core/installer: multi-arch talos support

Signed-off-by: nbykov0 <166552198+nbykov0@users.noreply.github.com>

.github/CODEOWNERS

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

@@ -1,18 +1,22 @@
 name: Pre-Commit Checks
 
 on:
-  push:
-    branches:
-      - main
   pull_request:
-    paths-ignore:
-      - '**.md'
+    types: [labeled, opened, synchronize, reopened]
+
+concurrency:
+  group: pre-commit-${{ github.workflow }}-${{ github.event.pull_request.number }}
+  cancel-in-progress: true
+
 jobs:
   pre-commit:
     runs-on: ubuntu-22.04
     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

@@ -4,6 +4,10 @@ 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
@@ -13,7 +17,6 @@ jobs:
       packages: write
 
     if: |
-      contains(github.event.pull_request.labels.*.name, 'ok-to-test') &&
       contains(github.event.pull_request.labels.*.name, 'release') &&
       github.event.action != 'closed'
 
@@ -31,6 +34,64 @@ jobs:
           password: ${{ secrets.GITHUB_TOKEN }}
           registry: ghcr.io
 
+      - name: Extract tag from PR branch
+        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);
+
+      - name: Find draft release and get asset IDs
+        id: fetch_assets
+        uses: actions/github-script@v7
+        with:
+          github-token: ${{ secrets.GH_PAT }}
+          script: |
+            const tag = '${{ steps.get_tag.outputs.tag }}';
+            const releases = await github.rest.repos.listReleases({
+              owner: context.repo.owner,
+              repo: context.repo.repo,
+              per_page: 100
+            });
+            const draft = releases.data.find(r => r.tag_name === tag && r.draft);
+            if (!draft) {
+              core.setFailed(`Draft release '${tag}' not found`);
+              return;
+            }
+            const findAssetId = (name) =>
+              draft.assets.find(a => a.name === name)?.id;
+            const installerId = findAssetId("cozystack-installer.yaml");
+            const diskId = findAssetId("nocloud-amd64.raw.xz");
+            if (!installerId || !diskId) {
+              core.setFailed("Missing required assets");
+              return;
+            }
+            core.setOutput("installer_id", installerId);
+            core.setOutput("disk_id", diskId);
+      
+      - name: Download assets from GitHub API
+        run: |
+          mkdir -p _out/assets
+          curl -sSL \
+            -H "Authorization: token ${GH_PAT}" \
+            -H "Accept: application/octet-stream" \
+            -o _out/assets/cozystack-installer.yaml \
+            "https://api.github.com/repos/${GITHUB_REPOSITORY}/releases/assets/${{ steps.fetch_assets.outputs.installer_id }}"
+          curl -sSL \
+            -H "Authorization: token ${GH_PAT}" \
+            -H "Accept: application/octet-stream" \
+            -o _out/assets/nocloud-amd64.raw.xz \
+            "https://api.github.com/repos/${GITHUB_REPOSITORY}/releases/assets/${{ steps.fetch_assets.outputs.disk_id }}"
+        env:
+          GH_PAT: ${{ secrets.GH_PAT }}
+
       - name: Run tests
         run: make test
 
@@ -39,38 +100,137 @@ jobs:
     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 match = branch.match(/^release-(\d+\.\d+\.\d+(?:[-\w\.]+)?)$/);
-  
-            if (!match) {
-              core.setFailed(`Branch '${branch}' does not match expected format 'release-X.Y.Z[-suffix]'`);
-            } else {
-              const tag = match[1];
-              core.setOutput('tag', tag);
-              console.log(`✅ Extracted tag: ${tag}`);
+            const m = branch.match(/^release-(\d+\.\d+\.\d+(?:[-\w\.]+)?)$/);
+            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 merged commit
+
+      - name: Create tag on merge commit
         run: |
-          git tag ${{ steps.get_tag.outputs.tag }} ${{ github.sha }}
-          git push origin ${{ steps.get_tag.outputs.tag }}
-  
+          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 = '${{ steps.semver.outputs.comparison-result }}' === '<';
+            core.setOutput('make_latest', isRc || outdated ? 'false' : 'legacy');
+
+      # Publish draft release with correct flags
       - name: Publish draft release
         uses: actions/github-script@v7
         with:
@@ -78,19 +238,17 @@ jobs:
             const tag = '${{ steps.get_tag.outputs.tag }}';
             const releases = await github.rest.repos.listReleases({
               owner: context.repo.owner,
-              repo: context.repo.repo
+              repo:  context.repo.repo
             });
-  
-            const release = releases.data.find(r => r.tag_name === tag && r.draft);
-            if (!release) {
-              throw new Error(`Draft release with tag ${tag} not found`);
-            }
-  
+            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: release.id,
-              draft: false
+              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}`);
+
+            console.log(`🚀 Published release for ${tag}`);

.github/workflows/pull-requests.yaml

@@ -4,16 +4,20 @@ 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
+  build:
+    name: Build
     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, 'ok-to-test') &&
       !contains(github.event.pull_request.labels.*.name, 'release')
 
     steps:
@@ -29,11 +33,50 @@ jobs:
           username: ${{ github.repository_owner }}
           password: ${{ secrets.GITHUB_TOKEN }}
           registry: ghcr.io
+        env:
+          DOCKER_CONFIG: ${{ runner.temp }}/.docker
 
-      - name: make build
-        run: |
-          make build
+      - name: Build
+        run: make build
+        env:
+          DOCKER_CONFIG: ${{ runner.temp }}/.docker
 
-      - name: make test
-        run: |
-          make test
+      - name: Build Talos image
+        run: make -C packages/core/installer talos-nocloud
+     
+      - name: Upload installer
+        uses: actions/upload-artifact@v4
+        with:
+          name: cozystack-installer
+          path: _out/assets/cozystack-installer.yaml
+
+      - name: Upload Talos image
+        uses: actions/upload-artifact@v4
+        with:
+          name: talos-image
+          path: _out/assets/nocloud-amd64.raw.xz
+ 
+  test:
+    name: Test
+    runs-on: [self-hosted]
+    needs: build
+
+    # Never run when the PR carries the "release" label.
+    if: |
+      !contains(github.event.pull_request.labels.*.name, 'release')
+
+    steps:
+      - name: Download installer
+        uses: actions/download-artifact@v4
+        with:
+          name: cozystack-installer
+          path: _out/assets/
+
+      - name: Download Talos image
+        uses: actions/download-artifact@v4
+        with:
+          name: talos-image
+          path: _out/assets/
+
+      - name: Test
+        run: make test

.github/workflows/tags.yaml

@@ -3,7 +3,14 @@ name: Versioned Tag
 on:
   push:
     tags:
-      - 'v*.*.*'
+      - '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:
@@ -13,8 +20,10 @@ jobs:
       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
@@ -23,140 +32,201 @@ jobs:
             const tag = context.ref.replace('refs/tags/', '');
             const releases = await github.rest.repos.listReleases({
               owner: context.repo.owner,
-              repo: context.repo.repo
+              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}`);
 
-            const existing = releases.data.find(r => r.tag_name === tag && !r.draft);
-            if (existing) {
-              core.setOutput('skip', 'true');
-            } else {
-              core.setOutput('skip', 'false');
-            }
-
+      # 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
+          fetch-tags:  true
 
-      - name: Login to GitHub Container Registry
+      - 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
+        env:
+          DOCKER_CONFIG: ${{ runner.temp }}/.docker
 
+      # Build project artifacts
       - name: Build
         if: steps.check_release.outputs.skip == 'false'
         run: make build
+        env:
+          DOCKER_CONFIG: ${{ runner.temp }}/.docker
 
+      # Commit built artifacts
       - name: Commit release artifacts
         if: steps.check_release.outputs.skip == 'false'
-        env:
-          GIT_AUTHOR_NAME: ${{ github.actor }}
-          GIT_AUTHOR_EMAIL: ${{ github.actor }}@users.noreply.github.com
         run: |
-          git config user.name "$GIT_AUTHOR_NAME"
-          git config user.email "$GIT_AUTHOR_EMAIL"
+          git 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: ${{ secrets.GITHUB_TOKEN }}
+
+      # Create release-X.Y.Z branch and push (force-update)
       - name: Create release branch
         if: steps.check_release.outputs.skip == 'false'
         run: |
-          BRANCH_NAME="release-${GITHUB_REF#refs/tags/v}"
-          git branch -f "$BRANCH_NAME"
-          git push origin "$BRANCH_NAME" --force
+          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 branch = `release-${version}`;
-            const base = 'main';
-      
+            const base    = '${{ 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}:${branch}`,
+              repo:  context.repo.repo,
+              head:  `${context.repo.owner}:${head}`,
               base
             });
-      
             if (prs.data.length === 0) {
-              const newPr = await github.rest.pulls.create({
+              const pr = await github.rest.pulls.create({
                 owner: context.repo.owner,
-                repo: context.repo.repo,
-                head: branch,
-                base: base,
+                repo:  context.repo.repo,
+                head,
+                base,
                 title: `Release v${version}`,
-                body:
-                  `This PR prepares the release \`v${version}\`.\n` +
-                  `(Please merge it before releasing draft)`,
+                body:  `This PR prepares the release \`v${version}\`.`,
                 draft: false
               });
-      
-              console.log(`Created pull request #${newPr.data.number} from ${branch} to ${base}`);
-      
               await github.rest.issues.addLabels({
                 owner: context.repo.owner,
-                repo: context.repo.repo,
-                issue_number: newPr.data.number,
+                repo:  context.repo.repo,
+                issue_number: pr.data.number,
                 labels: ['release']
               });
-      
+              console.log(`Created PR #${pr.data.number}`);
             } else {
-              console.log(`Pull request already exists from ${branch} to ${base}`);
+              console.log(`PR already exists from ${head} to ${base}`);
             }
-
-      - name: Create or reuse draft release
-        if: steps.check_release.outputs.skip == 'false'
-        id: create_release
-        uses: actions/github-script@v7
-        with:
-          script: |
-            const tag = context.ref.replace('refs/tags/', '');
-            const releases = await github.rest.repos.listReleases({
-              owner: context.repo.owner,
-              repo: context.repo.repo
-            });
-
-            let release = releases.data.find(r => r.tag_name === tag);
-            if (!release) {
-              release = await github.rest.repos.createRelease({
-                owner: context.repo.owner,
-                repo: context.repo.repo,
-                tag_name: tag,
-                name: `${tag}`,
-                draft: true,
-                prerelease: false
-              });
-            }
-            core.setOutput('upload_url', release.upload_url);
-
-      - name: Build assets
-        if: steps.check_release.outputs.skip == 'false'
-        run: make assets
-        env:
-          GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
-
-      - name: Upload assets
-        if: steps.check_release.outputs.skip == 'false'
-        run: make upload_assets VERSION=${GITHUB_REF#refs/tags/}
-        env:
-          GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
-
-      - name: Delete pushed tag
-        if: steps.check_release.outputs.skip == 'false'
-        run: |
-          git push --delete origin ${GITHUB_REF#refs/tags/}
-
-      - name: Run tests
-        run: make test

.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 "$dir" && make generate)
             fi
           done
+          git diff --color=always | cat
         '
       language: script
       files: ^.*$

Makefile

@@ -20,6 +20,7 @@ build: build-deps
 	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
@@ -42,12 +43,11 @@ manifests:
 	(cd packages/core/installer/; helm template -n cozy-installer installer .) > _out/assets/cozystack-installer.yaml
 
 assets:
-	make -C packages/core/installer/ 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

cmd/cozystack-controller/main.go

@@ -39,6 +39,8 @@ import (
 	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
 )
 
@@ -51,6 +53,7 @@ func init() {
 	utilruntime.Must(clientgoscheme.AddToScheme(scheme))
 
 	utilruntime.Must(cozystackiov1alpha1.AddToScheme(scheme))
+	utilruntime.Must(helmv2.AddToScheme(scheme))
 	// +kubebuilder:scaffold:scheme
 }
 
@@ -182,6 +185,14 @@ func main() {
 	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)

dashboards/flux/flux-control-plane.json

@@ -626,7 +626,7 @@
             "datasource": {
               "uid": "${DS_PROMETHEUS}"
             },
-            "expr": "sum(container_memory_working_set_bytes{namespace=\"$namespace\",container!=\"POD\",container!=\"\",pod=~\".*-controller-.*\"}) by (pod)",
+            "expr": "sum(container_memory_working_set_bytes{namespace=\"$namespace\",container!=\"\",pod=~\".*-controller-.*\"}) by (pod)",
             "hide": false,
             "interval": "",
             "legendFormat": "{{pod}}",

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 +1,243 @@
+Cozystack v0.31.0 is a significant release that brings new features, key fixes, and updates to underlying components.
+This version enhances GPU support, improves many components of Cozystack, and introduces a more robust release process to improve stability.
+Below, we'll go over the highlights in each area for current users, developers, and our community.
+
+## Major Features and Improvements
+
+### GPU support for tenant Kubernetes clusters
+
+Cozystack now integrates NVIDIA GPU Operator support for tenant Kubernetes clusters.
+This enables platform users to run GPU-powered AI/ML applications in their own clusters.
+To enable GPU Operator, set `addons.gpuOperator.enabled: true` in the cluster configuration.
+(@kvaps in https://github.com/cozystack/cozystack/pull/834)
+
+Check out Andrei Kvapil's CNCF webinar [showcasing the GPU support by running Stable Diffusion in Cozystack](https://www.youtube.com/watch?v=S__h_QaoYEk).
+
+<!--
+* [kubernetes] Introduce GPU support for tenant Kubernetes clusters. (@kvaps in https://github.com/cozystack/cozystack/pull/834)
+-->
+
+### Cilium Improvements
+
+Cozystack’s Cilium integration received two significant enhancements.
+First, Gateway API support in Cilium is now enabled, allowing advanced L4/L7 routing features via Kubernetes Gateway API.
+We thank Zdenek Janda @zdenekjanda for contributing this feature in https://github.com/cozystack/cozystack/pull/924.
+
+Second, Cozystack now permits custom user-provided parameters in the tenant cluster’s Cilium configuration.
+(@lllamnyp in https://github.com/cozystack/cozystack/pull/917)
+
+<!--
+* [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)
+-->
+
+### Cross-Architecture Builds (ARM Support Beta)
+
+Cozystack's build system was refactored to support multi-architecture binaries and container images.
+This paves the road to running Cozystack on ARM64 servers.
+Changes include Makefile improvements (https://github.com/cozystack/cozystack/pull/907)
+and multi-arch Docker image builds (https://github.com/cozystack/cozystack/pull/932 and https://github.com/cozystack/cozystack/pull/970).
+
+We thank Nikita Bykov @nbykov0 for his ongoing work on ARM support!
+
+<!--
+* 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)
+-->
+
+### VerticalPodAutoscaler (VPA) Expansion
+
+The VerticalPodAutoscaler is now enabled for more Cozystack components to automate resource tuning.
+Specifically, VPA was added for tenant Kubernetes control planes (@klinch0 in https://github.com/cozystack/cozystack/pull/806),
+the Cozystack Dashboard (https://github.com/cozystack/cozystack/pull/828),
+and the Cozystack etcd-operator (https://github.com/cozystack/cozystack/pull/850).
+All Cozystack components that have VPA enabled can automatically adjust their CPU and memory requests based on usage, improving platform and application stability.
+
+<!--
+* 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)
+-->
+
+### Tenant HelmRelease Reconcile Controller
+
+A new controller was introduced to monitor and synchronize HelmRelease resources across tenants.
+This controller propagates configuration changes to tenant workloads and ensures that any HelmRelease defined in a tenant
+stays in sync with platform updates.
+It improves the reliability of deploying managed applications in Cozystack.
+(@klinch0 in https://github.com/cozystack/cozystack/pull/870)
+
+<!--
+* [platform] Introduce a new controller to synchronize tenant HelmReleases and propagate configuration changes. (@klinch0 in https://github.com/cozystack/cozystack/pull/870)
+-->
+
+### Virtual Machine Improvements
+
+**Configurable KubeVirt CPU Overcommit**: The CPU allocation ratio in KubeVirt (how virtual CPUs are overcommitted relative to physical) is now configurable
+via the `cpu-allocation-ratio` value in the Cozystack configmap.
+This means Cozystack administrators can now tune CPU overcommitment for VMs to balance performance vs. density.
+(@lllamnyp in https://github.com/cozystack/cozystack/pull/905)
+
+**KubeVirt VM Export**: Cozystack now allows exporting KubeVirt virtual machines.
+This feature, enabled via KubeVirt's `VirtualMachineExport` capability, lets users snapshot or back up VM images.
+(@kvaps in https://github.com/cozystack/cozystack/pull/808)
+
+**Support for various storage classes in Virtual Machines**: The `virtual-machine` application (since version 0.9.2) lets you pick any StorageClass for a VM's 
+system disk instead of relying on a hard-coded PVC.
+Refer to values `systemDisk.storage` and `systemDisk.storageClass` in the [application's configs](https://cozystack.io/docs/reference/applications/virtual-machine/#common-parameters).
+(@kvaps in https://github.com/cozystack/cozystack/pull/974)
+
+<!--
+* [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)
+-->
+
+### Other Features and Improvements
+
+* [platform] Introduce options `expose-services`, `expose-ingress`, and `expose-external-ips` to the ingress service. (@kvaps in https://github.com/cozystack/cozystack/pull/929)
+* [cozystack-controller] Record the IP address pool and storage class in Workload objects. (@lllamnyp in https://github.com/cozystack/cozystack/pull/831)
+* [apps] Remove user-facing config of limits and requests. (@lllamnyp in https://github.com/cozystack/cozystack/pull/935)
+
+## New Release Lifecycle
+
+Cozystack release lifecycle is changing to provide a more stable and predictable lifecycle to customers running Cozystack in mission-critical environments.
+
+* **Gradual Release with Alpha, Beta, and Release Candidates**: Cozystack will now publish pre-release versions (alpha, beta, release candidates) before a stable release.
+  Starting with v0.31.0, the team made three release candidates before releasing version v0.31.0.
+  This allows more testing and feedback before marking a release as stable.
+
+* **Prolonged Release Support with Patch Versions**: After the initial `vX.Y.0` release, a long-lived branch `release-X.Y` will be created to backport fixes.
+  For example, with 0.31.0’s release, a `release-0.31` branch will track patch fixes (`0.31.x`).
+  This strategy lets Cozystack users receive timely patch releases and updates with minimal risks.
+
+To implement these new changes, we have rebuilt our CI/CD workflows and introduced automation, enabling automatic backports.
+You can read more about how it's implemented in the Development section below.
+
+For more information, read the [Cozystack Release Workflow](https://github.com/cozystack/cozystack/blob/main/docs/release.md) documentation.
+
+## 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)
+* [virtual-machine] Set PortList method by default. (@kvaps in https://github.com/cozystack/cozystack/pull/996)
+* [virtual-machine] Specify ports even for wholeIP mode. (@kvaps in https://github.com/cozystack/cozystack/pull/1000)
+* [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)
+* [kubernetes, apps] Enable `topologySpreadConstraints` for tenant Kubernetes clusters and fix it for managed PostgreSQL. (@klinch0 in https://github.com/cozystack/cozystack/pull/995)
+* [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)
+* [dx] remove version_map and building for library charts. (@kvaps in https://github.com/cozystack/cozystack/pull/998)
+* [docs] Review the tenant Kubernetes cluster docs. (@NickVolynkin in https://github.com/cozystack/cozystack/pull/969)
+* [docs] Explain that tenants cannot have dashes in their names. (@NickVolynkin in https://github.com/cozystack/cozystack/pull/980)
+
+## Dependencies
+
+* MetalLB images are now built in-tree based on version 0.14.9 with additional critical patches. (@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)
+
+## Documentation
+
+* [Installing Talos in Air-Gapped Environment](https://cozystack.io/docs/operations/talos/configuration/air-gapped/):
+  new guide for configuring and bootstrapping Talos Linux clusters in air-gapped environments.
+  (@klinch0 in https://github.com/cozystack/website/pull/203)
+
+* [Cozystack Bundles](https://cozystack.io/docs/guides/bundles/): new page in the learning section explaining how Cozystack bundles work and how to choose a bundle.
+  (@NickVolynkin in https://github.com/cozystack/website/pull/188, https://github.com/cozystack/website/pull/189, and others;
+  updated by @kvaps in https://github.com/cozystack/website/pull/192 and https://github.com/cozystack/website/pull/193)
+
+* [Managed Application Reference](https://cozystack.io/docs/reference/applications/): A set of new pages in the docs, mirroring application docs from the Cozystack dashboard.
+  (@NickVolynkin in https://github.com/cozystack/website/pull/198, https://github.com/cozystack/website/pull/202, and https://github.com/cozystack/website/pull/204)
+
+* **LINSTOR Networking**: Guides on [configuring dedicated network for LINSTOR](https://cozystack.io/docs/operations/storage/dedicated-network/)
+and [configuring network for distributed storage in multi-datacenter setup](https://cozystack.io/docs/operations/stretched/linstor-dedicated-network/).
+(@xy2, edited by @NickVolynkin in https://github.com/cozystack/website/pull/171, https://github.com/cozystack/website/pull/182, and https://github.com/cozystack/website/pull/184)
+
+### Fixes
+
+* Correct error in the doc for the command to edit the configmap. (@lb0o in https://github.com/cozystack/website/pull/207)
+* Fix group name in OIDC docs (@kingdonb in https://github.com/cozystack/website/pull/179)
+* A bit more explanation of Docker buildx builders. (@nbykov0 in https://github.com/cozystack/website/pull/187)
+
+## Development, Testing, and CI/CD
+
+### Testing
+
+Improvements:
+
+* Introduce `cozytest` — a new [BATS-based](https://github.com/bats-core/bats-core) testing framework. (@kvaps in https://github.com/cozystack/cozystack/pull/982)
+
+Fixes:
+
+* Fix `device_ownership_from_security_context` CRI. (@dtrdnk in https://github.com/cozystack/cozystack/pull/896)
+* Increase timeout durations for `capi` and `keycloak` to improve reliability during e2e-tests. (@kvaps in https://github.com/cozystack/cozystack/pull/858)
+* Return `genisoimage` to the e2e-test Dockerfile (@gwynbleidd2106 in https://github.com/cozystack/cozystack/pull/962)
+
+### CI/CD Changes
+                          
+Improvements:
+
+* 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:
+
+* 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)
+* If the release step was skipped on a tag, skip tests as well. (@kvaps in https://github.com/cozystack/cozystack/pull/822)
+* Allow CI to cancel the previous job if a new one is scheduled. (@kvaps in https://github.com/cozystack/cozystack/pull/873)
+* Use the correct version name when uploading build assets to the release page. (@kvaps in https://github.com/cozystack/cozystack/pull/876)
+* Stop using `ok-to-test` label to trigger CI in pull requests. (@kvaps in https://github.com/cozystack/cozystack/pull/875)
+* Do not run tests in the release building pipeline. (@kvaps in https://github.com/cozystack/cozystack/pull/882)
+* Fix release branch creation. (@kvaps in https://github.com/cozystack/cozystack/pull/884)
+* Reduce noise in the test logs by suppressing the `wget` progress bar. (@lllamnyp in https://github.com/cozystack/cozystack/pull/865)
+* Revert "automatically trigger tests in releasing PR". (@kvaps in https://github.com/cozystack/cozystack/pull/900)
+* Force-update release branch on tagged main commits. (@kvaps in https://github.com/cozystack/cozystack/pull/977)
+* Show detailed errors in the `pull-request-release` workflow. (@lllamnyp in https://github.com/cozystack/cozystack/pull/992)
+
+## Community and Maintenance
+
+### Repository Maintenance
+
+Added @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
+
+See https://github.com/cozystack/cozystack/compare/v0.30.0...v0.31.0

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.

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/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 +1,391 @@
+#!/usr/bin/env bats
+# -----------------------------------------------------------------------------
+# Cozystack end‑to‑end provisioning test (Bats)
+# -----------------------------------------------------------------------------
+
+@test "Required installer assets exist" {
+  if [ ! -f _out/assets/cozystack-installer.yaml ]; then
+    echo "Missing: _out/assets/cozystack-installer.yaml" >&2
+    exit 1
+  fi
+
+  if [ ! -f _out/assets/nocloud-amd64.raw.xz ]; then
+    echo "Missing: _out/assets/nocloud-amd64.raw.xz" >&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${i}" && genisoimage \
+        -output seed.img \
+        -volid cidata -rational-rock -joliet \
+        user-data meta-data network-config )
+  done
+}
+
+@test "Use Talos NoCloud image from assets" {
+  if [ ! -f _out/assets/nocloud-amd64.raw.xz ]; then
+    echo "Missing _out/assets/nocloud-amd64.raw.xz" 2>&1
+    exit 1
+  fi
+
+  rm -f nocloud-amd64.raw
+  cp _out/assets/nocloud-amd64.raw.xz .
+  xz --decompress nocloud-amd64.raw.xz
+}
+
+@test "Prepare VM disks" {
+  for i in 1 2 3; do
+    cp nocloud-amd64.raw srv${i}/system.img
+    qemu-img resize srv${i}/system.img 50G
+    qemu-img create srv${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 file
+  kubectl apply -f _out/assets/cozystack-installer.yaml
+
+  # 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

@@ -1,361 +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$i && genisoimage \
-      -output seed.img \
-      -volid cidata -rational-rock -joliet \
-      user-data meta-data network-config
-  )
-done
-
-# Prepare system drive
-if [ ! -f nocloud-amd64.raw ]; then
-  wget https://github.com/cozystack/cozystack/releases/latest/download/nocloud-amd64.raw.xz -O nocloud-amd64.raw.xz
-  rm -f nocloud-amd64.raw
-  xz --decompress nocloud-amd64.raw.xz
-fi
-for i in 1 2 3; do
-  cp nocloud-amd64.raw srv$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 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
-
-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
-  registries:
-    mirrors:
-      docker.io:
-        endpoints:
-        - https://mirror.gcr.io
-  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:
-  nodeLabels:
-    node.kubernetes.io/exclude-from-external-load-balancers:
-      $patch: delete
-  network:
-    interfaces:
-    - interface: eth0
-      vip:
-        ip: 192.168.123.10
-cluster:
-  allowSchedulingOnControlPlanes: true
-  controllerManager:
-    extraArgs:
-      bind-address: 0.0.0.0
-  scheduler:
-    extraArgs:
-      bind-address: 0.0.0.0
-  apiServer:
-    certSANs:
-    - 127.0.0.1
-  proxy:
-    disabled: true
-  discovery:
-    enabled: false
-  etcd:
-    advertisedSubnets:
-    - 192.168.123.0/24
-EOT
-
-# Gen configuration
-if [ ! -f secrets.yaml ]; then
-  talosctl gen secrets
-fi
-
-rm -f controlplane.yaml worker.yaml talosconfig kubeconfig
-talosctl gen config --with-secrets secrets.yaml cozystack https://192.168.123.10:6443 --config-patch=@patch.yaml --config-patch-control-plane @patch-controlplane.yaml
-export TALOSCONFIG=$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
-timeout 30 sh -c 'until kubectl get deploy -n cozy-cluster-api capi-controller-manager capi-kamaji-controller-manager capi-kubeadm-bootstrap-controller-manager capi-operator-cluster-api-operator capk-controller-manager; do sleep 1; done'
-kubectl wait deploy --timeout=30s --for=condition=available -n cozy-cluster-api capi-controller-manager capi-kamaji-controller-manager capi-kubeadm-bootstrap-controller-manager capi-operator-cluster-api-operator capk-controller-manager
-
-# Wait for linstor controller
-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
-
-# Wait for cozystack-api
-kubectl wait --for=condition=Available apiservices v1alpha1.apps.cozystack.io --timeout=2m
-
-kubectl patch -n tenant-root tenants.apps.cozystack.io root --type=merge -p '{"spec":{
-  "host": "example.org",
-  "ingress": true,
-  "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 tenant-root
-
-if ! kubectl wait --timeout=2m --for=condition=ready -n tenant-root hr monitoring; then
-  flux reconcile hr monitoring -n tenant-root --force
-  kubectl wait --timeout=2m --for=condition=ready -n tenant-root hr monitoring
-fi
-
-kubectl patch -n tenant-root ingresses.apps.cozystack.io ingress --type=merge -p '{"spec":{
-  "dashboard": true
-}}'
-
-# 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.updateStatus=operational -n tenant-root vlogs/generic
-kubectl wait --timeout=5m --for=jsonpath=.status.clusterStatus=operational -n tenant-root vmcluster/shortterm vmcluster/longterm
-
-# Wait for grafana
-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

@@ -16,22 +16,24 @@ if [ ! -f "$file" ] || [ ! -s "$file" ]; then
   exit 0
 fi
 
-miss_map=$(echo "$new_map" | awk 'NR==FNR { nm[$1 " " $2] = $3; next } { if (!($1 " " $2 in nm)) 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 -r chart version commit; do
+  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) = "${version}" ]; then
+    if [ "$(awk '$1 == "version:" {print $2}' ./${chart}/Chart.yaml)" = "${version}" ]; then
       echo "$chart $version HEAD"
       continue
     fi
 
     # if commit is not HEAD, check if it's valid
-    if [ $commit != "HEAD" ]; then
-      if [ $(git show "${commit}:./${chart}/Chart.yaml" 2>/dev/null | awk '$1 == "version:" {print $2}') != "${version}" ]; then
+    if [ "$commit" != "HEAD" ]; then
+      if [ "$(git show "${commit}:./${chart}/Chart.yaml" | awk '$1 == "version:" {print $2}')" != "${version}" ]; then
         echo "Commit $commit for $chart $version is not valid" >&2
         exit 1
       fi
@@ -44,7 +46,7 @@ resolved_miss_map=$(
     # if commit is HEAD, but version is not found in HEAD, check all tags
     found_tag=""
     for tag in $search_commits; do
-      if [ $(git show "${tag}:./${chart}/Chart.yaml" 2>/dev/null | awk '$1 == "version:" {print $2}') = "${version}" ]; then
+      if [ "$(git show "${tag}:./${chart}/Chart.yaml" | awk '$1 == "version:" {print $2}')" = "${version}" ]; then
         found_tag=$(git rev-parse --short "${tag}")
         break
       fi
@@ -56,7 +58,7 @@ resolved_miss_map=$(
     fi
     
     echo "$chart $version $found_tag"
-  done
+  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/upload-assets.sh

@@ -4,8 +4,18 @@ 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-arm64.iso
+
 gh release upload --clobber $version _out/assets/metal-amd64.raw.xz
+gh release upload --clobber $version _out/assets/metal-arm64.raw.xz
+
 gh release upload --clobber $version _out/assets/nocloud-amd64.raw.xz
+gh release upload --clobber $version _out/assets/nocloud-arm64.raw.xz
+
 gh release upload --clobber $version _out/assets/kernel-amd64
+gh release upload --clobber $version _out/assets/kernel-arm64
+
 gh release upload --clobber $version _out/assets/initramfs-metal-amd64.xz
+gh release upload --clobber $version _out/assets/initramfs-metal-arm64.xz

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

@@ -39,6 +39,15 @@ func (r *WorkloadReconciler) Reconcile(ctx context.Context, req ctrl.Request) (c
 	}
 
 	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
@@ -68,20 +77,23 @@ func (r *WorkloadReconciler) SetupWithManager(mgr ctrl.Manager) error {
 }
 
 func getMonitoredObject(w *cozyv1alpha1.Workload) client.Object {
-	if strings.HasPrefix(w.Name, "pvc-") {
+	switch {
+	case strings.HasPrefix(w.Name, "pvc-"):
 		obj := &corev1.PersistentVolumeClaim{}
 		obj.Name = strings.TrimPrefix(w.Name, "pvc-")
 		obj.Namespace = w.Namespace
 		return obj
-	}
-	if strings.HasPrefix(w.Name, "svc-") {
+	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
 	}
-	obj := &corev1.Pod{}
-	obj.Name = w.Name
-	obj.Namespace = w.Namespace
+	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

@@ -116,15 +116,24 @@ func (r *WorkloadMonitorReconciler) reconcileServiceForMonitor(
 
 	resources := make(map[string]resource.Quantity)
 
-	q := resource.MustParse("0")
+	quantity := resource.MustParse("0")
 
 	for _, ing := range svc.Status.LoadBalancer.Ingress {
 		if ing.IP != "" {
-			q.Add(resource.MustParse("1"))
+			quantity.Add(resource.MustParse("1"))
 		}
 	}
 
-	resources["public-ips"] = q
+	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
@@ -165,7 +174,12 @@ func (r *WorkloadMonitorReconciler) reconcilePVCForMonitor(
 	resources := make(map[string]resource.Quantity)
 
 	for resourceName, resourceQuantity := range pvc.Status.Capacity {
-		resources[resourceName.String()] = resourceQuantity
+		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 {
@@ -198,15 +212,12 @@ func (r *WorkloadMonitorReconciler) reconcilePodForMonitor(
 ) error {
 	logger := log.FromContext(ctx)
 
-	// Combine both init containers and normal containers to sum resources properly
-	combinedContainers := append(pod.Spec.InitContainers, pod.Spec.Containers...)
-
-	// totalResources will store the sum of all container resource limits
+	// totalResources will store the sum of all container resource requests
 	totalResources := make(map[string]resource.Quantity)
 
-	// Iterate over all containers to aggregate their Limits
-	for _, container := range combinedContainers {
-		for name, qty := range container.Resources.Limits {
+	// 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
@@ -235,7 +246,7 @@ func (r *WorkloadMonitorReconciler) reconcilePodForMonitor(
 
 	workload := &cozyv1alpha1.Workload{
 		ObjectMeta: metav1.ObjectMeta{
-			Name:      pod.Name,
+			Name:      fmt.Sprintf("pod-%s", pod.Name),
 			Namespace: pod.Namespace,
 		},
 	}

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

@@ -16,10 +16,15 @@ 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: 0.7.0
+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
 # follow Semantic Versioning. They should reflect the version the application is using.
 # It is recommended to use it with quotes.
 appVersion: "24.9.2"
+
+dependencies:
+  - name: cozy-lib
+    version: 0.1.0
+    repository: "http://cozystack.cozy-system.svc/repos/library"

packages/apps/clickhouse/Makefile

@@ -7,8 +7,10 @@ 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 \

packages/apps/clickhouse/charts/cozy-lib

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

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

@@ -1 +1 @@
-ghcr.io/cozystack/cozystack/clickhouse-backup:0.7.0@sha256:3faf7a4cebf390b9053763107482de175aa0fdb88c1e77424fd81100b1c3a205
+ghcr.io/cozystack/cozystack/clickhouse-backup:0.9.0@sha256:3faf7a4cebf390b9053763107482de175aa0fdb88c1e77424fd81100b1c3a205

packages/apps/clickhouse/templates/_resources.tpl

@@ -11,35 +11,34 @@ These presets are for basic testing and not meant to be used in production
 {{ include "resources.preset" (dict "type" "nano") -}}
 */}}
 {{- define "resources.preset" -}}
-{{/* The limits are the requests increased by 50% (except ephemeral-storage and xlarge/2xlarge sizes)*/}}
 {{- $presets := dict 
   "nano" (dict 
       "requests" (dict "cpu" "100m" "memory" "128Mi" "ephemeral-storage" "50Mi")
-      "limits" (dict "cpu" "150m" "memory" "192Mi" "ephemeral-storage" "2Gi")
+      "limits" (dict "memory" "128Mi" "ephemeral-storage" "2Gi")
    )
   "micro" (dict 
       "requests" (dict "cpu" "250m" "memory" "256Mi" "ephemeral-storage" "50Mi")
-      "limits" (dict "cpu" "375m" "memory" "384Mi" "ephemeral-storage" "2Gi")
+      "limits" (dict "memory" "256Mi" "ephemeral-storage" "2Gi")
    )
   "small" (dict 
       "requests" (dict "cpu" "500m" "memory" "512Mi" "ephemeral-storage" "50Mi")
-      "limits" (dict "cpu" "750m" "memory" "768Mi" "ephemeral-storage" "2Gi")
+      "limits" (dict "memory" "512Mi" "ephemeral-storage" "2Gi")
    )
   "medium" (dict 
-      "requests" (dict "cpu" "500m" "memory" "1024Mi" "ephemeral-storage" "50Mi")
-      "limits" (dict "cpu" "750m" "memory" "1536Mi" "ephemeral-storage" "2Gi")
+      "requests" (dict "cpu" "500m" "memory" "1Gi" "ephemeral-storage" "50Mi")
+      "limits" (dict "memory" "1Gi" "ephemeral-storage" "2Gi")
    )
   "large" (dict 
-      "requests" (dict "cpu" "1.0" "memory" "2048Mi" "ephemeral-storage" "50Mi")
-      "limits" (dict "cpu" "1.5" "memory" "3072Mi" "ephemeral-storage" "2Gi")
+      "requests" (dict "cpu" "1" "memory" "2Gi" "ephemeral-storage" "50Mi")
+      "limits" (dict "memory" "2Gi" "ephemeral-storage" "2Gi")
    )
   "xlarge" (dict 
-      "requests" (dict "cpu" "1.0" "memory" "3072Mi" "ephemeral-storage" "50Mi")
-      "limits" (dict "cpu" "3.0" "memory" "6144Mi" "ephemeral-storage" "2Gi")
+      "requests" (dict "cpu" "2" "memory" "4Gi" "ephemeral-storage" "50Mi")
+      "limits" (dict "memory" "4Gi" "ephemeral-storage" "2Gi")
    )
   "2xlarge" (dict 
-      "requests" (dict "cpu" "1.0" "memory" "3072Mi" "ephemeral-storage" "50Mi")
-      "limits" (dict "cpu" "6.0" "memory" "12288Mi" "ephemeral-storage" "2Gi")
+      "requests" (dict "cpu" "4" "memory" "8Gi" "ephemeral-storage" "50Mi")
+      "limits" (dict "memory" "8Gi" "ephemeral-storage" "2Gi")
    )
  }}
 {{- if hasKey $presets .type -}}

packages/apps/clickhouse/templates/clickhouse.yaml

@@ -122,9 +122,9 @@ spec:
             - name: clickhouse
               image: clickhouse/clickhouse-server:24.9.2.42
               {{- if .Values.resources }}
-              resources: {{- toYaml .Values.resources | nindent 16 }}
+              resources: {{- include "cozy-lib.resources.sanitize" (list .Values.resources $) | nindent 16 }}
               {{- else if ne .Values.resourcesPreset "none" }}
-              resources: {{- include "resources.preset" (dict "type" .Values.resourcesPreset "Release" .Release) | nindent 16 }}
+              resources: {{- include "cozy-lib.resources.preset" (list .Values.resourcesPreset $) | nindent 16 }}
               {{- end }}
               volumeMounts:
                 - name: data-volume-template

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: 0.5.0
+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/images/postgres-backup.tag

@@ -1 +1 @@
-ghcr.io/cozystack/cozystack/postgres-backup:0.10.0@sha256:10179ed56457460d95cd5708db2a00130901255fa30c4dd76c65d2ef5622b61f
+ghcr.io/cozystack/cozystack/postgres-backup:0.12.0@sha256:10179ed56457460d95cd5708db2a00130901255fa30c4dd76c65d2ef5622b61f

packages/apps/ferretdb/templates/_resources.tpl

@@ -11,35 +11,34 @@ These presets are for basic testing and not meant to be used in production
 {{ include "resources.preset" (dict "type" "nano") -}}
 */}}
 {{- define "resources.preset" -}}
-{{/* The limits are the requests increased by 50% (except ephemeral-storage and xlarge/2xlarge sizes)*/}}
 {{- $presets := dict 
   "nano" (dict 
       "requests" (dict "cpu" "100m" "memory" "128Mi" "ephemeral-storage" "50Mi")
-      "limits" (dict "cpu" "150m" "memory" "192Mi" "ephemeral-storage" "2Gi")
+      "limits" (dict "memory" "128Mi" "ephemeral-storage" "2Gi")
    )
   "micro" (dict 
       "requests" (dict "cpu" "250m" "memory" "256Mi" "ephemeral-storage" "50Mi")
-      "limits" (dict "cpu" "375m" "memory" "384Mi" "ephemeral-storage" "2Gi")
+      "limits" (dict "memory" "256Mi" "ephemeral-storage" "2Gi")
    )
   "small" (dict 
       "requests" (dict "cpu" "500m" "memory" "512Mi" "ephemeral-storage" "50Mi")
-      "limits" (dict "cpu" "750m" "memory" "768Mi" "ephemeral-storage" "2Gi")
+      "limits" (dict "memory" "512Mi" "ephemeral-storage" "2Gi")
    )
   "medium" (dict 
-      "requests" (dict "cpu" "500m" "memory" "1024Mi" "ephemeral-storage" "50Mi")
-      "limits" (dict "cpu" "750m" "memory" "1536Mi" "ephemeral-storage" "2Gi")
+      "requests" (dict "cpu" "500m" "memory" "1Gi" "ephemeral-storage" "50Mi")
+      "limits" (dict "memory" "1Gi" "ephemeral-storage" "2Gi")
    )
   "large" (dict 
-      "requests" (dict "cpu" "1.0" "memory" "2048Mi" "ephemeral-storage" "50Mi")
-      "limits" (dict "cpu" "1.5" "memory" "3072Mi" "ephemeral-storage" "2Gi")
+      "requests" (dict "cpu" "1" "memory" "2Gi" "ephemeral-storage" "50Mi")
+      "limits" (dict "memory" "2Gi" "ephemeral-storage" "2Gi")
    )
   "xlarge" (dict 
-      "requests" (dict "cpu" "1.0" "memory" "3072Mi" "ephemeral-storage" "50Mi")
-      "limits" (dict "cpu" "3.0" "memory" "6144Mi" "ephemeral-storage" "2Gi")
+      "requests" (dict "cpu" "2" "memory" "4Gi" "ephemeral-storage" "50Mi")
+      "limits" (dict "memory" "4Gi" "ephemeral-storage" "2Gi")
    )
   "2xlarge" (dict 
-      "requests" (dict "cpu" "1.0" "memory" "3072Mi" "ephemeral-storage" "50Mi")
-      "limits" (dict "cpu" "6.0" "memory" "12288Mi" "ephemeral-storage" "2Gi")
+      "requests" (dict "cpu" "4" "memory" "8Gi" "ephemeral-storage" "50Mi")
+      "limits" (dict "memory" "8Gi" "ephemeral-storage" "2Gi")
    )
  }}
 {{- if hasKey $presets .type -}}

packages/apps/ferretdb/templates/postgres.yaml

@@ -11,6 +11,9 @@ spec:
   {{- $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 }}

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: 0.4.0
+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

@@ -6,8 +6,10 @@ 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 \

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

@@ -1 +1 @@
-ghcr.io/cozystack/cozystack/nginx-cache:0.4.0@sha256:bef7344da098c4dc400a9e20ffad10ac991df67d09a30026207454abbc91f28b
+ghcr.io/cozystack/cozystack/nginx-cache:0.5.0@sha256:99cd04f09f80eb0c60cc0b2f6bc8180ada7ada00cb594606447674953dfa1b67

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

@@ -11,35 +11,34 @@ These presets are for basic testing and not meant to be used in production
 {{ include "resources.preset" (dict "type" "nano") -}}
 */}}
 {{- define "resources.preset" -}}
-{{/* The limits are the requests increased by 50% (except ephemeral-storage and xlarge/2xlarge sizes)*/}}
 {{- $presets := dict 
   "nano" (dict 
       "requests" (dict "cpu" "100m" "memory" "128Mi" "ephemeral-storage" "50Mi")
-      "limits" (dict "cpu" "150m" "memory" "192Mi" "ephemeral-storage" "2Gi")
+      "limits" (dict "memory" "128Mi" "ephemeral-storage" "2Gi")
    )
   "micro" (dict 
       "requests" (dict "cpu" "250m" "memory" "256Mi" "ephemeral-storage" "50Mi")
-      "limits" (dict "cpu" "375m" "memory" "384Mi" "ephemeral-storage" "2Gi")
+      "limits" (dict "memory" "256Mi" "ephemeral-storage" "2Gi")
    )
   "small" (dict 
       "requests" (dict "cpu" "500m" "memory" "512Mi" "ephemeral-storage" "50Mi")
-      "limits" (dict "cpu" "750m" "memory" "768Mi" "ephemeral-storage" "2Gi")
+      "limits" (dict "memory" "512Mi" "ephemeral-storage" "2Gi")
    )
   "medium" (dict 
-      "requests" (dict "cpu" "500m" "memory" "1024Mi" "ephemeral-storage" "50Mi")
-      "limits" (dict "cpu" "750m" "memory" "1536Mi" "ephemeral-storage" "2Gi")
+      "requests" (dict "cpu" "500m" "memory" "1Gi" "ephemeral-storage" "50Mi")
+      "limits" (dict "memory" "1Gi" "ephemeral-storage" "2Gi")
    )
   "large" (dict 
-      "requests" (dict "cpu" "1.0" "memory" "2048Mi" "ephemeral-storage" "50Mi")
-      "limits" (dict "cpu" "1.5" "memory" "3072Mi" "ephemeral-storage" "2Gi")
+      "requests" (dict "cpu" "1" "memory" "2Gi" "ephemeral-storage" "50Mi")
+      "limits" (dict "memory" "2Gi" "ephemeral-storage" "2Gi")
    )
   "xlarge" (dict 
-      "requests" (dict "cpu" "1.0" "memory" "3072Mi" "ephemeral-storage" "50Mi")
-      "limits" (dict "cpu" "3.0" "memory" "6144Mi" "ephemeral-storage" "2Gi")
+      "requests" (dict "cpu" "2" "memory" "4Gi" "ephemeral-storage" "50Mi")
+      "limits" (dict "memory" "4Gi" "ephemeral-storage" "2Gi")
    )
   "2xlarge" (dict 
-      "requests" (dict "cpu" "1.0" "memory" "3072Mi" "ephemeral-storage" "50Mi")
-      "limits" (dict "cpu" "6.0" "memory" "12288Mi" "ephemeral-storage" "2Gi")
+      "requests" (dict "cpu" "4" "memory" "8Gi" "ephemeral-storage" "50Mi")
+      "limits" (dict "memory" "8Gi" "ephemeral-storage" "2Gi")
    )
  }}
 {{- if hasKey $presets .type -}}

packages/apps/kafka/Chart.yaml

@@ -16,7 +16,7 @@ type: application
 # This is the chart version. This version number should be incremented each time you make changes
 # to the chart and its templates, including the app version.
 # Versions are expected to follow Semantic Versioning (https://semver.org/)
-version: 0.5.0
+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/kafka/templates/_resources.tpl

@@ -11,35 +11,34 @@ These presets are for basic testing and not meant to be used in production
 {{ include "resources.preset" (dict "type" "nano") -}}
 */}}
 {{- define "resources.preset" -}}
-{{/* The limits are the requests increased by 50% (except ephemeral-storage and xlarge/2xlarge sizes)*/}}
 {{- $presets := dict 
   "nano" (dict 
       "requests" (dict "cpu" "100m" "memory" "128Mi" "ephemeral-storage" "50Mi")
-      "limits" (dict "cpu" "150m" "memory" "192Mi" "ephemeral-storage" "2Gi")
+      "limits" (dict "memory" "128Mi" "ephemeral-storage" "2Gi")
    )
   "micro" (dict 
       "requests" (dict "cpu" "250m" "memory" "256Mi" "ephemeral-storage" "50Mi")
-      "limits" (dict "cpu" "375m" "memory" "384Mi" "ephemeral-storage" "2Gi")
+      "limits" (dict "memory" "256Mi" "ephemeral-storage" "2Gi")
    )
   "small" (dict 
       "requests" (dict "cpu" "500m" "memory" "512Mi" "ephemeral-storage" "50Mi")
-      "limits" (dict "cpu" "750m" "memory" "768Mi" "ephemeral-storage" "2Gi")
+      "limits" (dict "memory" "512Mi" "ephemeral-storage" "2Gi")
    )
   "medium" (dict 
-      "requests" (dict "cpu" "500m" "memory" "1024Mi" "ephemeral-storage" "50Mi")
-      "limits" (dict "cpu" "750m" "memory" "1536Mi" "ephemeral-storage" "2Gi")
+      "requests" (dict "cpu" "500m" "memory" "1Gi" "ephemeral-storage" "50Mi")
+      "limits" (dict "memory" "1Gi" "ephemeral-storage" "2Gi")
    )
   "large" (dict 
-      "requests" (dict "cpu" "1.0" "memory" "2048Mi" "ephemeral-storage" "50Mi")
-      "limits" (dict "cpu" "1.5" "memory" "3072Mi" "ephemeral-storage" "2Gi")
+      "requests" (dict "cpu" "1" "memory" "2Gi" "ephemeral-storage" "50Mi")
+      "limits" (dict "memory" "2Gi" "ephemeral-storage" "2Gi")
    )
   "xlarge" (dict 
-      "requests" (dict "cpu" "1.0" "memory" "3072Mi" "ephemeral-storage" "50Mi")
-      "limits" (dict "cpu" "3.0" "memory" "6144Mi" "ephemeral-storage" "2Gi")
+      "requests" (dict "cpu" "2" "memory" "4Gi" "ephemeral-storage" "50Mi")
+      "limits" (dict "memory" "4Gi" "ephemeral-storage" "2Gi")
    )
   "2xlarge" (dict 
-      "requests" (dict "cpu" "1.0" "memory" "3072Mi" "ephemeral-storage" "50Mi")
-      "limits" (dict "cpu" "6.0" "memory" "12288Mi" "ephemeral-storage" "2Gi")
+      "requests" (dict "cpu" "4" "memory" "8Gi" "ephemeral-storage" "50Mi")
+      "limits" (dict "memory" "8Gi" "ephemeral-storage" "2Gi")
    )
  }}
 {{- if hasKey $presets .type -}}

packages/apps/kubernetes/Chart.yaml

@@ -16,10 +16,10 @@ 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: 0.18.0
+version: 0.21.0
 
 # 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
 # follow Semantic Versioning. They should reflect the version the application is using.
 # It is recommended to use it with quotes.
-appVersion: "1.30.1"
+appVersion: 1.32.4

packages/apps/kubernetes/Makefile

@@ -1,4 +1,4 @@
-UBUNTU_CONTAINER_DISK_TAG = v1.30.1
+KUBERNETES_VERSION = v1.32
 KUBERNETES_PKG_TAG = $(shell awk '$$1 == "version:" {print $$2}' Chart.yaml)
 
 include ../../../scripts/common-envs.mk
@@ -6,27 +6,36 @@ include ../../../scripts/package.mk
 
 generate:
 	readme-generator -v values.yaml -s values.schema.json -r README.md
+	yq -o json -i '.properties.controlPlane.properties.apiServer.properties.resourcesPreset.enum = ["none","nano","micro","small","medium","large","xlarge","2xlarge"]' values.schema.json
+	yq -o json -i '.properties.controlPlane.properties.controllerManager.properties.resourcesPreset.enum = ["none","nano","micro","small","medium","large","xlarge","2xlarge"]' values.schema.json
+	yq -o json -i '.properties.controlPlane.properties.scheduler.properties.resourcesPreset.enum = ["none","nano","micro","small","medium","large","xlarge","2xlarge"]' values.schema.json
+	yq -o json -i '.properties.controlPlane.properties.konnectivity.properties.server.properties.resourcesPreset.enum = ["none","nano","micro","small","medium","large","xlarge","2xlarge"]' values.schema.json
 
 image: image-ubuntu-container-disk image-kubevirt-cloud-provider image-kubevirt-csi-driver image-cluster-autoscaler
 
 image-ubuntu-container-disk:
-	docker buildx build --platform linux/amd64 --build-arg ARCH=amd64 images/ubuntu-container-disk \
+	docker buildx build images/ubuntu-container-disk \
 		--provenance false \
-		--tag $(REGISTRY)/ubuntu-container-disk:$(call settag,$(UBUNTU_CONTAINER_DISK_TAG)) \
-		--tag $(REGISTRY)/ubuntu-container-disk:$(call settag,$(UBUNTU_CONTAINER_DISK_TAG)-$(TAG)) \
+		--builder=$(BUILDER) \
+		--platform=$(PLATFORM) \
+		--build-arg KUBERNETES_VERSION=${KUBERNETES_VERSION} \
+		--tag $(REGISTRY)/ubuntu-container-disk:$(call settag,$(KUBERNETES_VERSION)) \
+		--tag $(REGISTRY)/ubuntu-container-disk:$(call settag,$(KUBERNETES_VERSION)-$(TAG)) \
 		--cache-from type=registry,ref=$(REGISTRY)/ubuntu-container-disk:latest \
 		--cache-to type=inline \
 		--metadata-file images/ubuntu-container-disk.json \
 		--push=$(PUSH) \
 		--label "org.opencontainers.image.source=https://github.com/cozystack/cozystack" \
 		--load=$(LOAD)
-	echo "$(REGISTRY)/ubuntu-container-disk:$(call settag,$(UBUNTU_CONTAINER_DISK_TAG))@$$(yq e '."containerimage.digest"' images/ubuntu-container-disk.json -o json -r)" \
+	echo "$(REGISTRY)/ubuntu-container-disk:$(call settag,$(KUBERNETES_VERSION))@$$(yq e '."containerimage.digest"' images/ubuntu-container-disk.json -o json -r)" \
 		> images/ubuntu-container-disk.tag
 	rm -f images/ubuntu-container-disk.json
 
 image-kubevirt-cloud-provider:
-	docker buildx build --platform linux/amd64 --build-arg ARCH=amd64 images/kubevirt-cloud-provider \
+	docker buildx build images/kubevirt-cloud-provider \
 		--provenance false \
+		--builder=$(BUILDER) \
+		--platform=$(PLATFORM) \
 		--tag $(REGISTRY)/kubevirt-cloud-provider:$(call settag,$(KUBERNETES_PKG_TAG)) \
 		--tag $(REGISTRY)/kubevirt-cloud-provider:$(call settag,$(KUBERNETES_PKG_TAG)-$(TAG)) \
 		--cache-from type=registry,ref=$(REGISTRY)/kubevirt-cloud-provider:latest \
@@ -40,8 +49,10 @@ image-kubevirt-cloud-provider:
 	rm -f images/kubevirt-cloud-provider.json
 
 image-kubevirt-csi-driver:
-	docker buildx build --platform linux/amd64 --build-arg ARCH=amd64 images/kubevirt-csi-driver \
+	docker buildx build images/kubevirt-csi-driver \
 		--provenance false \
+		--builder=$(BUILDER) \
+		--platform=$(PLATFORM) \
 		--tag $(REGISTRY)/kubevirt-csi-driver:$(call settag,$(KUBERNETES_PKG_TAG)) \
 		--tag $(REGISTRY)/kubevirt-csi-driver:$(call settag,$(KUBERNETES_PKG_TAG)-$(TAG)) \
 		--cache-from type=registry,ref=$(REGISTRY)/kubevirt-csi-driver:latest \
@@ -56,8 +67,10 @@ image-kubevirt-csi-driver:
 
 
 image-cluster-autoscaler:
-	docker buildx build --platform linux/amd64 --build-arg ARCH=amd64 images/cluster-autoscaler \
+	docker buildx build images/cluster-autoscaler \
 		--provenance false \
+		--builder=$(BUILDER) \
+		--platform=$(PLATFORM) \
 		--tag $(REGISTRY)/cluster-autoscaler:$(call settag,$(KUBERNETES_PKG_TAG)) \
 		--tag $(REGISTRY)/cluster-autoscaler:$(call settag,$(KUBERNETES_PKG_TAG)-$(TAG)) \
 		--cache-from type=registry,ref=$(REGISTRY)/cluster-autoscaler:latest \

packages/apps/kubernetes/README.md

@@ -1,49 +1,199 @@
 # Managed Kubernetes Service
 
-## Overview
+## Managed Kubernetes in Cozystack
 
-The Managed Kubernetes Service offers a streamlined solution for efficiently managing server workloads. Kubernetes has emerged as the industry standard, providing a unified and accessible API, primarily utilizing YAML for configuration. This means that teams can easily understand and work with Kubernetes, streamlining infrastructure management.
+Whenever you want to deploy a custom containerized application in Cozystack, it's best to deploy it to a managed Kubernetes cluster.
 
-The Kubernetes leverages robust software design patterns, enabling continuous recovery in any scenario through the reconciliation method. Additionally, it ensures seamless scaling across a multitude of servers, addressing the challenges posed by complex and outdated APIs found in traditional virtualization platforms. This managed service eliminates the need for developing custom solutions or modifying source code, saving valuable time and effort.
+Cozystack deploys and manages Kubernetes-as-a-service as standalone applications within each tenant’s isolated environment.
+In Cozystack, such clusters are named tenant Kubernetes clusters, while the base Cozystack cluster is called a management or root cluster.
+Tenant clusters are fully separated from the management cluster and are intended for deploying tenant-specific or customer-developed applications.
 
-## Deployment Details
+Within a tenant cluster, users can take advantage of LoadBalancer services and easily provision physical volumes as needed.                               
+The control-plane operates within containers, while the worker nodes are deployed as virtual machines, all seamlessly managed by the application.
 
-The managed Kubernetes service deploys a standard Kubernetes cluster utilizing the Cluster API, Kamaji as control-plane provicer and the KubeVirt infrastructure provider. This ensures a consistent and reliable setup for workloads.
+## Why Use a Managed Kubernetes Cluster?
 
-Within this cluster, users can take advantage of LoadBalancer services and easily provision physical volumes as needed. The control-plane operates within containers, while the worker nodes are deployed as virtual machines, all seamlessly managed by the application.
+Kubernetes has emerged as the industry standard, providing a unified and accessible API, primarily utilizing YAML for configuration.
+This means that teams can easily understand and work with Kubernetes, streamlining infrastructure management.
 
-- Docs: https://github.com/clastix/kamaji
-- Docs: https://cluster-api.sigs.k8s.io/
-- GitHub: https://github.com/clastix/kamaji
-- GitHub: https://github.com/kubernetes-sigs/cluster-api-provider-kubevirt
-- GitHub: https://github.com/kubevirt/csi-driver
+Kubernetes leverages robust software design patterns, enabling continuous recovery in any scenario through the reconciliation method.
+Additionally, it ensures seamless scaling across a multitude of servers,
+addressing the challenges posed by complex and outdated APIs found in traditional virtualization platforms.
+This managed service eliminates the need for developing custom solutions or modifying source code, saving valuable time and effort.
 
+The Managed Kubernetes Service in Cozystack offers a streamlined solution for efficiently managing server workloads.
 
-## How-Tos
+## Starting Work
 
-How to access to deployed cluster:
+Once the tenant Kubernetes cluster is ready, you can get a kubeconfig file to work with it.
+It can be done via UI or a `kubectl` request:
 
-```
-kubectl get secret -n <namespace> kubernetes-<clusterName>-admin-kubeconfig -o go-template='{{ printf "%s\n" (index .data "super-admin.conf" | base64decode) }}' > test
+-   Open the Cozystack dashboard, switch to your tenant, find and open the application page. Copy one of the config files from the **Secrets** section.
+-   Run the following command (using the management cluster kubeconfig):
+
+    ```bash
+    kubectl get secret -n tenant-<name> kubernetes-<clusterName>-admin-kubeconfig -o go-template='{{ printf "%s\n" (index .data "admin.conf" | base64decode) }}' > admin.conf
+    ```
+
+There are several kubeconfig options available:
+
+-   `admin.conf` — The standard kubeconfig for accessing your new cluster.
+    You can create additional Kubernetes users using this configuration.
+-   `admin.svc` — Same token as `admin.conf`, but with the API server address set to the internal service name.
+    Use it for applications running inside the cluster that need API access.
+-   `super-admin.conf` — Similar to `admin.conf`, but with extended administrative permissions.
+    Intended for troubleshooting and cluster maintenance tasks.
+-   `super-admin.svc` — Same as `super-admin.conf`, but pointing to the internal API server address.
+
+## Implementation Details
+
+A tenant Kubernetes cluster in Cozystack is essentially Kubernetes-in-Kubernetes.
+Deploying it involves the following components:
+
+-   **Kamaji Control Plane**: [Kamaji](https://kamaji.clastix.io/) is an open-source project that facilitates the deployment
+    of Kubernetes control planes as pods within a root cluster.
+    Each control plane pod includes essential components like `kube-apiserver`, `controller-manager`, and `scheduler`,
+    allowing for efficient multi-tenancy and resource utilization.
+
+-   **Etcd Cluster**: A dedicated etcd cluster is deployed using Ænix's [etcd-operator](https://github.com/aenix-io/etcd-operator).
+    It provides reliable and scalable key-value storage for the Kubernetes control plane.
+
+-   **Worker Nodes**: Virtual Machines are provisioned to serve as worker nodes using KubeVirt.
+    These nodes are configured to join the tenant Kubernetes cluster, enabling the deployment and management of workloads.
+
+-   **Cluster API**: Cozystack is using the [Kubernetes Cluster API](https://cluster-api.sigs.k8s.io/) to provision the components of a cluster.
+
+This architecture ensures isolated, scalable, and efficient tenant Kubernetes environments.
+
+See the reference for components utilized in this service:
+
+- [Kamaji Control Plane](https://kamaji.clastix.io)
+- [Kamaji — Cluster API](https://kamaji.clastix.io/cluster-api/)
+- [github.com/clastix/kamaji](https://github.com/clastix/kamaji)
+- [KubeVirt](https://kubevirt.io/)
+- [github.com/kubevirt/kubevirt](https://github.com/kubevirt/kubevirt)
+- [github.com/aenix-io/etcd-operator](https://github.com/aenix-io/etcd-operator)
+- [Kubernetes Cluster API](https://cluster-api.sigs.k8s.io/)
+- [github.com/kubernetes-sigs/cluster-api-provider-kubevirt](https://github.com/kubernetes-sigs/cluster-api-provider-kubevirt)
+- [github.com/kubevirt/csi-driver](https://github.com/kubevirt/csi-driver)
+
+## Parameters
+
+### Common Parameters
+
+| Name                    | Description                                                                                                       | Value        |
+| ----------------------- | ----------------------------------------------------------------------------------------------------------------- | ------------ |
+| `host`                  | Hostname used to access the Kubernetes cluster externally. Defaults to `<cluster-name>.<tenant-host>` when empty. | `""`         |
+| `controlPlane.replicas` | Number of replicas for Kubernetes control-plane components.                                                       | `2`          |
+| `storageClass`          | StorageClass used to store user data.                                                                             | `replicated` |
+| `nodeGroups`            | nodeGroups configuration                                                                                          | `{}`         |
+
+### Cluster Addons
+
+| Name                                          | Description                                                                                                                                                                       | Value   |
+| --------------------------------------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ------- |
+| `addons.certManager.enabled`                  | Enable cert-manager, which automatically creates and manages SSL/TLS certificates.                                                                                                | `false` |
+| `addons.certManager.valuesOverride`           | Custom values to override                                                                                                                                                         | `{}`    |
+| `addons.cilium.valuesOverride`                | Custom values to override                                                                                                                                                         | `{}`    |
+| `addons.gatewayAPI.enabled`                   | Enable the Gateway API                                                                                                                                                            | `false` |
+| `addons.ingressNginx.enabled`                 | Enable the Ingress-NGINX controller (requires nodes labeled with the 'ingress-nginx' role).                                                                                       | `false` |
+| `addons.ingressNginx.valuesOverride`          | Custom values to override                                                                                                                                                         | `{}`    |
+| `addons.ingressNginx.hosts`                   | List of domain names that the parent cluster should route to this tenant cluster.                                                                                                 | `[]`    |
+| `addons.gpuOperator.enabled`                  | Enable the GPU-operator                                                                                                                                                           | `false` |
+| `addons.gpuOperator.valuesOverride`           | Custom values to override                                                                                                                                                         | `{}`    |
+| `addons.fluxcd.enabled`                       | Enable FluxCD                                                                                                                                                                     | `false` |
+| `addons.fluxcd.valuesOverride`                | Custom values to override                                                                                                                                                         | `{}`    |
+| `addons.monitoringAgents.enabled`             | Enable monitoring agents (Fluent Bit and VMAgents) to send logs and metrics. If tenant monitoring is enabled, data is sent to tenant storage; otherwise, it goes to root storage. | `false` |
+| `addons.monitoringAgents.valuesOverride`      | Custom values to override                                                                                                                                                         | `{}`    |
+| `addons.verticalPodAutoscaler.valuesOverride` | Custom values to override                                                                                                                                                         | `{}`    |
+
+### Kubernetes Control Plane Configuration
+
+| Name                                               | Description                                                                  | Value   |
+| -------------------------------------------------- | ---------------------------------------------------------------------------- | ------- |
+| `controlPlane.apiServer.resources`                 | Explicit CPU/memory resource requests and limits for the API server.         | `{}`    |
+| `controlPlane.apiServer.resourcesPreset`           | Use a common resources preset when `resources` is not set explicitly.        | `small` |
+| `controlPlane.controllerManager.resources`         | Explicit CPU/memory resource requests and limits for the controller manager. | `{}`    |
+| `controlPlane.controllerManager.resourcesPreset`   | Use a common resources preset when `resources` is not set explicitly.        | `micro` |
+| `controlPlane.scheduler.resources`                 | Explicit CPU/memory resource requests and limits for the scheduler.          | `{}`    |
+| `controlPlane.scheduler.resourcesPreset`           | Use a common resources preset when `resources` is not set explicitly.        | `micro` |
+| `controlPlane.konnectivity.server.resources`       | Explicit CPU/memory resource requests and limits for the Konnectivity.       | `{}`    |
+| `controlPlane.konnectivity.server.resourcesPreset` | Use a common resources preset when `resources` is not set explicitly.        | `micro` |
+
+In production environments, it's recommended to set `resources` explicitly.
+Example of `controlPlane.*.resources`:
+
+```yaml
+resources:
+  limits:
+    cpu: 4000m
+    memory: 4Gi
+  requests:
+    cpu: 100m
+    memory: 512Mi
 ```
 
-# Series
+Allowed values for `controlPlane.*.resourcesPreset` are `none`, `nano`, `micro`, `small`, `medium`, `large`, `xlarge`, `2xlarge`.
+This value is ignored if the corresponding `resources` value is set. 
 
-<!-- source: https://github.com/kubevirt/common-instancetypes/blob/main/README.md -->
+## Resources Reference
 
-.                           |  U  |  O  |  CX  |  M  |  RT
-----------------------------|-----|-----|------|-----|------
-*Has GPUs*                  |     |     |      |     |
-*Hugepages*                 |     |     |  ✓   |  ✓  |  ✓
-*Overcommitted Memory*      |     |  ✓  |      |     |
-*Dedicated CPU*             |     |     |  ✓   |     |  ✓
-*Burstable CPU performance* |  ✓  |  ✓  |      |  ✓  |
-*Isolated emulator threads* |     |     |  ✓   |     |  ✓
-*vNUMA*                     |     |     |  ✓   |     |  ✓
-*vCPU-To-Memory Ratio*      | 1:4 | 1:4 |  1:2 | 1:8 | 1:4
+### instanceType Resources
 
+The following instanceType resources are provided by Cozystack:
 
-## U Series
+| Name          | vCPUs | Memory |
+|---------------|-------|--------|
+| `cx1.2xlarge` | 8     | 16Gi   |
+| `cx1.4xlarge` | 16    | 32Gi   |
+| `cx1.8xlarge` | 32    | 64Gi   |
+| `cx1.large`   | 2     | 4Gi    |
+| `cx1.medium`  | 1     | 2Gi    |
+| `cx1.xlarge`  | 4     | 8Gi    |
+| `gn1.2xlarge` | 8     | 32Gi   |
+| `gn1.4xlarge` | 16    | 64Gi   |
+| `gn1.8xlarge` | 32    | 128Gi  |
+| `gn1.xlarge`  | 4     | 16Gi   |
+| `m1.2xlarge`  | 8     | 64Gi   |
+| `m1.4xlarge`  | 16    | 128Gi  |
+| `m1.8xlarge`  | 32    | 256Gi  |
+| `m1.large`    | 2     | 16Gi   |
+| `m1.xlarge`   | 4     | 32Gi   |
+| `n1.2xlarge`  | 16    | 32Gi   |
+| `n1.4xlarge`  | 32    | 64Gi   |
+| `n1.8xlarge`  | 64    | 128Gi  |
+| `n1.large`    | 4     | 8Gi    |
+| `n1.medium`   | 4     | 4Gi    |
+| `n1.xlarge`   | 8     | 16Gi   |
+| `o1.2xlarge`  | 8     | 32Gi   |
+| `o1.4xlarge`  | 16    | 64Gi   |
+| `o1.8xlarge`  | 32    | 128Gi  |
+| `o1.large`    | 2     | 8Gi    |
+| `o1.medium`   | 1     | 4Gi    |
+| `o1.micro`    | 1     | 1Gi    |
+| `o1.nano`     | 1     | 512Mi  |
+| `o1.small`    | 1     | 2Gi    |
+| `o1.xlarge`   | 4     | 16Gi   |
+| `rt1.2xlarge` | 8     | 32Gi   |
+| `rt1.4xlarge` | 16    | 64Gi   |
+| `rt1.8xlarge` | 32    | 128Gi  |
+| `rt1.large`   | 2     | 8Gi    |
+| `rt1.medium`  | 1     | 4Gi    |
+| `rt1.micro`   | 1     | 1Gi    |
+| `rt1.small`   | 1     | 2Gi    |
+| `rt1.xlarge`  | 4     | 16Gi   |
+| `u1.2xlarge`  | 8     | 32Gi   |
+| `u1.2xmedium` | 2     | 4Gi    |
+| `u1.4xlarge`  | 16    | 64Gi   |
+| `u1.8xlarge`  | 32    | 128Gi  |
+| `u1.large`    | 2     | 8Gi    |
+| `u1.medium`   | 1     | 4Gi    |
+| `u1.micro`    | 1     | 1Gi    |
+| `u1.nano`     | 1     | 512Mi  |
+| `u1.small`    | 1     | 2Gi    |
+| `u1.xlarge`   | 4     | 16Gi   |
+
+### U Series: Universal
 
 The U Series is quite neutral and provides resources for
 general purpose applications.
@@ -54,7 +204,7 @@ attitude towards workloads.
 VMs of instance types will share physical CPU cores on a
 time-slice basis with other VMs.
 
-### U Series Characteristics
+#### U Series Characteristics
 
 Specific characteristics of this series are:
 - *Burstable CPU performance* - The workload has a baseline compute
@@ -63,14 +213,14 @@ Specific characteristics of this series are:
 - *vCPU-To-Memory Ratio (1:4)* - A vCPU-to-Memory ratio of 1:4, for less
   noise per node.
 
-## O Series
+### O Series: Overcommitted
 
 The O Series is based on the U Series, with the only difference
 being that memory is overcommitted.
 
 *O* is the abbreviation for "Overcommitted".
 
-### UO Series Characteristics
+#### O Series Characteristics
 
 Specific characteristics of this series are:
 - *Burstable CPU performance* - The workload has a baseline compute
@@ -81,7 +231,7 @@ Specific characteristics of this series are:
 - *vCPU-To-Memory Ratio (1:4)* - A vCPU-to-Memory ratio of 1:4, for less
   noise per node.
 
-## CX Series
+### CX Series: Compute Exclusive
 
 The CX Series provides exclusive compute resources for compute
 intensive applications.
@@ -95,7 +245,7 @@ the IO threading from cores dedicated to the workload.
 In addition, in this series, the NUMA topology of the used
 cores is provided to the VM.
 
-### CX Series Characteristics
+#### CX Series Characteristics
 
 Specific characteristics of this series are:
 - *Hugepages* - Hugepages are used in order to improve memory
@@ -110,14 +260,14 @@ Specific characteristics of this series are:
   optimize guest sided cache utilization.
 - *vCPU-To-Memory Ratio (1:2)* - A vCPU-to-Memory ratio of 1:2.
 
-## M Series
+### M Series: Memory
 
 The M Series provides resources for memory intensive
 applications.
 
 *M* is the abbreviation of "Memory".
 
-### M Series Characteristics
+#### M Series Characteristics
 
 Specific characteristics of this series are:
 - *Hugepages* - Hugepages are used in order to improve memory
@@ -128,7 +278,7 @@ Specific characteristics of this series are:
 - *vCPU-To-Memory Ratio (1:8)* - A vCPU-to-Memory ratio of 1:8, for much
   less noise per node.
 
-## RT Series
+### RT Series: RealTime
 
 The RT Series provides resources for realtime applications, like Oslat.
 
@@ -137,7 +287,7 @@ The RT Series provides resources for realtime applications, like Oslat.
 This series of instance types requires nodes capable of running
 realtime applications.
 
-### RT Series Characteristics
+#### RT Series Characteristics
 
 Specific characteristics of this series are:
 - *Hugepages* - Hugepages are used in order to improve memory
@@ -151,57 +301,3 @@ Specific characteristics of this series are:
 - *vCPU-To-Memory Ratio (1:4)* - A vCPU-to-Memory ratio of 1:4 starting from
   the medium size.
 
-## Resources
-
-The following instancetype resources are provided by Cozystack:
-
-Name | vCPUs | Memory
------|-------|-------
-cx1.2xlarge  |  8  |  16Gi
-cx1.4xlarge  |  16  |  32Gi
-cx1.8xlarge  |  32  |  64Gi
-cx1.large  |  2  |  4Gi
-cx1.medium  |  1  |  2Gi
-cx1.xlarge  |  4  |  8Gi
-gn1.2xlarge  |  8  |  32Gi
-gn1.4xlarge  |  16  |  64Gi
-gn1.8xlarge  |  32  |  128Gi
-gn1.xlarge  |  4  |  16Gi
-m1.2xlarge  |  8  |  64Gi
-m1.4xlarge  |  16  |  128Gi
-m1.8xlarge  |  32  |  256Gi
-m1.large  |  2  |  16Gi
-m1.xlarge  |  4  |  32Gi
-n1.2xlarge  |  16  |  32Gi
-n1.4xlarge  |  32  |  64Gi
-n1.8xlarge  |  64  |  128Gi
-n1.large  |  4  |  8Gi
-n1.medium  |  4  |  4Gi
-n1.xlarge  |  8  |  16Gi
-o1.2xlarge  |  8  |  32Gi
-o1.4xlarge  |  16  |  64Gi
-o1.8xlarge  |  32  |  128Gi
-o1.large  |  2  |  8Gi
-o1.medium  |  1  |  4Gi
-o1.micro  |  1  |  1Gi
-o1.nano  |  1  |  512Mi
-o1.small  |  1  |  2Gi
-o1.xlarge  |  4  |  16Gi
-rt1.2xlarge  |  8  |  32Gi
-rt1.4xlarge  |  16  |  64Gi
-rt1.8xlarge  |  32  |  128Gi
-rt1.large  |  2  |  8Gi
-rt1.medium  |  1  |  4Gi
-rt1.micro  |  1  |  1Gi
-rt1.small  |  1  |  2Gi
-rt1.xlarge  |  4  |  16Gi
-u1.2xlarge  |  8  |  32Gi
-u1.2xmedium  |  2  |  4Gi
-u1.4xlarge  |  16  |  64Gi
-u1.8xlarge  |  32  |  128Gi
-u1.large  |  2  |  8Gi
-u1.medium  |  1  |  4Gi
-u1.micro  |  1  |  1Gi
-u1.nano  |  1  |  512Mi
-u1.small  |  1  |  2Gi
-u1.xlarge  |  4  |  16Gi

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

@@ -1 +1 @@
-ghcr.io/cozystack/cozystack/cluster-autoscaler:0.17.1@sha256:85371c6aabf5a7fea2214556deac930c600e362f92673464fe2443784e2869c3
+ghcr.io/cozystack/cozystack/cluster-autoscaler:0.21.0@sha256:7315850634728a5864a3de3150c12f0e1454f3f1ce33cdf21a278f57611dd5e9

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

@@ -1,7 +1,14 @@
 # Source: https://raw.githubusercontent.com/kubernetes/autoscaler/refs/heads/master/cluster-autoscaler/Dockerfile.amd64
 ARG builder_image=docker.io/library/golang:1.23.4
-ARG BASEIMAGE=gcr.io/distroless/static:nonroot-amd64
+ARG BASEIMAGE=gcr.io/distroless/static:nonroot-${TARGETARCH}
+
 FROM ${builder_image} AS builder
+
+ARG TARGETOS
+ARG TARGETARCH
+ENV GOOS=$TARGETOS
+ENV GOARCH=$TARGETARCH
+
 RUN git clone https://github.com/kubernetes/autoscaler /src/autoscaler \
  && cd /src/autoscaler/cluster-autoscaler \
  && git checkout cluster-autoscaler-1.32.0
@@ -14,6 +21,8 @@ RUN make build
 FROM $BASEIMAGE
 LABEL maintainer="Marcin Wielgus <mwielgus@google.com>"
 
-COPY --from=builder /src/autoscaler/cluster-autoscaler/cluster-autoscaler-amd64 /cluster-autoscaler
+ARG TARGETARCH
+
+COPY --from=builder /src/autoscaler/cluster-autoscaler/cluster-autoscaler-${TARGETARCH} /cluster-autoscaler
 WORKDIR /
 CMD ["/cluster-autoscaler"]

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

@@ -1 +1 @@
-ghcr.io/cozystack/cozystack/kubevirt-cloud-provider:0.17.1@sha256:795d8e1ef4b2b0df2aa1e09d96cd13476ebb545b4bf4b5779b7547a70ef64cf9
+ghcr.io/cozystack/cozystack/kubevirt-cloud-provider:0.21.0@sha256:6962bdf51ab2ff40b420b9cff7c850aeea02187da2a65a67f10e0471744649d7

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

@@ -1,5 +1,10 @@
 # Source: https://github.com/kubevirt/cloud-provider-kubevirt/blob/main/build/images/kubevirt-cloud-controller-manager/Dockerfile
-FROM --platform=linux/amd64 golang:1.20.6 AS builder
+FROM golang:1.20.6 AS builder
+
+ARG TARGETOS
+ARG TARGETARCH
+ENV GOOS=$TARGETOS
+ENV GOARCH=$TARGETARCH
 
 RUN git clone https://github.com/kubevirt/cloud-provider-kubevirt /go/src/kubevirt.io/cloud-provider-kubevirt \
  && cd /go/src/kubevirt.io/cloud-provider-kubevirt \
@@ -14,7 +19,7 @@ RUN go get 'k8s.io/endpointslice/util@v0.28' 'k8s.io/apiserver@v0.28'
 RUN go mod tidy
 RUN go mod vendor
 
-RUN	CGO_ENABLED=0 GOOS=linux go build -mod=vendor -ldflags="-s -w" -o bin/kubevirt-cloud-controller-manager ./cmd/kubevirt-cloud-controller-manager
+RUN CGO_ENABLED=0 go build -mod=vendor -ldflags="-s -w" -o bin/kubevirt-cloud-controller-manager ./cmd/kubevirt-cloud-controller-manager
 
 FROM registry.access.redhat.com/ubi9/ubi-micro
 COPY --from=builder /go/src/kubevirt.io/cloud-provider-kubevirt/bin/kubevirt-cloud-controller-manager /bin/kubevirt-cloud-controller-manager

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

@@ -1 +1 @@
-ghcr.io/cozystack/cozystack/kubevirt-csi-driver:0.17.1@sha256:d1346d59224e6d2d07f1551af918ed31e57ba84b750122c1aeceaf9b33dd2271
+ghcr.io/cozystack/cozystack/kubevirt-csi-driver:0.21.0@sha256:b1525163cd21938ac934bb1b860f2f3151464fa463b82880ab058167aeaf3e29

packages/apps/kubernetes/images/kubevirt-csi-driver/Dockerfile

@@ -5,6 +5,11 @@ RUN git clone https://github.com/kubevirt/csi-driver /src/kubevirt-csi-driver \
  && cd /src/kubevirt-csi-driver \
  && git checkout 35836e0c8b68d9916d29a838ea60cdd3fc6199cf
 
+ARG TARGETOS
+ARG TARGETARCH
+ENV GOOS=$TARGETOS
+ENV GOARCH=$TARGETARCH
+
 WORKDIR /src/kubevirt-csi-driver
 RUN make build
 

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

@@ -1 +1 @@
-ghcr.io/cozystack/cozystack/ubuntu-container-disk:v1.30.1@sha256:07392e7a87a3d4ef1c86c1b146e6c5de5c2b524aed5a53bf48870dc8a296f99a
+ghcr.io/cozystack/cozystack/ubuntu-container-disk:v1.32@sha256:bfe568db4b768a4b6c67a8d562892bbba766d0245e140d431754589b347f0b41

packages/apps/kubernetes/images/ubuntu-container-disk/Dockerfile

@@ -1,19 +1,26 @@
-FROM ubuntu:22.04 as guestfish
+# TODO: Here we use ubuntu:22.04, as guestfish has some network issues running in ubuntu:24.04
+FROM ubuntu:22.04 AS guestfish
 
 ARG DEBIAN_FRONTEND=noninteractive
 RUN apt-get update \
  && apt-get -y install \
      libguestfs-tools \
      linux-image-generic \
+     wget \
      make \
-     bash-completion \
- && apt-get clean
+     bash-completion
 
 WORKDIR /build
 
-FROM guestfish as builder
+FROM guestfish AS builder
 
-RUN wget -O image.img https://cloud-images.ubuntu.com/jammy/current/jammy-server-cloudimg-amd64.img
+ARG TARGETOS
+ARG TARGETARCH
+
+# noble is a code name for the Ubuntu 24.04 LTS release
+RUN wget -O image.img https://cloud-images.ubuntu.com/noble/current/noble-server-cloudimg-${TARGETARCH}.img --show-progress --output-file /dev/stdout --progress=dot:giga 2>/dev/null
+
+ARG KUBERNETES_VERSION
 
 RUN qemu-img resize image.img 5G \
  && eval "$(guestfish --listen --network)" \
@@ -24,19 +31,21 @@ RUN qemu-img resize image.img 5G \
  && guestfish --remote command "resize2fs /dev/sda1" \
 # docker repo
  && guestfish --remote sh "curl -fsSL https://download.docker.com/linux/ubuntu/gpg | gpg --dearmor -o /etc/apt/keyrings/docker.gpg" \
- && guestfish --remote sh 'echo "deb [arch=amd64 signed-by=/etc/apt/keyrings/docker.gpg] https://download.docker.com/linux/ubuntu $(lsb_release -cs) stable" | tee /etc/apt/sources.list.d/docker.list' \
+ && guestfish --remote sh 'echo "deb [signed-by=/etc/apt/keyrings/docker.gpg] https://download.docker.com/linux/ubuntu $(lsb_release -cs) stable" | tee /etc/apt/sources.list.d/docker.list' \
 # kubernetes repo
- && guestfish --remote sh "curl -fsSL https://pkgs.k8s.io/core:/stable:/v1.30/deb/Release.key | gpg --dearmor -o /etc/apt/keyrings/kubernetes-apt-keyring.gpg" \
- && guestfish --remote sh "echo 'deb [signed-by=/etc/apt/keyrings/kubernetes-apt-keyring.gpg] https://pkgs.k8s.io/core:/stable:/v1.30/deb/ /' | tee /etc/apt/sources.list.d/kubernetes.list" \
+ && guestfish --remote sh "curl -fsSL https://pkgs.k8s.io/core:/stable:/${KUBERNETES_VERSION}/deb/Release.key | gpg --dearmor -o /etc/apt/keyrings/kubernetes-apt-keyring.gpg" \
+ && guestfish --remote sh "echo 'deb [signed-by=/etc/apt/keyrings/kubernetes-apt-keyring.gpg] https://pkgs.k8s.io/core:/stable:/${KUBERNETES_VERSION}/deb/ /' | tee /etc/apt/sources.list.d/kubernetes.list" \
+ && guestfish --remote command "apt-get check -q" \
 # install containerd
- && guestfish --remote command "apt-get update -y" \
- && guestfish --remote command "apt-get install -y containerd.io" \
+ && guestfish --remote command "apt-get update -q" \
+ && guestfish --remote command "apt-get install -yq containerd.io" \
 # configure containerd
  && guestfish --remote command "mkdir -p /etc/containerd" \
  && guestfish --remote sh "containerd config default | tee /etc/containerd/config.toml" \
  && guestfish --remote command "sed -i '/SystemdCgroup/ s/=.*/= true/' /etc/containerd/config.toml" \
+ && guestfish --remote command "containerd config dump >/dev/null" \
 # install kubernetes
- && guestfish --remote command "apt-get install -y kubelet kubeadm" \
+ && guestfish --remote command "apt-get install -yq kubelet kubeadm" \
 # clean apt cache
  && guestfish --remote sh 'apt-get clean && rm -rf /var/lib/apt/lists/*' \
 # write system configuration

packages/apps/kubernetes/templates/_resources.tpl

@@ -11,35 +11,34 @@ These presets are for basic testing and not meant to be used in production
 {{ include "resources.preset" (dict "type" "nano") -}}
 */}}
 {{- define "resources.preset" -}}
-{{/* The limits are the requests increased by 50% (except ephemeral-storage and xlarge/2xlarge sizes)*/}}
 {{- $presets := dict 
   "nano" (dict 
       "requests" (dict "cpu" "100m" "memory" "128Mi" "ephemeral-storage" "50Mi")
-      "limits" (dict "cpu" "150m" "memory" "192Mi" "ephemeral-storage" "2Gi")
+      "limits" (dict "memory" "128Mi" "ephemeral-storage" "2Gi")
    )
   "micro" (dict 
       "requests" (dict "cpu" "250m" "memory" "256Mi" "ephemeral-storage" "50Mi")
-      "limits" (dict "cpu" "375m" "memory" "384Mi" "ephemeral-storage" "2Gi")
+      "limits" (dict "memory" "256Mi" "ephemeral-storage" "2Gi")
    )
   "small" (dict 
       "requests" (dict "cpu" "500m" "memory" "512Mi" "ephemeral-storage" "50Mi")
-      "limits" (dict "cpu" "750m" "memory" "768Mi" "ephemeral-storage" "2Gi")
+      "limits" (dict "memory" "512Mi" "ephemeral-storage" "2Gi")
    )
   "medium" (dict 
-      "requests" (dict "cpu" "500m" "memory" "1024Mi" "ephemeral-storage" "50Mi")
-      "limits" (dict "cpu" "750m" "memory" "1536Mi" "ephemeral-storage" "2Gi")
+      "requests" (dict "cpu" "500m" "memory" "1Gi" "ephemeral-storage" "50Mi")
+      "limits" (dict "memory" "1Gi" "ephemeral-storage" "2Gi")
    )
   "large" (dict 
-      "requests" (dict "cpu" "1.0" "memory" "2048Mi" "ephemeral-storage" "50Mi")
-      "limits" (dict "cpu" "1.5" "memory" "3072Mi" "ephemeral-storage" "2Gi")
+      "requests" (dict "cpu" "1" "memory" "2Gi" "ephemeral-storage" "50Mi")
+      "limits" (dict "memory" "2Gi" "ephemeral-storage" "2Gi")
    )
   "xlarge" (dict 
-      "requests" (dict "cpu" "1.0" "memory" "3072Mi" "ephemeral-storage" "50Mi")
-      "limits" (dict "cpu" "3.0" "memory" "6144Mi" "ephemeral-storage" "2Gi")
+      "requests" (dict "cpu" "2" "memory" "4Gi" "ephemeral-storage" "50Mi")
+      "limits" (dict "memory" "4Gi" "ephemeral-storage" "2Gi")
    )
   "2xlarge" (dict 
-      "requests" (dict "cpu" "1.0" "memory" "3072Mi" "ephemeral-storage" "50Mi")
-      "limits" (dict "cpu" "6.0" "memory" "12288Mi" "ephemeral-storage" "2Gi")
+      "requests" (dict "cpu" "4" "memory" "8Gi" "ephemeral-storage" "50Mi")
+      "limits" (dict "memory" "8Gi" "ephemeral-storage" "2Gi")
    )
  }}
 {{- if hasKey $presets .type -}}

packages/apps/kubernetes/templates/cluster.yaml

@@ -31,6 +31,16 @@ spec:
             {{- end }}
             cluster.x-k8s.io/deployment-name: {{ $.Release.Name }}-{{ .groupName }}
         spec:
+          {{- $configMap := lookup "v1" "ConfigMap" "cozy-system" "cozystack-scheduling" }}
+          {{- if $configMap }}
+          {{- $rawConstraints := get $configMap.data "globalAppTopologySpreadConstraints" }}
+          {{- if $rawConstraints }}
+          {{- $rawConstraints | fromYaml | toYaml | nindent 10 }}
+            labelSelector:
+              matchLabels:
+                cluster.x-k8s.io/cluster-name: {{ $.Release.Name }}
+          {{- end }}
+          {{- end }}
           domain:
             {{- if and .group.resources .group.resources.cpu }}
             cpu:
@@ -39,6 +49,13 @@ spec:
               sockets: 1
             {{- end }}
             devices:
+              {{- if .group.gpus }}
+              gpus:
+              {{- range $i, $gpu := .group.gpus }}
+              - name: gpu{{ add $i 1 }}
+                deviceName: {{ $gpu.name }}
+              {{- end }}
+              {{- end }}
               disks:
               - name: system
                 disk:
@@ -103,22 +120,22 @@ metadata:
     kamaji.clastix.io/kubeconfig-secret-key: "super-admin.svc"
 spec:
   apiServer:
-    {{- if .Values.kamajiControlPlane.apiServer.resources }}
-    resources: {{- toYaml .Values.kamajiControlPlane.apiServer.resources | nindent 6 }}
-    {{- else if ne .Values.kamajiControlPlane.apiServer.resourcesPreset "none" }}
-    resources: {{- include "resources.preset" (dict "type" .Values.kamajiControlPlane.apiServer.resourcesPreset "Release" .Release) | nindent 6 }}
+    {{- if .Values.controlPlane.apiServer.resources }}
+    resources: {{- toYaml .Values.controlPlane.apiServer.resources | nindent 6 }}
+    {{- else if ne .Values.controlPlane.apiServer.resourcesPreset "none" }}
+    resources: {{- include "resources.preset" (dict "type" .Values.controlPlane.apiServer.resourcesPreset "Release" .Release) | nindent 6 }}
     {{- end }}
   controllerManager:
-    {{- if .Values.kamajiControlPlane.controllerManager.resources }}
-    resources: {{- toYaml .Values.kamajiControlPlane.controllerManager.resources | nindent 6 }}
-    {{- else if ne .Values.kamajiControlPlane.controllerManager.resourcesPreset "none" }}
-    resources: {{- include "resources.preset" (dict "type" .Values.kamajiControlPlane.controllerManager.resourcesPreset "Release" .Release) | nindent 6 }}
+    {{- if .Values.controlPlane.controllerManager.resources }}
+    resources: {{- toYaml .Values.controlPlane.controllerManager.resources | nindent 6 }}
+    {{- else if ne .Values.controlPlane.controllerManager.resourcesPreset "none" }}
+    resources: {{- include "resources.preset" (dict "type" .Values.controlPlane.controllerManager.resourcesPreset "Release" .Release) | nindent 6 }}
     {{- end }}
   scheduler:
-    {{- if .Values.kamajiControlPlane.scheduler.resources }}
-    resources: {{- toYaml .Values.kamajiControlPlane.scheduler.resources | nindent 6 }}
-    {{- else if ne .Values.kamajiControlPlane.scheduler.resourcesPreset "none" }}
-    resources: {{- include "resources.preset" (dict "type" .Values.kamajiControlPlane.scheduler.resourcesPreset "Release" .Release) | nindent 6 }}
+    {{- if .Values.controlPlane.scheduler.resources }}
+    resources: {{- toYaml .Values.controlPlane.scheduler.resources | nindent 6 }}
+    {{- else if ne .Values.controlPlane.scheduler.resourcesPreset "none" }}
+    resources: {{- include "resources.preset" (dict "type" .Values.controlPlane.scheduler.resourcesPreset "Release" .Release) | nindent 6 }}
     {{- end }}
   dataStoreName: "{{ $etcd }}"
   addons:
@@ -128,10 +145,10 @@ spec:
     konnectivity:
       server:
         port: 8132
-        {{- if .Values.kamajiControlPlane.addons.konnectivity.server.resources }}
-        resources: {{- toYaml .Values.kamajiControlPlane.addons.konnectivity.server.resources | nindent 10 }}
-        {{- else if ne .Values.kamajiControlPlane.addons.konnectivity.server.resourcesPreset "none" }}
-        resources: {{- include "resources.preset" (dict "type" .Values.kamajiControlPlane.addons.konnectivity.server.resourcesPreset "Release" .Release) | nindent 10 }}
+        {{- if .Values.controlPlane.konnectivity.server.resources }}
+        resources: {{- toYaml .Values.controlPlane.konnectivity.server.resources | nindent 10 }}
+        {{- else if ne .Values.controlPlane.konnectivity.server.resourcesPreset "none" }}
+        resources: {{- include "resources.preset" (dict "type" .Values.controlPlane.konnectivity.server.resourcesPreset "Release" .Release) | nindent 10 }}
         {{- end }}
   kubelet:
     cgroupfs: systemd
@@ -143,14 +160,14 @@ spec:
     ingress:
       extraAnnotations:
         nginx.ingress.kubernetes.io/ssl-passthrough: "true"
-      hostname: {{ .Values.host | default (printf "%s.%s" .Release.Name $host) }}
+      hostname: {{ .Values.host | default (printf "%s.%s" .Release.Name $host) }}:443
       className: "{{ $ingress }}"
   deployment:
     podAdditionalMetadata:
       labels:
         policy.cozystack.io/allow-to-etcd: "true"
   replicas: 2
-  version: 1.30.1
+  version: {{ $.Chart.AppVersion }}
 ---
 apiVersion: cozystack.io/v1alpha1
 kind: WorkloadMonitor
@@ -276,7 +293,7 @@ spec:
         kind: KubevirtMachineTemplate
         name: {{ $.Release.Name }}-{{ $groupName }}-{{ $kubevirtmachinetemplateHash }}
         namespace: {{ $.Release.Namespace }}
-      version: v1.30.1
+      version: v{{ $.Chart.AppVersion }}
 ---
 apiVersion: cluster.x-k8s.io/v1beta1
 kind: MachineHealthCheck

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

@@ -4,7 +4,7 @@ metadata:
   name: {{ .Release.Name }}-cert-manager-crds
   labels:
     cozystack.io/repository: system
-    coztstack.io/target-cluster-name: {{ .Release.Name }}
+    cozystack.io/target-cluster-name: {{ .Release.Name }}
 spec:
   interval: 5m
   releaseName: cert-manager-crds
@@ -16,6 +16,7 @@ spec:
         kind: HelmRepository
         name: cozystack-system
         namespace: cozy-system
+      version: '>= 0.0.0-0'
   kubeConfig:
     secretRef:
       name: {{ .Release.Name }}-admin-kubeconfig

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

@@ -5,7 +5,7 @@ metadata:
   name: {{ .Release.Name }}-cert-manager
   labels:
     cozystack.io/repository: system
-    coztstack.io/target-cluster-name: {{ .Release.Name }}
+    cozystack.io/target-cluster-name: {{ .Release.Name }}
 spec:
   interval: 5m
   releaseName: cert-manager
@@ -17,6 +17,7 @@ spec:
         kind: HelmRepository
         name: cozystack-system
         namespace: cozy-system
+      version: '>= 0.0.0-0'
   kubeConfig:
     secretRef:
       name: {{ .Release.Name }}-admin-kubeconfig
@@ -30,11 +31,9 @@ spec:
   upgrade:
     remediation:
       retries: -1
-  {{- if .Values.addons.certManager.valuesOverride }}
-  valuesFrom:
-  - kind: Secret
-    name: {{ .Release.Name }}-cert-manager-values-override
-    valuesKey: values
+  {{- with .Values.addons.certManager.valuesOverride }}
+  values:
+    {{- toYaml . | nindent 4 }}
   {{- end }}
 
   dependsOn:
@@ -47,13 +46,3 @@ spec:
   - name: {{ .Release.Name }}-cert-manager-crds
     namespace: {{ .Release.Namespace }}
 {{- end }}
-{{- if .Values.addons.certManager.valuesOverride }}
----
-apiVersion: v1
-kind: Secret
-metadata:
-  name: {{ .Release.Name }}-cert-manager-values-override
-stringData:
-  values: |
-    {{- toYaml .Values.addons.certManager.valuesOverride | nindent 4 }}
-{{- end }}

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

@@ -1,10 +1,25 @@
+{{- define "cozystack.defaultCiliumValues" -}}
+cilium:
+  k8sServiceHost: {{ .Release.Name }}.{{ .Release.Namespace }}.svc
+  k8sServicePort: 6443
+  routingMode: tunnel
+  enableIPv4Masquerade: true
+  ipv4NativeRoutingCIDR: ""
+  {{- if $.Values.addons.gatewayAPI.enabled }}
+  gatewayAPI:
+    enabled: true
+  envoy:
+    enabled: true
+  {{- end }}
+{{- end }}
+
 apiVersion: helm.toolkit.fluxcd.io/v2
 kind: HelmRelease
 metadata:
   name: {{ .Release.Name }}-cilium
   labels:
     cozystack.io/repository: system
-    coztstack.io/target-cluster-name: {{ .Release.Name }}
+    cozystack.io/target-cluster-name: {{ .Release.Name }}
 spec:
   interval: 5m
   releaseName: cilium
@@ -16,6 +31,7 @@ spec:
         kind: HelmRepository
         name: cozystack-system
         namespace: cozy-system
+      version: '>= 0.0.0-0'
   kubeConfig:
     secretRef:
       name: {{ .Release.Name }}-admin-kubeconfig
@@ -30,14 +46,13 @@ spec:
     remediation:
       retries: -1
   values:
-    cilium:
-      k8sServiceHost: {{ .Release.Name }}.{{ .Release.Namespace }}.svc
-      k8sServicePort: 6443
-      routingMode: tunnel
-      enableIPv4Masquerade: true
-      ipv4NativeRoutingCIDR: ""
+    {{- toYaml (deepCopy .Values.addons.cilium.valuesOverride | mergeOverwrite (fromYaml (include "cozystack.defaultCiliumValues" .))) | nindent 4 }}
   dependsOn:
   {{- if lookup "helm.toolkit.fluxcd.io/v2" "HelmRelease" .Release.Namespace .Release.Name }}
   - name: {{ .Release.Name }}
     namespace: {{ .Release.Namespace }}
   {{- end }}
+  {{- if $.Values.addons.gatewayAPI.enabled }}
+  - name: {{ .Release.Name }}-gateway-api-crds
+    namespace: {{ .Release.Namespace }}
+  {{- end }}

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

@@ -4,7 +4,7 @@ metadata:
   name: {{ .Release.Name }}-csi
   labels:
     cozystack.io/repository: system
-    coztstack.io/target-cluster-name: {{ .Release.Name }}
+    cozystack.io/target-cluster-name: {{ .Release.Name }}
 spec:
   interval: 5m
   releaseName: csi
@@ -16,6 +16,7 @@ spec:
         kind: HelmRepository
         name: cozystack-system
         namespace: cozy-system
+      version: '>= 0.0.0-0'
   kubeConfig:
     secretRef:
       name: {{ .Release.Name }}-admin-kubeconfig

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

@@ -20,7 +20,7 @@ spec:
           effect: "NoSchedule"
       containers:
         - name: kubectl
-          image: docker.io/clastix/kubectl:v1.30.1
+          image: docker.io/clastix/kubectl:v1.32
           command:
             - /bin/sh
             - -c
@@ -30,11 +30,16 @@ spec:
                 patch
                 helmrelease
                 {{ .Release.Name }}-cilium
+                {{ .Release.Name }}-gateway-api-crds
                 {{ .Release.Name }}-csi
                 {{ .Release.Name }}-cert-manager
+                {{ .Release.Name }}-cert-manager-crds
+                {{ .Release.Name }}-vertical-pod-autoscaler
+                {{ .Release.Name }}-vertical-pod-autoscaler-crds
                 {{ .Release.Name }}-ingress-nginx
                 {{ .Release.Name }}-fluxcd-operator
                 {{ .Release.Name }}-fluxcd
+                {{ .Release.Name }}-gpu-operator
                 -p '{"spec": {"suspend": true}}'
                 --type=merge --field-manager=flux-client-side-apply || true
 ---
@@ -67,9 +72,13 @@ rules:
       - {{ .Release.Name }}-cilium
       - {{ .Release.Name }}-csi
       - {{ .Release.Name }}-cert-manager
+      - {{ .Release.Name }}-cert-manager-crds
+      - {{ .Release.Name }}-vertical-pod-autoscaler
+      - {{ .Release.Name }}-vertical-pod-autoscaler-crds
       - {{ .Release.Name }}-ingress-nginx
       - {{ .Release.Name }}-fluxcd-operator
       - {{ .Release.Name }}-fluxcd
+      - {{ .Release.Name }}-gpu-operator
 ---
 apiVersion: rbac.authorization.k8s.io/v1
 kind: RoleBinding

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

@@ -5,7 +5,7 @@ metadata:
   name: {{ .Release.Name }}-fluxcd-operator
   labels:
     cozystack.io/repository: system
-    coztstack.io/target-cluster-name: {{ .Release.Name }}
+    cozystack.io/target-cluster-name: {{ .Release.Name }}
 spec:
   interval: 5m
   releaseName: fluxcd-operator
@@ -17,6 +17,7 @@ spec:
         kind: HelmRepository
         name: cozystack-system
         namespace: cozy-system
+      version: '>= 0.0.0-0'
   kubeConfig:
     secretRef:
       name: {{ .Release.Name }}-admin-kubeconfig
@@ -49,7 +50,7 @@ metadata:
   name: {{ .Release.Name }}-fluxcd
   labels:
     cozystack.io/repository: system
-    coztstack.io/target-cluster-name: {{ .Release.Name }}
+    cozystack.io/target-cluster-name: {{ .Release.Name }}
 spec:
   interval: 5m
   releaseName: fluxcd
@@ -61,6 +62,7 @@ spec:
         kind: HelmRepository
         name: cozystack-system
         namespace: cozy-system
+      version: '>= 0.0.0-0'
   kubeConfig:
     secretRef:
       name: {{ .Release.Name }}-kubeconfig
@@ -73,11 +75,9 @@ spec:
   upgrade:
     remediation:
       retries: -1
-  {{- if .Values.addons.fluxcd.valuesOverride }}
-  valuesFrom:
-  - kind: Secret
-    name: {{ .Release.Name }}-fluxcd-values-override
-    valuesKey: values
+  {{- with .Values.addons.fluxcd.valuesOverride }}
+  values:
+    {{- toYaml . | nindent 4 }}
   {{- end }}
   dependsOn:
   {{- if lookup "helm.toolkit.fluxcd.io/v2" "HelmRelease" .Release.Namespace .Release.Name }}
@@ -89,14 +89,3 @@ spec:
   - name: {{ .Release.Name }}-fluxcd-operator
     namespace: {{ .Release.Namespace }}
 {{- end }}
-
-{{- if .Values.addons.fluxcd.valuesOverride }}
----
-apiVersion: v1
-kind: Secret
-metadata:
-  name: {{ .Release.Name }}-fluxcd-values-override
-stringData:
-  values: |
-    {{- toYaml .Values.addons.fluxcd.valuesOverride | nindent 4 }}
-{{- end }}

packages/apps/kubernetes/templates/helmreleases/gateway-api-crds.yaml

@@ -0,0 +1,38 @@
+{{- if $.Values.addons.gatewayAPI.enabled }}
+apiVersion: helm.toolkit.fluxcd.io/v2
+kind: HelmRelease
+metadata:
+  name: {{ .Release.Name }}-gateway-api-crds
+  labels:
+    cozystack.io/repository: system
+    cozystack.io/target-cluster-name: {{ .Release.Name }}
+spec:
+  interval: 5m
+  releaseName: gateway-api-crds
+  chart:
+    spec:
+      chart: cozy-gateway-api-crds
+      reconcileStrategy: Revision
+      sourceRef:
+        kind: HelmRepository
+        name: cozystack-system
+        namespace: cozy-system
+  kubeConfig:
+    secretRef:
+      name: {{ .Release.Name }}-admin-kubeconfig
+      key: super-admin.svc
+  targetNamespace: kube-system
+  storageNamespace: kube-system
+  install:
+    createNamespace: false
+    remediation:
+      retries: -1
+  upgrade:
+    remediation:
+      retries: -1
+  dependsOn:
+  {{- if lookup "helm.toolkit.fluxcd.io/v2" "HelmRelease" .Release.Namespace .Release.Name }}
+  - name: {{ .Release.Name }}
+    namespace: {{ .Release.Namespace }}
+  {{- end }}
+{{- end }}

packages/apps/kubernetes/templates/helmreleases/gpu-operator.yaml

@@ -0,0 +1,46 @@
+{{- if .Values.addons.gpuOperator.enabled }}
+apiVersion: helm.toolkit.fluxcd.io/v2
+kind: HelmRelease
+metadata:
+  name: {{ .Release.Name }}-gpu-operator
+  labels:
+    cozystack.io/repository: system
+    cozystack.io/target-cluster-name: {{ .Release.Name }}
+spec:
+  interval: 5m
+  releaseName: gpu-operator
+  chart:
+    spec:
+      chart: cozy-gpu-operator
+      reconcileStrategy: Revision
+      sourceRef:
+        kind: HelmRepository
+        name: cozystack-system
+        namespace: cozy-system
+      version: '>= 0.0.0-0'
+  kubeConfig:
+    secretRef:
+      name: {{ .Release.Name }}-admin-kubeconfig
+      key: super-admin.svc
+  targetNamespace: cozy-gpu-operator
+  storageNamespace: cozy-gpu-operator
+  install:
+    createNamespace: true
+    remediation:
+      retries: -1
+  upgrade:
+    remediation:
+      retries: -1
+  {{- with .Values.addons.gpuOperator.valuesOverride }}
+  values:
+    {{- toYaml . | nindent 4 }}
+  {{- end }}
+
+  dependsOn:
+  {{- if lookup "helm.toolkit.fluxcd.io/v2" "HelmRelease" .Release.Namespace .Release.Name }}
+  - name: {{ .Release.Name }}
+    namespace: {{ .Release.Namespace }}
+  {{- end }}
+  - name: {{ .Release.Name }}-cilium
+    namespace: {{ .Release.Namespace }}
+{{- end }}

packages/apps/kubernetes/templates/helmreleases/ingress-nginx.yaml

@@ -1,3 +1,20 @@
+{{- define "cozystack.defaultIngressValues" -}}
+ingress-nginx:
+  fullnameOverride: ingress-nginx
+  controller:
+    kind: DaemonSet
+    hostNetwork: true
+    service:
+      enabled: false
+    {{- if not .Values.addons.certManager.enabled }}
+    admissionWebhooks:
+      certManager:
+        enabled: false
+    {{- end }}
+  nodeSelector:
+    node-role.kubernetes.io/ingress-nginx: ""
+{{- end }}
+
 {{- if .Values.addons.ingressNginx.enabled }}
 apiVersion: helm.toolkit.fluxcd.io/v2
 kind: HelmRelease
@@ -5,7 +22,7 @@ metadata:
   name: {{ .Release.Name }}-ingress-nginx
   labels:
     cozystack.io/repository: system
-    coztstack.io/target-cluster-name: {{ .Release.Name }}
+    cozystack.io/target-cluster-name: {{ .Release.Name }}
 spec:
   interval: 5m
   releaseName: ingress-nginx
@@ -17,6 +34,7 @@ spec:
         kind: HelmRepository
         name: cozystack-system
         namespace: cozy-system
+      version: '>= 0.0.0-0'
   kubeConfig:
     secretRef:
       name: {{ .Release.Name }}-admin-kubeconfig
@@ -31,21 +49,7 @@ spec:
     remediation:
       retries: -1
   values:
-    ingress-nginx:
-      fullnameOverride: ingress-nginx
-      controller:
-        kind: DaemonSet
-        hostNetwork: true
-        service:
-          enabled: false
-      nodeSelector:
-        node-role.kubernetes.io/ingress-nginx: ""
-  {{- if .Values.addons.ingressNginx.valuesOverride }}
-  valuesFrom:
-  - kind: Secret
-    name: {{ .Release.Name }}-ingress-nginx-values-override
-    valuesKey: values
-  {{- end }}
+    {{- toYaml (deepCopy .Values.addons.ingressNginx.valuesOverride | mergeOverwrite (fromYaml (include "cozystack.defaultIngressValues" .))) | nindent 4 }}
   dependsOn:
   {{- if lookup "helm.toolkit.fluxcd.io/v2" "HelmRelease" .Release.Namespace .Release.Name }}
   - name: {{ .Release.Name }}
@@ -54,14 +58,3 @@ spec:
   - name: {{ .Release.Name }}-cilium
     namespace: {{ .Release.Namespace }}
 {{- end }}
-
-{{- if .Values.addons.ingressNginx.valuesOverride }}
----
-apiVersion: v1
-kind: Secret
-metadata:
-  name: {{ .Release.Name }}-ingress-nginx-values-override
-stringData:
-  values: |
-    {{- toYaml .Values.addons.ingressNginx.valuesOverride | nindent 4 }}
-{{- end }}

packages/apps/kubernetes/templates/helmreleases/monitoring-agents.yaml

@@ -7,7 +7,7 @@ metadata:
   name: {{ .Release.Name }}-monitoring-agents
   labels:
     cozystack.io/repository: system
-    coztstack.io/target-cluster-name: {{ .Release.Name }}
+    cozystack.io/target-cluster-name: {{ .Release.Name }}
 spec:
   interval: 5m
   releaseName: cozy-monitoring-agents
@@ -19,6 +19,7 @@ spec:
         kind: HelmRepository
         name: cozystack-system
         namespace: cozy-system
+      version: '>= 0.0.0-0'
   kubeConfig:
     secretRef:
       name: {{ .Release.Name }}-admin-kubeconfig

packages/apps/kubernetes/templates/helmreleases/vertical-pod-autoscaler-crds.yaml

@@ -5,7 +5,7 @@ metadata:
   name: {{ .Release.Name }}-vertical-pod-autoscaler-crds
   labels:
     cozystack.io/repository: system
-    coztstack.io/target-cluster-name: {{ .Release.Name }}
+    cozystack.io/target-cluster-name: {{ .Release.Name }}
 spec:
   interval: 5m
   releaseName: vertical-pod-autoscaler-crds
@@ -17,6 +17,7 @@ spec:
         kind: HelmRepository
         name: cozystack-system
         namespace: cozy-system
+      version: '>= 0.0.0-0'
   kubeConfig:
     secretRef:
       name: {{ .Release.Name }}-admin-kubeconfig

packages/apps/kubernetes/templates/helmreleases/vertical-pod-autoscaler.yaml

@@ -1,5 +1,28 @@
+{{- define "cozystack.defaultVPAValues" -}}
 {{- $myNS := lookup "v1" "Namespace" "" .Release.Namespace }}
 {{- $targetTenant := index $myNS.metadata.annotations "namespace.cozystack.io/monitoring" }}
+vertical-pod-autoscaler:
+  recommender:
+    extraArgs:
+      container-name-label: container
+      container-namespace-label: namespace
+      container-pod-name-label: pod
+      storage: prometheus
+      memory-saver: true
+      pod-label-prefix: label_
+      metric-for-pod-labels: kube_pod_labels{job="kube-state-metrics", tenant="{{ .Release.Namespace }}", cluster="{{ .Release.Name }}"}[8d]
+      pod-name-label: pod
+      pod-namespace-label: namespace
+      prometheus-address: http://vmselect-shortterm.{{ $targetTenant }}.svc.cozy.local:8481/select/0/prometheus/
+      prometheus-cadvisor-job-name: cadvisor
+    resources:
+      limits:
+        memory: 1600Mi
+      requests:
+        cpu: 100m
+        memory: 1600Mi
+{{- end }}
+
 {{- if .Values.addons.monitoringAgents.enabled }}
 apiVersion: helm.toolkit.fluxcd.io/v2
 kind: HelmRelease
@@ -7,7 +30,7 @@ metadata:
   name: {{ .Release.Name }}-vertical-pod-autoscaler
   labels:
     cozystack.io/repository: system
-    coztstack.io/target-cluster-name: {{ .Release.Name }}
+    cozystack.io/target-cluster-name: {{ .Release.Name }}
 spec:
   interval: 5m
   releaseName: vertical-pod-autoscaler
@@ -19,6 +42,7 @@ spec:
         kind: HelmRepository
         name: cozystack-system
         namespace: cozy-system
+      version: '>= 0.0.0-0'
   kubeConfig:
     secretRef:
       name: {{ .Release.Name }}-admin-kubeconfig
@@ -33,32 +57,7 @@ spec:
     remediation:
       retries: -1
   values:
-    vertical-pod-autoscaler:
-      recommender:
-        extraArgs:
-          container-name-label: container
-          container-namespace-label: namespace
-          container-pod-name-label: pod
-          storage: prometheus
-          memory-saver: true
-          pod-label-prefix: label_
-          metric-for-pod-labels: kube_pod_labels{job="kube-state-metrics", tenant="{{ .Release.Namespace }}", cluster="{{ .Release.Name }}"}[8d]
-          pod-name-label: pod
-          pod-namespace-label: namespace
-          prometheus-address: http://vmselect-shortterm.{{ $targetTenant }}.svc.cozy.local:8481/select/0/prometheus/
-          prometheus-cadvisor-job-name: cadvisor
-        resources:
-          limits:
-            memory: 1600Mi
-          requests:
-            cpu: 100m
-            memory: 1600Mi
-  {{- if .Values.addons.verticalPodAutoscaler.valuesOverride }}
-  valuesFrom:
-  - kind: Secret
-    name: {{ .Release.Name }}-vertical-pod-autoscaler-values-override
-    valuesKey: values
-  {{- end }}
+    {{- toYaml (deepCopy .Values.addons.verticalPodAutoscaler.valuesOverride | mergeOverwrite (fromYaml (include "cozystack.defaultVPAValues" .))) | nindent 4 }}
   dependsOn:
   {{- if lookup "helm.toolkit.fluxcd.io/v2" "HelmRelease" .Release.Namespace .Release.Name }}
   - name: {{ .Release.Name }}

packages/apps/kubernetes/templates/helmreleases/victoria-metrics-operator.yaml

@@ -5,7 +5,7 @@ metadata:
   name: {{ .Release.Name }}-cozy-victoria-metrics-operator
   labels:
     cozystack.io/repository: system
-    coztstack.io/target-cluster-name: {{ .Release.Name }}
+    cozystack.io/target-cluster-name: {{ .Release.Name }}
 spec:
   interval: 5m
   releaseName: cozy-victoria-metrics-operator
@@ -17,6 +17,7 @@ spec:
         kind: HelmRepository
         name: cozystack-system
         namespace: cozy-system
+      version: '>= 0.0.0-0'
   kubeConfig:
     secretRef:
       name: {{ .Release.Name }}-admin-kubeconfig

packages/apps/kubernetes/values.schema.json

@@ -1,97 +1,247 @@
 {
-    "title": "Chart Values",
-    "type": "object",
-    "properties": {
-        "host": {
-            "type": "string",
-            "description": "The hostname used to access the Kubernetes cluster externally (defaults to using the cluster name as a subdomain for the tenant host).",
-            "default": ""
+  "title": "Chart Values",
+  "type": "object",
+  "properties": {
+    "host": {
+      "type": "string",
+      "description": "Hostname used to access the Kubernetes cluster externally. Defaults to `<cluster-name>.<tenant-host>` when empty.",
+      "default": ""
+    },
+    "controlPlane": {
+      "type": "object",
+      "properties": {
+        "replicas": {
+          "type": "number",
+          "description": "Number of replicas for Kubernetes control-plane components.",
+          "default": 2
         },
-        "controlPlane": {
-            "type": "object",
-            "properties": {
-                "replicas": {
-                    "type": "number",
-                    "description": "Number of replicas for Kubernetes contorl-plane components",
-                    "default": 2
-                }
+        "apiServer": {
+          "type": "object",
+          "properties": {
+            "resources": {
+              "type": "object",
+              "description": "Explicit CPU/memory resource requests and limits for the API server.",
+              "default": {}
+            },
+            "resourcesPreset": {
+              "type": "string",
+              "description": "Use a common resources preset when `resources` is not set explicitly.",
+              "default": "small",
+              "enum": [
+                "none",
+                "nano",
+                "micro",
+                "small",
+                "medium",
+                "large",
+                "xlarge",
+                "2xlarge"
+              ]
             }
+          }
         },
-        "storageClass": {
-            "type": "string",
-            "description": "StorageClass used to store user data",
-            "default": "replicated"
-        },
-        "addons": {
-            "type": "object",
-            "properties": {
-                "certManager": {
-                    "type": "object",
-                    "properties": {
-                        "enabled": {
-                            "type": "boolean",
-                            "description": "Enables the cert-manager",
-                            "default": false
-                        },
-                        "valuesOverride": {
-                            "type": "object",
-                            "description": "Custom values to override",
-                            "default": {}
-                        }
-                    }
-                },
-                "ingressNginx": {
-                    "type": "object",
-                    "properties": {
-                        "enabled": {
-                            "type": "boolean",
-                            "description": "Enable Ingress-NGINX controller (expect nodes with 'ingress-nginx' role)",
-                            "default": false
-                        },
-                        "valuesOverride": {
-                            "type": "object",
-                            "description": "Custom values to override",
-                            "default": {}
-                        },
-                        "hosts": {
-                            "type": "array",
-                            "description": "List of domain names that should be passed through to the cluster by upper cluster",
-                            "default": [],
-                            "items": {}
-                        }
-                    }
-                },
-                "fluxcd": {
-                    "type": "object",
-                    "properties": {
-                        "enabled": {
-                            "type": "boolean",
-                            "description": "Enables Flux CD",
-                            "default": false
-                        },
-                        "valuesOverride": {
-                            "type": "object",
-                            "description": "Custom values to override",
-                            "default": {}
-                        }
-                    }
-                },
-                "monitoringAgents": {
-                    "type": "object",
-                    "properties": {
-                        "enabled": {
-                            "type": "boolean",
-                            "description": "Enables MonitoringAgents (fluentbit, vmagents for sending logs and metrics to storage) if tenant monitoring enabled, send to tenant storage, else to root storage",
-                            "default": false
-                        },
-                        "valuesOverride": {
-                            "type": "object",
-                            "description": "Custom values to override",
-                            "default": {}
-                        }
-                    }
-                }
+        "controllerManager": {
+          "type": "object",
+          "properties": {
+            "resources": {
+              "type": "object",
+              "description": "Explicit CPU/memory resource requests and limits for the controller manager.",
+              "default": {}
+            },
+            "resourcesPreset": {
+              "type": "string",
+              "description": "Use a common resources preset when `resources` is not set explicitly.",
+              "default": "micro",
+              "enum": [
+                "none",
+                "nano",
+                "micro",
+                "small",
+                "medium",
+                "large",
+                "xlarge",
+                "2xlarge"
+              ]
             }
+          }
+        },
+        "scheduler": {
+          "type": "object",
+          "properties": {
+            "resources": {
+              "type": "object",
+              "description": "Explicit CPU/memory resource requests and limits for the scheduler.",
+              "default": {}
+            },
+            "resourcesPreset": {
+              "type": "string",
+              "description": "Use a common resources preset when `resources` is not set explicitly.",
+              "default": "micro",
+              "enum": [
+                "none",
+                "nano",
+                "micro",
+                "small",
+                "medium",
+                "large",
+                "xlarge",
+                "2xlarge"
+              ]
+            }
+          }
+        },
+        "konnectivity": {
+          "type": "object",
+          "properties": {
+            "server": {
+              "type": "object",
+              "properties": {
+                "resources": {
+                  "type": "object",
+                  "description": "Explicit CPU/memory resource requests and limits for the Konnectivity.",
+                  "default": {}
+                },
+                "resourcesPreset": {
+                  "type": "string",
+                  "description": "Use a common resources preset when `resources` is not set explicitly.",
+                  "default": "micro",
+                  "enum": [
+                    "none",
+                    "nano",
+                    "micro",
+                    "small",
+                    "medium",
+                    "large",
+                    "xlarge",
+                    "2xlarge"
+                  ]
+                }
+              }
+            }
+          }
         }
+      }
+    },
+    "storageClass": {
+      "type": "string",
+      "description": "StorageClass used to store user data.",
+      "default": "replicated"
+    },
+    "addons": {
+      "type": "object",
+      "properties": {
+        "certManager": {
+          "type": "object",
+          "properties": {
+            "enabled": {
+              "type": "boolean",
+              "description": "Enable cert-manager, which automatically creates and manages SSL/TLS certificates.",
+              "default": false
+            },
+            "valuesOverride": {
+              "type": "object",
+              "description": "Custom values to override",
+              "default": {}
+            }
+          }
+        },
+        "cilium": {
+          "type": "object",
+          "properties": {
+            "valuesOverride": {
+              "type": "object",
+              "description": "Custom values to override",
+              "default": {}
+            }
+          }
+        },
+        "gatewayAPI": {
+          "type": "object",
+          "properties": {
+            "enabled": {
+              "type": "boolean",
+              "description": "Enable the Gateway API",
+              "default": false
+            }
+          }
+        },
+        "ingressNginx": {
+          "type": "object",
+          "properties": {
+            "enabled": {
+              "type": "boolean",
+              "description": "Enable the Ingress-NGINX controller (requires nodes labeled with the 'ingress-nginx' role).",
+              "default": false
+            },
+            "valuesOverride": {
+              "type": "object",
+              "description": "Custom values to override",
+              "default": {}
+            },
+            "hosts": {
+              "type": "array",
+              "description": "List of domain names that the parent cluster should route to this tenant cluster.",
+              "default": [],
+              "items": {}
+            }
+          }
+        },
+        "gpuOperator": {
+          "type": "object",
+          "properties": {
+            "enabled": {
+              "type": "boolean",
+              "description": "Enable the GPU-operator",
+              "default": false
+            },
+            "valuesOverride": {
+              "type": "object",
+              "description": "Custom values to override",
+              "default": {}
+            }
+          }
+        },
+        "fluxcd": {
+          "type": "object",
+          "properties": {
+            "enabled": {
+              "type": "boolean",
+              "description": "Enable FluxCD",
+              "default": false
+            },
+            "valuesOverride": {
+              "type": "object",
+              "description": "Custom values to override",
+              "default": {}
+            }
+          }
+        },
+        "monitoringAgents": {
+          "type": "object",
+          "properties": {
+            "enabled": {
+              "type": "boolean",
+              "description": "Enable monitoring agents (Fluent Bit and VMAgents) to send logs and metrics. If tenant monitoring is enabled, data is sent to tenant storage; otherwise, it goes to root storage.",
+              "default": false
+            },
+            "valuesOverride": {
+              "type": "object",
+              "description": "Custom values to override",
+              "default": {}
+            }
+          }
+        },
+        "verticalPodAutoscaler": {
+          "type": "object",
+          "properties": {
+            "valuesOverride": {
+              "type": "object",
+              "description": "Custom values to override",
+              "default": {}
+            }
+          }
+        }
+      }
     }
+  }
 }

packages/apps/kubernetes/values.yaml

@@ -1,12 +1,10 @@
-## @section Common parameters
+## @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
+## @param host Hostname used to access the Kubernetes cluster externally. Defaults to `<cluster-name>.<tenant-host>` when empty.
+## @param controlPlane.replicas Number of replicas for Kubernetes control-plane components.
+## @param storageClass StorageClass used to store user data.
 ##
 host: ""
-controlPlane:
-  replicas: 2
 storageClass: replicated
 
 ## @param nodeGroups [object] nodeGroups configuration
@@ -24,6 +22,14 @@ nodeGroups:
       cpu: ""
       memory: ""
 
+    ## List of GPUs to attach (WARN: NVIDIA driver requires at least 4 GiB of RAM)
+    ## e.g:
+    ## instanceType: "u1.xlarge"
+    ## gpus:
+    ## - name: nvidia.com/AD102GL_L40S
+    gpus: []
+
+
 ## @section Cluster Addons
 ##
 addons:
@@ -31,19 +37,31 @@ addons:
   ## Cert-manager: automatically creates and manages SSL/TLS certificate
   ##
   certManager:
-    ## @param addons.certManager.enabled Enables the cert-manager
+    ## @param addons.certManager.enabled Enable cert-manager, which automatically creates and manages SSL/TLS certificates.
     ## @param addons.certManager.valuesOverride Custom values to override
     enabled: false
     valuesOverride: {}
 
+  ## Cilium CNI plugin
+  ##
+  cilium:
+    ## @param addons.cilium.valuesOverride Custom values to override
+    valuesOverride: {}
+
+  ## Gateway API
+  ##
+  gatewayAPI:
+    ## @param addons.gatewayAPI.enabled Enable the Gateway API
+    enabled: false
+
   ## Ingress-NGINX Controller
   ##
   ingressNginx:
-    ## @param addons.ingressNginx.enabled Enable Ingress-NGINX controller (expect nodes with 'ingress-nginx' role)
+    ## @param addons.ingressNginx.enabled Enable the Ingress-NGINX controller (requires nodes labeled with the 'ingress-nginx' role).
     ## @param addons.ingressNginx.valuesOverride Custom values to override
     ##
     enabled: false
-    ## @param addons.ingressNginx.hosts List of domain names that should be passed through to the cluster by upper cluster
+    ## @param addons.ingressNginx.hosts List of domain names that the parent cluster should route to this tenant cluster.
     ## e.g:
     ## hosts:
     ## - example.org
@@ -52,10 +70,18 @@ addons:
     hosts: []
     valuesOverride: {}
 
+  ## GPU-operator: NVIDIA GPU Operator
+  ##
+  gpuOperator:
+    ## @param addons.gpuOperator.enabled Enable the GPU-operator
+    ## @param addons.gpuOperator.valuesOverride Custom values to override
+    enabled: false
+    valuesOverride: {}
+
   ## Flux CD
   ##
   fluxcd:
-    ## @param addons.fluxcd.enabled Enables Flux CD
+    ## @param addons.fluxcd.enabled Enable FluxCD
     ## @param addons.fluxcd.valuesOverride Custom values to override
     ##
     enabled: false
@@ -64,7 +90,7 @@ addons:
   ## MonitoringAgents
   ##
   monitoringAgents:
-    ## @param addons.monitoringAgents.enabled Enables MonitoringAgents (fluentbit, vmagents for sending logs and metrics to storage) if tenant monitoring enabled, send to tenant storage, else to root storage
+    ## @param addons.monitoringAgents.enabled Enable monitoring agents (Fluent Bit and VMAgents) to send logs and metrics. If tenant monitoring is enabled, data is sent to tenant storage; otherwise, it goes to root storage.
     ## @param addons.monitoringAgents.valuesOverride Custom values to override
     ##
     enabled: false
@@ -77,62 +103,42 @@ addons:
     ##
     valuesOverride: {}
 
-## @section Kamaji control plane
+## @section Kubernetes Control Plane Configuration
 ##
-kamajiControlPlane:
+
+controlPlane:
+  replicas: 2
+
   apiServer:
-    ## @param kamajiControlPlane.apiServer.resources Resources
-    resources: {}
-    # resources:
-    #   limits:
-    #     cpu: 4000m
-    #     memory: 4Gi
-    #   requests:
-    #     cpu: 100m
-    #     memory: 512Mi
-    
-    ## @param kamajiControlPlane.apiServer.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).
+    ## @param controlPlane.apiServer.resources Explicit CPU/memory resource requests and limits for the API server.
+    ## @param controlPlane.apiServer.resourcesPreset Use a common resources preset when `resources` is not set explicitly.
+    ## e.g:
+    ## resources:
+    ##   limits:
+    ##     cpu: 4000m
+    ##     memory: 4Gi
+    ##   requests:
+    ##     cpu: 100m
+    ##     memory: 512Mi
+    ##
     resourcesPreset: "small"
+    resources: {}
 
   controllerManager:
-    ## @param kamajiControlPlane.controllerManager.resources Resources
-    resources: {}
-    # resources:
-    #   limits:
-    #     cpu: 4000m
-    #     memory: 4Gi
-    #   requests:
-    #     cpu: 100m
-    #     memory: 512Mi
-    
-    ## @param kamajiControlPlane.controllerManager.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).
+    ## @param controlPlane.controllerManager.resources Explicit CPU/memory resource requests and limits for the controller manager.
+    ## @param controlPlane.controllerManager.resourcesPreset Use a common resources preset when `resources` is not set explicitly.
     resourcesPreset: "micro"
+    resources: {}
+
   scheduler:
-    ## @param kamajiControlPlane.scheduler.resources Resources
-    resources: {}
-    # resources:
-    #   limits:
-    #     cpu: 4000m
-    #     memory: 4Gi
-    #   requests:
-    #     cpu: 100m
-    #     memory: 512Mi
-    
-    ## @param kamajiControlPlane.scheduler.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).
+    ## @param controlPlane.scheduler.resources Explicit CPU/memory resource requests and limits for the scheduler.
+    ## @param controlPlane.scheduler.resourcesPreset Use a common resources preset when `resources` is not set explicitly.
     resourcesPreset: "micro"
-  addons:
-    konnectivity:
-      server:
-        ## @param kamajiControlPlane.addons.konnectivity.server.resources Resources
-        resources: {}
-        # resources:
-        #   limits:
-        #     cpu: 4000m
-        #     memory: 4Gi
-        #   requests:
-        #     cpu: 100m
-        #     memory: 512Mi
-        
-        ## @param kamajiControlPlane.addons.konnectivity.server.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: "micro"
-            
+    resources: {}
+
+  konnectivity:
+    server:
+      ## @param controlPlane.konnectivity.server.resources Explicit CPU/memory resource requests and limits for the Konnectivity.
+      ## @param controlPlane.konnectivity.server.resourcesPreset Use a common resources preset when `resources` is not set explicitly.
+      resourcesPreset: "micro"
+      resources: {}

packages/apps/mysql/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: 0.6.0
+version: 0.7.0
 
 # This is the version number of the application being deployed. This version number should be
 # incremented each time you make changes to the application. Versions are not expected to

packages/apps/mysql/Makefile

@@ -7,8 +7,10 @@ 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/mariadb-backup \
+	docker buildx build images/mariadb-backup \
 		--provenance false \
+		--builder=$(BUILDER) \
+		--platform=$(PLATFORM) \
 		--tag $(REGISTRY)/mariadb-backup:$(call settag,$(MARIADB_BACKUP_TAG)) \
 		--cache-from type=registry,ref=$(REGISTRY)/mariadb-backup:latest \
 		--cache-to type=inline \

packages/apps/mysql/images/mariadb-backup.tag

@@ -1 +1 @@
-ghcr.io/cozystack/cozystack/mariadb-backup:0.6.0@sha256:cfd1c37d8ad24e10681d82d6e6ce8a641b4602c1b0ffa8516ae15b4958bb12d4
+ghcr.io/cozystack/cozystack/mariadb-backup:0.7.0@sha256:cfd1c37d8ad24e10681d82d6e6ce8a641b4602c1b0ffa8516ae15b4958bb12d4

packages/apps/mysql/templates/_resources.tpl

@@ -11,35 +11,34 @@ These presets are for basic testing and not meant to be used in production
 {{ include "resources.preset" (dict "type" "nano") -}}
 */}}
 {{- define "resources.preset" -}}
-{{/* The limits are the requests increased by 50% (except ephemeral-storage and xlarge/2xlarge sizes)*/}}
 {{- $presets := dict 
   "nano" (dict 
       "requests" (dict "cpu" "100m" "memory" "128Mi" "ephemeral-storage" "50Mi")
-      "limits" (dict "cpu" "150m" "memory" "192Mi" "ephemeral-storage" "2Gi")
+      "limits" (dict "memory" "128Mi" "ephemeral-storage" "2Gi")
    )
   "micro" (dict 
       "requests" (dict "cpu" "250m" "memory" "256Mi" "ephemeral-storage" "50Mi")
-      "limits" (dict "cpu" "375m" "memory" "384Mi" "ephemeral-storage" "2Gi")
+      "limits" (dict "memory" "256Mi" "ephemeral-storage" "2Gi")
    )
   "small" (dict 
       "requests" (dict "cpu" "500m" "memory" "512Mi" "ephemeral-storage" "50Mi")
-      "limits" (dict "cpu" "750m" "memory" "768Mi" "ephemeral-storage" "2Gi")
+      "limits" (dict "memory" "512Mi" "ephemeral-storage" "2Gi")
    )
   "medium" (dict 
-      "requests" (dict "cpu" "500m" "memory" "1024Mi" "ephemeral-storage" "50Mi")
-      "limits" (dict "cpu" "750m" "memory" "1536Mi" "ephemeral-storage" "2Gi")
+      "requests" (dict "cpu" "500m" "memory" "1Gi" "ephemeral-storage" "50Mi")
+      "limits" (dict "memory" "1Gi" "ephemeral-storage" "2Gi")
    )
   "large" (dict 
-      "requests" (dict "cpu" "1.0" "memory" "2048Mi" "ephemeral-storage" "50Mi")
-      "limits" (dict "cpu" "1.5" "memory" "3072Mi" "ephemeral-storage" "2Gi")
+      "requests" (dict "cpu" "1" "memory" "2Gi" "ephemeral-storage" "50Mi")
+      "limits" (dict "memory" "2Gi" "ephemeral-storage" "2Gi")
    )
   "xlarge" (dict 
-      "requests" (dict "cpu" "1.0" "memory" "3072Mi" "ephemeral-storage" "50Mi")
-      "limits" (dict "cpu" "3.0" "memory" "6144Mi" "ephemeral-storage" "2Gi")
+      "requests" (dict "cpu" "2" "memory" "4Gi" "ephemeral-storage" "50Mi")
+      "limits" (dict "memory" "4Gi" "ephemeral-storage" "2Gi")
    )
   "2xlarge" (dict 
-      "requests" (dict "cpu" "1.0" "memory" "3072Mi" "ephemeral-storage" "50Mi")
-      "limits" (dict "cpu" "6.0" "memory" "12288Mi" "ephemeral-storage" "2Gi")
+      "requests" (dict "cpu" "4" "memory" "8Gi" "ephemeral-storage" "50Mi")
+      "limits" (dict "memory" "8Gi" "ephemeral-storage" "2Gi")
    )
  }}
 {{- if hasKey $presets .type -}}

packages/apps/nats/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: 0.5.0
+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/nats/templates/_resources.tpl

@@ -11,35 +11,34 @@ These presets are for basic testing and not meant to be used in production
 {{ include "resources.preset" (dict "type" "nano") -}}
 */}}
 {{- define "resources.preset" -}}
-{{/* The limits are the requests increased by 50% (except ephemeral-storage and xlarge/2xlarge sizes)*/}}
 {{- $presets := dict 
   "nano" (dict 
       "requests" (dict "cpu" "100m" "memory" "128Mi" "ephemeral-storage" "50Mi")
-      "limits" (dict "cpu" "150m" "memory" "192Mi" "ephemeral-storage" "2Gi")
+      "limits" (dict "memory" "128Mi" "ephemeral-storage" "2Gi")
    )
   "micro" (dict 
       "requests" (dict "cpu" "250m" "memory" "256Mi" "ephemeral-storage" "50Mi")
-      "limits" (dict "cpu" "375m" "memory" "384Mi" "ephemeral-storage" "2Gi")
+      "limits" (dict "memory" "256Mi" "ephemeral-storage" "2Gi")
    )
   "small" (dict 
       "requests" (dict "cpu" "500m" "memory" "512Mi" "ephemeral-storage" "50Mi")
-      "limits" (dict "cpu" "750m" "memory" "768Mi" "ephemeral-storage" "2Gi")
+      "limits" (dict "memory" "512Mi" "ephemeral-storage" "2Gi")
    )
   "medium" (dict 
-      "requests" (dict "cpu" "500m" "memory" "1024Mi" "ephemeral-storage" "50Mi")
-      "limits" (dict "cpu" "750m" "memory" "1536Mi" "ephemeral-storage" "2Gi")
+      "requests" (dict "cpu" "500m" "memory" "1Gi" "ephemeral-storage" "50Mi")
+      "limits" (dict "memory" "1Gi" "ephemeral-storage" "2Gi")
    )
   "large" (dict 
-      "requests" (dict "cpu" "1.0" "memory" "2048Mi" "ephemeral-storage" "50Mi")
-      "limits" (dict "cpu" "1.5" "memory" "3072Mi" "ephemeral-storage" "2Gi")
+      "requests" (dict "cpu" "1" "memory" "2Gi" "ephemeral-storage" "50Mi")
+      "limits" (dict "memory" "2Gi" "ephemeral-storage" "2Gi")
    )
   "xlarge" (dict 
-      "requests" (dict "cpu" "1.0" "memory" "3072Mi" "ephemeral-storage" "50Mi")
-      "limits" (dict "cpu" "3.0" "memory" "6144Mi" "ephemeral-storage" "2Gi")
+      "requests" (dict "cpu" "2" "memory" "4Gi" "ephemeral-storage" "50Mi")
+      "limits" (dict "memory" "4Gi" "ephemeral-storage" "2Gi")
    )
   "2xlarge" (dict 
-      "requests" (dict "cpu" "1.0" "memory" "3072Mi" "ephemeral-storage" "50Mi")
-      "limits" (dict "cpu" "6.0" "memory" "12288Mi" "ephemeral-storage" "2Gi")
+      "requests" (dict "cpu" "4" "memory" "8Gi" "ephemeral-storage" "50Mi")
+      "limits" (dict "memory" "8Gi" "ephemeral-storage" "2Gi")
    )
  }}
 {{- if hasKey $presets .type -}}

packages/apps/nats/templates/nats.yaml

@@ -33,7 +33,7 @@ spec:
         kind: HelmRepository
         name: cozystack-system
         namespace: cozy-system
-      version: '*'
+      version: '>= 0.0.0-0'
   interval: 1m0s
   timeout: 5m0s
   values:

packages/apps/postgres/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: 0.10.0
+version: 0.12.0
 
 # 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/postgres/Makefile

@@ -7,8 +7,10 @@ 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/postgres-backup \
+	docker buildx build images/postgres-backup \
 		--provenance false \
+		--builder=$(BUILDER) \
+		--platform=$(PLATFORM) \
 		--tag $(REGISTRY)/postgres-backup:$(call settag,$(POSTGRES_BACKUP_TAG)) \
 		--cache-from type=registry,ref=$(REGISTRY)/postgres-backup:latest \
 		--cache-to type=inline \

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

@@ -1 +1 @@
-ghcr.io/cozystack/cozystack/postgres-backup:0.10.0@sha256:10179ed56457460d95cd5708db2a00130901255fa30c4dd76c65d2ef5622b61f
+ghcr.io/cozystack/cozystack/postgres-backup:0.12.0@sha256:10179ed56457460d95cd5708db2a00130901255fa30c4dd76c65d2ef5622b61f

packages/apps/postgres/templates/_resources.tpl

@@ -11,35 +11,34 @@ These presets are for basic testing and not meant to be used in production
 {{ include "resources.preset" (dict "type" "nano") -}}
 */}}
 {{- define "resources.preset" -}}
-{{/* The limits are the requests increased by 50% (except ephemeral-storage and xlarge/2xlarge sizes)*/}}
 {{- $presets := dict 
   "nano" (dict 
       "requests" (dict "cpu" "100m" "memory" "128Mi" "ephemeral-storage" "50Mi")
-      "limits" (dict "cpu" "150m" "memory" "192Mi" "ephemeral-storage" "2Gi")
+      "limits" (dict "memory" "128Mi" "ephemeral-storage" "2Gi")
    )
   "micro" (dict 
       "requests" (dict "cpu" "250m" "memory" "256Mi" "ephemeral-storage" "50Mi")
-      "limits" (dict "cpu" "375m" "memory" "384Mi" "ephemeral-storage" "2Gi")
+      "limits" (dict "memory" "256Mi" "ephemeral-storage" "2Gi")
    )
   "small" (dict 
       "requests" (dict "cpu" "500m" "memory" "512Mi" "ephemeral-storage" "50Mi")
-      "limits" (dict "cpu" "750m" "memory" "768Mi" "ephemeral-storage" "2Gi")
+      "limits" (dict "memory" "512Mi" "ephemeral-storage" "2Gi")
    )
   "medium" (dict 
-      "requests" (dict "cpu" "500m" "memory" "1024Mi" "ephemeral-storage" "50Mi")
-      "limits" (dict "cpu" "750m" "memory" "1536Mi" "ephemeral-storage" "2Gi")
+      "requests" (dict "cpu" "500m" "memory" "1Gi" "ephemeral-storage" "50Mi")
+      "limits" (dict "memory" "1Gi" "ephemeral-storage" "2Gi")
    )
   "large" (dict 
-      "requests" (dict "cpu" "1.0" "memory" "2048Mi" "ephemeral-storage" "50Mi")
-      "limits" (dict "cpu" "1.5" "memory" "3072Mi" "ephemeral-storage" "2Gi")
+      "requests" (dict "cpu" "1" "memory" "2Gi" "ephemeral-storage" "50Mi")
+      "limits" (dict "memory" "2Gi" "ephemeral-storage" "2Gi")
    )
   "xlarge" (dict 
-      "requests" (dict "cpu" "1.0" "memory" "3072Mi" "ephemeral-storage" "50Mi")
-      "limits" (dict "cpu" "3.0" "memory" "6144Mi" "ephemeral-storage" "2Gi")
+      "requests" (dict "cpu" "2" "memory" "4Gi" "ephemeral-storage" "50Mi")
+      "limits" (dict "memory" "4Gi" "ephemeral-storage" "2Gi")
    )
   "2xlarge" (dict 
-      "requests" (dict "cpu" "1.0" "memory" "3072Mi" "ephemeral-storage" "50Mi")
-      "limits" (dict "cpu" "6.0" "memory" "12288Mi" "ephemeral-storage" "2Gi")
+      "requests" (dict "cpu" "4" "memory" "8Gi" "ephemeral-storage" "50Mi")
+      "limits" (dict "memory" "8Gi" "ephemeral-storage" "2Gi")
    )
  }}
 {{- if hasKey $presets .type -}}

packages/apps/postgres/templates/backup-cronjob.yaml

@@ -13,9 +13,6 @@ spec:
   jobTemplate:
     spec:
       backoffLimit: 2
-      template:
-        spec:
-          restartPolicy: OnFailure
       template:
         metadata:
           annotations:
@@ -24,7 +21,7 @@ spec:
         spec:
           imagePullSecrets:
           - name: {{ .Release.Name }}-regsecret
-          restartPolicy: Never
+          restartPolicy: OnFailure
           containers:
           - name: pgdump
             image: "{{ $.Files.Get "images/postgres-backup.tag" | trim }}"