             "uid": "$ds_prometheus"
           },
-          "expr": "sum by (namespace) (avg_over_time(container_memory_working_set_bytes:without_kmem{node=~\"$node\", namespace=~\"$namespace\", container!=\"POD\"}[$__rate_interval]))",
+          "expr": "sum by (namespace) (avg_over_time(container_memory_working_set_bytes:without_kmem{node=~\"$node\", namespace=~\"$namespace\", container!=\"\"}[$__rate_interval]))",
           "format": "time_series",
           "intervalFactor": 1,
           "legendFormat": "{{ namespace }}",
@@ -2754,14 +2754,14 @@
       "pluginVersion": "8.5.13",
       "targets": [
         {
-          "expr": "sum (avg_over_time(container_memory_rss{node=~\"$node\", namespace=~\"$namespace\", container!=\"POD\"}[$__rate_interval]))",
+          "expr": "sum (avg_over_time(container_memory_rss{node=~\"$node\", namespace=~\"$namespace\", container!=\"\"}[$__rate_interval]))",
           "format": "time_series",
           "intervalFactor": 1,
           "legendFormat": "RSS",
           "refId": "A"
         },
         {
-          "expr": "sum (avg_over_time(container_memory_cache{node=~\"$node\", namespace=~\"$namespace\", container!=\"POD\"}[$__rate_interval]))",
+          "expr": "sum (avg_over_time(container_memory_cache{node=~\"$node\", namespace=~\"$namespace\", container!=\"\"}[$__rate_interval]))",
           "format": "time_series",
           "interval": "",
           "intervalFactor": 1,
@@ -2769,7 +2769,7 @@
           "refId": "B"
         },
         {
-          "expr": "sum (avg_over_time(container_memory_swap{node=~\"$node\", namespace=~\"$namespace\", container!=\"POD\"}[$__rate_interval]))",
+          "expr": "sum (avg_over_time(container_memory_swap{node=~\"$node\", namespace=~\"$namespace\", container!=\"\"}[$__rate_interval]))",
           "format": "time_series",
           "interval": "",
           "intervalFactor": 1,
@@ -2777,14 +2777,14 @@
           "refId": "C"
         },
         {
-          "expr": "sum (avg_over_time(container_memory_working_set_bytes:without_kmem{node=~\"$node\", namespace=~\"$namespace\", container!=\"POD\"}[$__rate_interval]))",
+          "expr": "sum (avg_over_time(container_memory_working_set_bytes:without_kmem{node=~\"$node\", namespace=~\"$namespace\", container!=\"\"}[$__rate_interval]))",
           "format": "time_series",
           "intervalFactor": 1,
           "legendFormat": "Working set bytes without kmem",
           "refId": "D"
         },
         {
-          "expr": "sum (avg_over_time(container_memory:kmem{node=~\"$node\", namespace=~\"$namespace\", container!=\"POD\"}[$__rate_interval]))",
+          "expr": "sum (avg_over_time(container_memory:kmem{node=~\"$node\", namespace=~\"$namespace\", container!=\"\"}[$__rate_interval]))",
           "format": "time_series",
           "intervalFactor": 1,
           "legendFormat": "Kmem",
@@ -2910,7 +2910,7 @@
             "type": "prometheus",
             "uid": "$ds_prometheus"
           },
-          "expr": "sum by (namespace)\n  (\n    (\n      sum by(namespace, pod, container) (avg_over_time(kube_pod_container_resource_requests{resource=\"memory\",unit=\"byte\",node=~\"$node\", namespace=~\"$namespace\"}[$__rate_interval]))\n      -\n      sum by(namespace, pod, container) (avg_over_time(container_memory_working_set_bytes:without_kmem{node=~\"$node\", container!=\"POD\", namespace=~\"$namespace\"}[$__rate_interval]))\n    ) > 0\n  )",
+          "expr": "sum by (namespace)\n  (\n    (\n      sum by(namespace, pod, container) (avg_over_time(kube_pod_container_resource_requests{resource=\"memory\",unit=\"byte\",node=~\"$node\", namespace=~\"$namespace\"}[$__rate_interval]))\n      -\n      sum by(namespace, pod, container) (avg_over_time(container_memory_working_set_bytes:without_kmem{node=~\"$node\", container!=\"\", namespace=~\"$namespace\"}[$__rate_interval]))\n    ) > 0\n  )",
           "format": "time_series",
           "intervalFactor": 1,
           "legendFormat": "{{ namespace }}",
@@ -3046,7 +3046,7 @@
             "type": "prometheus",
             "uid": "$ds_prometheus"
           },
-          "expr": "sum by (namespace)\n  (\n    (\n      (\n        sum by(namespace, pod, container) (avg_over_time(container_memory_working_set_bytes:without_kmem{node=~\"$node\", container!=\"POD\", namespace=~\"$namespace\"}[$__rate_interval]))\n        -\n        sum by(namespace, pod, container) (avg_over_time(kube_pod_container_resource_requests{resource=\"memory\",unit=\"byte\",node=~\"$node\", namespace=~\"$namespace\"}[$__rate_interval]))\n      ) or sum by(namespace, pod, container) (avg_over_time(container_memory_working_set_bytes:without_kmem{node=~\"$node\", container!=\"POD\", namespace=~\"$namespace\"}[$__rate_interval]))\n    )\n    > 0\n  )",
+          "expr": "sum by (namespace)\n  (\n    (\n      (\n        sum by(namespace, pod, container) (avg_over_time(container_memory_working_set_bytes:without_kmem{node=~\"$node\", container!=\"\", namespace=~\"$namespace\"}[$__rate_interval]))\n        -\n        sum by(namespace, pod, container) (avg_over_time(kube_pod_container_resource_requests{resource=\"memory\",unit=\"byte\",node=~\"$node\", namespace=~\"$namespace\"}[$__rate_interval]))\n      ) or sum by(namespace, pod, container) (avg_over_time(container_memory_working_set_bytes:without_kmem{node=~\"$node\", container!=\"\", namespace=~\"$namespace\"}[$__rate_interval]))\n    )\n    > 0\n  )",
           "format": "time_series",
           "intervalFactor": 1,
           "legendFormat": "{{ namespace }}",
@@ -3370,14 +3370,14 @@
           "repeatDirection": "h",
           "targets": [
             {
-              "expr": "sum by (namespace) (avg_over_time(container_memory_rss{node=~\"$node\", namespace=\"$namespace\", container!=\"POD\"}[$__rate_interval]))",
+              "expr": "sum by (namespace) (avg_over_time(container_memory_rss{node=~\"$node\", namespace=\"$namespace\", container!=\"\"}[$__rate_interval]))",
               "format": "time_series",
               "intervalFactor": 1,
               "legendFormat": "RSS",
               "refId": "A"
             },
             {
-              "expr": "sum by (namespace) (avg_over_time(container_memory_cache{node=~\"$node\", namespace=\"$namespace\", container!=\"POD\"}[$__rate_interval]))",
+              "expr": "sum by (namespace) (avg_over_time(container_memory_cache{node=~\"$node\", namespace=\"$namespace\", container!=\"\"}[$__rate_interval]))",
               "format": "time_series",
               "interval": "",
               "intervalFactor": 1,
@@ -3385,7 +3385,7 @@
               "refId": "B"
             },
             {
-              "expr": "sum by (namespace) (avg_over_time(container_memory_swap{node=~\"$node\", namespace=\"$namespace\", container!=\"POD\"}[$__rate_interval]))",
+              "expr": "sum by (namespace) (avg_over_time(container_memory_swap{node=~\"$node\", namespace=\"$namespace\", container!=\"\"}[$__rate_interval]))",
               "format": "time_series",
               "interval": "",
               "intervalFactor": 1,
@@ -3393,35 +3393,35 @@
               "refId": "C"
             },
             {
-              "expr": "sum by (namespace) (avg_over_time(container_memory_working_set_bytes:without_kmem{node=~\"$node\", namespace=\"$namespace\", container!=\"POD\"}[$__rate_interval]))",
+              "expr": "sum by (namespace) (avg_over_time(container_memory_working_set_bytes:without_kmem{node=~\"$node\", namespace=\"$namespace\", container!=\"\"}[$__rate_interval]))",
               "format": "time_series",
               "intervalFactor": 1,
               "legendFormat": "Working set bytes without kmem",
               "refId": "D"
             },
             {
-              "expr": "sum by(namespace) (avg_over_time(vpa_target_recommendation{container!=\"POD\",namespace=\"$namespace\", resource=\"memory\"}[$__rate_interval]))",
+              "expr": "sum by(namespace) (avg_over_time(vpa_target_recommendation{container!=\"\",namespace=\"$namespace\", resource=\"memory\"}[$__rate_interval]))",
               "format": "time_series",
               "intervalFactor": 1,
               "legendFormat": "VPA Target",
               "refId": "E"
             },
             {
-              "expr": "sum by(namespace) (avg_over_time(kube_pod_container_resource_requests{resource=\"memory\",unit=\"byte\",node=~\"$node\", container!=\"POD\", namespace=\"$namespace\"}[$__rate_interval]))",
+              "expr": "sum by(namespace) (avg_over_time(kube_pod_container_resource_requests{resource=\"memory\",unit=\"byte\",node=~\"$node\", container!=\"\", namespace=\"$namespace\"}[$__rate_interval]))",
               "format": "time_series",
               "intervalFactor": 1,
               "legendFormat": "Requests",
               "refId": "F"
             },
             {
-              "expr": "sum by(namespace) (avg_over_time(kube_pod_container_resource_limits{resource=\"memory\",unit=\"byte\",node=~\"$node\", container!=\"POD\", namespace=\"$namespace\"}[$__rate_interval]))",
+              "expr": "sum by(namespace) (avg_over_time(kube_pod_container_resource_limits{resource=\"memory\",unit=\"byte\",node=~\"$node\", container!=\"\", namespace=\"$namespace\"}[$__rate_interval]))",
               "format": "time_series",
               "intervalFactor": 1,
               "legendFormat": "Limits",
               "refId": "G"
             },
             {
-              "expr": "sum by (namespace) (avg_over_time(container_memory:kmem{node=~\"$node\", namespace=\"$namespace\", container!=\"POD\"}[$__rate_interval]))",
+              "expr": "sum by (namespace) (avg_over_time(container_memory:kmem{node=~\"$node\", namespace=\"$namespace\", container!=\"\"}[$__rate_interval]))",
               "format": "time_series",
               "intervalFactor": 1,
               "legendFormat": "Kmem",
@@ -3873,7 +3873,7 @@
             "type": "prometheus",
             "uid": "$ds_prometheus"
           },
-          "expr": "sum by (namespace) (rate(container_fs_reads_total{node=~\"$node\", namespace=~\"$namespace\", container!=\"POD\"}[$__rate_interval]))",
+          "expr": "sum by (namespace) (rate(container_fs_reads_total{node=~\"$node\", namespace=~\"$namespace\", container!=\"\"}[$__rate_interval]))",
           "format": "time_series",
           "intervalFactor": 1,
           "legendFormat": "{{ namespace }}",
@@ -4008,7 +4008,7 @@
             "type": "prometheus",
             "uid": "$ds_prometheus"
           },
-          "expr": "sum by (namespace) (rate(container_fs_writes_total{node=~\"$node\", namespace=~\"$namespace\", container!=\"POD\"}[$__rate_interval]))",
+          "expr": "sum by (namespace) (rate(container_fs_writes_total{node=~\"$node\", namespace=~\"$namespace\", container!=\"\"}[$__rate_interval]))",
           "format": "time_series",
           "intervalFactor": 1,
           "legendFormat": "{{ namespace }}",

dashboards/main/pod.json

@@ -686,7 +686,7 @@
             "type": "prometheus",
             "uid": "${ds_prometheus}"
           },
-          "expr": "sum by (container) (rate(container_cpu_usage_seconds_total{namespace=\"$namespace\", pod=\"$pod\", container!=\"POD\", container=~\"$container\"}[$__range]))\nor\nsum by (container) (avg_over_time(kube_pod_container_info{namespace=\"$namespace\", pod=\"$pod\", container=~\"$container\"}[$__range]) * 0)",
+          "expr": "sum by (container) (rate(container_cpu_usage_seconds_total{namespace=\"$namespace\", pod=\"$pod\", container!=\"\", container=~\"$container\"}[$__range]))\nor\nsum by (container) (avg_over_time(kube_pod_container_info{namespace=\"$namespace\", pod=\"$pod\", container=~\"$container\"}[$__range]) * 0)",
           "format": "table",
           "hide": false,
           "instant": true,
@@ -759,7 +759,7 @@
             "type": "prometheus",
             "uid": "${ds_prometheus}"
           },
-          "expr": "sum by (container) (avg_over_time(container_memory_working_set_bytes:without_kmem{namespace=\"$namespace\", pod=\"$pod\", container!=\"POD\", container=~\"$container\"}[$__range]))\nor\nsum by (container) (avg_over_time(kube_pod_container_info{namespace=\"$namespace\", pod=\"$pod\", container=~\"$container\"}[$__range]) * 0)",
+          "expr": "sum by (container) (avg_over_time(container_memory_working_set_bytes:without_kmem{namespace=\"$namespace\", pod=\"$pod\", container!=\"\", container=~\"$container\"}[$__range]))\nor\nsum by (container) (avg_over_time(kube_pod_container_info{namespace=\"$namespace\", pod=\"$pod\", container=~\"$container\"}[$__range]) * 0)",
           "format": "table",
           "instant": true,
           "intervalFactor": 1,
@@ -847,7 +847,7 @@
             "type": "prometheus",
             "uid": "${ds_prometheus}"
           },
-          "expr": "sum by(container) (rate(container_fs_reads_total{namespace=\"$namespace\", pod=\"$pod\", container!=\"POD\"}[$__range]))",
+          "expr": "sum by(container) (rate(container_fs_reads_total{namespace=\"$namespace\", pod=\"$pod\", container!=\"\"}[$__range]))",
           "format": "table",
           "hide": false,
           "instant": true,
@@ -860,7 +860,7 @@
             "type": "prometheus",
             "uid": "${ds_prometheus}"
           },
-          "expr": "sum by(container) (rate(container_fs_writes_total{namespace=\"$namespace\", pod=\"$pod\", container!=\"POD\"}[$__range]))",
+          "expr": "sum by(container) (rate(container_fs_writes_total{namespace=\"$namespace\", pod=\"$pod\", container!=\"\"}[$__range]))",
           "format": "table",
           "hide": false,
           "instant": true,
@@ -899,7 +899,7 @@
             "type": "prometheus",
             "uid": "${ds_prometheus}"
           },
-          "expr": "sum by (container) (avg_over_time(container_memory:kmem{namespace=\"$namespace\", pod=\"$pod\", container!=\"POD\", container=~\"$container\"}[$__range]))\nor\nsum by (container) (avg_over_time(kube_pod_container_info{namespace=\"$namespace\", pod=\"$pod\", container=~\"$container\"}[$__range]) * 0)",
+          "expr": "sum by (container) (avg_over_time(container_memory:kmem{namespace=\"$namespace\", pod=\"$pod\", container!=\"\", container=~\"$container\"}[$__range]))\nor\nsum by (container) (avg_over_time(kube_pod_container_info{namespace=\"$namespace\", pod=\"$pod\", container=~\"$container\"}[$__range]) * 0)",
           "format": "table",
           "instant": true,
           "intervalFactor": 1,
@@ -1503,7 +1503,7 @@
             "type": "prometheus",
             "uid": "$ds_prometheus"
           },
-          "expr": "sum by(container) (rate(container_cpu_usage_seconds_total{container!=\"POD\", pod=\"$pod\", namespace=\"$namespace\"}[$__rate_interval]))",
+          "expr": "sum by(container) (rate(container_cpu_usage_seconds_total{container!=\"\", pod=\"$pod\", namespace=\"$namespace\"}[$__rate_interval]))",
           "format": "time_series",
           "instant": false,
           "intervalFactor": 1,
@@ -1669,7 +1669,7 @@
             "type": "prometheus",
             "uid": "$ds_prometheus"
           },
-          "expr": "sum by(pod) (rate(container_cpu_system_seconds_total{container!=\"POD\", pod=\"$pod\", namespace=\"$namespace\"}[$__rate_interval]))",
+          "expr": "sum by(pod) (rate(container_cpu_system_seconds_total{container!=\"\", pod=\"$pod\", namespace=\"$namespace\"}[$__rate_interval]))",
           "format": "time_series",
           "instant": false,
           "intervalFactor": 1,
@@ -1681,7 +1681,7 @@
             "type": "prometheus",
             "uid": "$ds_prometheus"
           },
-          "expr": "sum by(pod) (rate(container_cpu_user_seconds_total{container!=\"POD\", pod=\"$pod\", namespace=\"$namespace\"}[$__rate_interval]))",
+          "expr": "sum by(pod) (rate(container_cpu_user_seconds_total{container!=\"\", pod=\"$pod\", namespace=\"$namespace\"}[$__rate_interval]))",
           "format": "time_series",
           "intervalFactor": 1,
           "legendFormat": "User",
@@ -1820,7 +1820,7 @@
             "type": "prometheus",
             "uid": "$ds_prometheus"
           },
-          "expr": "sum by (namespace, pod, container)\n  (\n    (\n      sum by(namespace, pod, container) (avg_over_time(kube_pod_container_resource_requests{resource=\"cpu\",unit=\"core\",namespace=\"$namespace\", pod=\"$pod\", container=~\"$container\"}[$__rate_interval]))\n      -\n      sum by(namespace, pod, container) (rate(container_cpu_usage_seconds_total{container!=\"POD\", namespace=\"$namespace\", pod=\"$pod\", container=~\"$container\"}[$__rate_interval]))\n    ) > 0\n  )",
+          "expr": "sum by (namespace, pod, container)\n  (\n    (\n      sum by(namespace, pod, container) (avg_over_time(kube_pod_container_resource_requests{resource=\"cpu\",unit=\"core\",namespace=\"$namespace\", pod=\"$pod\", container=~\"$container\"}[$__rate_interval]))\n      -\n      sum by(namespace, pod, container) (rate(container_cpu_usage_seconds_total{container!=\"\", namespace=\"$namespace\", pod=\"$pod\", container=~\"$container\"}[$__rate_interval]))\n    ) > 0\n  )",
           "format": "time_series",
           "hide": false,
           "intervalFactor": 1,
@@ -2269,7 +2269,7 @@
           "repeatDirection": "h",
           "targets": [
             {
-              "expr": "sum by(container) (rate(container_cpu_usage_seconds_total{namespace=\"$namespace\", pod=\"$pod\", container!=\"POD\", container=\"$container\"}[$__rate_interval]))",
+              "expr": "sum by(container) (rate(container_cpu_usage_seconds_total{namespace=\"$namespace\", pod=\"$pod\", container!=\"\", container=\"$container\"}[$__rate_interval]))",
               "format": "time_series",
               "intervalFactor": 1,
               "legendFormat": "Usage",
@@ -2476,7 +2476,7 @@
             "type": "prometheus",
             "uid": "$ds_prometheus"
           },
-          "expr": "sum by(container) (rate(container_cpu_system_seconds_total{container!=\"POD\", pod=\"$pod\", namespace=\"$namespace\", container=\"$container\"}[$__rate_interval]))",
+          "expr": "sum by(container) (rate(container_cpu_system_seconds_total{container!=\"\", pod=\"$pod\", namespace=\"$namespace\", container=\"$container\"}[$__rate_interval]))",
           "format": "time_series",
           "instant": false,
           "intervalFactor": 1,
@@ -2488,7 +2488,7 @@
             "type": "prometheus",
             "uid": "$ds_prometheus"
           },
-          "expr": "sum by(container) (rate(container_cpu_user_seconds_total{container!=\"POD\", pod=\"$pod\", namespace=\"$namespace\", container=\"$container\"}[$__rate_interval]))",
+          "expr": "sum by(container) (rate(container_cpu_user_seconds_total{container!=\"\", pod=\"$pod\", namespace=\"$namespace\", container=\"$container\"}[$__rate_interval]))",
           "format": "time_series",
           "intervalFactor": 1,
           "legendFormat": "User",
@@ -2639,7 +2639,7 @@
             "type": "prometheus",
             "uid": "$ds_prometheus"
           },
-          "expr": "sum by(container) (avg_over_time(container_memory_working_set_bytes:without_kmem{container!=\"POD\", pod=\"$pod\", namespace=\"$namespace\"}[$__rate_interval]))",
+          "expr": "sum by(container) (avg_over_time(container_memory_working_set_bytes:without_kmem{container!=\"\", pod=\"$pod\", namespace=\"$namespace\"}[$__rate_interval]))",
           "format": "time_series",
           "instant": false,
           "intervalFactor": 1,
@@ -2816,7 +2816,7 @@
       "pluginVersion": "8.5.13",
       "targets": [
         {
-          "expr": "sum by(pod) (avg_over_time(container_memory_rss{namespace=\"$namespace\", pod=\"$pod\", container!=\"POD\"}[$__rate_interval]))",
+          "expr": "sum by(pod) (avg_over_time(container_memory_rss{namespace=\"$namespace\", pod=\"$pod\", container!=\"\"}[$__rate_interval]))",
           "format": "time_series",
           "instant": false,
           "intervalFactor": 1,
@@ -2824,28 +2824,28 @@
           "refId": "A"
         },
         {
-          "expr": "sum by(pod) (avg_over_time(container_memory_cache{namespace=\"$namespace\", pod=\"$pod\", container!=\"POD\"}[$__rate_interval]))",
+          "expr": "sum by(pod) (avg_over_time(container_memory_cache{namespace=\"$namespace\", pod=\"$pod\", container!=\"\"}[$__rate_interval]))",
           "format": "time_series",
           "intervalFactor": 1,
           "legendFormat": "Cache",
           "refId": "B"
         },
         {
-          "expr": "sum by(pod) (avg_over_time(container_memory_swap{namespace=\"$namespace\", pod=\"$pod\", container!=\"POD\"}[$__rate_interval]))",
+          "expr": "sum by(pod) (avg_over_time(container_memory_swap{namespace=\"$namespace\", pod=\"$pod\", container!=\"\"}[$__rate_interval]))",
           "format": "time_series",
           "intervalFactor": 1,
           "legendFormat": "Swap",
           "refId": "C"
         },
         {
-          "expr": "sum by(pod) (avg_over_time(container_memory_working_set_bytes:without_kmem{namespace=\"$namespace\", pod=\"$pod\", container!=\"POD\"}[$__rate_interval]))",
+          "expr": "sum by(pod) (avg_over_time(container_memory_working_set_bytes:without_kmem{namespace=\"$namespace\", pod=\"$pod\", container!=\"\"}[$__rate_interval]))",
           "format": "time_series",
           "intervalFactor": 1,
           "legendFormat": "Working set bytes without kmem",
           "refId": "D"
         },
         {
-          "expr": "sum by(pod) (avg_over_time(container_memory:kmem{namespace=\"$namespace\", pod=\"$pod\", container!=\"POD\"}[$__rate_interval]))",
+          "expr": "sum by(pod) (avg_over_time(container_memory:kmem{namespace=\"$namespace\", pod=\"$pod\", container!=\"\"}[$__rate_interval]))",
           "format": "time_series",
           "intervalFactor": 1,
           "legendFormat": "Kmem",
@@ -2974,7 +2974,7 @@
             "type": "prometheus",
             "uid": "$ds_prometheus"
           },
-          "expr": "sum by (container)\n  (\n    (\n      sum by (namespace, pod, container) (avg_over_time(kube_pod_container_resource_requests{resource=\"memory\",unit=\"byte\",namespace=\"$namespace\", pod=\"$pod\", container=~\"$container\"}[$__rate_interval]))\n      -\n      sum by (namespace, pod, container) (avg_over_time(container_memory_working_set_bytes:without_kmem{namespace=\"$namespace\", pod=\"$pod\", container=~\"$container\", container!=\"POD\"}[$__rate_interval]))\n    ) > 0\n  )",
+          "expr": "sum by (container)\n  (\n    (\n      sum by (namespace, pod, container) (avg_over_time(kube_pod_container_resource_requests{resource=\"memory\",unit=\"byte\",namespace=\"$namespace\", pod=\"$pod\", container=~\"$container\"}[$__rate_interval]))\n      -\n      sum by (namespace, pod, container) (avg_over_time(container_memory_working_set_bytes:without_kmem{namespace=\"$namespace\", pod=\"$pod\", container=~\"$container\", container!=\"\"}[$__rate_interval]))\n    ) > 0\n  )",
           "format": "time_series",
           "hide": false,
           "intervalFactor": 1,
@@ -3110,7 +3110,7 @@
             "type": "prometheus",
             "uid": "$ds_prometheus"
           },
-          "expr": "sum by (container)\n  (\n    (\n      (\n        sum by (namespace, pod, container) (avg_over_time(container_memory_working_set_bytes:without_kmem{namespace=\"$namespace\", pod=\"$pod\", container=~\"$container\"}[$__rate_interval]))\n        -\n        sum by (namespace, pod, container) (avg_over_time(kube_pod_container_resource_requests{resource=\"memory\",unit=\"byte\",namespace=\"$namespace\", pod=\"$pod\", container=~\"$container\", container!=\"POD\"}[$__rate_interval]))\n      ) or sum by (namespace, pod, container) (avg_over_time(container_memory_working_set_bytes:without_kmem{namespace=\"$namespace\", pod=\"$pod\", container=~\"$container\", container!=\"POD\"}[$__rate_interval]))\n    ) > 0\n  )",
+          "expr": "sum by (container)\n  (\n    (\n      (\n        sum by (namespace, pod, container) (avg_over_time(container_memory_working_set_bytes:without_kmem{namespace=\"$namespace\", pod=\"$pod\", container=~\"$container\"}[$__rate_interval]))\n        -\n        sum by (namespace, pod, container) (avg_over_time(kube_pod_container_resource_requests{resource=\"memory\",unit=\"byte\",namespace=\"$namespace\", pod=\"$pod\", container=~\"$container\", container!=\"\"}[$__rate_interval]))\n      ) or sum by (namespace, pod, container) (avg_over_time(container_memory_working_set_bytes:without_kmem{namespace=\"$namespace\", pod=\"$pod\", container=~\"$container\", container!=\"\"}[$__rate_interval]))\n    ) > 0\n  )",
           "format": "time_series",
           "hide": false,
           "intervalFactor": 1,
@@ -3431,7 +3431,7 @@
           "repeatDirection": "h",
           "targets": [
             {
-              "expr": "sum by(container) (avg_over_time(container_memory_rss{namespace=\"$namespace\", pod=\"$pod\", container!=\"POD\", container=\"$container\"}[$__rate_interval]))",
+              "expr": "sum by(container) (avg_over_time(container_memory_rss{namespace=\"$namespace\", pod=\"$pod\", container!=\"\", container=\"$container\"}[$__rate_interval]))",
               "format": "time_series",
               "instant": false,
               "intervalFactor": 1,
@@ -3439,7 +3439,7 @@
               "refId": "A"
             },
             {
-              "expr": "sum by(container) (avg_over_time(container_memory_cache{namespace=\"$namespace\", pod=\"$pod\", container!=\"POD\", container=\"$container\"}[$__rate_interval]))",
+              "expr": "sum by(container) (avg_over_time(container_memory_cache{namespace=\"$namespace\", pod=\"$pod\", container!=\"\", container=\"$container\"}[$__rate_interval]))",
               "format": "time_series",
               "interval": "",
               "intervalFactor": 1,
@@ -3447,28 +3447,28 @@
               "refId": "B"
             },
             {
-              "expr": "sum by(container) (avg_over_time(container_memory_swap{namespace=\"$namespace\", pod=\"$pod\", container!=\"POD\", container=\"$container\"}[$__rate_interval]))",
+              "expr": "sum by(container) (avg_over_time(container_memory_swap{namespace=\"$namespace\", pod=\"$pod\", container!=\"\", container=\"$container\"}[$__rate_interval]))",
               "format": "time_series",
               "intervalFactor": 1,
               "legendFormat": "Swap",
               "refId": "C"
             },
             {
-              "expr": "sum by(container) (avg_over_time(container_memory_working_set_bytes:without_kmem{namespace=\"$namespace\", pod=\"$pod\", container!=\"POD\", container=\"$container\"}[$__rate_interval]))",
+              "expr": "sum by(container) (avg_over_time(container_memory_working_set_bytes:without_kmem{namespace=\"$namespace\", pod=\"$pod\", container!=\"\", container=\"$container\"}[$__rate_interval]))",
               "format": "time_series",
               "intervalFactor": 1,
               "legendFormat": "Working set bytes without kmem",
               "refId": "D"
             },
             {
-              "expr": "sum by(container) (avg_over_time(kube_pod_container_resource_limits{resource=\"memory\",unit=\"byte\",namespace=\"$namespace\", pod=\"$pod\", container!=\"POD\", container=\"$container\"}[$__rate_interval]))",
+              "expr": "sum by(container) (avg_over_time(kube_pod_container_resource_limits{resource=\"memory\",unit=\"byte\",namespace=\"$namespace\", pod=\"$pod\", container!=\"\", container=\"$container\"}[$__rate_interval]))",
               "format": "time_series",
               "intervalFactor": 1,
               "legendFormat": "Limits",
               "refId": "E"
             },
             {
-              "expr": "sum by(container) (avg_over_time(kube_pod_container_resource_requests{resource=\"memory\",unit=\"byte\",namespace=\"$namespace\", pod=\"$pod\", container!=\"POD\", container=\"$container\"}[$__rate_interval]))",
+              "expr": "sum by(container) (avg_over_time(kube_pod_container_resource_requests{resource=\"memory\",unit=\"byte\",namespace=\"$namespace\", pod=\"$pod\", container!=\"\", container=\"$container\"}[$__rate_interval]))",
               "format": "time_series",
               "intervalFactor": 1,
               "legendFormat": "Requests",
@@ -3482,7 +3482,7 @@
               "refId": "G"
             },
             {
-              "expr": "sum by(container) (avg_over_time(container_memory:kmem{namespace=\"$namespace\", pod=\"$pod\", container!=\"POD\", container=\"$container\"}[$__rate_interval]))",
+              "expr": "sum by(container) (avg_over_time(container_memory:kmem{namespace=\"$namespace\", pod=\"$pod\", container!=\"\", container=\"$container\"}[$__rate_interval]))",
               "format": "time_series",
               "intervalFactor": 1,
               "legendFormat": "Kmem",
@@ -3930,7 +3930,7 @@
             "type": "prometheus",
             "uid": "$ds_prometheus"
           },
-          "expr": "sum by(container) (rate(container_fs_reads_total{container!=\"POD\", pod=\"$pod\", namespace=\"$namespace\"}[$__rate_interval]))",
+          "expr": "sum by(container) (rate(container_fs_reads_total{container!=\"\", pod=\"$pod\", namespace=\"$namespace\"}[$__rate_interval]))",
           "format": "time_series",
           "intervalFactor": 1,
           "legendFormat": "{{ container }}",
@@ -4068,7 +4068,7 @@
             "type": "prometheus",
             "uid": "$ds_prometheus"
           },
-          "expr": "sum by(container) (rate(container_fs_writes_total{container!=\"POD\", pod=\"$pod\", namespace=\"$namespace\"}[$__rate_interval]))",
+          "expr": "sum by(container) (rate(container_fs_writes_total{container!=\"\", pod=\"$pod\", namespace=\"$namespace\"}[$__rate_interval]))",
           "format": "time_series",
           "intervalFactor": 1,
           "legendFormat": "{{ container }}",

docs/changelogs/v0.31.0.md

@@ -0,0 +1,97 @@
+This is the third release candidate for the upcoming Cozystack v0.31.0 release.
+The release notes show changes accumulated since the release of previous version, Cozystack v0.30.0.
+
+Cozystack 0.31.0 further advances GPU support, monitoring, and all-around convenience features.
+
+## New Features and Changes
+
+* [kubernetes] Introduce GPU support for tenant Kubernetes clusters. (@kvaps in https://github.com/cozystack/cozystack/pull/834)
+* Add VerticalPodAutoscaler to a few more components:
+    * [kubernetes] Kubernetes clusters in user tenants. (@klinch0 in https://github.com/cozystack/cozystack/pull/806)
+    * [platform] Cozystack dashboard. (@klinch0 in https://github.com/cozystack/cozystack/pull/828)
+    * [platform] Cozystack etcd-operator (@klinch0 in https://github.com/cozystack/cozystack/pull/850)
+* Introduce support for cross-architecture builds and Cozystack on ARM:
+    * [build] Refactor Makefiles introducing build variables. (@nbykov0 in https://github.com/cozystack/cozystack/pull/907)
+    * [build] Add support for multi-architecture and cross-platform image builds. (@nbykov0 in https://github.com/cozystack/cozystack/pull/932 and https://github.com/cozystack/cozystack/pull/970)
+* [platform] Introduce a new controller to synchronize tenant HelmReleases and propagate configuration changes. (@klinch0 in https://github.com/cozystack/cozystack/pull/870)
+* [platform] Introduce options `expose-services`, `expose-ingress` and `expose-external-ips` to the ingress service. (@kvaps in https://github.com/cozystack/cozystack/pull/929)
+* [kubevirt] Enable exporting VMs. (@kvaps in https://github.com/cozystack/cozystack/pull/808)
+* [kubevirt] Make KubeVirt's CPU allocation ratio configurable. (@lllamnyp in https://github.com/cozystack/cozystack/pull/905)
+* [virtual-machine] Add support for various storages. (@kvaps in https://github.com/cozystack/cozystack/pull/974)
+* [cozystack-controller] Record the IP address pool and storage class in Workload objects. (@lllamnyp in https://github.com/cozystack/cozystack/pull/831)
+* [cilium] Enable Cilium Gateway API. (@zdenekjanda in https://github.com/cozystack/cozystack/pull/924)
+* [cilium] Enable user-added parameters in a tenant cluster Cilium. (@lllamnyp in https://github.com/cozystack/cozystack/pull/917)
+* [apps] Remove user-facing config of limits and requests. (@lllamnyp in https://github.com/cozystack/cozystack/pull/935)
+* Update the Cozystack release policy to include long-lived release branches and start with release candidates. Update CI workflows and docs accordingly.
+    * Use release branches `release-X.Y` for gathering and releasing fixes after initial `vX.Y.0` release. (@kvaps in https://github.com/cozystack/cozystack/pull/816)
+    * Automatically create release branches after initial `vX.Y.0` release is published. (@kvaps in https://github.com/cozystack/cozystack/pull/886)
+    * Introduce Release Candidate versions. Automate patch backporting by applying patches from pull requests labeled `[backport]` to the current release branch. (@kvaps in https://github.com/cozystack/cozystack/pull/841 and https://github.com/cozystack/cozystack/pull/901, @nickvolynkin in https://github.com/cozystack/cozystack/pull/890)
+    * Support alpha and beta pre-releases. (@kvaps in https://github.com/cozystack/cozystack/pull/978)
+    * Commit changes in release pipelines under `github-actions <github-actions@github.com>`. (@kvaps in https://github.com/cozystack/cozystack/pull/823)
+    * Describe the Cozystack release workflow. (@NickVolynkin in https://github.com/cozystack/cozystack/pull/817 and https://github.com/cozystack/cozystack/pull/897)
+
+## Fixes
+
+* [virtual-machine] Add GPU names to the virtual machine specifications. (@kvaps in https://github.com/cozystack/cozystack/pull/862)
+* [virtual-machine] Count Workload resources for pods by requests, not limits. Other improvements to VM resource tracking. (@lllamnyp in https://github.com/cozystack/cozystack/pull/904)
+* [platform] Fix installing HelmReleases on initial setup. (@kvaps in https://github.com/cozystack/cozystack/pull/833)
+* [platform] Migration scripts update Kubernetes ConfigMap with the current stack version for improved version tracking. (@klinch0 in https://github.com/cozystack/cozystack/pull/840)
+* [platform] Reduce requested CPU and RAM for the `kamaji` provider. (@klinch0 in https://github.com/cozystack/cozystack/pull/825)
+* [platform] Improve the reconciliation loop for the Cozystack system HelmReleases logic. (@klinch0 in https://github.com/cozystack/cozystack/pull/809 and https://github.com/cozystack/cozystack/pull/810, @kvaps in https://github.com/cozystack/cozystack/pull/811)
+* [platform] Remove extra dependencies for the Piraeus operator. (@klinch0 in https://github.com/cozystack/cozystack/pull/856)
+* [platform] Refactor dashboard values. (@kvaps in https://github.com/cozystack/cozystack/pull/928, patched by @llamnyp in https://github.com/cozystack/cozystack/pull/952)
+* [platform] Make FluxCD artifact disabled by default. (@klinch0 in https://github.com/cozystack/cozystack/pull/964)
+* [kubernetes] Update garbage collection of HelmReleases in tenant Kubernetes clusters. (@kvaps in https://github.com/cozystack/cozystack/pull/835)
+* [kubernetes] Fix merging `valuesOverride` for tenant clusters. (@kvaps in https://github.com/cozystack/cozystack/pull/879)
+* [kubernetes] Fix `ubuntu-container-disk` tag. (@kvaps in https://github.com/cozystack/cozystack/pull/887)
+* [kubernetes] Refactor Helm manifests for tenant Kubernetes clusters. (@kvaps in https://github.com/cozystack/cozystack/pull/866)
+* [kubernetes] Fix Ingress-NGINX depends on Cert-Manager . (@kvaps in https://github.com/cozystack/cozystack/pull/976)
+* [tenant] Fix an issue with accessing external IPs of a cluster from the cluster itself. (@kvaps in https://github.com/cozystack/cozystack/pull/854)
+* [cluster-api] Remove the no longer necessary workaround for Kamaji. (@kvaps in https://github.com/cozystack/cozystack/pull/867, patched in https://github.com/cozystack/cozystack/pull/956) 
+* [monitoring] Remove legacy label "POD" from the exclude filter in metrics. (@xy2 in https://github.com/cozystack/cozystack/pull/826)
+* [monitoring] Refactor management etcd monitoring config. Introduce a migration script for updating monitoring resources (`kube-rbac-proxy` daemonset). (@lllamnyp in https://github.com/cozystack/cozystack/pull/799 and https://github.com/cozystack/cozystack/pull/830)
+* [monitoring] Fix VerticalPodAutoscaler resource allocation for VMagent. (@klinch0 in https://github.com/cozystack/cozystack/pull/820)
+* [postgres] Remove duplicated `template` entry from backup manifest. (@etoshutka in https://github.com/cozystack/cozystack/pull/872)
+* [kube-ovn] Fix versions mapping in Makefile. (@kvaps in https://github.com/cozystack/cozystack/pull/883)
+* [dx] Automatically detect version for migrations in the installer.sh. (@kvaps in https://github.com/cozystack/cozystack/pull/837)
+* [e2e] Increase timeout durations for `capi` and `keycloak` to improve reliability during environment setup. (@kvaps in https://github.com/cozystack/cozystack/pull/858)
+* [e2e] Fix `device_ownership_from_security_context` CRI. (@dtrdnk in https://github.com/cozystack/cozystack/pull/896)
+* [e2e] Return `genisoimage` to the e2e-test Dockerfile (@gwynbleidd2106 in https://github.com/cozystack/cozystack/pull/962)
+* [ci] Improve the check for `versions_map` running on pull requests. (@kvaps and @klinch0 in https://github.com/cozystack/cozystack/pull/836, https://github.com/cozystack/cozystack/pull/842, and https://github.com/cozystack/cozystack/pull/845)
+* [ci] If the release step was skipped on a tag, skip tests as well. (@kvaps in https://github.com/cozystack/cozystack/pull/822)
+* [ci] Allow CI to cancel the previous job if a new one is scheduled. (@kvaps in https://github.com/cozystack/cozystack/pull/873)
+* [ci] Use the correct version name when uploading build assets to the release page. (@kvaps in https://github.com/cozystack/cozystack/pull/876)
+* [ci] Stop using `ok-to-test` label to trigger CI in pull requests. (@kvaps in https://github.com/cozystack/cozystack/pull/875)
+* [ci] Do not run tests in the release building pipeline. (@kvaps in https://github.com/cozystack/cozystack/pull/882)
+* [ci] Fix release branch creation. (@kvaps in https://github.com/cozystack/cozystack/pull/884)
+* [ci, dx] Reduce noise in the test logs by suppressing the `wget` progress bar. (@lllamnyp in https://github.com/cozystack/cozystack/pull/865)
+* [ci] Revert "automatically trigger tests in releasing PR". (@kvaps in https://github.com/cozystack/cozystack/pull/900)
+* [ci] Force-update release branch on tagged main commits . (@kvaps in https://github.com/cozystack/cozystack/pull/977)
+* [docs] Explain that tenants cannot have dashes in the names. (@NickVolynkin in https://github.com/cozystack/cozystack/pull/980)
+
+## Dependencies
+
+* MetalLB s now included directly as a patched image based on version 0.14.9. (@lllamnyp in https://github.com/cozystack/cozystack/pull/945)
+* Update Kubernetes to v1.32.4. (@kvaps in https://github.com/cozystack/cozystack/pull/949)
+* Update Talos Linux to v1.10.1. (@kvaps in https://github.com/cozystack/cozystack/pull/931)
+* Update Cilium to v1.17.3. (@kvaps in https://github.com/cozystack/cozystack/pull/848)
+* Update LINSTOR to v1.31.0. (@kvaps in https://github.com/cozystack/cozystack/pull/846)
+* Update Kube-OVN to v1.13.11. (@kvaps in https://github.com/cozystack/cozystack/pull/847, @lllamnyp in https://github.com/cozystack/cozystack/pull/922)
+* Update tenant Kubernetes to v1.32. (@kvaps in https://github.com/cozystack/cozystack/pull/871)
+* Update flux-operator to 0.20.0. (@kingdonb in https://github.com/cozystack/cozystack/pull/880 and https://github.com/cozystack/cozystack/pull/934)
+* Update multiple Cluster API components. (@kvaps in https://github.com/cozystack/cozystack/pull/867 and https://github.com/cozystack/cozystack/pull/947)
+* Update KamajiControlPlane to edge-25.4.1. (@kvaps in https://github.com/cozystack/cozystack/pull/953, fixed by @nbykov0 in https://github.com/cozystack/cozystack/pull/983)
+* Update cert-manager to v1.17.2. (@kvaps in https://github.com/cozystack/cozystack/pull/975)
+
+## Maintenance
+
+* Add @klinch0 to CODEOWNERS. (@kvaps in https://github.com/cozystack/cozystack/pull/838)
+
+## New Contributors
+
+* @etoshutka made their first contribution in https://github.com/cozystack/cozystack/pull/872
+* @dtrdnk made their first contribution in https://github.com/cozystack/cozystack/pull/896
+* @zdenekjanda made their first contribution in https://github.com/cozystack/cozystack/pull/924
+* @gwynbleidd2106 made their first contribution in https://github.com/cozystack/cozystack/pull/962
+
+**Full Changelog**: https://github.com/cozystack/cozystack/compare/v0.30.0...v0.31.0-rc.3

docs/release.md

@@ -0,0 +1,166 @@
+# Release Workflow
+
+This document describes Cozystack’s release process.
+
+## Introduction
+
+Cozystack uses a staged release process to ensure stability and flexibility during development.
+
+There are three types of releases:
+
+- **Release Candidates (RC)** – Preview versions (e.g., `v0.42.0-rc.1`) used for final testing and validation.
+- **Regular Releases** – Final versions (e.g., `v0.42.0`) that are feature-complete and thoroughly tested.
+- **Patch Releases** – Bugfix-only updates (e.g., `v0.42.1`) made after a stable release, based on a dedicated release branch.
+
+Each type plays a distinct role in delivering reliable and tested updates while allowing ongoing development to continue smoothly.
+
+## Release Candidates
+
+Release candidates are Cozystack versions that introduce new features and are published before a stable release.
+Their purpose is to help validate stability before finalizing a new feature release.
+They allow for final rounds of testing and bug fixes without freezing development.
+
+Release candidates are given numbers `vX.Y.0-rc.N`, for example, `v0.42.0-rc.1`.
+They are created directly in the `main` branch.
+An RC is typically tagged when all major features for the upcoming release have been merged into main and the release enters its testing phase.
+However, new features and changes can still be added before the regular release `vX.Y.0`.
+
+Each RC contributes to a cumulative set of release notes that will be finalized when `vX.Y.0` is released.
+After testing, if no critical issues remain, the regular release (`vX.Y.0`) is tagged from the last RC or a later commit in main.
+This begins the regular release process, creates a dedicated `release-X.Y` branch, and opens the way for patch releases.
+
+## Regular Releases
+
+When making a regular release, we tag the latest RC or a subsequent minimal-change commit as `vX.Y.0`.
+In this explanation, we'll use version `v0.42.0` as an example:
+
+```mermaid
+gitGraph
+    commit id: "feature"
+    commit id: "feature 2"
+    commit id: "feature 3" tag: "v0.42.0"
+```
+
+A regular release sequence starts in the following way:
+
+1. Maintainer tags a commit in `main` with `v0.42.0` and pushes it to GitHub.
+2. CI workflow triggers on tag push:
+   1. Creates a draft page for release `v0.42.0`, if it wasn't created before.
+   2. Takes code from tag `v0.42.0`, builds images, and pushes them to ghcr.io.
+   3. Makes a new commit `Prepare release v0.42.0` with updated digests, pushes it to the new branch `release-0.42.0`, and opens a PR to `main`.
+   4. Builds Cozystack release assets from the new commit `Prepare release v0.42.0` and uploads them to the release draft page.
+3. Maintainer reviews PR, tests build artifacts, and edits changelogs on the release draft page.
+
+   ```mermaid
+   gitGraph
+       commit id: "feature"
+       commit id: "feature 2"
+       commit id: "feature 3" tag: "v0.42.0"
+       branch release-0.42.0
+       checkout release-0.42.0
+       commit id: "Prepare release v0.42.0"
+       checkout main
+       merge release-0.42.0 id: "Pull Request"
+   ```
+
+   When testing and editing are completed, the sequence goes on.
+
+4. Maintainer merges the PR. GitHub removes the merged branch `release-0.42.0`.
+5. CI workflow triggers on merge:
+   1. Moves the tag `v0.42.0` to the newly created merge commit by force-pushing a tag to GitHub.
+   2. Publishes the release page (`draft` → `latest`).
+6. The maintainer can now announce the release to the community.
+
+```mermaid
+gitGraph
+    commit id: "feature"
+    commit id: "feature 2"
+    commit id: "feature 3"
+    branch release-0.42.0
+    checkout release-0.42.0
+    commit id: "Prepare release v0.42.0"
+    checkout main
+    merge release-0.42.0 id: "Release v0.42.0" tag: "v0.42.0"
+```
+
+## Patch Releases
+
+Making a patch release has a lot in common with a regular release, with a couple of differences:
+
+* A release branch is used instead of `main`
+* Patch commits are cherry-picked to the release branch.
+* A pull request is opened against the release branch.
+
+
+Let's assume that we've released `v0.42.0` and that development is ongoing.
+We have introduced a couple of new features and some fixes to features that we have released 
+in `v0.42.0`.
+
+Once problems were found and fixed, a patch release is due.
+
+```mermaid
+gitGraph
+   commit id: "Release v0.42.0" tag: "v0.42.0"
+    checkout main
+    commit id: "feature 4"
+    commit id: "patch 1"
+    commit id: "feature 5"
+    commit id: "patch 2"
+```
+
+
+1. The maintainer creates a release branch, `release-0.42,` and cherry-picks patch commits from `main` to `release-0.42`.
+   These must be only patches to features that were present in version `v0.42.0`.
+
+   Cherry-picking can be done as soon as each patch is merged into `main`,
+   or directly before the release.
+
+   ```mermaid
+   gitGraph
+       commit id: "Release v0.42.0" tag: "v0.42.0"
+       branch release-0.42
+       checkout main
+       commit id: "feature 4"
+       commit id: "patch 1"
+       commit id: "feature 5"
+       commit id: "patch 2"
+       checkout release-0.42
+       cherry-pick id: "patch 1"
+       cherry-pick id: "patch 2"
+   ```
+
+   When all relevant patch commits are cherry-picked, the branch is ready for release.
+
+2. The maintainer tags the `HEAD` commit of branch `release-0.42` as `v0.42.1` and then pushes it to GitHub.
+3. CI workflow triggers on tag push:
+    1. Creates a draft page for release `v0.42.1`, if it wasn't created before.
+    2. Takes code from tag `v0.42.1`, builds images, and pushes them to ghcr.io.
+    3. Makes a new commit `Prepare release v0.42.1` with updated digests, pushes it to the new branch `release-0.42.1`, and opens a PR to `release-0.42`.
+    4. Builds Cozystack release assets from the new commit `Prepare release v0.42.1` and uploads them to the release draft page.
+4. Maintainer reviews PR, tests build artifacts, and edits changelogs on the release draft page.
+   
+   ```mermaid
+   gitGraph
+       commit id: "Release v0.42.0" tag: "v0.42.0"
+       branch release-0.42
+       checkout main
+       commit id: "feature 4"
+       commit id: "patch 1"
+       commit id: "feature 5"
+       commit id: "patch 2"
+       checkout release-0.42
+       cherry-pick id: "patch 1"
+       cherry-pick id: "patch 2" tag: "v0.42.1"
+       branch release-0.42.1
+       commit id: "Prepare release v0.42.1"
+       checkout release-0.42
+       merge release-0.42.1 id: "Pull request"
+   ```
+
+   Finally, when release is confirmed, the release sequence goes on.
+
+5. Maintainer merges the PR. GitHub removes the merged branch `release-0.42.1`.
+6. CI workflow triggers on merge:
+   1. Moves the tag `v0.42.1` to the newly created merge commit by force-pushing a tag to GitHub.
+   2. Publishes the release page (`draft` → `latest`).
+7. The maintainer can now announce the release to the community.

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/cozytest.sh

@@ -0,0 +1,117 @@
+#!/bin/sh
+###############################################################################
+# cozytest.sh - Bats-compatible test runner with live trace and enhanced      #
+# output, written in pure shell                                               #
+###############################################################################
+set -eu
+
+TEST_FILE=${1:?Usage: ./cozytest.sh <file.bats> [pattern]}
+PATTERN=${2:-*}
+LINE='----------------------------------------------------------------'
+
+cols() { stty size 2>/dev/null | awk '{print $2}' || echo 80; }
+MAXW=$(( $(cols) - 12 )); [ "$MAXW" -lt 40 ] && MAXW=70
+BEGIN=$(date +%s)
+timestamp() { s=$(( $(date +%s) - BEGIN )); printf '[%02d:%02d]' $((s/60)) $((s%60)); }
+
+###############################################################################
+# run_one <fn> <title>                                                        #
+###############################################################################
+run_one() {
+  fn=$1 title=$2
+  tmp=$(mktemp -d) || { echo "Failed to create temp directory" >&2; exit 1; }
+  log="$tmp/log"
+
+  echo "╭ » Run test: $title"
+  START=$(date +%s)
+  skip_next="+ $fn"      # первую строку трассировки с именем функции пропустим
+
+  {
+    (
+      PS4='+ '           # prefix for set -x
+      set -eu -x         # strict + trace
+      "$fn"
+    )
+    printf '__RC__%s\n' "$?"
+  } 2>&1 | tee "$log" | while IFS= read -r line; do
+        case "$line" in
+          '__RC__'*) : ;;
+          '+ '*)   cmd=${line#'+ '}
+                    [ "$cmd" = "${skip_next#+ }" ] && continue
+                    case "$cmd" in
+                      'set -e'|'set -x'|'set -u'|'return 0') continue ;;
+                    esac
+                    out=$cmd ;;
+          *)       out=$line ;;
+        esac
+        now=$(( $(date +%s) - START ))
+        [ ${#out} -gt "$MAXW" ] && out="$(printf '%.*s…' "$MAXW" "$out")"
+        printf '┊[%02d:%02d] %s\n' $((now/60)) $((now%60)) "$out"
+  done
+
+  rc=$(awk '/^__RC__/ {print substr($0,7)}' "$log" | tail -n1)
+  [ -z "$rc" ] && rc=1
+  now=$(( $(date +%s) - START ))
+
+  if [ "$rc" -eq 0 ]; then
+    printf '╰[%02d:%02d] ✅ Test OK: %s\n' $((now/60)) $((now%60)) "$title"
+  else
+    printf '╰[%02d:%02d] ❌ Test failed: %s (exit %s)\n' \
+           $((now/60)) $((now%60)) "$title" "$rc"
+    echo "----- captured output -----------------------------------------"
+    grep -v '^__RC__' "$log"
+    echo "$LINE"
+    exit "$rc"
+  fi
+
+  rm -rf "$tmp"
+}
+
+###############################################################################
+# convert .bats -> shell-functions                                            #
+###############################################################################
+TMP_SH=$(mktemp) || { echo "Failed to create temp file" >&2; exit 1; }
+trap 'rm -f "$TMP_SH"' EXIT
+awk '
+  /^@test[[:space:]]+"/ {
+    line  = substr($0, index($0, "\"") + 1)
+    title = substr(line, 1, index(line, "\"") - 1)
+    fname = "test_"
+    for (i = 1; i <= length(title); i++) {
+      c = substr(title, i, 1)
+      fname = fname (c ~ /[A-Za-z0-9]/ ? c : "_")
+    }
+    printf("### %s\n", title)
+    printf("%s() {\n", fname)
+    print "  set -e"           # ошибка → падение теста
+    next
+  }
+  /^}$/ {
+    print "  return 0"         # если автор не сделал exit 1 — тест ОК
+    print "}"
+    next
+  }
+  { print }
+' "$TEST_FILE" > "$TMP_SH"
+
+[ -f "$TMP_SH" ] || { echo "Failed to generate test functions" >&2; exit 1; }
+# shellcheck disable=SC1090
+. "$TMP_SH"
+
+###############################################################################
+# run selected tests                                                          #
+###############################################################################
+awk -v pat="$PATTERN" '
+  /^### / {
+    title = substr($0, 5)
+    name = "test_"
+    for (i = 1; i <= length(title); i++) {
+      c = substr(title, i, 1)
+      name = name (c ~ /[A-Za-z0-9]/ ? c : "_")
+    }
+    if (pat == "*" || index(title, pat) > 0)
+      printf("%s %s\n", name, title)
+  }
+' "$TMP_SH" | while IFS=' ' read -r fn title; do
+  run_one "$fn" "$title"
+done

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-apps.bats

@@ -0,0 +1,94 @@
+#!/usr/bin/env bats
+# -----------------------------------------------------------------------------
+# Cozystack end‑to‑end provisioning test (Bats)
+# -----------------------------------------------------------------------------
+
+@test "Create tenant with isolated mode enabled" {
+  kubectl create -f - <<EOF
+apiVersion: apps.cozystack.io/v1alpha1
+kind: Tenant
+metadata:
+  name: test
+  namespace: tenant-root
+spec:
+  etcd: false
+  host: ""
+  ingress: false
+  isolated: true
+  monitoring: false
+  resourceQuotas: {}
+  seaweedfs: false
+EOF
+  kubectl wait hr/tenant-test -n tenant-root --timeout=1m --for=condition=ready
+  kubectl wait namespace tenant-test --timeout=20s --for=jsonpath='{.status.phase}'=Active
+}
+
+@test "Create a tenant Kubernetes control plane" {
+  kubectl create -f - <<EOF
+apiVersion: apps.cozystack.io/v1alpha1
+kind: Kubernetes
+metadata:
+  name: test
+  namespace: tenant-test
+spec:
+  addons:
+    certManager:
+      enabled: false
+      valuesOverride: {}
+    cilium:
+      valuesOverride: {}
+    fluxcd:
+      enabled: false
+      valuesOverride: {}
+    gatewayAPI:
+      enabled: false
+    gpuOperator:
+      enabled: false
+      valuesOverride: {}
+    ingressNginx:
+      enabled: true
+      hosts: []
+      valuesOverride: {}
+    monitoringAgents:
+      enabled: false
+      valuesOverride: {}
+    verticalPodAutoscaler:
+      valuesOverride: {}
+  controlPlane:
+    apiServer:
+      resources: {}
+      resourcesPreset: small
+    controllerManager:
+      resources: {}
+      resourcesPreset: micro
+    konnectivity:
+      server:
+        resources: {}
+        resourcesPreset: micro
+    replicas: 2
+    scheduler:
+      resources: {}
+      resourcesPreset: micro
+  host: ""
+  nodeGroups:
+    md0:
+      ephemeralStorage: 20Gi
+      gpus: []
+      instanceType: u1.medium
+      maxReplicas: 10
+      minReplicas: 0
+      resources:
+        cpu: ""
+        memory: ""
+      roles:
+      - ingress-nginx
+  storageClass: replicated
+EOF
+  kubectl wait namespace tenant-test --timeout=20s --for=jsonpath='{.status.phase}'=Active
+  timeout 10 sh -ec 'until kubectl get kamajicontrolplane -n tenant-test kubernetes-test; do sleep 1; done'
+  kubectl wait --for=condition=TenantControlPlaneCreated kamajicontrolplane -n tenant-test kubernetes-test --timeout=4m
+  kubectl wait tcp -n tenant-test kubernetes-test --timeout=2m --for=jsonpath='{.status.kubernetesResources.version.status}'=Ready
+  kubectl wait deploy --timeout=4m --for=condition=available -n tenant-test kubernetes-test kubernetes-test-cluster-autoscaler kubernetes-test-kccm kubernetes-test-kcsi-controller
+  kubectl wait machinedeployment kubernetes-test-md0 -n tenant-test --timeout=1m --for=jsonpath='{.status.replicas}'=2
+  kubectl wait machinedeployment kubernetes-test-md0 -n tenant-test --timeout=5m --for=jsonpath='{.status.v1beta2.readyReplicas}'=2
+}

hack/e2e-cluster.bats

@@ -0,0 +1,387 @@
+#!/usr/bin/env bats
+# -----------------------------------------------------------------------------
+# Cozystack end‑to‑end provisioning test (Bats)
+# -----------------------------------------------------------------------------
+
+@test "Environment variable COZYSTACK_INSTALLER_YAML is defined" {
+  if [ -z "${COZYSTACK_INSTALLER_YAML:-}" ]; then
+    echo 'COZYSTACK_INSTALLER_YAML environment variable is not set!' >&2
+    echo >&2
+    echo 'Please export it with the following command:' >&2
+    echo '  export COZYSTACK_INSTALLER_YAML=$(helm template -n cozy-system installer packages/core/installer)' >&2
+    exit 1
+  fi
+}
+
+@test "IPv4 forwarding is enabled" {
+  if [ "$(cat /proc/sys/net/ipv4/ip_forward)" != 1 ]; then
+    echo "IPv4 forwarding is disabled!" >&2
+    echo >&2
+    echo "Enable it with:" >&2
+    echo "  echo 1 > /proc/sys/net/ipv4/ip_forward" >&2
+    exit 1
+  fi
+}
+
+@test "Clean previous VMs" {
+ kill $(cat srv1/qemu.pid srv2/qemu.pid srv3/qemu.pid 2>/dev/null) 2>/dev/null || true
+ rm -rf srv1 srv2 srv3
+}
+
+@test "Prepare networking and masquerading" {
+  ip link del cozy-br0 2>/dev/null || true
+  ip link add cozy-br0 type bridge
+  ip link set cozy-br0 up
+  ip address add 192.168.123.1/24 dev cozy-br0
+
+  # Masquerading rule – idempotent (delete first, then add)
+  iptables -t nat -D POSTROUTING -s 192.168.123.0/24 ! -d 192.168.123.0/24 -j MASQUERADE 2>/dev/null || true
+  iptables -t nat -A POSTROUTING -s 192.168.123.0/24 ! -d 192.168.123.0/24 -j MASQUERADE
+}
+
+@test "Prepare cloud‑init drive for VMs" {
+  mkdir -p srv1 srv2 srv3
+
+  # Generate cloud‑init ISOs
+  for i in 1 2 3; do
+    echo "hostname: srv${i}" > "srv${i}/meta-data"
+
+    cat > "srv${i}/user-data" <<'EOF'
+#cloud-config
+EOF
+
+    cat > "srv${i}/network-config" <<EOF
+version: 2
+ethernets:
+  eth0:
+    dhcp4: false
+    addresses:
+      - "192.168.123.1${i}/26"
+    gateway4: "192.168.123.1"
+    nameservers:
+      search: [cluster.local]
+      addresses: [8.8.8.8]
+EOF
+
+    ( cd "srv${i}" && genisoimage \
+        -output seed.img \
+        -volid cidata -rational-rock -joliet \
+        user-data meta-data network-config )
+  done
+}
+
+@test "Download Talos NoCloud image" {
+  if [ ! -f nocloud-amd64.raw ]; then
+    wget https://github.com/cozystack/cozystack/releases/latest/download/nocloud-amd64.raw.xz \
+      -O nocloud-amd64.raw.xz --show-progress --output-file /dev/stdout --progress=dot:giga 2>/dev/null
+    rm -f nocloud-amd64.raw
+    xz --decompress nocloud-amd64.raw.xz
+  fi
+}
+
+@test "Prepare VM disks" {
+  for i in 1 2 3; do
+    cp nocloud-amd64.raw srv${i}/system.img
+    qemu-img resize srv${i}/system.img 20G
+    qemu-img create srv${i}/data.img 100G
+  done
+}
+
+@test "Create tap devices" {
+  for i in 1 2 3; do
+    ip link del cozy-srv${i} 2>/dev/null || true
+    ip tuntap add dev cozy-srv${i} mode tap
+    ip link set cozy-srv${i} up
+    ip link set cozy-srv${i} master cozy-br0
+  done
+}
+
+@test "Boot QEMU VMs" {
+  for i in 1 2 3; do
+    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 \
+      -drive file=srv${i}/data.img,if=virtio,format=raw \
+      -display none -daemonize -pidfile srv${i}/qemu.pid
+  done
+
+  # Give qemu a few seconds to start up networking
+  sleep 5
+}
+
+@test "Wait until Talos API port 50000 is reachable on all machines" {
+  timeout 60 sh -ec 'until nc -nz 192.168.123.11 50000 && nc -nz 192.168.123.12 50000 && nc -nz 192.168.123.13 50000; do sleep 1; done'
+}
+
+@test "Generate Talos cluster configuration" {
+  # Cluster‑wide patches
+  cat > patch.yaml <<'EOF'
+machine:
+  kubelet:
+    nodeIP:
+      validSubnets:
+      - 192.168.123.0/24
+    extraConfig:
+      maxPods: 512
+  kernel:
+    modules:
+    - name: openvswitch
+    - name: drbd
+      parameters:
+        - usermode_helper=disabled
+    - name: zfs
+    - name: spl
+  registries:
+    mirrors:
+      docker.io:
+        endpoints:
+        - https://mirror.gcr.io
+  files:
+  - content: |
+      [plugins]
+        [plugins."io.containerd.cri.v1.runtime"]
+          device_ownership_from_security_context = true
+    path: /etc/cri/conf.d/20-customization.part
+    op: create
+
+cluster:
+  apiServer:
+    extraArgs:
+      oidc-issuer-url: "https://keycloak.example.org/realms/cozy"
+      oidc-client-id: "kubernetes"
+      oidc-username-claim: "preferred_username"
+      oidc-groups-claim: "groups"
+  network:
+    cni:
+      name: none
+    dnsDomain: cozy.local
+    podSubnets:
+    - 10.244.0.0/16
+    serviceSubnets:
+    - 10.96.0.0/16
+EOF
+
+  # Control‑plane‑only patches
+  cat > patch-controlplane.yaml <<'EOF'
+machine:
+  nodeLabels:
+    node.kubernetes.io/exclude-from-external-load-balancers:
+      $patch: delete
+  network:
+    interfaces:
+    - interface: eth0
+      vip:
+        ip: 192.168.123.10
+cluster:
+  allowSchedulingOnControlPlanes: true
+  controllerManager:
+    extraArgs:
+      bind-address: 0.0.0.0
+  scheduler:
+    extraArgs:
+      bind-address: 0.0.0.0
+  apiServer:
+    certSANs:
+    - 127.0.0.1
+  proxy:
+    disabled: true
+  discovery:
+    enabled: false
+  etcd:
+    advertisedSubnets:
+    - 192.168.123.0/24
+EOF
+
+  # Generate secrets once
+  if [ ! -f secrets.yaml ]; then
+    talosctl gen secrets
+  fi
+
+  rm -f controlplane.yaml worker.yaml talosconfig kubeconfig
+  talosctl gen config --with-secrets secrets.yaml cozystack https://192.168.123.10:6443 \
+           --config-patch=@patch.yaml --config-patch-control-plane @patch-controlplane.yaml
+}
+
+@test "Apply Talos configuration to the node" {
+  # Apply the configuration to all three nodes
+  for node in 11 12 13; do
+    talosctl apply -f controlplane.yaml -n 192.168.123.${node} -e 192.168.123.${node} -i
+  done
+
+  # Wait for Talos services to come up again
+  timeout 60 sh -ec 'until nc -nz 192.168.123.11 50000 && nc -nz 192.168.123.12 50000 && nc -nz 192.168.123.13 50000; do sleep 1; done'
+}
+
+@test "Bootstrap Talos cluster" {
+  # Bootstrap etcd on the first node
+  timeout 10 sh -ec 'until talosctl bootstrap -n 192.168.123.11 -e 192.168.123.11; do sleep 1; done'
+
+  # Wait until etcd is healthy
+  timeout 180 sh -ec 'until talosctl etcd members -n 192.168.123.11,192.168.123.12,192.168.123.13 -e 192.168.123.10 >/dev/null 2>&1; do sleep 1; done'
+  timeout 60 sh -ec 'while talosctl etcd members -n 192.168.123.11,192.168.123.12,192.168.123.13 -e 192.168.123.10 2>&1 | grep -q "rpc error"; do sleep 1; done'
+
+  # Retrieve kubeconfig
+  rm -f kubeconfig
+  talosctl kubeconfig kubeconfig -e 192.168.123.10 -n 192.168.123.10
+
+  # Wait until all three nodes register in Kubernetes
+  timeout 60 sh -ec 'until [ $(kubectl get node --no-headers | wc -l) -eq 3 ]; do sleep 1; done'
+}
+
+@test "Install Cozystack" {
+  # Create namespace & configmap required by installer
+  kubectl create namespace cozy-system --dry-run=client -o yaml | kubectl apply -f -
+  kubectl create configmap cozystack -n cozy-system \
+          --from-literal=bundle-name=paas-full \
+          --from-literal=ipv4-pod-cidr=10.244.0.0/16 \
+          --from-literal=ipv4-pod-gateway=10.244.0.1 \
+          --from-literal=ipv4-svc-cidr=10.96.0.0/16 \
+          --from-literal=ipv4-join-cidr=100.64.0.0/16 \
+          --from-literal=root-host=example.org \
+          --from-literal=api-server-endpoint=https://192.168.123.10:6443 \
+          --dry-run=client -o yaml | kubectl apply -f -
+
+  # Apply installer manifests from env variable
+  echo "$COZYSTACK_INSTALLER_YAML" | kubectl apply -f -
+
+  # Wait for the installer deployment to become available
+  kubectl wait deployment/cozystack -n cozy-system --timeout=1m --for=condition=Available
+
+  # Wait until HelmReleases appear & reconcile them
+  timeout 60 sh -ec 'until kubectl get hr -A | grep -q cozys; do sleep 1; done'
+  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 -ex
+
+  # Fail the test if any HelmRelease is not Ready
+  if kubectl get hr -A | grep -v " True " | grep -v NAME; then
+    kubectl get hr -A
+    fail "Some HelmReleases failed to reconcile"
+  fi
+}
+
+@test "Wait for Cluster‑API provider deployments" {
+  # Wait for Cluster‑API provider deployments
+  timeout 60 sh -ec '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 >/dev/null 2>&1; do sleep 1; done'
+  kubectl wait deployment/capi-controller-manager deployment/capi-kamaji-controller-manager deployment/capi-kubeadm-bootstrap-controller-manager deployment/capi-operator-cluster-api-operator deployment/capk-controller-manager -n cozy-cluster-api --timeout=1m --for=condition=available
+}
+
+@test "Wait for LINSTOR and configure storage" {
+  # Linstor controller and nodes
+  kubectl wait deployment/linstor-controller -n cozy-linstor --timeout=5m --for=condition=available
+  timeout 60 sh -ec 'until [ $(kubectl exec -n cozy-linstor deploy/linstor-controller -- linstor node list | grep -c Online) -eq 3 ]; do sleep 1; done'
+
+  for node in srv1 srv2 srv3; do
+    kubectl exec -n cozy-linstor deploy/linstor-controller -- linstor ps cdp zfs ${node} /dev/vdc --pool-name data --storage-pool data
+  done
+
+  # Storage classes
+  kubectl apply -f - <<'EOF'
+---
+apiVersion: storage.k8s.io/v1
+kind: StorageClass
+metadata:
+  name: local
+  annotations:
+    storageclass.kubernetes.io/is-default-class: "true"
+provisioner: linstor.csi.linbit.com
+parameters:
+  linstor.csi.linbit.com/storagePool: "data"
+  linstor.csi.linbit.com/layerList: "storage"
+  linstor.csi.linbit.com/allowRemoteVolumeAccess: "false"
+volumeBindingMode: WaitForFirstConsumer
+allowVolumeExpansion: true
+---
+apiVersion: storage.k8s.io/v1
+kind: StorageClass
+metadata:
+  name: replicated
+provisioner: linstor.csi.linbit.com
+parameters:
+  linstor.csi.linbit.com/storagePool: "data"
+  linstor.csi.linbit.com/autoPlace: "3"
+  linstor.csi.linbit.com/layerList: "drbd storage"
+  linstor.csi.linbit.com/allowRemoteVolumeAccess: "true"
+  property.linstor.csi.linbit.com/DrbdOptions/auto-quorum: suspend-io
+  property.linstor.csi.linbit.com/DrbdOptions/Resource/on-no-data-accessible: suspend-io
+  property.linstor.csi.linbit.com/DrbdOptions/Resource/on-suspended-primary-outdated: force-secondary
+  property.linstor.csi.linbit.com/DrbdOptions/Net/rr-conflict: retry-connect
+volumeBindingMode: WaitForFirstConsumer
+allowVolumeExpansion: true
+EOF
+}
+
+@test "Wait for MetalLB and configure address pool" {
+  # MetalLB address pool
+  kubectl apply -f - <<'EOF'
+---
+apiVersion: metallb.io/v1beta1
+kind: L2Advertisement
+metadata:
+  name: cozystack
+  namespace: cozy-metallb
+spec:
+  ipAddressPools: [cozystack]
+---
+apiVersion: metallb.io/v1beta1
+kind: IPAddressPool
+metadata:
+  name: cozystack
+  namespace: cozy-metallb
+spec:
+  addresses: [192.168.123.200-192.168.123.250]
+  autoAssign: true
+  avoidBuggyIPs: false
+EOF
+}
+
+@test "Check Cozystack API service" {
+  kubectl wait --for=condition=Available apiservices/v1alpha1.apps.cozystack.io --timeout=2m
+}
+
+@test "Configure Tenant and wait for applications" {
+  # Patch root tenant and wait for its releases
+  kubectl patch tenants/root -n tenant-root --type merge -p '{"spec":{"host":"example.org","ingress":true,"monitoring":true,"etcd":true,"isolated":true}}'
+
+  timeout 60 sh -ec 'until kubectl get hr -n tenant-root etcd ingress monitoring tenant-root >/dev/null 2>&1; do sleep 1; done'
+  kubectl wait hr/etcd hr/ingress hr/tenant-root -n tenant-root --timeout=2m --for=condition=ready
+
+  if ! kubectl wait hr/monitoring -n tenant-root --timeout=2m --for=condition=ready; then
+    flux reconcile hr monitoring -n tenant-root --force
+    kubectl wait hr/monitoring -n tenant-root --timeout=2m --for=condition=ready
+  fi
+
+  # Expose Cozystack services through ingress
+  kubectl patch configmap/cozystack -n cozy-system --type merge -p '{"data":{"expose-services":"api,dashboard,cdi-uploadproxy,vm-exportproxy,keycloak"}}'
+
+  # NGINX ingress controller
+  timeout 60 sh -ec 'until kubectl get deploy root-ingress-controller -n tenant-root >/dev/null 2>&1; do sleep 1; done'
+  kubectl wait deploy/root-ingress-controller -n tenant-root --timeout=5m --for=condition=available
+
+  # etcd statefulset
+  kubectl wait sts/etcd -n tenant-root --for=jsonpath='{.status.readyReplicas}'=3 --timeout=5m
+
+  # VictoriaMetrics components
+  kubectl wait vmalert/vmalert-shortterm vmalertmanager/alertmanager -n tenant-root --for=jsonpath='{.status.updateStatus}'=operational --timeout=5m
+  kubectl wait vlogs/generic -n tenant-root --for=jsonpath='{.status.updateStatus}'=operational --timeout=5m
+  kubectl wait vmcluster/shortterm vmcluster/longterm -n tenant-root --for=jsonpath='{.status.clusterStatus}'=operational --timeout=5m
+
+  # Grafana
+  kubectl wait clusters.postgresql.cnpg.io/grafana-db -n tenant-root --for=condition=ready --timeout=5m
+  kubectl wait deploy/grafana-deployment -n tenant-root --for=condition=available --timeout=5m
+
+  # Verify Grafana via ingress
+  ingress_ip=$(kubectl get svc root-ingress-controller -n tenant-root -o jsonpath='{.status.loadBalancer.ingress[0].ip}')
+  if ! curl -sS -k "https://${ingress_ip}" -H 'Host: grafana.example.org' --max-time 30 | grep -q Found; then
+    echo "Failed to access Grafana via ingress at ${ingress_ip}" >&2
+    exit 1
+  fi
+}
+
+@test "Keycloak OIDC stack is healthy" {
+  kubectl patch configmap/cozystack -n cozy-system --type merge -p '{"data":{"oidc-enabled":"true"}}'
+
+  timeout 120 sh -ec 'until kubectl get hr -n cozy-keycloak keycloak keycloak-configure keycloak-operator >/dev/null 2>&1; do sleep 1; done'
+  kubectl wait hr/keycloak hr/keycloak-configure hr/keycloak-operator -n cozy-keycloak --timeout=10m --for=condition=ready
+}

hack/e2e.application.sh

@@ -1,165 +0,0 @@
-#!/bin/bash
-
-RED='\033[0;31m'
-GREEN='\033[0;32m'
-RESET='\033[0m'
-YELLOW='\033[0;33m'
-
-
-ROOT_NS="tenant-root"
-TEST_TENANT="tenant-e2e"
-
-values_base_path="/hack/testdata/"
-checks_base_path="/hack/testdata/"
-
-function delete_hr() {
-    local release_name="$1"
-    local namespace="$2"
-
-    if [[ -z "$release_name" ]]; then
-        echo -e "${RED}Error: Release name is required.${RESET}"
-        exit 1
-    fi
-
-    if [[ -z "$namespace" ]]; then
-        echo -e "${RED}Error: Namespace name is required.${RESET}"
-        exit 1
-    fi
-
-    if [[ "$release_name" == "tenant-e2e" ]]; then
-        echo -e "${YELLOW}Skipping deletion for release tenant-e2e.${RESET}"
-        return 0
-    fi
-
-    kubectl delete helmrelease $release_name -n $namespace
-}
-
-function install_helmrelease() {
-    local release_name="$1"
-    local namespace="$2"
-    local chart_path="$3"
-    local repo_name="$4"
-    local repo_ns="$5"
-    local values_file="$6"
-
-    if [[ -z "$release_name" ]]; then
-        echo -e "${RED}Error: Release name is required.${RESET}"
-        exit 1
-    fi
-
-    if [[ -z "$namespace" ]]; then
-        echo -e "${RED}Error: Namespace name is required.${RESET}"
-        exit 1
-    fi
-
-    if [[ -z "$chart_path" ]]; then
-        echo -e "${RED}Error: Chart path name is required.${RESET}"
-        exit 1
-    fi
-
-    if [[ -n "$values_file" && -f "$values_file" ]]; then
-        local values_section
-        values_section=$(echo "  values:" && sed 's/^/    /' "$values_file")
-    fi
-
-    local helmrelease_file=$(mktemp /tmp/HelmRelease.XXXXXX.yaml)
-    {
-        echo "apiVersion: helm.toolkit.fluxcd.io/v2"
-        echo "kind: HelmRelease"
-        echo "metadata:"
-        echo "  labels:"
-        echo "    cozystack.io/ui: \"true\""
-        echo "  name: \"$release_name\""
-        echo "  namespace: \"$namespace\""
-        echo "spec:"
-        echo "  chart:"
-        echo "    spec:"
-        echo "      chart: \"$chart_path\""
-        echo "      reconcileStrategy: Revision"
-        echo "      sourceRef:"
-        echo "        kind: HelmRepository"
-        echo "        name: \"$repo_name\""
-        echo "        namespace: \"$repo_ns\""
-        echo "      version: '*'"
-        echo "  interval: 1m0s"
-        echo "  timeout: 5m0s"
-        [[ -n "$values_section" ]] && echo "$values_section"
-    } > "$helmrelease_file"
-
-    kubectl apply -f "$helmrelease_file"
-
-    rm -f "$helmrelease_file"
-}
-
-function install_tenant (){
-    local release_name="$1"
-    local namespace="$2"
-    local values_file="${values_base_path}tenant/values.yaml"
-    local repo_name="cozystack-apps"
-    local repo_ns="cozy-public"
-    install_helmrelease "$release_name" "$namespace" "tenant" "$repo_name" "$repo_ns" "$values_file"
-}
-
-function make_extra_checks(){
-    local checks_file="$1"
-    echo "after exec make $checks_file"
-    if [[ -n "$checks_file" && -f "$checks_file" ]]; then
-        echo -e "${YELLOW}Start extra checks with file: ${checks_file}${RESET}"
-
-    fi
-}
-
-function check_helmrelease_status() {
-    local release_name="$1"
-    local namespace="$2"
-    local checks_file="$3"
-    local timeout=300  # Timeout in seconds
-    local interval=5   # Interval between checks in seconds
-    local elapsed=0
-
-
-    while [[ $elapsed -lt $timeout ]]; do
-        local status_output
-        status_output=$(kubectl get helmrelease "$release_name" -n "$namespace" -o json | jq -r '.status.conditions[-1].reason')
-
-        if [[ "$status_output" == "InstallSucceeded" || "$status_output" == "UpgradeSucceeded" ]]; then
-            echo -e "${GREEN}Helm release '$release_name' is ready.${RESET}"
-            make_extra_checks "$checks_file"
-            delete_hr $release_name $namespace
-            return 0
-        elif [[ "$status_output" == "InstallFailed" ]]; then
-          echo -e "${RED}Helm release '$release_name': InstallFailed${RESET}"
-          exit 1
-        else
-            echo -e "${YELLOW}Helm release '$release_name' is not ready. Current status: $status_output${RESET}"
-        fi
-
-        sleep "$interval"
-        elapsed=$((elapsed + interval))
-    done
-
-    echo -e "${RED}Timeout reached. Helm release '$release_name' is still not ready after $timeout seconds.${RESET}"
-    exit 1
-}
-
-chart_name="$1"
-
-if [ -z "$chart_name" ]; then
-    echo -e "${RED}No chart name provided. Exiting...${RESET}"
-    exit 1
-fi
-
-
-checks_file="${checks_base_path}${chart_name}/check.sh"
-repo_name="cozystack-apps"
-repo_ns="cozy-public"
-release_name="$chart_name-e2e"
-values_file="${values_base_path}${chart_name}/values.yaml"
-
-install_tenant $TEST_TENANT $ROOT_NS
-check_helmrelease_status $TEST_TENANT $ROOT_NS "${checks_base_path}tenant/check.sh"
-
-echo -e "${YELLOW}Running tests for chart: $chart_name${RESET}"
-
-install_helmrelease $release_name $TEST_TENANT $chart_name $repo_name $repo_ns $values_file
-check_helmrelease_status $release_name $TEST_TENANT $checks_file

hack/e2e.sh

@@ -1,346 +0,0 @@
-#!/bin/bash
-if [ "$COZYSTACK_INSTALLER_YAML" = "" ]; then
-  echo 'COZYSTACK_INSTALLER_YAML variable is not set!' >&2
-  echo 'please set it with following command:' >&2
-  echo >&2
-  echo 'export COZYSTACK_INSTALLER_YAML=$(helm template -n cozy-system installer packages/core/installer)' >&2
-  echo >&2
-  exit 1
-fi
-
-if [ "$(cat /proc/sys/net/ipv4/ip_forward)" != 1 ]; then
-  echo "IPv4 forwarding is not enabled!" >&2
-  echo 'please enable forwarding with the following command:' >&2
-  echo >&2
-  echo 'echo 1 > /proc/sys/net/ipv4/ip_forward' >&2
-  echo >&2
-  exit 1
-fi
-
-set -x
-set -e
-
-kill `cat srv1/qemu.pid srv2/qemu.pid srv3/qemu.pid` || true
-
-ip link del cozy-br0 || true
-ip link add cozy-br0 type bridge
-ip link set cozy-br0 up
-ip addr add 192.168.123.1/24 dev cozy-br0
-
-# Enable masquerading
-iptables -t nat -D POSTROUTING -s 192.168.123.0/24 ! -d 192.168.123.0/24 -j MASQUERADE 2>/dev/null || true
-iptables -t nat -A POSTROUTING -s 192.168.123.0/24 ! -d 192.168.123.0/24 -j MASQUERADE
-
-rm -rf srv1 srv2 srv3
-mkdir -p srv1 srv2 srv3
-
-# Prepare cloud-init
-for i in 1 2 3; do
-  echo "hostname: srv$i" > "srv$i/meta-data"
-  echo '#cloud-config' > "srv$i/user-data"
-  cat > "srv$i/network-config" <<EOT
-version: 2
-ethernets:
-  eth0:
-    dhcp4: false
-    addresses:
-      - "192.168.123.1$i/26"
-    gateway4: "192.168.123.1"
-    nameservers:
-      search: [cluster.local]
-      addresses: [8.8.8.8]
-EOT
-
-  ( cd srv$i && genisoimage \
-      -output seed.img \
-      -volid cidata -rational-rock -joliet \
-      user-data meta-data network-config
-  )
-done
-
-# Prepare system drive
-if [ ! -f nocloud-amd64.raw ]; then
-  wget https://github.com/aenix-io/cozystack/releases/latest/download/nocloud-amd64.raw.xz -O nocloud-amd64.raw.xz
-  rm -f nocloud-amd64.raw
-  xz --decompress nocloud-amd64.raw.xz
-fi
-for i in 1 2 3; do
-  cp nocloud-amd64.raw srv$i/system.img
-  qemu-img resize srv$i/system.img 20G
-done
-
-# Prepare data drives
-for i in 1 2 3; do
-  qemu-img create srv$i/data.img 100G
-done
-
-# Prepare networking
-for i in 1 2 3; do
-  ip link del cozy-srv$i || true
-  ip tuntap add dev cozy-srv$i mode tap
-  ip link set cozy-srv$i up
-  ip link set cozy-srv$i master cozy-br0
-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 \
-    -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 \
-    -drive file=srv$i/data.img,if=virtio,format=raw \
-    -display none -daemonize -pidfile srv$i/qemu.pid
-done
-
-sleep 5
-
-# Wait for VM to start up
-timeout 60 sh -c 'until nc -nzv 192.168.123.11 50000 && nc -nzv 192.168.123.12 50000 && nc -nzv 192.168.123.13 50000; do sleep 1; done'
-
-cat > patch.yaml <<\EOT
-machine:
-  kubelet:
-    nodeIP:
-      validSubnets:
-      - 192.168.123.0/24
-    extraConfig:
-      maxPods: 512
-  kernel:
-    modules:
-    - name: openvswitch
-    - name: drbd
-      parameters:
-        - usermode_helper=disabled
-    - name: zfs
-    - name: spl
-  install:
-    image: ghcr.io/aenix-io/cozystack/talos:v1.8.3
-  files:
-  - content: |
-      [plugins]
-        [plugins."io.containerd.grpc.v1.cri"]
-          device_ownership_from_security_context = true      
-    path: /etc/cri/conf.d/20-customization.part
-    op: create
-
-cluster:
-  apiServer:
-    extraArgs:
-      oidc-issuer-url: "https://keycloak.example.org/realms/cozy"
-      oidc-client-id: "kubernetes"
-      oidc-username-claim: "preferred_username"
-      oidc-groups-claim: "groups"
-  network:
-    cni:
-      name: none
-    dnsDomain: cozy.local
-    podSubnets:
-    - 10.244.0.0/16
-    serviceSubnets:
-    - 10.96.0.0/16
-EOT
-
-cat > patch-controlplane.yaml <<\EOT
-machine:
-  network:
-    interfaces:
-    - interface: eth0
-      vip:
-        ip: 192.168.123.10
-cluster:
-  allowSchedulingOnControlPlanes: true
-  controllerManager:
-    extraArgs:
-      bind-address: 0.0.0.0
-  scheduler:
-    extraArgs:
-      bind-address: 0.0.0.0
-  apiServer:
-    certSANs:
-    - 127.0.0.1
-  proxy:
-    disabled: true
-  discovery:
-    enabled: false
-  etcd:
-    advertisedSubnets:
-    - 192.168.123.0/24
-EOT
-
-# Gen configuration
-if [ ! -f secrets.yaml ]; then
-  talosctl gen secrets
-fi
-
-rm -f controlplane.yaml worker.yaml talosconfig kubeconfig
-talosctl gen config --with-secrets secrets.yaml cozystack https://192.168.123.10:6443 --config-patch=@patch.yaml --config-patch-control-plane @patch-controlplane.yaml
-export TALOSCONFIG=$PWD/talosconfig
-
-# Apply configuration
-talosctl apply -f controlplane.yaml -n 192.168.123.11 -e 192.168.123.11 -i
-talosctl apply -f controlplane.yaml -n 192.168.123.12 -e 192.168.123.12 -i
-talosctl apply -f controlplane.yaml -n 192.168.123.13 -e 192.168.123.13 -i
-
-# Wait for VM to be configured
-timeout 60 sh -c 'until nc -nzv 192.168.123.11 50000 && nc -nzv 192.168.123.12 50000 && nc -nzv 192.168.123.13 50000; do sleep 1; done'
-
-# Bootstrap
-timeout 10 sh -c 'until talosctl bootstrap -n 192.168.123.11 -e 192.168.123.11; do sleep 1; done'
-
-# Wait for etcd
-timeout 180 sh -c 'until timeout -s 9 2 talosctl etcd members -n 192.168.123.11,192.168.123.12,192.168.123.13 -e 192.168.123.10 2>&1; do sleep 1; done'
-timeout 60 sh -c 'while talosctl etcd members -n 192.168.123.11,192.168.123.12,192.168.123.13 -e 192.168.123.10 2>&1 | grep "rpc error"; do sleep 1; done'
-
-rm -f kubeconfig
-talosctl kubeconfig kubeconfig -e 192.168.123.10 -n 192.168.123.10
-export KUBECONFIG=$PWD/kubeconfig
-
-# Wait for kubernetes nodes appear
-timeout 60 sh -c 'until [ $(kubectl get node -o name | wc -l) = 3 ]; do sleep 1; done'
-kubectl create ns cozy-system -o yaml | kubectl apply -f -
-kubectl create -f - <<\EOT
-apiVersion: v1
-kind: ConfigMap
-metadata:
-  name: cozystack
-  namespace: cozy-system
-data:
-  bundle-name: "paas-full"
-  ipv4-pod-cidr: "10.244.0.0/16"
-  ipv4-pod-gateway: "10.244.0.1"
-  ipv4-svc-cidr: "10.96.0.0/16"
-  ipv4-join-cidr: "100.64.0.0/16"
-  root-host: example.org
-  api-server-endpoint: https://192.168.123.10:6443
-EOT
-
-#
-echo "$COZYSTACK_INSTALLER_YAML" | kubectl apply -f -
-
-# wait for cozystack pod to start
-kubectl wait deploy  --timeout=1m --for=condition=available -n cozy-system cozystack
-
-# wait for helmreleases appear
-timeout 60 sh -c 'until kubectl get hr -A | grep cozy; do sleep 1; done'
-
-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
-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
-kubectl wait deploy --timeout=5m --for=condition=available -n cozy-linstor linstor-controller
-
-# Wait for all linstor nodes become Online
-timeout 60 sh -c 'until [ $(kubectl exec -n cozy-linstor deploy/linstor-controller -- linstor node list | grep -c Online) = 3 ]; do sleep 1; done'
-
-kubectl exec -n cozy-linstor deploy/linstor-controller -- linstor ps cdp zfs srv1 /dev/vdc --pool-name data --storage-pool data
-kubectl exec -n cozy-linstor deploy/linstor-controller -- linstor ps cdp zfs srv2 /dev/vdc --pool-name data --storage-pool data
-kubectl exec -n cozy-linstor deploy/linstor-controller -- linstor ps cdp zfs srv3 /dev/vdc --pool-name data --storage-pool data
-
-kubectl create -f- <<EOT
----
-apiVersion: storage.k8s.io/v1
-kind: StorageClass
-metadata:
-  name: local
-  annotations:
-    storageclass.kubernetes.io/is-default-class: "true"
-provisioner: linstor.csi.linbit.com
-parameters:
-  linstor.csi.linbit.com/storagePool: "data"
-  linstor.csi.linbit.com/layerList: "storage"
-  linstor.csi.linbit.com/allowRemoteVolumeAccess: "false"
-volumeBindingMode: WaitForFirstConsumer
-allowVolumeExpansion: true
----
-apiVersion: storage.k8s.io/v1
-kind: StorageClass
-metadata:
-  name: replicated
-provisioner: linstor.csi.linbit.com
-parameters:
-  linstor.csi.linbit.com/storagePool: "data"
-  linstor.csi.linbit.com/autoPlace: "3"
-  linstor.csi.linbit.com/layerList: "drbd storage"
-  linstor.csi.linbit.com/allowRemoteVolumeAccess: "true"
-  property.linstor.csi.linbit.com/DrbdOptions/auto-quorum: suspend-io
-  property.linstor.csi.linbit.com/DrbdOptions/Resource/on-no-data-accessible: suspend-io
-  property.linstor.csi.linbit.com/DrbdOptions/Resource/on-suspended-primary-outdated: force-secondary
-  property.linstor.csi.linbit.com/DrbdOptions/Net/rr-conflict: retry-connect
-volumeBindingMode: WaitForFirstConsumer
-allowVolumeExpansion: true
-EOT
-kubectl create -f- <<EOT
----
-apiVersion: metallb.io/v1beta1
-kind: L2Advertisement
-metadata:
-  name: cozystack
-  namespace: cozy-metallb
-spec:
-  ipAddressPools:
-  - cozystack
----
-apiVersion: metallb.io/v1beta1
-kind: IPAddressPool
-metadata:
-  name: cozystack
-  namespace: cozy-metallb
-spec:
-  addresses:
-  - 192.168.123.200-192.168.123.250
-  autoAssign: true
-  avoidBuggyIPs: false
-EOT
-
-kubectl patch -n tenant-root tenants.apps.cozystack.io root --type=merge -p '{"spec":{
-  "host": "example.org",
-  "ingress": true,
-  "monitoring": true,
-  "etcd": true,
-  "isolated": true
-}}'
-
-# Wait for HelmRelease be created
-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 patch -n tenant-root ingresses.apps.cozystack.io ingress --type=merge -p '{"spec":{
-  "dashboard": true
-}}'
-
-# Wait for nginx-ingress-controller
-timeout 60 sh -c 'until kubectl get deploy -n tenant-root root-ingress-controller; do sleep 1; done'
-kubectl wait --timeout=5m --for=condition=available -n tenant-root deploy root-ingress-controller
-
-# Wait for etcd
-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-shortterm vmalertmanager/alertmanager
-kubectl wait --timeout=5m --for=jsonpath=.status.status=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
-kubectl wait --timeout=5m --for=condition=ready -n tenant-root clusters.postgresql.cnpg.io grafana-db
-kubectl wait --timeout=5m --for=condition=available -n tenant-root deploy grafana-deployment 
-
-# Get IP of nginx-ingress
-ip=$(kubectl get svc -n tenant-root root-ingress-controller -o jsonpath='{.status.loadBalancer.ingress..ip}')
-
-# Check Grafana
-curl -sS -k "https://$ip" -H 'Host: grafana.example.org' | grep Found
-
-
-# Test OIDC
-kubectl patch -n cozy-system cm/cozystack --type=merge -p '{"data":{
-  "oidc-enabled": "true"
-}}'
-
-timeout 60 sh -c 'until kubectl get hr -n cozy-keycloak keycloak keycloak-configure keycloak-operator; do sleep 1; done'
-kubectl wait --timeout=10m --for=condition=ready -n cozy-keycloak hr keycloak keycloak-configure keycloak-operator

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
 )
 
@@ -15,48 +16,49 @@ 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}' - $file)
+miss_map=$(mktemp)
+trap 'rm -f "$miss_map"' EXIT
+echo -n "$new_map" | awk 'NR==FNR { nm[$1 " " $2] = $3; next } { if (!($1 " " $2 in nm)) print $1, $2, $3}' - "$file" > $miss_map
+
+# search accross all tags sorted by version
+search_commits=$(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 "$change_commit~1")
-        fi
+  while read -r chart version commit; do
+    # if version is found in HEAD, it's HEAD
+    if [ "$(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" | 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"
-  done
+
+    # 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" | 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 < $miss_map
 )
 
 printf "%s\n" "$new_map" "$resolved_miss_map" | sort -k1,1 -k2,2 -V | awk '$1' > "$file"

hack/package_chart.sh

@@ -0,0 +1,65 @@
+#!/bin/sh
+
+set -e
+
+usage() {
+        printf "%s\n" "Usage:" >&2 ;
+        printf -- "%s\n" '---' >&2 ;
+        printf "%s %s\n" "$0" "INPUT_DIR OUTPUT_DIR TMP_DIR [DEPENDENCY_DIR]" >&2 ;
+        printf -- "%s\n" '---' >&2 ;
+        printf "%s\n" "Takes a helm repository from INPUT_DIR, with an optional library repository in" >&2 ;
+        printf "%s\n" "DEPENDENCY_DIR, prepares a view of the git archive at select points in history" >&2 ;
+        printf "%s\n" "in TMP_DIR and packages helm charts, outputting the tarballs to OUTPUT_DIR" >&2 ;
+}
+
+if [ "x$(basename $PWD)" != "xpackages" ]
+then
+        echo "Error: This script must run from the ./packages/ directory" >&2
+        echo >&2
+        usage
+        exit 1
+fi
+
+if [ "x$#" != "x3" ] && [ "x$#" != "x4" ]
+then
+        echo "Error: This script takes 3 or 4 arguments" >&2
+        echo "Got $# arguments:" "$@" >&2
+        echo >&2
+        usage
+        exit 1
+fi
+
+input_dir=$1
+output_dir=$2
+tmp_dir=$3
+
+if [ "x$#" = "x4" ]
+then
+        dependency_dir=$4
+fi
+
+rm -rf "${output_dir:?}"
+mkdir -p "${output_dir}"
+while read package _ commit
+do
+        # this lets devs build the packages from a dirty repo for quick local testing
+        if [ "x$commit" = "xHEAD" ]
+        then
+                helm package "${input_dir}/${package}" -d "${output_dir}"
+                continue
+        fi
+        git archive --format tar "${commit}" "${input_dir}/${package}" | tar -xf- -C "${tmp_dir}/"
+
+        # the library chart is not present in older commits and git archive doesn't fail gracefully if the path is not found
+        if [ "x${dependency_dir}" != "x" ] && git ls-tree --name-only "${commit}" "${dependency_dir}" | grep -qx "${dependency_dir}"
+        then
+                git archive --format tar "${commit}" "${dependency_dir}" | tar -xf- -C "${tmp_dir}/"
+        fi
+        helm package "${tmp_dir}/${input_dir}/${package}" -d "${output_dir}"
+        rm -rf "${tmp_dir:?}/${input_dir:?}/${package:?}"
+        if [ "x${dependency_dir}" != "x" ]
+        then
+                rm -rf "${tmp_dir:?}/${dependency_dir:?}"
+        fi
+done < "${input_dir}/versions_map"
+helm repo index "${output_dir}"

hack/testdata/http-cache/check.sh

@@ -1 +0,0 @@
-return 0

hack/testdata/http-cache/values.yaml

@@ -1,2 +0,0 @@
-endpoints:
-  - 8.8.8.8:443

hack/testdata/kubernetes/check.sh

@@ -1 +0,0 @@
-return 0

hack/testdata/kubernetes/values.yaml

@@ -1,62 +0,0 @@
-## @section Common parameters
-
-## @param host The hostname used to access the Kubernetes cluster externally (defaults to using the cluster name as a subdomain for the tenant host).
-## @param controlPlane.replicas Number of replicas for Kubernetes contorl-plane components
-## @param storageClass StorageClass used to store user data
-##
-host: ""
-controlPlane:
-  replicas: 2
-storageClass: replicated
-
-## @param nodeGroups [object] nodeGroups configuration
-##
-nodeGroups:
-  md0:
-    minReplicas: 0
-    maxReplicas: 10
-    instanceType: "u1.medium"
-    ephemeralStorage: 20Gi
-    roles:
-    - ingress-nginx
-
-    resources:
-      cpu: ""
-      memory: ""
-
-## @section Cluster Addons
-##
-addons:
-
-  ## Cert-manager: automatically creates and manages SSL/TLS certificate
-  ##
-  certManager:
-    ## @param addons.certManager.enabled Enables the cert-manager
-    ## @param addons.certManager.valuesOverride Custom values to override
-    enabled: true
-    valuesOverride: {}
-
-  ## Ingress-NGINX Controller
-  ##
-  ingressNginx:
-    ## @param addons.ingressNginx.enabled Enable Ingress-NGINX controller (expect nodes with 'ingress-nginx' role)
-    ## @param addons.ingressNginx.valuesOverride Custom values to override
-    ##
-    enabled: true
-    ## @param addons.ingressNginx.hosts List of domain names that should be passed through to the cluster by upper cluster
-    ## e.g:
-    ## hosts:
-    ## - example.org
-    ## - foo.example.net
-    ##
-    hosts: []
-    valuesOverride: {}
-
-  ## Flux CD
-  ##
-  fluxcd:
-    ## @param addons.fluxcd.enabled Enables Flux CD
-    ## @param addons.fluxcd.valuesOverride Custom values to override
-    ##
-    enabled: true
-    valuesOverride: {}

hack/testdata/nats/check.sh

@@ -1 +0,0 @@
-return 0

hack/testdata/nats/values.yaml

@@ -1,10 +0,0 @@
-
-## @section Common parameters
-
-## @param external Enable external access from outside the cluster
-## @param replicas Persistent Volume size for NATS
-## @param storageClass StorageClass used to store the data
-##
-external: false
-replicas: 2
-storageClass: ""

hack/testdata/tenant/check.sh

@@ -1 +0,0 @@
-return 0

hack/testdata/tenant/values.yaml

@@ -1,6 +0,0 @@
-host: ""
-etcd: false
-monitoring: false
-ingress: false
-seaweedfs: false
-isolated: true

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/tenant_helm_reconciler.go

@@ -0,0 +1,158 @@
+package controller
+
+import (
+	"context"
+	"fmt"
+	"strings"
+	"time"
+
+	e "errors"
+
+	helmv2 "github.com/fluxcd/helm-controller/api/v2"
+	"gopkg.in/yaml.v2"
+	corev1 "k8s.io/api/core/v1"
+	apiextensionsv1 "k8s.io/apiextensions-apiserver/pkg/apis/apiextensions/v1"
+	"k8s.io/apimachinery/pkg/api/errors"
+	"k8s.io/apimachinery/pkg/runtime"
+	ctrl "sigs.k8s.io/controller-runtime"
+	"sigs.k8s.io/controller-runtime/pkg/client"
+	"sigs.k8s.io/controller-runtime/pkg/log"
+)
+
+type TenantHelmReconciler struct {
+	client.Client
+	Scheme *runtime.Scheme
+}
+
+func (r *TenantHelmReconciler) Reconcile(ctx context.Context, req ctrl.Request) (ctrl.Result, error) {
+	logger := log.FromContext(ctx)
+
+	hr := &helmv2.HelmRelease{}
+	if err := r.Get(ctx, req.NamespacedName, hr); err != nil {
+		if errors.IsNotFound(err) {
+			return ctrl.Result{}, nil
+		}
+		logger.Error(err, "unable to fetch HelmRelease")
+		return ctrl.Result{}, err
+	}
+
+	if !strings.HasPrefix(hr.Name, "tenant-") {
+		return ctrl.Result{}, nil
+	}
+
+	if len(hr.Status.Conditions) == 0 || hr.Status.Conditions[0].Type != "Ready" {
+		return ctrl.Result{}, nil
+	}
+
+	if len(hr.Status.History) == 0 {
+		logger.Info("no history in HelmRelease status", "name", hr.Name)
+		return ctrl.Result{}, nil
+	}
+
+	if hr.Status.History[0].Status != "deployed" {
+		return ctrl.Result{}, nil
+	}
+
+	newDigest := hr.Status.History[0].Digest
+	var hrList helmv2.HelmReleaseList
+	childNamespace := getChildNamespace(hr.Namespace, hr.Name)
+	if childNamespace == "tenant-root" && hr.Name == "tenant-root" {
+		if hr.Spec.Values == nil {
+			logger.Error(e.New("hr.Spec.Values is nil"), "cant annotate tenant-root ns")
+			return ctrl.Result{}, nil
+		}
+		err := annotateTenantRootNs(*hr.Spec.Values, r.Client)
+		if err != nil {
+			logger.Error(err, "cant annotate tenant-root ns")
+			return ctrl.Result{}, nil
+		}
+		logger.Info("namespace 'tenant-root' annotated")
+	}
+
+	if err := r.List(ctx, &hrList, client.InNamespace(childNamespace)); err != nil {
+		logger.Error(err, "unable to list HelmReleases in namespace", "namespace", hr.Name)
+		return ctrl.Result{}, err
+	}
+
+	for _, item := range hrList.Items {
+		if item.Name == hr.Name {
+			continue
+		}
+		oldDigest := item.GetAnnotations()["cozystack.io/tenant-config-digest"]
+		if oldDigest == newDigest {
+			continue
+		}
+		patchTarget := item.DeepCopy()
+
+		if patchTarget.Annotations == nil {
+			patchTarget.Annotations = map[string]string{}
+		}
+		ts := time.Now().Format(time.RFC3339Nano)
+
+		patchTarget.Annotations["cozystack.io/tenant-config-digest"] = newDigest
+		patchTarget.Annotations["reconcile.fluxcd.io/forceAt"] = ts
+		patchTarget.Annotations["reconcile.fluxcd.io/requestedAt"] = ts
+
+		patch := client.MergeFrom(item.DeepCopy())
+		if err := r.Patch(ctx, patchTarget, patch); err != nil {
+			logger.Error(err, "failed to patch HelmRelease", "name", patchTarget.Name)
+			continue
+		}
+
+		logger.Info("patched HelmRelease with new digest", "name", patchTarget.Name, "digest", newDigest, "version", hr.Status.History[0].Version)
+	}
+
+	return ctrl.Result{}, nil
+}
+
+func (r *TenantHelmReconciler) SetupWithManager(mgr ctrl.Manager) error {
+	return ctrl.NewControllerManagedBy(mgr).
+		For(&helmv2.HelmRelease{}).
+		Complete(r)
+}
+
+func getChildNamespace(currentNamespace, hrName string) string {
+	tenantName := strings.TrimPrefix(hrName, "tenant-")
+
+	switch {
+	case currentNamespace == "tenant-root" && hrName == "tenant-root":
+		// 1) root tenant inside root namespace
+		return "tenant-root"
+
+	case currentNamespace == "tenant-root":
+		// 2) any other tenant in root namespace
+		return fmt.Sprintf("tenant-%s", tenantName)
+
+	default:
+		// 3) tenant in a dedicated namespace
+		return fmt.Sprintf("%s-%s", currentNamespace, tenantName)
+	}
+}
+
+func annotateTenantRootNs(values apiextensionsv1.JSON, c client.Client) error {
+	var data map[string]interface{}
+	if err := yaml.Unmarshal(values.Raw, &data); err != nil {
+		return fmt.Errorf("failed to parse HelmRelease values: %w", err)
+	}
+
+	host, ok := data["host"].(string)
+	if !ok || host == "" {
+		return fmt.Errorf("host field not found or not a string")
+	}
+
+	var ns corev1.Namespace
+	if err := c.Get(context.TODO(), client.ObjectKey{Name: "tenant-root"}, &ns); err != nil {
+		return fmt.Errorf("failed to get namespace tenant-root: %w", err)
+	}
+
+	if ns.Annotations == nil {
+		ns.Annotations = map[string]string{}
+	}
+	ns.Annotations["namespace.cozystack.io/host"] = host
+
+	if err := c.Update(context.TODO(), &ns); err != nil {
+		return fmt.Errorf("failed to update namespace: %w", err)
+	}
+
+	return nil
+}

internal/controller/workload_controller.go

@@ -0,0 +1,99 @@
+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)
+
+	if t == nil {
+		err = r.Delete(ctx, w)
+		if err != nil {
+			logger.Error(err, "failed to delete workload")
+		}
+		return ctrl.Result{}, err
+	}
+
+	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 {
+	switch {
+	case strings.HasPrefix(w.Name, "pvc-"):
+		obj := &corev1.PersistentVolumeClaim{}
+		obj.Name = strings.TrimPrefix(w.Name, "pvc-")
+		obj.Namespace = w.Namespace
+		return obj
+	case strings.HasPrefix(w.Name, "svc-"):
+		obj := &corev1.Service{}
+		obj.Name = strings.TrimPrefix(w.Name, "svc-")
+		obj.Namespace = w.Namespace
+		return obj
+	case strings.HasPrefix(w.Name, "pod-"):
+		obj := &corev1.Pod{}
+		obj.Name = strings.TrimPrefix(w.Name, "pod-")
+		obj.Namespace = w.Namespace
+		return obj
+	}
+	var obj client.Object
+	return obj
+}

internal/controller/workload_controller_test.go

@@ -0,0 +1,26 @@
+package controller
+
+import (
+	"testing"
+
+	cozyv1alpha1 "github.com/cozystack/cozystack/api/v1alpha1"
+	corev1 "k8s.io/api/core/v1"
+)
+
+func TestUnprefixedMonitoredObjectReturnsNil(t *testing.T) {
+	w := &cozyv1alpha1.Workload{}
+	w.Name = "unprefixed-name"
+	obj := getMonitoredObject(w)
+	if obj != nil {
+		t.Errorf(`getMonitoredObject(&Workload{Name: "%s"}) == %v, want nil`, w.Name, obj)
+	}
+}
+
+func TestPodMonitoredObject(t *testing.T) {
+	w := &cozyv1alpha1.Workload{}
+	w.Name = "pod-mypod"
+	obj := getMonitoredObject(w)
+	if pod, ok := obj.(*corev1.Pod); !ok || pod.Name != "mypod" {
+		t.Errorf(`getMonitoredObject(&Workload{Name: "%s"}) == %v, want &Pod{Name: "mypod"}`, w.Name, obj)
+	}
+}

internal/controller/workloadmonitor_controller.go

@@ -0,0 +1,435 @@
+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)
+
+	quantity := resource.MustParse("0")
+
+	for _, ing := range svc.Status.LoadBalancer.Ingress {
+		if ing.IP != "" {
+			quantity.Add(resource.MustParse("1"))
+		}
+	}
+
+	var resourceLabel string
+	if svc.Annotations != nil {
+		var ok bool
+		resourceLabel, ok = svc.Annotations["metallb.universe.tf/ip-allocated-from-pool"]
+		if !ok {
+			resourceLabel = "default"
+		}
+	}
+	resourceLabel = fmt.Sprintf("%s.ipaddresspool.metallb.io/requests.ipaddresses", resourceLabel)
+	resources[resourceLabel] = quantity
+
+	_, 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 {
+		storageClass := "default"
+		if pvc.Spec.StorageClassName != nil || *pvc.Spec.StorageClassName == "" {
+			storageClass = *pvc.Spec.StorageClassName
+		}
+		resourceLabel := fmt.Sprintf("%s.storageclass.storage.k8s.io/requests.%s", storageClass, resourceName.String())
+		resources[resourceLabel] = 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)
+
+	// totalResources will store the sum of all container resource requests
+	totalResources := make(map[string]resource.Quantity)
+
+	// Iterate over all containers to aggregate their requests
+	for _, container := range pod.Spec.Containers {
+		for name, qty := range container.Resources.Requests {
+			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:      fmt.Sprintf("pod-%s", 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:v0.20.2"
-        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:v0.20.2"
-        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/Makefile

@@ -1,14 +1,8 @@
-OUT=../../_out/repos/apps
-TMP=../../_out/repos/apps/historical
+OUT=../_out/repos/apps
+TMP := $(shell mktemp -d)
 
 repo:
-	rm -rf "$(OUT)"
-	mkdir -p "$(OUT)"
-	awk '$$3 != "HEAD" {print "mkdir -p $(TMP)/" $$1 "-" $$2}' versions_map | sh -ex
-	awk '$$3 != "HEAD" {print "git archive " $$3 " " $$1 " | tar -xf- --strip-components=1 -C $(TMP)/" $$1 "-" $$2 }' versions_map | sh -ex
-	helm package -d "$(OUT)" $$(find . $(TMP) -mindepth 2 -maxdepth 2 -name Chart.yaml | awk 'sub("/Chart.yaml", "")' | sort -V)
-	cd "$(OUT)" && helm repo index . --url http://cozystack.cozy-system.svc/repos/apps
-	rm -rf "$(TMP)"
+	cd .. && ../hack/package_chart.sh apps $(OUT) $(TMP) library
 
 fix-chartnames:
 	find . -maxdepth 2 -name Chart.yaml  | awk -F/ '{print $$2}' | while read i; do sed -i "s/^name: .*/name: $$i/" "$$i/Chart.yaml"; done

packages/apps/bucket/README.md

@@ -0,0 +1,3 @@
+# S3 bucket
+
+## Parameters

packages/apps/bucket/templates/helmrelease.yaml

@@ -11,7 +11,7 @@ spec:
         kind: HelmRepository
         name: cozystack-system
         namespace: cozy-system
-      version: '*'
+      version: '>= 0.0.0-0'
   interval: 1m0s
   timeout: 5m0s
   values:

packages/apps/bucket/values.schema.json

@@ -0,0 +1,5 @@
+{
+    "title": "Chart Values",
+    "type": "object",
+    "properties": {}
+}

packages/apps/bucket/values.yaml

@@ -0,0 +1 @@
+{}

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: 0.9.0
 
 # 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

@@ -7,13 +7,16 @@ generate:
 	readme-generator -v values.yaml -s values.schema.json -r README.md
 
 image:
-	docker buildx build --platform linux/amd64 --build-arg ARCH=amd64 images/clickhouse-backup \
+	docker buildx build images/clickhouse-backup \
 		--provenance false \
+		--builder=$(BUILDER) \
+		--platform=$(PLATFORM) \
 		--tag $(REGISTRY)/clickhouse-backup:$(call settag,$(CLICKHOUSE_BACKUP_TAG)) \
 		--cache-from type=registry,ref=$(REGISTRY)/clickhouse-backup:latest \
 		--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/charts/cozy-lib

@@ -0,0 +1 @@
+../../../library/cozy-lib

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

@@ -1 +1 @@
-ghcr.io/aenix-io/cozystack/clickhouse-backup:0.6.1@sha256:dda84420cb8648721299221268a00d72a05c7af5b7fb452619bac727068b9e61
+ghcr.io/cozystack/cozystack/clickhouse-backup:0.9.0@sha256:3faf7a4cebf390b9053763107482de175aa0fdb88c1e77424fd81100b1c3a205

packages/apps/clickhouse/templates/_resources.tpl

@@ -0,0 +1,49 @@
+{{/*
+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" -}}
+{{- $presets := dict 
+  "nano" (dict 
+      "requests" (dict "cpu" "100m" "memory" "128Mi" "ephemeral-storage" "50Mi")
+      "limits" (dict "memory" "128Mi" "ephemeral-storage" "2Gi")
+   )
+  "micro" (dict 
+      "requests" (dict "cpu" "250m" "memory" "256Mi" "ephemeral-storage" "50Mi")
+      "limits" (dict "memory" "256Mi" "ephemeral-storage" "2Gi")
+   )
+  "small" (dict 
+      "requests" (dict "cpu" "500m" "memory" "512Mi" "ephemeral-storage" "50Mi")
+      "limits" (dict "memory" "512Mi" "ephemeral-storage" "2Gi")
+   )
+  "medium" (dict 
+      "requests" (dict "cpu" "500m" "memory" "1Gi" "ephemeral-storage" "50Mi")
+      "limits" (dict "memory" "1Gi" "ephemeral-storage" "2Gi")
+   )
+  "large" (dict 
+      "requests" (dict "cpu" "1" "memory" "2Gi" "ephemeral-storage" "50Mi")
+      "limits" (dict "memory" "2Gi" "ephemeral-storage" "2Gi")
+   )
+  "xlarge" (dict 
+      "requests" (dict "cpu" "2" "memory" "4Gi" "ephemeral-storage" "50Mi")
+      "limits" (dict "memory" "4Gi" "ephemeral-storage" "2Gi")
+   )
+  "2xlarge" (dict 
+      "requests" (dict "cpu" "4" "memory" "8Gi" "ephemeral-storage" "50Mi")
+      "limits" (dict "memory" "8Gi" "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: {{- include "cozy-lib.resources.sanitize" .Values.resources | nindent 16 }}
+              {{- else if ne .Values.resourcesPreset "none" }}
+              resources: {{- include "cozy-lib.resources.preset" .Values.resourcesPreset | 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: 0.6.0
 
 # 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@sha256:406d2c5a30fa8b6fe10eab3cba45c06fea3876e81fd123ead6dc3c19347762d0
+ghcr.io/cozystack/cozystack/postgres-backup:0.12.0@sha256:10179ed56457460d95cd5708db2a00130901255fa30c4dd76c65d2ef5622b61f

packages/apps/ferretdb/templates/_resources.tpl

@@ -0,0 +1,49 @@
+{{/*
+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" -}}
+{{- $presets := dict 
+  "nano" (dict 
+      "requests" (dict "cpu" "100m" "memory" "128Mi" "ephemeral-storage" "50Mi")
+      "limits" (dict "memory" "128Mi" "ephemeral-storage" "2Gi")
+   )
+  "micro" (dict 
+      "requests" (dict "cpu" "250m" "memory" "256Mi" "ephemeral-storage" "50Mi")
+      "limits" (dict "memory" "256Mi" "ephemeral-storage" "2Gi")
+   )
+  "small" (dict 
+      "requests" (dict "cpu" "500m" "memory" "512Mi" "ephemeral-storage" "50Mi")
+      "limits" (dict "memory" "512Mi" "ephemeral-storage" "2Gi")
+   )
+  "medium" (dict 
+      "requests" (dict "cpu" "500m" "memory" "1Gi" "ephemeral-storage" "50Mi")
+      "limits" (dict "memory" "1Gi" "ephemeral-storage" "2Gi")
+   )
+  "large" (dict 
+      "requests" (dict "cpu" "1" "memory" "2Gi" "ephemeral-storage" "50Mi")
+      "limits" (dict "memory" "2Gi" "ephemeral-storage" "2Gi")
+   )
+  "xlarge" (dict 
+      "requests" (dict "cpu" "2" "memory" "4Gi" "ephemeral-storage" "50Mi")
+      "limits" (dict "memory" "4Gi" "ephemeral-storage" "2Gi")
+   )
+  "2xlarge" (dict 
+      "requests" (dict "cpu" "4" "memory" "8Gi" "ephemeral-storage" "50Mi")
+      "limits" (dict "memory" "8Gi" "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 +6,23 @@ 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 }}
+    labelSelector:
+      matchLabels:
+        cnpg.io/cluster: {{ .Release.Name }}-postgres
+  {{- 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: 0.5.0
 
 # 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/http-cache/Makefile

@@ -6,13 +6,16 @@ include ../../../scripts/package.mk
 image: image-nginx
 
 image-nginx:
-	docker buildx build --platform linux/amd64 --build-arg ARCH=amd64 images/nginx-cache \
+	docker buildx build images/nginx-cache \
 		--provenance false \
+		--builder=$(BUILDER) \
+		--platform=$(PLATFORM) \
 		--tag $(REGISTRY)/nginx-cache:$(call settag,$(NGINX_CACHE_TAG)) \
 		--cache-from type=registry,ref=$(REGISTRY)/nginx-cache:latest \
 		--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@sha256:27112d470a31725b75b29b29919af06b4ce1339e3b502b08889a92ab7099adde
+ghcr.io/cozystack/cozystack/nginx-cache:0.5.0@sha256:158c35dd6a512bd14e86a423be5c8c7ca91ac71999c73cce2714e4db60a2db43

packages/apps/http-cache/images/nginx-cache/Dockerfile

@@ -1,4 +1,4 @@
-FROM ubuntu:22.04 as stage
+FROM ubuntu:22.04 AS stage
 
 ARG NGINX_VERSION=1.25.3
 ARG IP2LOCATION_C_VERSION=8.6.1
@@ -9,11 +9,15 @@ ARG FIFTYONEDEGREES_NGINX_VERSION=3.2.21.1
 ARG NGINX_CACHE_PURGE_VERSION=2.5.3
 ARG NGINX_VTS_VERSION=0.2.2
 
+ARG TARGETOS
+ARG TARGETARCH
+
 # Install required packages for development
-RUN apt-get update -q \
- && apt-get install -yq \
+RUN apt update -q \
+ && apt install -yq --no-install-recommends \
+    ca-certificates \
     unzip \
-    autoconf \
+    automake \
     build-essential \
     libtool \
     libpcre3 \
@@ -68,7 +72,7 @@ RUN checkinstall \
   --default \
   --pkgname=ip2location-c \
   --pkgversion=${IP2LOCATION_C_VERSION} \
-  --pkgarch=amd64 \
+  --pkgarch=${TARGETARCH} \
   --pkggroup=lib \
   --pkgsource="https://github.com/chrislim2888/IP2Location-C-Library" \
   --maintainer="Eduard Generalov <eduard@generalov.net>" \
@@ -97,7 +101,7 @@ RUN checkinstall \
   --default \
   --pkgname=ip2proxy-c \
   --pkgversion=${IP2PROXY_C_VERSION} \
-  --pkgarch=amd64 \
+  --pkgarch=${TARGETARCH} \
   --pkggroup=lib \
   --pkgsource="https://github.com/ip2location/ip2proxy-c" \
   --maintainer="Eduard Generalov <eduard@generalov.net>" \
@@ -144,7 +148,7 @@ RUN checkinstall \
   --default \
   --pkgname=nginx \
   --pkgversion=$VERS \
-  --pkgarch=amd64 \
+  --pkgarch=${TARGETARCH} \
   --pkggroup=web \
   --provides=nginx \
   --requires=ip2location-c,ip2proxy-c,libssl3,libc-bin,libc6,libzstd1,libpcre++0v5,libpcre16-3,libpcre2-8-0,libpcre3,libpcre32-3,libpcrecpp0v5,libmaxminddb0 \
@@ -165,10 +169,9 @@ COPY nginx-reloader.sh /usr/bin/nginx-reloader.sh
 RUN set -x \
  && groupadd --system --gid 101 nginx \
  && useradd --system --gid nginx --no-create-home --home /nonexistent --comment "nginx user" --shell /bin/false --uid 101 nginx \
- && apt update \
- && apt-get install --no-install-recommends --no-install-suggests -y gnupg1 ca-certificates inotify-tools \
- && apt -y install /packages/*.deb \
- && apt-get clean \
+ && apt update -q \
+ && apt install -yq --no-install-recommends --no-install-suggests gnupg1 ca-certificates inotify-tools \
+ && apt install -y /packages/*.deb \
  && rm -rf /var/lib/apt/lists/* \
  && mkdir -p /var/lib/nginx /var/log/nginx \
  && ln -sf /dev/stdout /var/log/nginx/access.log \

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

@@ -0,0 +1,49 @@
+{{/*
+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" -}}
+{{- $presets := dict 
+  "nano" (dict 
+      "requests" (dict "cpu" "100m" "memory" "128Mi" "ephemeral-storage" "50Mi")
+      "limits" (dict "memory" "128Mi" "ephemeral-storage" "2Gi")
+   )
+  "micro" (dict 
+      "requests" (dict "cpu" "250m" "memory" "256Mi" "ephemeral-storage" "50Mi")
+      "limits" (dict "memory" "256Mi" "ephemeral-storage" "2Gi")
+   )
+  "small" (dict 
+      "requests" (dict "cpu" "500m" "memory" "512Mi" "ephemeral-storage" "50Mi")
+      "limits" (dict "memory" "512Mi" "ephemeral-storage" "2Gi")
+   )
+  "medium" (dict 
+      "requests" (dict "cpu" "500m" "memory" "1Gi" "ephemeral-storage" "50Mi")
+      "limits" (dict "memory" "1Gi" "ephemeral-storage" "2Gi")
+   )
+  "large" (dict 
+      "requests" (dict "cpu" "1" "memory" "2Gi" "ephemeral-storage" "50Mi")
+      "limits" (dict "memory" "2Gi" "ephemeral-storage" "2Gi")
+   )
+  "xlarge" (dict 
+      "requests" (dict "cpu" "2" "memory" "4Gi" "ephemeral-storage" "50Mi")
+      "limits" (dict "memory" "4Gi" "ephemeral-storage" "2Gi")
+   )
+  "2xlarge" (dict 
+      "requests" (dict "cpu" "4" "memory" "8Gi" "ephemeral-storage" "50Mi")
+      "limits" (dict "memory" "8Gi" "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