Fix virtual machine resource tracking (#904) (#916)

* Count Workload resources for pods by requests, not limits
* Do not count init container requests
* Prefix Workloads for pods with `pod-`, just like the other types to
prevent possible name collisions (closes #787)

The previous version of the WorkloadMonitor controller incorrectly
summed resource limits on pods, rather than requests. This prevented it
from tracking the resource allocation for pods, which only had requests
specified, which is particularly the case for kubevirt's virtual machine
pods. Additionally, it counted the limits for all containers, including
init containers, which are short-lived and do not contribute much to the
total resource usage.

(cherry picked from commit 1e59e5fbb6)
Signed-off-by: Timofei Larkin <lllamnyp@gmail.com>

.github/workflows/backport.yaml

@@ -0,0 +1,49 @@
+name: Automatic Backport
+
+on:
+  pull_request_target:
+    types: [closed]   # fires when PR is closed (merged)
+
+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

@@ -1,13 +1,21 @@
 name: Pre-Commit Checks
 
-on: [push, pull_request]
-
+on:
+  push:
+    branches:
+      - main
+  pull_request:
+    paths-ignore:
+      - '**.md'
 jobs:
   pre-commit:
     runs-on: ubuntu-22.04
     steps:
       - name: Checkout code
         uses: actions/checkout@v3
+        with:
+          fetch-depth: 0
+          fetch-tags: true
 
       - name: Set up Python
         uses: actions/setup-python@v4

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

@@ -0,0 +1,138 @@
+name: Releasing PR
+
+on:
+  pull_request:
+    types: [labeled, opened, synchronize, reopened, closed]
+
+jobs:
+  verify:
+    name: Test Release
+    runs-on: [self-hosted]
+    permissions:
+      contents: read
+      packages: write
+
+    if: |
+      contains(github.event.pull_request.labels.*.name, 'ok-to-test') &&
+      contains(github.event.pull_request.labels.*.name, 'release') &&
+      github.event.action != 'closed'
+
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v4
+        with:
+          fetch-depth: 0
+          fetch-tags: true
+
+      - name: Login to GitHub Container Registry
+        uses: docker/login-action@v3
+        with:
+          username: ${{ github.repository_owner }}
+          password: ${{ secrets.GITHUB_TOKEN }}
+          registry: ghcr.io
+
+      - name: Run tests
+        run: make test
+
+  finalize:
+    name: Finalize Release
+    runs-on: [self-hosted]
+    permissions:
+      contents: write
+
+    if: |
+      github.event.pull_request.merged == true &&
+      contains(github.event.pull_request.labels.*.name, 'release')
+
+    steps:
+      # Extract tag from branch name  (branch = release-X.Y.Z*)
+      - name: Extract tag from branch name
+        id: get_tag
+        uses: actions/github-script@v7
+        with:
+          script: |
+            const branch = context.payload.pull_request.head.ref;
+            const m = branch.match(/^release-(\d+\.\d+\.\d+(?:[-\w\.]+)?)$/);
+            if (!m) {
+              core.setFailed(`Branch '${branch}' does not match 'release-X.Y.Z[-suffix]'`);
+              return;
+            }
+            const tag = `v${m[1]}`;
+            core.setOutput('tag', tag);
+            console.log(`✅ Tag to publish: ${tag}`);
+
+      # Checkout repo & create / push annotated tag
+      - name: Checkout repo
+        uses: actions/checkout@v4
+        with:
+          fetch-depth: 0
+
+      - name: Create tag on merge commit
+        run: |
+          git tag -f ${{ steps.get_tag.outputs.tag }} ${{ github.sha }}
+          git push -f origin ${{ steps.get_tag.outputs.tag }}
+
+      # 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-rc1
+            const m = tag.match(/^v(\d+\.\d+\.\d+)(-rc\d+)?$/);
+            if (!m) {
+              core.setFailed(`❌ tag '${tag}' must match 'vX.Y.Z' or 'vX.Y.Z-rcN'`);
+              return;
+            }
+            const version = m[1] + (m[2] ?? '');                         // 0.31.5‑rc1
+            const isRc    = Boolean(m[2]);
+            core.setOutput('is_rc',      isRc);
+            const outdated = '${{ steps.semver.outputs.comparison-result }}' === '<';
+            core.setOutput('make_latest', isRc || outdated ? 'false' : 'legacy');
+
+      # Publish draft release with correct flags
+      - name: Publish draft release
+        uses: actions/github-script@v7
+        with:
+          script: |
+            const tag = '${{ steps.get_tag.outputs.tag }}';
+            const releases = await github.rest.repos.listReleases({
+              owner: context.repo.owner,
+              repo:  context.repo.repo
+            });
+            const draft = releases.data.find(r => r.tag_name === tag && r.draft);
+            if (!draft) throw new Error(`Draft release for ${tag} not found`);
+            await github.rest.repos.updateRelease({
+              owner:       context.repo.owner,
+              repo:        context.repo.repo,
+              release_id:  draft.id,
+              draft:       false,
+              prerelease:  ${{ steps.flags.outputs.is_rc }},
+              make_latest: '${{ steps.flags.outputs.make_latest }}'
+            });
+
+            console.log(`🚀 Published release for ${tag}`);

.github/workflows/pull-requests.yaml

@@ -0,0 +1,48 @@
+name: Pull Request
+
+on:
+  pull_request:
+    types: [labeled, opened, synchronize, reopened]
+
+jobs:
+  e2e:
+    name: Build and Test
+    runs-on: [self-hosted]
+    permissions:
+      contents: read
+      packages: write
+
+    # ─────────────────────────────────────────────────────────────
+    # Run automatically for internal PRs (same repo).
+    # For external PRs (forks) require the "ok‑to‑test" label.
+    # Never run when the PR carries the "release" label.
+    # ─────────────────────────────────────────────────────────────
+    if: |
+      !contains(github.event.pull_request.labels.*.name, 'release') &&
+      (
+        github.event.pull_request.head.repo.full_name == github.repository ||
+        (
+          github.event.pull_request.head.repo.full_name != github.repository &&
+          contains(github.event.pull_request.labels.*.name, 'ok-to-test')
+        )
+      )
+
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v4
+        with:
+          fetch-depth: 0
+          fetch-tags: true
+
+      - name: Login to GitHub Container Registry
+        uses: docker/login-action@v3
+        with:
+          username: ${{ github.repository_owner }}
+          password: ${{ secrets.GITHUB_TOKEN }}
+          registry: ghcr.io
+
+      - name: Build
+        run: make build
+
+      - name: Test
+        run: make test

.github/workflows/tags.yaml

@@ -0,0 +1,251 @@
+name: Versioned Tag
+
+on:
+  push:
+    tags:
+      - 'v*.*.*' # vX.Y.Z or vX.Y.Z-rcN
+
+jobs:
+  prepare-release:
+    name: Prepare Release
+    runs-on: [self-hosted]
+    permissions:
+      contents: write
+      packages: write
+      pull-requests: write
+
+    steps:
+      # Check if a non-draft release with this tag already exists
+      - name: Check if release already exists
+        id: check_release
+        uses: actions/github-script@v7
+        with:
+          script: |
+            const tag = context.ref.replace('refs/tags/', '');
+            const releases = await github.rest.repos.listReleases({
+              owner: context.repo.owner,
+              repo:  context.repo.repo
+            });
+            const exists = releases.data.some(r => r.tag_name === tag && !r.draft);
+            core.setOutput('skip', exists);
+            console.log(exists ? `Release ${tag} already published` : `No published release ${tag}`);
+
+      # If a published release already exists, skip the rest of the workflow
+      - name: Skip if release already exists
+        if: steps.check_release.outputs.skip == 'true'
+        run: echo "Release already exists, skipping workflow."
+
+      # Parse tag meta‑data (rc?, maintenance line, etc.)
+      - name: Parse tag
+        if: steps.check_release.outputs.skip == 'false'
+        id: tag
+        uses: actions/github-script@v7
+        with:
+          script: |
+            const ref = context.ref.replace('refs/tags/', '');           // e.g. v0.31.5-rc1
+            const m = ref.match(/^v(\d+\.\d+\.\d+)(-rc\d+)?$/);
+            if (!m) {
+              core.setFailed(`❌ tag '${ref}' must match 'vX.Y.Z' or 'vX.Y.Z-rcN'`);
+              return;
+            }
+            const version = m[1] + (m[2] ?? '');                         // 0.31.5‑rc1
+            const isRc    = Boolean(m[2]);
+            const [maj, min] = m[1].split('.');
+            core.setOutput('tag',     ref);
+            core.setOutput('version', version);
+            core.setOutput('is_rc',   isRc);
+            core.setOutput('line',    `${maj}.${min}`);                  // 0.31
+
+      # Detect base branch (main or release‑X.Y) the tag was pushed from
+      - name: Get base branch
+        if: steps.check_release.outputs.skip == 'false'
+        id: get_base
+        uses: actions/github-script@v7
+        with:
+          script: |
+            const baseRef = context.payload.base_ref;
+            if (!baseRef) {
+              core.setFailed(`❌ base_ref is empty. Push the tag via 'git push origin HEAD:refs/tags/<tag>'.`);
+              return;
+            }
+            const branch = baseRef.replace('refs/heads/', '');
+            const ok     = branch === 'main' || /^release-\d+\.\d+$/.test(branch);
+            if (!ok) {
+              core.setFailed(`❌ Tagged commit must belong to 'main' or 'release-X.Y'. Got '${branch}'`);
+              return;
+            }
+            core.setOutput('branch', branch);
+
+      # Checkout & login once
+      - name: Checkout code
+        if: steps.check_release.outputs.skip == 'false'
+        uses: actions/checkout@v4
+        with:
+          fetch-depth: 0
+          fetch-tags:  true
+
+      - name: Login to GHCR
+        if: steps.check_release.outputs.skip == 'false'
+        uses: docker/login-action@v3
+        with:
+          username: ${{ github.repository_owner }}
+          password: ${{ secrets.GITHUB_TOKEN }}
+          registry: ghcr.io
+
+      # Build project artifacts
+      - name: Build
+        if: steps.check_release.outputs.skip == 'false'
+        run: make build
+
+      # Commit built artifacts
+      - name: Commit release artifacts
+        if: steps.check_release.outputs.skip == 'false'
+        run: |
+          git config user.name  "github-actions"
+          git config user.email "github-actions@github.com"
+          git add .
+          git commit -m "Prepare release ${GITHUB_REF#refs/tags/}" -s || echo "No changes to commit"
+          git push origin HEAD || true
+
+      # Get `latest_version` from latest published release 
+      - name: Get latest published release
+        if: steps.check_release.outputs.skip == 'false'
+        id: latest_release
+        uses: actions/github-script@v7
+        with:
+          script: |
+            try {
+              const rel = await github.rest.repos.getLatestRelease({
+                owner: context.repo.owner,
+                repo:  context.repo.repo
+              });
+              core.setOutput('tag', rel.data.tag_name);
+            } catch (_) {
+              core.setOutput('tag', '');
+            }
+
+      # Compare tag (A) with latest (B)
+      - name: Semver compare
+        if: steps.check_release.outputs.skip == 'false'
+        id: semver
+        uses: madhead/semver-utils@v4.3.0
+        with:
+          version:     ${{ steps.tag.outputs.tag }}            # A
+          compare-to:  ${{ steps.latest_release.outputs.tag }} # B
+
+      # Create or reuse DRAFT GitHub Release
+      - name: Create / reuse draft release
+        if: steps.check_release.outputs.skip == 'false'
+        id: release
+        uses: actions/github-script@v7
+        with:
+          script: |
+            const tag        = '${{ steps.tag.outputs.tag }}';
+            const isRc       = ${{ steps.tag.outputs.is_rc }};
+            const outdated   = '${{ steps.semver.outputs.comparison-result }}' === '<';
+            const makeLatest = outdated ? false : 'legacy';
+            const releases   = await github.rest.repos.listReleases({
+              owner: context.repo.owner,
+              repo:  context.repo.repo
+            });
+            let rel          = releases.data.find(r => r.tag_name === tag);
+            if (!rel) {
+              rel = await github.rest.repos.createRelease({
+                owner: context.repo.owner,
+                repo:  context.repo.repo,
+                tag_name:    tag,
+                name:        tag,
+                draft:       true,
+                prerelease:  isRc,
+                make_latest: makeLatest
+              });
+              console.log(`Draft release created for ${tag}`);
+            } else {
+              console.log(`Re‑using existing release ${tag}`);
+            }
+            core.setOutput('upload_url', rel.upload_url);
+
+      # Build + upload assets (optional)
+      - name: Build & upload assets
+        if: steps.check_release.outputs.skip == 'false'
+        run: |
+          make assets
+          make upload_assets VERSION=${{ steps.tag.outputs.tag }}
+        env:
+          GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+
+      # Ensure long‑lived maintenance branch release‑X.Y
+      - name: Ensure maintenance branch release‑${{ steps.tag.outputs.line }}
+        if: |
+          steps.check_release.outputs.skip == 'false' &&
+          steps.get_base.outputs.branch == 'main'
+        uses: actions/github-script@v7
+        with:
+          script: |
+            const branch = `release-${'${{ steps.tag.outputs.line }}'}`;
+            try {
+              await github.rest.repos.getBranch({
+                owner: context.repo.owner,
+                repo:  context.repo.repo,
+                branch
+              });
+              console.log(`Branch '${branch}' already exists`);
+            } catch (_) {
+              await github.git.createRef({
+                owner: context.repo.owner,
+                repo:  context.repo.repo,
+                ref:   `refs/heads/${branch}`,
+                sha:   context.sha
+              });
+              console.log(`Branch '${branch}' created at ${context.sha}`);
+            }
+
+      # Create release‑X.Y.Z branch and push (force‑update)
+      - name: Create release branch
+        if: steps.check_release.outputs.skip == 'false'
+        run: |
+          BRANCH="release-${GITHUB_REF#refs/tags/v}"
+          git branch -f "$BRANCH"
+          git push -f origin "$BRANCH"
+
+      # Create pull request into original base branch (if absent)
+      - name: Create pull request if not exists
+        if: steps.check_release.outputs.skip == 'false'
+        uses: actions/github-script@v7
+        with:
+          script: |
+            const version = context.ref.replace('refs/tags/v', '');
+            const base    = '${{ steps.get_base.outputs.branch }}';
+            const head    = `release-${version}`;
+
+            const prs = await github.rest.pulls.list({
+              owner: context.repo.owner,
+              repo:  context.repo.repo,
+              head:  `${context.repo.owner}:${head}`,
+              base
+            });
+            if (prs.data.length === 0) {
+              const pr = await github.rest.pulls.create({
+                owner: context.repo.owner,
+                repo:  context.repo.repo,
+                head,
+                base,
+                title: `Release v${version}`,
+                body:  `This PR prepares the release \`v${version}\`.`,
+                draft: false
+              });
+              await github.rest.issues.addLabels({
+                owner: context.repo.owner,
+                repo:  context.repo.repo,
+                issue_number: pr.data.number,
+                labels: ['release']
+              });
+              console.log(`Created PR #${pr.data.number}`);
+            } else {
+              console.log(`PR already exists from ${head} to ${base}`);
+            }
+
+      # Run tests 
+      - name: Test
+        if: steps.check_release.outputs.skip == 'false'
+        run: make test

CONTRIBUTING.md

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

GOVERNANCE.md

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

Makefile

@@ -1,6 +1,13 @@
 .PHONY: manifests repos assets
 
-build:
+build-deps:
+	@command -V find docker skopeo jq gh helm > /dev/null
+	@yq --version | grep -q "mikefarah" || (echo "mikefarah/yq is required" && exit 1)
+	@tar --version | grep -q GNU || (echo "GNU tar is required" && exit 1)
+	@sed --version | grep -q GNU || (echo "GNU sed is required" && exit 1)
+	@awk --version | grep -q GNU || (echo "GNU awk is required" && exit 1)
+
+build: build-deps
 	make -C packages/apps/http-cache image
 	make -C packages/apps/postgres image
 	make -C packages/apps/mysql image
@@ -19,10 +26,6 @@ build:
 	make -C packages/core/installer image
 	make manifests
 
-manifests:
-	(cd packages/core/installer/; helm template -n cozy-installer installer .) > manifests/cozystack-installer.yaml
-	sed -i 's|@sha256:[^"]\+||' manifests/cozystack-installer.yaml
-
 repos:
 	rm -rf _out
 	make -C packages/apps check-version-map
@@ -33,14 +36,21 @@ repos:
 	mkdir -p _out/logos
 	cp ./packages/apps/*/logos/*.svg ./packages/extra/*/logos/*.svg _out/logos/
 
+
+manifests:
+	mkdir -p _out/assets
+	(cd packages/core/installer/; helm template -n cozy-installer installer .) > _out/assets/cozystack-installer.yaml
+
 assets:
 	make -C packages/core/installer/ assets
 
 test:
-	test -f _out/assets/nocloud-amd64.raw.xz || make -C packages/core/installer talos-nocloud
 	make -C packages/core/testing apply
 	make -C packages/core/testing test
-	make -C packages/core/testing test-applications
+	#make -C packages/core/testing test-applications
 
 generate:
 	hack/update-codegen.sh
+
+upload_assets: manifests
+	hack/upload-assets.sh

README.md

@@ -12,20 +12,21 @@
 
 **Cozystack** is a free PaaS platform and framework for building clouds.
 
-With Cozystack, you can transform your bunch of servers into an intelligent system with a simple REST API for spawning Kubernetes clusters, Database-as-a-Service, virtual machines, load balancers, HTTP caching services, and other services with ease.
+With Cozystack, you can transform a bunch of servers into an intelligent system with a simple REST API for spawning Kubernetes clusters,
+Database-as-a-Service, virtual machines, load balancers, HTTP caching services, and other services with ease.
 
-You can use Cozystack to build your own cloud or to provide a cost-effective development environments.  
+Use Cozystack to build your own cloud or provide a cost-effective development environment.  
 
 ## Use-Cases
 
-* [**Using Cozystack to build public cloud**](https://cozystack.io/docs/use-cases/public-cloud/)  
-You can use Cozystack as backend for a public cloud
+* [**Using Cozystack to build a public cloud**](https://cozystack.io/docs/guides/use-cases/public-cloud/)  
+You can use Cozystack as a backend for a public cloud
 
-* [**Using Cozystack to build private cloud**](https://cozystack.io/docs/use-cases/private-cloud/)  
-You can use Cozystack as platform to build a private cloud powered by Infrastructure-as-Code approach
+* [**Using Cozystack to build a private cloud**](https://cozystack.io/docs/guides/use-cases/private-cloud/)  
+You can use Cozystack as a platform to build a private cloud powered by Infrastructure-as-Code approach
 
-* [**Using Cozystack as Kubernetes distribution**](https://cozystack.io/docs/use-cases/kubernetes-distribution/)  
-You can use Cozystack as Kubernetes distribution for Bare Metal
+* [**Using Cozystack as a Kubernetes distribution**](https://cozystack.io/docs/guides/use-cases/kubernetes-distribution/)  
+You can use Cozystack as a Kubernetes distribution for Bare Metal
 
 ## Screenshot
 
@@ -33,11 +34,11 @@ You can use Cozystack as Kubernetes distribution for Bare Metal
 
 ## Documentation
 
-The documentation is located on official [cozystack.io](https://cozystack.io) website.
+The documentation is located on the [cozystack.io](https://cozystack.io) website.
 
-Read [Get Started](https://cozystack.io/docs/get-started/) section for a quick start.
+Read the [Getting Started](https://cozystack.io/docs/getting-started/) section for a quick start.
 
-If you encounter any difficulties, start with the [troubleshooting guide](https://cozystack.io/docs/troubleshooting/), and work your way through the process that we've outlined.
+If you encounter any difficulties, start with the [troubleshooting guide](https://cozystack.io/docs/operations/troubleshooting/) and work your way through the process that we've outlined.
 
 ## Versioning
 
@@ -50,15 +51,15 @@ A full list of the available releases is available in the GitHub repository's [R
 
 Contributions are highly appreciated and very welcomed!
 
-In case of bugs, please, check if the issue has been already opened by checking the [GitHub Issues](https://github.com/cozystack/cozystack/issues) section.
-In case it isn't, you can open a new one: a detailed report will help us to replicate it, assess it, and work on a fix.
+In case of bugs, please check if the issue has already been opened by checking the [GitHub Issues](https://github.com/cozystack/cozystack/issues) section.
+If it isn't, you can open a new one. A detailed report will help us replicate it, assess it, and work on a fix.
 
-You can express your intention in working on the fix on your own.
+You can express your intention to on the fix on your own.
 Commits are used to generate the changelog, and their author will be referenced in it.
 
-In case of **Feature Requests** please use the [Discussion's Feature Request section](https://github.com/cozystack/cozystack/discussions/categories/feature-requests).
+If you have **Feature Requests** please use the [Discussion's Feature Request section](https://github.com/cozystack/cozystack/discussions/categories/feature-requests).
 
-You can join our weekly community meetings (just add this events to your [Google Calendar](https://calendar.google.com/calendar?cid=ZTQzZDIxZTVjOWI0NWE5NWYyOGM1ZDY0OWMyY2IxZTFmNDMzZTJlNjUzYjU2ZGJiZGE3NGNhMzA2ZjBkMGY2OEBncm91cC5jYWxlbmRhci5nb29nbGUuY29t) or [iCal](https://calendar.google.com/calendar/ical/e43d21e5c9b45a95f28c5d649c2cb1e1f433e2e653b56dbbda74ca306f0d0f68%40group.calendar.google.com/public/basic.ics)) or [Telegram group](https://t.me/cozystack).
+You are welcome to join our weekly community meetings (just add this events to your [Google Calendar](https://calendar.google.com/calendar?cid=ZTQzZDIxZTVjOWI0NWE5NWYyOGM1ZDY0OWMyY2IxZTFmNDMzZTJlNjUzYjU2ZGJiZGE3NGNhMzA2ZjBkMGY2OEBncm91cC5jYWxlbmRhci5nb29nbGUuY29t) or [iCal](https://calendar.google.com/calendar/ical/e43d21e5c9b45a95f28c5d649c2cb1e1f433e2e653b56dbbda74ca306f0d0f68%40group.calendar.google.com/public/basic.ics)) or [Telegram group](https://t.me/cozystack).
 
 ## License
 

cmd/cozystack-controller/main.go

@@ -178,6 +178,15 @@ func main() {
 		setupLog.Error(err, "unable to create controller", "controller", "WorkloadMonitor")
 		os.Exit(1)
 	}
+
+	if err = (&controller.WorkloadReconciler{
+		Client: mgr.GetClient(),
+		Scheme: mgr.GetScheme(),
+	}).SetupWithManager(mgr); err != nil {
+		setupLog.Error(err, "unable to create controller", "controller", "Workload")
+		os.Exit(1)
+	}
+
 	// +kubebuilder:scaffold:builder
 
 	if err := mgr.AddHealthzCheck("healthz", healthz.Ping); err != nil {

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 }}",

hack/e2e.sh

@@ -60,7 +60,7 @@ 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
+  wget https://github.com/cozystack/cozystack/releases/latest/download/nocloud-amd64.raw.xz -O nocloud-amd64.raw.xz --show-progress --output-file /dev/stdout --progress=dot:giga 2>/dev/null
   rm -f nocloud-amd64.raw
   xz --decompress nocloud-amd64.raw.xz
 fi
@@ -84,7 +84,7 @@ done
 
 # Start VMs
 for i in 1 2 3; do
-  qemu-system-x86_64 -machine type=pc,accel=kvm -cpu host -smp 4 -m 8192 \
+  qemu-system-x86_64 -machine type=pc,accel=kvm -cpu host -smp 8 -m 16384 \
     -device virtio-net,netdev=net0,mac=52:54:00:12:34:5$i -netdev tap,id=net0,ifname=cozy-srv$i,script=no,downscript=no \
     -drive file=srv$i/system.img,if=virtio,format=raw \
     -drive file=srv$i/seed.img,if=virtio,format=raw \
@@ -113,6 +113,11 @@ machine:
         - usermode_helper=disabled
     - name: zfs
     - name: spl
+  registries:
+    mirrors:
+      docker.io:
+        endpoints:
+        - https://mirror.gcr.io
   files:
   - content: |
       [plugins]
@@ -229,8 +234,8 @@ 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
+timeout 60 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=1m --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
@@ -313,7 +318,12 @@ kubectl patch -n tenant-root tenants.apps.cozystack.io root --type=merge -p '{"s
 timeout 60 sh -c 'until kubectl get hr -n tenant-root etcd ingress monitoring tenant-root; do sleep 1; done'
 
 # Wait for HelmReleases be installed
-kubectl wait --timeout=2m --for=condition=ready -n tenant-root hr etcd ingress monitoring tenant-root
+kubectl wait --timeout=2m --for=condition=ready -n tenant-root hr etcd ingress tenant-root
+
+if ! kubectl wait --timeout=2m --for=condition=ready -n tenant-root hr monitoring; then
+  flux reconcile hr monitoring -n tenant-root --force
+  kubectl wait --timeout=2m --for=condition=ready -n tenant-root hr monitoring
+fi
 
 kubectl patch -n tenant-root ingresses.apps.cozystack.io ingress --type=merge -p '{"spec":{
   "dashboard": true
@@ -328,7 +338,7 @@ kubectl wait --timeout=5m --for=jsonpath=.status.readyReplicas=3 -n tenant-root
 
 # Wait for Victoria metrics
 kubectl wait --timeout=5m --for=jsonpath=.status.updateStatus=operational -n tenant-root vmalert/vmalert-shortterm vmalertmanager/alertmanager
-kubectl wait --timeout=5m --for=jsonpath=.status.status=operational -n tenant-root vlogs/generic
+kubectl wait --timeout=5m --for=jsonpath=.status.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
@@ -347,5 +357,5 @@ 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'
+timeout 120 sh -c 'until kubectl get hr -n cozy-keycloak keycloak keycloak-configure keycloak-operator; do sleep 1; done'
 kubectl wait --timeout=10m --for=condition=ready -n cozy-keycloak hr keycloak keycloak-configure keycloak-operator

hack/gen_versions_map.sh

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

hack/upload-assets.sh

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

internal/controller/workload_controller.go

@@ -0,0 +1,99 @@
+package controller
+
+import (
+	"context"
+	"strings"
+
+	corev1 "k8s.io/api/core/v1"
+	apierrors "k8s.io/apimachinery/pkg/api/errors"
+	"k8s.io/apimachinery/pkg/runtime"
+	"k8s.io/apimachinery/pkg/types"
+	ctrl "sigs.k8s.io/controller-runtime"
+	"sigs.k8s.io/controller-runtime/pkg/client"
+	"sigs.k8s.io/controller-runtime/pkg/log"
+
+	cozyv1alpha1 "github.com/cozystack/cozystack/api/v1alpha1"
+)
+
+// WorkloadMonitorReconciler reconciles a WorkloadMonitor object
+type WorkloadReconciler struct {
+	client.Client
+	Scheme *runtime.Scheme
+}
+
+func (r *WorkloadReconciler) Reconcile(ctx context.Context, req ctrl.Request) (ctrl.Result, error) {
+	logger := log.FromContext(ctx)
+	w := &cozyv1alpha1.Workload{}
+	err := r.Get(ctx, req.NamespacedName, w)
+	if err != nil {
+		if apierrors.IsNotFound(err) {
+			return ctrl.Result{}, nil
+		}
+		logger.Error(err, "Unable to fetch Workload")
+		return ctrl.Result{}, err
+	}
+
+	// it's being deleted, nothing to handle
+	if w.DeletionTimestamp != nil {
+		return ctrl.Result{}, nil
+	}
+
+	t := getMonitoredObject(w)
+
+	if t == nil {
+		err = r.Delete(ctx, w)
+		if err != nil {
+			logger.Error(err, "failed to delete workload")
+		}
+		return ctrl.Result{}, err
+	}
+
+	err = r.Get(ctx, types.NamespacedName{Name: t.GetName(), Namespace: t.GetNamespace()}, t)
+
+	// found object, nothing to do
+	if err == nil {
+		return ctrl.Result{}, nil
+	}
+
+	// error getting object but not 404 -- requeue
+	if !apierrors.IsNotFound(err) {
+		logger.Error(err, "failed to get dependent object", "kind", t.GetObjectKind(), "dependent-object-name", t.GetName())
+		return ctrl.Result{}, err
+	}
+
+	err = r.Delete(ctx, w)
+	if err != nil {
+		logger.Error(err, "failed to delete workload")
+	}
+	return ctrl.Result{}, err
+}
+
+// SetupWithManager registers our controller with the Manager and sets up watches.
+func (r *WorkloadReconciler) SetupWithManager(mgr ctrl.Manager) error {
+	return ctrl.NewControllerManagedBy(mgr).
+		// Watch WorkloadMonitor objects
+		For(&cozyv1alpha1.Workload{}).
+		Complete(r)
+}
+
+func getMonitoredObject(w *cozyv1alpha1.Workload) client.Object {
+	switch {
+	case strings.HasPrefix(w.Name, "pvc-"):
+		obj := &corev1.PersistentVolumeClaim{}
+		obj.Name = strings.TrimPrefix(w.Name, "pvc-")
+		obj.Namespace = w.Namespace
+		return obj
+	case strings.HasPrefix(w.Name, "svc-"):
+		obj := &corev1.Service{}
+		obj.Name = strings.TrimPrefix(w.Name, "svc-")
+		obj.Namespace = w.Namespace
+		return obj
+	case strings.HasPrefix(w.Name, "pod-"):
+		obj := &corev1.Pod{}
+		obj.Name = strings.TrimPrefix(w.Name, "pod-")
+		obj.Namespace = w.Namespace
+		return obj
+	}
+	var obj client.Object
+	return obj
+}

internal/controller/workload_controller_test.go

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

internal/controller/workloadmonitor_controller.go

@@ -3,6 +3,7 @@ package controller
 import (
 	"context"
 	"encoding/json"
+	"fmt"
 	"sort"
 
 	apierrors "k8s.io/apimachinery/pkg/api/errors"
@@ -33,6 +34,17 @@ type WorkloadMonitorReconciler struct {
 // +kubebuilder:rbac:groups=cozystack.io,resources=workloads,verbs=get;list;watch;create;update;patch;delete
 // +kubebuilder:rbac:groups=cozystack.io,resources=workloads/status,verbs=get;update;patch
 // +kubebuilder:rbac:groups=core,resources=pods,verbs=get;list;watch
+// +kubebuilder:rbac:groups=core,resources=persistentvolumeclaims,verbs=get;list;watch
+
+// isServiceReady checks if the service has an external IP bound
+func (r *WorkloadMonitorReconciler) isServiceReady(svc *corev1.Service) bool {
+	return len(svc.Status.LoadBalancer.Ingress) > 0
+}
+
+// isPVCReady checks if the PVC is bound
+func (r *WorkloadMonitorReconciler) isPVCReady(pvc *corev1.PersistentVolumeClaim) bool {
+	return pvc.Status.Phase == corev1.ClaimBound
+}
 
 // isPodReady checks if the Pod is in the Ready condition.
 func (r *WorkloadMonitorReconciler) isPodReady(pod *corev1.Pod) bool {
@@ -88,6 +100,96 @@ func updateOwnerReferences(obj metav1.Object, monitor client.Object) {
 	obj.SetOwnerReferences(owners)
 }
 
+// reconcileServiceForMonitor creates or updates a Workload object for the given Service and WorkloadMonitor.
+func (r *WorkloadMonitorReconciler) reconcileServiceForMonitor(
+	ctx context.Context,
+	monitor *cozyv1alpha1.WorkloadMonitor,
+	svc corev1.Service,
+) error {
+	logger := log.FromContext(ctx)
+	workload := &cozyv1alpha1.Workload{
+		ObjectMeta: metav1.ObjectMeta{
+			Name:      fmt.Sprintf("svc-%s", svc.Name),
+			Namespace: svc.Namespace,
+		},
+	}
+
+	resources := make(map[string]resource.Quantity)
+
+	q := resource.MustParse("0")
+
+	for _, ing := range svc.Status.LoadBalancer.Ingress {
+		if ing.IP != "" {
+			q.Add(resource.MustParse("1"))
+		}
+	}
+
+	resources["public-ips"] = q
+
+	_, err := ctrl.CreateOrUpdate(ctx, r.Client, workload, func() error {
+		// Update owner references with the new monitor
+		updateOwnerReferences(workload.GetObjectMeta(), monitor)
+
+		workload.Labels = svc.Labels
+
+		// Fill Workload status fields:
+		workload.Status.Kind = monitor.Spec.Kind
+		workload.Status.Type = monitor.Spec.Type
+		workload.Status.Resources = resources
+		workload.Status.Operational = r.isServiceReady(&svc)
+
+		return nil
+	})
+	if err != nil {
+		logger.Error(err, "Failed to CreateOrUpdate Workload", "workload", workload.Name)
+		return err
+	}
+
+	return nil
+}
+
+// reconcilePVCForMonitor creates or updates a Workload object for the given PVC and WorkloadMonitor.
+func (r *WorkloadMonitorReconciler) reconcilePVCForMonitor(
+	ctx context.Context,
+	monitor *cozyv1alpha1.WorkloadMonitor,
+	pvc corev1.PersistentVolumeClaim,
+) error {
+	logger := log.FromContext(ctx)
+	workload := &cozyv1alpha1.Workload{
+		ObjectMeta: metav1.ObjectMeta{
+			Name:      fmt.Sprintf("pvc-%s", pvc.Name),
+			Namespace: pvc.Namespace,
+		},
+	}
+
+	resources := make(map[string]resource.Quantity)
+
+	for resourceName, resourceQuantity := range pvc.Status.Capacity {
+		resources[resourceName.String()] = resourceQuantity
+	}
+
+	_, err := ctrl.CreateOrUpdate(ctx, r.Client, workload, func() error {
+		// Update owner references with the new monitor
+		updateOwnerReferences(workload.GetObjectMeta(), monitor)
+
+		workload.Labels = pvc.Labels
+
+		// Fill Workload status fields:
+		workload.Status.Kind = monitor.Spec.Kind
+		workload.Status.Type = monitor.Spec.Type
+		workload.Status.Resources = resources
+		workload.Status.Operational = r.isPVCReady(&pvc)
+
+		return nil
+	})
+	if err != nil {
+		logger.Error(err, "Failed to CreateOrUpdate Workload", "workload", workload.Name)
+		return err
+	}
+
+	return nil
+}
+
 // reconcilePodForMonitor creates or updates a Workload object for the given Pod and WorkloadMonitor.
 func (r *WorkloadMonitorReconciler) reconcilePodForMonitor(
 	ctx context.Context,
@@ -96,15 +198,12 @@ 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
@@ -133,7 +232,7 @@ func (r *WorkloadMonitorReconciler) reconcilePodForMonitor(
 
 	workload := &cozyv1alpha1.Workload{
 		ObjectMeta: metav1.ObjectMeta{
-			Name:      pod.Name,
+			Name:      fmt.Sprintf("pod-%s", pod.Name),
 			Namespace: pod.Namespace,
 		},
 	}
@@ -205,6 +304,45 @@ func (r *WorkloadMonitorReconciler) Reconcile(ctx context.Context, req ctrl.Requ
 		}
 	}
 
+	pvcList := &corev1.PersistentVolumeClaimList{}
+	if err := r.List(
+		ctx,
+		pvcList,
+		client.InNamespace(monitor.Namespace),
+		client.MatchingLabels(monitor.Spec.Selector),
+	); err != nil {
+		logger.Error(err, "Unable to list PVCs for WorkloadMonitor", "monitor", monitor.Name)
+		return ctrl.Result{}, err
+	}
+
+	for _, pvc := range pvcList.Items {
+		if err := r.reconcilePVCForMonitor(ctx, monitor, pvc); err != nil {
+			logger.Error(err, "Failed to reconcile Workload for PVC", "PVC", pvc.Name)
+			continue
+		}
+	}
+
+	svcList := &corev1.ServiceList{}
+	if err := r.List(
+		ctx,
+		svcList,
+		client.InNamespace(monitor.Namespace),
+		client.MatchingLabels(monitor.Spec.Selector),
+	); err != nil {
+		logger.Error(err, "Unable to list Services for WorkloadMonitor", "monitor", monitor.Name)
+		return ctrl.Result{}, err
+	}
+
+	for _, svc := range svcList.Items {
+		if svc.Spec.Type != corev1.ServiceTypeLoadBalancer {
+			continue
+		}
+		if err := r.reconcileServiceForMonitor(ctx, monitor, svc); err != nil {
+			logger.Error(err, "Failed to reconcile Workload for Service", "Service", svc.Name)
+			continue
+		}
+	}
+
 	// Update WorkloadMonitor status based on observed pods
 	monitor.Status.ObservedReplicas = observedReplicas
 	monitor.Status.AvailableReplicas = availableReplicas
@@ -233,41 +371,51 @@ func (r *WorkloadMonitorReconciler) SetupWithManager(mgr ctrl.Manager) error {
 		// Also watch Pod objects and map them back to WorkloadMonitor if labels match
 		Watches(
 			&corev1.Pod{},
-			handler.EnqueueRequestsFromMapFunc(func(ctx context.Context, obj client.Object) []reconcile.Request {
-				pod, ok := obj.(*corev1.Pod)
-				if !ok {
-					return nil
-				}
-
-				var monitorList cozyv1alpha1.WorkloadMonitorList
-				// List all WorkloadMonitors in the same namespace
-				if err := r.List(ctx, &monitorList, client.InNamespace(pod.Namespace)); err != nil {
-					return nil
-				}
-
-				// Match each monitor's selector with the Pod's labels
-				var requests []reconcile.Request
-				for _, m := range monitorList.Items {
-					matches := true
-					for k, v := range m.Spec.Selector {
-						if podVal, exists := pod.Labels[k]; !exists || podVal != v {
-							matches = false
-							break
-						}
-					}
-					if matches {
-						requests = append(requests, reconcile.Request{
-							NamespacedName: types.NamespacedName{
-								Namespace: m.Namespace,
-								Name:      m.Name,
-							},
-						})
-					}
-				}
-				return requests
-			}),
+			handler.EnqueueRequestsFromMapFunc(mapObjectToMonitor(&corev1.Pod{}, r.Client)),
+		).
+		// Watch PVCs as well
+		Watches(
+			&corev1.PersistentVolumeClaim{},
+			handler.EnqueueRequestsFromMapFunc(mapObjectToMonitor(&corev1.PersistentVolumeClaim{}, r.Client)),
 		).
 		// Watch for changes to Workload objects we create (owned by WorkloadMonitor)
 		Owns(&cozyv1alpha1.Workload{}).
 		Complete(r)
 }
+
+func mapObjectToMonitor[T client.Object](_ T, c client.Client) func(ctx context.Context, obj client.Object) []reconcile.Request {
+	return func(ctx context.Context, obj client.Object) []reconcile.Request {
+		concrete, ok := obj.(T)
+		if !ok {
+			return nil
+		}
+
+		var monitorList cozyv1alpha1.WorkloadMonitorList
+		// List all WorkloadMonitors in the same namespace
+		if err := c.List(ctx, &monitorList, client.InNamespace(concrete.GetNamespace())); err != nil {
+			return nil
+		}
+
+		labels := concrete.GetLabels()
+		// Match each monitor's selector with the Pod's labels
+		var requests []reconcile.Request
+		for _, m := range monitorList.Items {
+			matches := true
+			for k, v := range m.Spec.Selector {
+				if labelVal, exists := labels[k]; !exists || labelVal != v {
+					matches = false
+					break
+				}
+			}
+			if matches {
+				requests = append(requests, reconcile.Request{
+					NamespacedName: types.NamespacedName{
+						Namespace: m.Namespace,
+						Name:      m.Name,
+					},
+				})
+			}
+		}
+		return requests
+	}
+}

manifests/cozystack-installer.yaml

@@ -1,104 +0,0 @@
----
-# Source: cozy-installer/templates/cozystack.yaml
-apiVersion: v1
-kind: Namespace
-metadata:
-  name: cozy-system
-  labels:
-    pod-security.kubernetes.io/enforce: privileged
----
-# Source: cozy-installer/templates/cozystack.yaml
-apiVersion: v1
-kind: ServiceAccount
-metadata:
-  name: cozystack
-  namespace: cozy-system
----
-# Source: cozy-installer/templates/cozystack.yaml
-apiVersion: rbac.authorization.k8s.io/v1
-kind: ClusterRoleBinding
-metadata:
-  name: cozystack
-subjects:
-- kind: ServiceAccount
-  name: cozystack
-  namespace: cozy-system
-roleRef:
-  kind: ClusterRole
-  name: cluster-admin
-  apiGroup: rbac.authorization.k8s.io
----
-# Source: cozy-installer/templates/cozystack.yaml
-apiVersion: v1
-kind: Service
-metadata:
-  name: cozystack
-  namespace: cozy-system
-spec:
-  ports:
-  - name: http
-    port: 80
-    targetPort: 8123
-  selector:
-    app: cozystack
-  type: ClusterIP
----
-# Source: cozy-installer/templates/cozystack.yaml
-apiVersion: apps/v1
-kind: Deployment
-metadata:
-  name: cozystack
-  namespace: cozy-system
-spec:
-  replicas: 1
-  selector:
-    matchLabels:
-      app: cozystack
-  strategy:
-    type: RollingUpdate
-    rollingUpdate:
-      maxSurge: 0
-      maxUnavailable: 1
-  template:
-    metadata:
-      labels:
-        app: cozystack
-    spec:
-      hostNetwork: true
-      serviceAccountName: cozystack
-      containers:
-      - name: cozystack
-        image: "ghcr.io/aenix-io/cozystack/cozystack:v0.27.0"
-        env:
-        - name: KUBERNETES_SERVICE_HOST
-          value: localhost
-        - name: KUBERNETES_SERVICE_PORT
-          value: "7445"
-        - name: K8S_AWAIT_ELECTION_ENABLED
-          value: "1"
-        - name: K8S_AWAIT_ELECTION_NAME
-          value: cozystack
-        - name: K8S_AWAIT_ELECTION_LOCK_NAME
-          value: cozystack
-        - name: K8S_AWAIT_ELECTION_LOCK_NAMESPACE
-          value: cozy-system
-        - name: K8S_AWAIT_ELECTION_IDENTITY
-          valueFrom:
-            fieldRef:
-              fieldPath: metadata.name
-      - name: assets
-        image: "ghcr.io/aenix-io/cozystack/cozystack:v0.27.0"
-        command:
-        - /usr/bin/cozystack-assets-server
-        - "-dir=/cozystack/assets"
-        - "-address=:8123"
-        ports:
-        - name: http
-          containerPort: 8123
-      tolerations:
-      - key: "node.kubernetes.io/not-ready"
-        operator: "Exists"
-        effect: "NoSchedule"
-      - key: "node.cilium.io/agent-not-ready"
-        operator: "Exists"
-        effect: "NoSchedule"

packages/apps/clickhouse/Chart.yaml

@@ -16,7 +16,7 @@ type: application
 # This is the chart version. This version number should be incremented each time you make changes
 # to the chart and its templates, including the app version.
 # Versions are expected to follow Semantic Versioning (https://semver.org/)
-version: 0.6.2
+version: 0.7.0
 
 # This is the version number of the application being deployed. This version number should be
 # incremented each time you make changes to the application. Versions are not expected to

packages/apps/clickhouse/README.md

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

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

@@ -1 +1 @@
-ghcr.io/aenix-io/cozystack/clickhouse-backup:0.6.2@sha256:7a99cabdfd541f863aa5d1b2f7b49afd39838fb94c8448986634a1dc9050751c
+ghcr.io/cozystack/cozystack/clickhouse-backup:0.7.0@sha256:3faf7a4cebf390b9053763107482de175aa0fdb88c1e77424fd81100b1c3a205

packages/apps/clickhouse/templates/_resources.tpl

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

packages/apps/clickhouse/templates/clickhouse.yaml

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

packages/apps/clickhouse/values.schema.json

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

packages/apps/clickhouse/values.yaml

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

packages/apps/ferretdb/Chart.yaml

@@ -16,7 +16,7 @@ type: application
 # This is the chart version. This version number should be incremented each time you make changes
 # to the chart and its templates, including the app version.
 # Versions are expected to follow Semantic Versioning (https://semver.org/)
-version: 0.4.2
+version: 0.5.0
 
 # This is the version number of the application being deployed. This version number should be
 # incremented each time you make changes to the application. Versions are not expected to

packages/apps/ferretdb/README.md

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

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

@@ -1 +1 @@
-ghcr.io/aenix-io/cozystack/postgres-backup:0.9.0@sha256:6cc07280c0e2432ed37b2646faf82efe9702c6d93504844744aa505b890cac6f
+ghcr.io/cozystack/cozystack/postgres-backup:0.10.1@sha256:10179ed56457460d95cd5708db2a00130901255fa30c4dd76c65d2ef5622b61f

packages/apps/ferretdb/templates/_resources.tpl

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

packages/apps/ferretdb/templates/postgres.yaml

@@ -15,7 +15,11 @@ spec:
   {{- end }}
   minSyncReplicas: {{ .Values.quorum.minSyncReplicas }}
   maxSyncReplicas: {{ .Values.quorum.maxSyncReplicas }}
-
+  {{- if .Values.resources }}
+  resources: {{- toYaml .Values.resources | nindent 4 }}
+  {{- else if ne .Values.resourcesPreset "none" }}
+  resources: {{- include "resources.preset" (dict "type" .Values.resourcesPreset "Release" .Release) | nindent 4 }}
+  {{- end }}
   monitoring:
     enablePodMonitor: true
 

packages/apps/ferretdb/values.schema.json

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

packages/apps/ferretdb/values.yaml

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

packages/apps/http-cache/Chart.yaml

@@ -16,7 +16,7 @@ type: application
 # This is the chart version. This version number should be incremented each time you make changes
 # to the chart and its templates, including the app version.
 # Versions are expected to follow Semantic Versioning (https://semver.org/)
-version: 0.3.1
+version: 0.4.0
 
 # This is the version number of the application being deployed. This version number should be
 # incremented each time you make changes to the application. Versions are not expected to

packages/apps/http-cache/README.md

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

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

@@ -1 +1 @@
-ghcr.io/aenix-io/cozystack/nginx-cache:0.3.1@sha256:72ced2b1d8da2c784d6231af6cb0752170f6ea845c73effb11adb006b7a7fbb2
+ghcr.io/cozystack/cozystack/nginx-cache:0.4.0@sha256:4da14241052d2c4bd29d1766c4a569446f808a19538ef7f6acc05a981913df8e

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

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

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

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

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

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

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

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

packages/apps/http-cache/values.yaml

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

packages/apps/kafka/Chart.yaml

@@ -16,7 +16,7 @@ type: application
 # This is the chart version. This version number should be incremented each time you make changes
 # to the chart and its templates, including the app version.
 # Versions are expected to follow Semantic Versioning (https://semver.org/)
-version: 0.3.3
+version: 0.5.0
 
 # This is the version number of the application being deployed. This version number should be
 # incremented each time you make changes to the application. Versions are not expected to

packages/apps/kafka/README.md

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

packages/apps/kafka/templates/_resources.tpl

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

packages/apps/kafka/templates/kafka.yaml

@@ -8,6 +8,11 @@ metadata:
 spec:
   kafka:
     replicas: {{ .Values.kafka.replicas }}
+    {{- if .Values.kafka.resources }}
+    resources: {{- toYaml .Values.kafka.resources | nindent 6 }}
+    {{- else if ne .Values.kafka.resourcesPreset "none" }}
+    resources: {{- include "resources.preset" (dict "type" .Values.kafka.resourcesPreset "Release" .Release) | nindent 6 }}
+    {{- end }}
     listeners:
       - name: plain
         port: 9092
@@ -65,6 +70,11 @@ spec:
           key: kafka-metrics-config.yml
   zookeeper:
     replicas: {{ .Values.zookeeper.replicas }}
+    {{- if .Values.zookeeper.resources }}
+    resources: {{- toYaml .Values.zookeeper.resources | nindent 6 }}
+    {{- else if ne .Values.zookeeper.resourcesPreset "none" }}
+    resources: {{- include "resources.preset" (dict "type" .Values.zookeeper.resourcesPreset "Release" .Release) | nindent 6 }}
+    {{- end }}
     storage:
       type: persistent-claim
       {{- with .Values.zookeeper.size }}

packages/apps/kafka/values.schema.json

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

packages/apps/kafka/values.yaml

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

packages/apps/kubernetes/Chart.yaml

@@ -16,7 +16,7 @@ type: application
 # This is the chart version. This version number should be incremented each time you make changes
 # to the chart and its templates, including the app version.
 # Versions are expected to follow Semantic Versioning (https://semver.org/)
-version: 0.15.2
+version: 0.18.1
 
 # This is the version number of the application being deployed. This version number should be
 # incremented each time you make changes to the application. Versions are not expected to

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

@@ -1 +1 @@
-ghcr.io/aenix-io/cozystack/cluster-autoscaler:0.15.2@sha256:077023fc24d466ac18f8d43fec41b9a14c0b3d32c0013e836e7448e7a1e7d661
+ghcr.io/cozystack/cozystack/cluster-autoscaler:0.18.1@sha256:85371c6aabf5a7fea2214556deac930c600e362f92673464fe2443784e2869c3

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

@@ -1 +1 @@
-ghcr.io/aenix-io/cozystack/kubevirt-cloud-provider:0.15.2@sha256:5ef7198eaaa4e422caa5f3d8f906c908046f1fbaf2d7a1e72b5a98627db3bda8
+ghcr.io/cozystack/cozystack/kubevirt-cloud-provider:0.18.1@sha256:795d8e1ef4b2b0df2aa1e09d96cd13476ebb545b4bf4b5779b7547a70ef64cf9

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

@@ -3,12 +3,11 @@ FROM --platform=linux/amd64 golang:1.20.6 AS builder
 
 RUN git clone https://github.com/kubevirt/cloud-provider-kubevirt /go/src/kubevirt.io/cloud-provider-kubevirt \
  && cd /go/src/kubevirt.io/cloud-provider-kubevirt \
- && git checkout da9e0cf
+ && git checkout 443a1fe
 
 WORKDIR /go/src/kubevirt.io/cloud-provider-kubevirt
 
 # see: https://github.com/kubevirt/cloud-provider-kubevirt/pull/335
-# see: https://github.com/kubevirt/cloud-provider-kubevirt/pull/336
 ADD patches /patches
 RUN git apply /patches/*.diff
 RUN go get 'k8s.io/endpointslice/util@v0.28' 'k8s.io/apiserver@v0.28'

packages/apps/kubernetes/images/kubevirt-cloud-provider/patches/335.diff

@@ -1,20 +0,0 @@
-diff --git a/pkg/controller/kubevirteps/kubevirteps_controller.go b/pkg/controller/kubevirteps/kubevirteps_controller.go
-index a3c1aa33..95c31438 100644
---- a/pkg/controller/kubevirteps/kubevirteps_controller.go
-+++ b/pkg/controller/kubevirteps/kubevirteps_controller.go
-@@ -412,11 +412,11 @@ func (c *Controller) reconcileByAddressType(service *v1.Service, tenantSlices []
- 	// Create the desired port configuration
- 	var desiredPorts []discovery.EndpointPort
- 
--	for _, port := range service.Spec.Ports {
-+	for i := range service.Spec.Ports {
- 		desiredPorts = append(desiredPorts, discovery.EndpointPort{
--			Port:     &port.TargetPort.IntVal,
--			Protocol: &port.Protocol,
--			Name:     &port.Name,
-+			Port:     &service.Spec.Ports[i].TargetPort.IntVal,
-+			Protocol: &service.Spec.Ports[i].Protocol,
-+			Name:     &service.Spec.Ports[i].Name,
- 		})
- 	}
- 

packages/apps/kubernetes/images/kubevirt-cloud-provider/patches/336.diff

@@ -1,129 +0,0 @@
-diff --git a/pkg/controller/kubevirteps/kubevirteps_controller.go b/pkg/controller/kubevirteps/kubevirteps_controller.go
-index a3c1aa33..6f6e3d32 100644
---- a/pkg/controller/kubevirteps/kubevirteps_controller.go
-+++ b/pkg/controller/kubevirteps/kubevirteps_controller.go
-@@ -108,32 +108,24 @@ func newRequest(reqType ReqType, obj interface{}, oldObj interface{}) *Request {
- }
- 
- func (c *Controller) Init() error {
--
--	// Act on events from Services on the infra cluster. These are created by the EnsureLoadBalancer function.
--	// We need to watch for these events so that we can update the EndpointSlices in the infra cluster accordingly.
-+	// Existing Service event handlers...
- 	_, err := c.infraFactory.Core().V1().Services().Informer().AddEventHandler(cache.ResourceEventHandlerFuncs{
- 		AddFunc: func(obj interface{}) {
--			// cast obj to Service
- 			svc := obj.(*v1.Service)
--			// Only act on Services of type LoadBalancer
- 			if svc.Spec.Type == v1.ServiceTypeLoadBalancer {
- 				klog.Infof("Service added: %v/%v", svc.Namespace, svc.Name)
- 				c.queue.Add(newRequest(AddReq, obj, nil))
- 			}
- 		},
- 		UpdateFunc: func(oldObj, newObj interface{}) {
--			// cast obj to Service
- 			newSvc := newObj.(*v1.Service)
--			// Only act on Services of type LoadBalancer
- 			if newSvc.Spec.Type == v1.ServiceTypeLoadBalancer {
- 				klog.Infof("Service updated: %v/%v", newSvc.Namespace, newSvc.Name)
- 				c.queue.Add(newRequest(UpdateReq, newObj, oldObj))
- 			}
- 		},
- 		DeleteFunc: func(obj interface{}) {
--			// cast obj to Service
- 			svc := obj.(*v1.Service)
--			// Only act on Services of type LoadBalancer
- 			if svc.Spec.Type == v1.ServiceTypeLoadBalancer {
- 				klog.Infof("Service deleted: %v/%v", svc.Namespace, svc.Name)
- 				c.queue.Add(newRequest(DeleteReq, obj, nil))
-@@ -144,7 +136,7 @@ func (c *Controller) Init() error {
- 		return err
- 	}
- 
--	// Monitor endpoint slices that we are interested in based on known services in the infra cluster
-+	// Existing EndpointSlice event handlers in tenant cluster...
- 	_, err = c.tenantFactory.Discovery().V1().EndpointSlices().Informer().AddEventHandler(cache.ResourceEventHandlerFuncs{
- 		AddFunc: func(obj interface{}) {
- 			eps := obj.(*discovery.EndpointSlice)
-@@ -194,10 +186,80 @@ func (c *Controller) Init() error {
- 		return err
- 	}
- 
--	//TODO: Add informer for EndpointSlices in the infra cluster to watch for (unwanted) changes
-+	// Add an informer for EndpointSlices in the infra cluster
-+	_, err = c.infraFactory.Discovery().V1().EndpointSlices().Informer().AddEventHandler(cache.ResourceEventHandlerFuncs{
-+		AddFunc: func(obj interface{}) {
-+			eps := obj.(*discovery.EndpointSlice)
-+			if c.managedByController(eps) {
-+				svc, svcErr := c.getInfraServiceForEPS(context.TODO(), eps)
-+				if svcErr != nil {
-+					klog.Errorf("Failed to get infra Service for EndpointSlice %s/%s: %v", eps.Namespace, eps.Name, svcErr)
-+					return
-+				}
-+				if svc != nil {
-+					klog.Infof("Infra EndpointSlice added: %v/%v, requeuing Service: %v/%v", eps.Namespace, eps.Name, svc.Namespace, svc.Name)
-+					c.queue.Add(newRequest(AddReq, svc, nil))
-+				}
-+			}
-+		},
-+		UpdateFunc: func(oldObj, newObj interface{}) {
-+			eps := newObj.(*discovery.EndpointSlice)
-+			if c.managedByController(eps) {
-+				svc, svcErr := c.getInfraServiceForEPS(context.TODO(), eps)
-+				if svcErr != nil {
-+					klog.Errorf("Failed to get infra Service for EndpointSlice %s/%s: %v", eps.Namespace, eps.Name, svcErr)
-+					return
-+				}
-+				if svc != nil {
-+					klog.Infof("Infra EndpointSlice updated: %v/%v, requeuing Service: %v/%v", eps.Namespace, eps.Name, svc.Namespace, svc.Name)
-+					c.queue.Add(newRequest(UpdateReq, svc, nil))
-+				}
-+			}
-+		},
-+		DeleteFunc: func(obj interface{}) {
-+			eps := obj.(*discovery.EndpointSlice)
-+			if c.managedByController(eps) {
-+				svc, svcErr := c.getInfraServiceForEPS(context.TODO(), eps)
-+				if svcErr != nil {
-+					klog.Errorf("Failed to get infra Service for EndpointSlice %s/%s on delete: %v", eps.Namespace, eps.Name, svcErr)
-+					return
-+				}
-+				if svc != nil {
-+					klog.Infof("Infra EndpointSlice deleted: %v/%v, requeuing Service: %v/%v", eps.Namespace, eps.Name, svc.Namespace, svc.Name)
-+					c.queue.Add(newRequest(DeleteReq, svc, nil))
-+				}
-+			}
-+		},
-+	})
-+	if err != nil {
-+		return err
-+	}
-+
- 	return nil
- }
- 
-+// getInfraServiceForEPS returns the Service in the infra cluster associated with the given EndpointSlice.
-+// It does this by reading the "kubernetes.io/service-name" label from the EndpointSlice, which should correspond
-+// to the Service name. If not found or if the Service doesn't exist, it returns nil.
-+func (c *Controller) getInfraServiceForEPS(ctx context.Context, eps *discovery.EndpointSlice) (*v1.Service, error) {
-+	svcName := eps.Labels[discovery.LabelServiceName]
-+	if svcName == "" {
-+		// No service name label found, can't determine infra service.
-+		return nil, nil
-+	}
-+
-+	svc, err := c.infraClient.CoreV1().Services(c.infraNamespace).Get(ctx, svcName, metav1.GetOptions{})
-+	if err != nil {
-+		if k8serrors.IsNotFound(err) {
-+			// Service doesn't exist
-+			return nil, nil
-+		}
-+		return nil, err
-+	}
-+
-+	return svc, nil
-+}
-+
- // Run starts an asynchronous loop that monitors and updates GKENetworkParamSet in the cluster.
- func (c *Controller) Run(numWorkers int, stopCh <-chan struct{}, controllerManagerMetrics *controllersmetrics.ControllerManagerMetrics) {
- 	defer utilruntime.HandleCrash()

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

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

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

@@ -1 +1 @@
-ghcr.io/aenix-io/cozystack/kubevirt-csi-driver:0.15.2@sha256:f862c233399b213e376628ffbb55304f08d171e991371d5bde067b47890cc959
+ghcr.io/cozystack/cozystack/kubevirt-csi-driver:0.18.1@sha256:5717919c75e609902c6d67138311a2a8fd07be822e2173f3802b67cf5f3486e9

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

@@ -1 +1 @@
-ghcr.io/aenix-io/cozystack/ubuntu-container-disk:v1.30.1@sha256:7ce5467b8f34ef7897141b0ca96c455459c2729cae5824a2c20f32b01a841f90
+ghcr.io/cozystack/cozystack/ubuntu-container-disk:v1.30.1@sha256:6359b7877f04c6ac6641c0ebcc2a1d03cabfe1718464cd43f82e97724ad6aad8

packages/apps/kubernetes/templates/_resources.tpl

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

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

@@ -26,6 +26,13 @@ spec:
       containers:
       - image: "{{ $.Files.Get "images/cluster-autoscaler.tag" | trim }}"
         name: cluster-autoscaler
+        resources:
+          limits:
+            cpu: 512m
+            memory: 512Mi
+          requests:
+            cpu: 125m
+            memory: 128Mi
         command:
         - /cluster-autoscaler
         args:

packages/apps/kubernetes/templates/cluster.yaml

@@ -102,12 +102,37 @@ metadata:
   annotations:
     kamaji.clastix.io/kubeconfig-secret-key: "super-admin.svc"
 spec:
+  apiServer:
+    {{- if .Values.kamajiControlPlane.apiServer.resources }}
+    resources: {{- toYaml .Values.kamajiControlPlane.apiServer.resources | nindent 6 }}
+    {{- else if ne .Values.kamajiControlPlane.apiServer.resourcesPreset "none" }}
+    resources: {{- include "resources.preset" (dict "type" .Values.kamajiControlPlane.apiServer.resourcesPreset "Release" .Release) | nindent 6 }}
+    {{- end }}
+  controllerManager:
+    {{- if .Values.kamajiControlPlane.controllerManager.resources }}
+    resources: {{- toYaml .Values.kamajiControlPlane.controllerManager.resources | nindent 6 }}
+    {{- else if ne .Values.kamajiControlPlane.controllerManager.resourcesPreset "none" }}
+    resources: {{- include "resources.preset" (dict "type" .Values.kamajiControlPlane.controllerManager.resourcesPreset "Release" .Release) | nindent 6 }}
+    {{- end }}
+  scheduler:
+    {{- if .Values.kamajiControlPlane.scheduler.resources }}
+    resources: {{- toYaml .Values.kamajiControlPlane.scheduler.resources | nindent 6 }}
+    {{- else if ne .Values.kamajiControlPlane.scheduler.resourcesPreset "none" }}
+    resources: {{- include "resources.preset" (dict "type" .Values.kamajiControlPlane.scheduler.resourcesPreset "Release" .Release) | nindent 6 }}
+    {{- end }}
   dataStoreName: "{{ $etcd }}"
   addons:
     coreDNS:
       dnsServiceIPs:
       - 10.95.0.10
-    konnectivity: {}
+    konnectivity:
+      server:
+        port: 8132
+        {{- if .Values.kamajiControlPlane.addons.konnectivity.server.resources }}
+        resources: {{- toYaml .Values.kamajiControlPlane.addons.konnectivity.server.resources | nindent 10 }}
+        {{- else if ne .Values.kamajiControlPlane.addons.konnectivity.server.resourcesPreset "none" }}
+        resources: {{- include "resources.preset" (dict "type" .Values.kamajiControlPlane.addons.konnectivity.server.resourcesPreset "Release" .Release) | nindent 10 }}
+        {{- end }}
   kubelet:
     cgroupfs: systemd
     preferredAddressTypes:

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

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

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

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

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

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

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

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

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

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

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

@@ -32,6 +32,9 @@ spec:
                 {{ .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
@@ -67,6 +70,9 @@ 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

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

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

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

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

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

@@ -21,7 +21,8 @@ spec:
         namespace: cozy-system
   kubeConfig:
     secretRef:
-      name: {{ .Release.Name }}-kubeconfig
+      name: {{ .Release.Name }}-admin-kubeconfig
+      key: super-admin.svc
   targetNamespace: cozy-monitoring-agents
   storageNamespace: cozy-monitoring-agents
   install:
@@ -37,10 +38,10 @@ spec:
   - name: {{ .Release.Name }}
     namespace: {{ .Release.Namespace }}
   {{- end }}
-  - name: {{ .Release.Name }}-cilium
-    namespace: {{ .Release.Namespace }}
   - name: {{ .Release.Name }}-cozy-victoria-metrics-operator
     namespace: {{ .Release.Namespace }}
+  - name: {{ .Release.Name }}-vertical-pod-autoscaler-crds
+    namespace: {{ .Release.Namespace }}
   values:
     vmagent:
       externalLabels:

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

@@ -0,0 +1,41 @@
+{{- if .Values.addons.monitoringAgents.enabled }}
+apiVersion: helm.toolkit.fluxcd.io/v2
+kind: HelmRelease
+metadata:
+  name: {{ .Release.Name }}-vertical-pod-autoscaler-crds
+  labels:
+    cozystack.io/repository: system
+    coztstack.io/target-cluster-name: {{ .Release.Name }}
+spec:
+  interval: 5m
+  releaseName: vertical-pod-autoscaler-crds
+  chart:
+    spec:
+      chart: cozy-vertical-pod-autoscaler-crds
+      reconcileStrategy: Revision
+      sourceRef:
+        kind: HelmRepository
+        name: cozystack-system
+        namespace: cozy-system
+  kubeConfig:
+    secretRef:
+      name: {{ .Release.Name }}-admin-kubeconfig
+      key: super-admin.svc
+  targetNamespace: cozy-vertical-pod-autoscaler-crds
+  storageNamespace: cozy-vertical-pod-autoscaler-crds
+  install:
+    createNamespace: true
+    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 }}
+  - name: {{ .Release.Name }}-cilium
+    namespace: {{ .Release.Namespace }}
+{{- end }}

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

@@ -0,0 +1,69 @@
+{{- $myNS := lookup "v1" "Namespace" "" .Release.Namespace }}
+{{- $targetTenant := index $myNS.metadata.annotations "namespace.cozystack.io/monitoring" }}
+{{- if .Values.addons.monitoringAgents.enabled }}
+apiVersion: helm.toolkit.fluxcd.io/v2
+kind: HelmRelease
+metadata:
+  name: {{ .Release.Name }}-vertical-pod-autoscaler
+  labels:
+    cozystack.io/repository: system
+    coztstack.io/target-cluster-name: {{ .Release.Name }}
+spec:
+  interval: 5m
+  releaseName: vertical-pod-autoscaler
+  chart:
+    spec:
+      chart: cozy-vertical-pod-autoscaler
+      reconcileStrategy: Revision
+      sourceRef:
+        kind: HelmRepository
+        name: cozystack-system
+        namespace: cozy-system
+  kubeConfig:
+    secretRef:
+      name: {{ .Release.Name }}-admin-kubeconfig
+      key: super-admin.svc
+  targetNamespace: cozy-vertical-pod-autoscaler
+  storageNamespace: cozy-vertical-pod-autoscaler
+  install:
+    createNamespace: true
+    remediation:
+      retries: -1
+  upgrade:
+    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 }}
+  dependsOn:
+  {{- if lookup "helm.toolkit.fluxcd.io/v2" "HelmRelease" .Release.Namespace .Release.Name }}
+  - name: {{ .Release.Name }}
+    namespace: {{ .Release.Namespace }}
+  {{- end }}
+  - name: {{ .Release.Name }}-monitoring-agents
+    namespace: {{ .Release.Namespace }}
+{{- end }}

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

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

packages/apps/kubernetes/templates/kccm/manager.yaml

@@ -36,8 +36,12 @@ spec:
         #securityContext:
         #  privileged: true
         resources:
+          limits:
+            cpu: 512m
+            memory: 512Mi
           requests:
-            cpu: 100m
+            cpu: 125m
+            memory: 128Mi
         volumeMounts:
         - mountPath: /etc/kubernetes/kubeconfig
           name: kubeconfig

packages/apps/kubernetes/values.yaml

@@ -69,3 +69,70 @@ addons:
     ##
     enabled: false
     valuesOverride: {}
+
+  ## VerticalPodAutoscaler
+  ##
+  verticalPodAutoscaler:
+    ## @param addons.verticalPodAutoscaler.valuesOverride Custom values to override
+    ##
+    valuesOverride: {}
+
+## @section Kamaji control plane
+##
+kamajiControlPlane:
+  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).
+    resourcesPreset: "small"
+
+  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).
+    resourcesPreset: "micro"
+  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).
+    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"
+            

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: 0.5.3
+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/mysql/README.md

@@ -83,14 +83,16 @@ more details:
 
 ### Backup parameters
 
-| Name                     | Description                                    | Value                                                  |
-| ------------------------ | ---------------------------------------------- | ------------------------------------------------------ |
-| `backup.enabled`         | Enable pereiodic backups                       | `false`                                                |
-| `backup.s3Region`        | The AWS S3 region where backups are stored     | `us-east-1`                                            |
-| `backup.s3Bucket`        | The S3 bucket used for storing backups         | `s3.example.org/postgres-backups`                      |
-| `backup.schedule`        | Cron schedule for automated backups            | `0 2 * * *`                                            |
-| `backup.cleanupStrategy` | The strategy for cleaning up old backups       | `--keep-last=3 --keep-daily=3 --keep-within-weekly=1m` |
-| `backup.s3AccessKey`     | The access key for S3, used for authentication | `oobaiRus9pah8PhohL1ThaeTa4UVa7gu`                     |
-| `backup.s3SecretKey`     | The secret key for S3, used for authentication | `ju3eum4dekeich9ahM1te8waeGai0oog`                     |
-| `backup.resticPassword`  | The password for Restic backup encryption      | `ChaXoveekoh6eigh4siesheeda2quai0`                     |
+| Name                     | Description                                                                                                                                                                                                       | Value                                                  |
+| ------------------------ | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------ |
+| `backup.enabled`         | Enable pereiodic backups                                                                                                                                                                                          | `false`                                                |
+| `backup.s3Region`        | The AWS S3 region where backups are stored                                                                                                                                                                        | `us-east-1`                                            |
+| `backup.s3Bucket`        | The S3 bucket used for storing backups                                                                                                                                                                            | `s3.example.org/postgres-backups`                      |
+| `backup.schedule`        | Cron schedule for automated backups                                                                                                                                                                               | `0 2 * * *`                                            |
+| `backup.cleanupStrategy` | The strategy for cleaning up old backups                                                                                                                                                                          | `--keep-last=3 --keep-daily=3 --keep-within-weekly=1m` |
+| `backup.s3AccessKey`     | The access key for S3, used for authentication                                                                                                                                                                    | `oobaiRus9pah8PhohL1ThaeTa4UVa7gu`                     |
+| `backup.s3SecretKey`     | The secret key for S3, used for authentication                                                                                                                                                                    | `ju3eum4dekeich9ahM1te8waeGai0oog`                     |
+| `backup.resticPassword`  | The password for Restic backup encryption                                                                                                                                                                         | `ChaXoveekoh6eigh4siesheeda2quai0`                     |
+| `resources`              | Resources                                                                                                                                                                                                         | `{}`                                                   |
+| `resourcesPreset`        | Set container resources according to one common preset (allowed values: none, nano, micro, small, medium, large, xlarge, 2xlarge). This is ignored if resources is set (resources is recommended for production). | `nano`                                                 |
 

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

@@ -1 +1 @@
-ghcr.io/aenix-io/cozystack/mariadb-backup:0.5.3@sha256:89641695e0c1f4ad7b82697c27a2245bb4a1bc403845235ed0df98e04aa9a71f
+ghcr.io/cozystack/cozystack/mariadb-backup:0.6.0@sha256:cfd1c37d8ad24e10681d82d6e6ce8a641b4602c1b0ffa8516ae15b4958bb12d4

packages/apps/mysql/templates/_resources.tpl

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

packages/apps/mysql/templates/mariadb.yaml

@@ -72,3 +72,9 @@ spec:
 
   #secondaryService:
   #  type: LoadBalancer
+
+  {{- if .Values.resources }}
+  resources: {{- toYaml .Values.resources | nindent 4 }}
+  {{- else if ne .Values.resourcesPreset "none" }}
+  resources: {{- include "resources.preset" (dict "type" .Values.resourcesPreset "Release" .Release) | nindent 4 }}
+  {{- end }}

packages/apps/mysql/values.schema.json

@@ -66,6 +66,16 @@
                     "default": "ChaXoveekoh6eigh4siesheeda2quai0"
                 }
             }
+        },
+        "resources": {
+            "type": "object",
+            "description": "Resources",
+            "default": {}
+        },
+        "resourcesPreset": {
+            "type": "string",
+            "description": "Set container resources according to one common preset (allowed values: none, nano, micro, small, medium, large, xlarge, 2xlarge). This is ignored if resources is set (resources is recommended for production).",
+            "default": "nano"
         }
     }
 }

packages/apps/mysql/values.yaml

@@ -54,3 +54,16 @@ backup:
   s3AccessKey: oobaiRus9pah8PhohL1ThaeTa4UVa7gu
   s3SecretKey: ju3eum4dekeich9ahM1te8waeGai0oog
   resticPassword: ChaXoveekoh6eigh4siesheeda2quai0
+
+## @param resources Resources
+resources: {}
+ # resources:
+ #   limits:
+ #     cpu: 4000m
+ #     memory: 4Gi
+ #   requests:
+ #     cpu: 100m
+ #     memory: 512Mi
+ 
+## @param resourcesPreset Set container resources according to one common preset (allowed values: none, nano, micro, small, medium, large, xlarge, 2xlarge). This is ignored if resources is set (resources is recommended for production).
+resourcesPreset: "nano"

packages/apps/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: 0.4.1
+version: 0.5.0
 
 # This is the version number of the application being deployed. This version number should be
 # incremented each time you make changes to the application. Versions are not expected to

packages/apps/nats/README.md

@@ -4,13 +4,15 @@
 
 ### Common parameters
 
-| Name                | Description                                        | Value   |
-| ------------------- | -------------------------------------------------- | ------- |
-| `external`          | Enable external access from outside the cluster    | `false` |
-| `replicas`          | Persistent Volume size for NATS                    | `2`     |
-| `storageClass`      | StorageClass used to store the data                | `""`    |
-| `users`             | Users configuration                                | `{}`    |
-| `jetstream.size`    | Jetstream persistent storage size                  | `10Gi`  |
-| `jetstream.enabled` | Enable or disable Jetstream                        | `true`  |
-| `config.merge`      | Additional configuration to merge into NATS config | `{}`    |
-| `config.resolver`   | Additional configuration to merge into NATS config | `{}`    |
+| Name                | Description                                                                                                                                                                                                       | Value   |
+| ------------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ------- |
+| `external`          | Enable external access from outside the cluster                                                                                                                                                                   | `false` |
+| `replicas`          | Persistent Volume size for NATS                                                                                                                                                                                   | `2`     |
+| `storageClass`      | StorageClass used to store the data                                                                                                                                                                               | `""`    |
+| `users`             | Users configuration                                                                                                                                                                                               | `{}`    |
+| `jetstream.size`    | Jetstream persistent storage size                                                                                                                                                                                 | `10Gi`  |
+| `jetstream.enabled` | Enable or disable Jetstream                                                                                                                                                                                       | `true`  |
+| `config.merge`      | Additional configuration to merge into NATS config                                                                                                                                                                | `{}`    |
+| `config.resolver`   | Additional configuration to merge into NATS config                                                                                                                                                                | `{}`    |
+| `resources`         | Resources                                                                                                                                                                                                         | `{}`    |
+| `resourcesPreset`   | Set container resources according to one common preset (allowed values: none, nano, micro, small, medium, large, xlarge, 2xlarge). This is ignored if resources is set (resources is recommended for production). | `nano`  |

packages/apps/nats/templates/_resources.tpl

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

packages/apps/nats/templates/nats.yaml

@@ -38,6 +38,17 @@ spec:
   timeout: 5m0s
   values:
     nats:
+      podTemplate:
+        merge:
+          spec:
+            containers:
+              - name: nats
+                image: nats:2.10.17-alpine
+                {{- if .Values.resources }}
+                resources: {{- toYaml .Values.resources | nindent 22 }}
+                {{- else if ne .Values.resourcesPreset "none" }}
+                resources: {{- include "resources.preset" (dict "type" .Values.resourcesPreset "Release" .Release) | nindent 22 }}
+                {{- end }}
       fullnameOverride: {{ .Release.Name }}
       config:
         {{- if or (gt (len $passwords) 0) (gt (len .Values.config.merge) 0) }}

packages/apps/nats/values.schema.json

@@ -46,6 +46,16 @@
                     "default": {}
                 }
             }
+        },
+        "resources": {
+            "type": "object",
+            "description": "Resources",
+            "default": {}
+        },
+        "resourcesPreset": {
+            "type": "string",
+            "description": "Set container resources according to one common preset (allowed values: none, nano, micro, small, medium, large, xlarge, 2xlarge). This is ignored if resources is set (resources is recommended for production).",
+            "default": "nano"
         }
     }
 }

packages/apps/nats/values.yaml

@@ -61,3 +61,16 @@ config:
   ## Default: {}
   ## Example see: https://github.com/nats-io/k8s/blob/main/helm/charts/nats/values.yaml#L247
   resolver: {}
+
+## @param resources Resources
+resources: {}
+ # resources:
+ #   limits:
+ #     cpu: 4000m
+ #     memory: 4Gi
+ #   requests:
+ #     cpu: 100m
+ #     memory: 512Mi
+ 
+## @param resourcesPreset Set container resources according to one common preset (allowed values: none, nano, micro, small, medium, large, xlarge, 2xlarge). This is ignored if resources is set (resources is recommended for production).
+resourcesPreset: "nano"

packages/apps/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: 0.9.0
+version: 0.10.1
 
 # This is the version number of the application being deployed. This version number should be
 # incremented each time you make changes to the application. Versions are not expected to

packages/apps/postgres/README.md

@@ -58,13 +58,15 @@ more details:
 
 ### Backup parameters
 
-| Name                     | Description                                    | Value                                                  |
-| ------------------------ | ---------------------------------------------- | ------------------------------------------------------ |
-| `backup.enabled`         | Enable pereiodic backups                       | `false`                                                |
-| `backup.s3Region`        | The AWS S3 region where backups are stored     | `us-east-1`                                            |
-| `backup.s3Bucket`        | The S3 bucket used for storing backups         | `s3.example.org/postgres-backups`                      |
-| `backup.schedule`        | Cron schedule for automated backups            | `0 2 * * *`                                            |
-| `backup.cleanupStrategy` | The strategy for cleaning up old backups       | `--keep-last=3 --keep-daily=3 --keep-within-weekly=1m` |
-| `backup.s3AccessKey`     | The access key for S3, used for authentication | `oobaiRus9pah8PhohL1ThaeTa4UVa7gu`                     |
-| `backup.s3SecretKey`     | The secret key for S3, used for authentication | `ju3eum4dekeich9ahM1te8waeGai0oog`                     |
-| `backup.resticPassword`  | The password for Restic backup encryption      | `ChaXoveekoh6eigh4siesheeda2quai0`                     |
+| Name                     | Description                                                                                                                                                                                                       | Value                                                  |
+| ------------------------ | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------ |
+| `backup.enabled`         | Enable pereiodic backups                                                                                                                                                                                          | `false`                                                |
+| `backup.s3Region`        | The AWS S3 region where backups are stored                                                                                                                                                                        | `us-east-1`                                            |
+| `backup.s3Bucket`        | The S3 bucket used for storing backups                                                                                                                                                                            | `s3.example.org/postgres-backups`                      |
+| `backup.schedule`        | Cron schedule for automated backups                                                                                                                                                                               | `0 2 * * *`                                            |
+| `backup.cleanupStrategy` | The strategy for cleaning up old backups                                                                                                                                                                          | `--keep-last=3 --keep-daily=3 --keep-within-weekly=1m` |
+| `backup.s3AccessKey`     | The access key for S3, used for authentication                                                                                                                                                                    | `oobaiRus9pah8PhohL1ThaeTa4UVa7gu`                     |
+| `backup.s3SecretKey`     | The secret key for S3, used for authentication                                                                                                                                                                    | `ju3eum4dekeich9ahM1te8waeGai0oog`                     |
+| `backup.resticPassword`  | The password for Restic backup encryption                                                                                                                                                                         | `ChaXoveekoh6eigh4siesheeda2quai0`                     |
+| `resources`              | Resources                                                                                                                                                                                                         | `{}`                                                   |
+| `resourcesPreset`        | Set container resources according to one common preset (allowed values: none, nano, micro, small, medium, large, xlarge, 2xlarge). This is ignored if resources is set (resources is recommended for production). | `nano`                                                 |

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

@@ -1 +1 @@
-ghcr.io/aenix-io/cozystack/postgres-backup:0.9.0@sha256:6cc07280c0e2432ed37b2646faf82efe9702c6d93504844744aa505b890cac6f
+ghcr.io/cozystack/cozystack/postgres-backup:0.10.1@sha256:10179ed56457460d95cd5708db2a00130901255fa30c4dd76c65d2ef5622b61f

packages/apps/postgres/templates/_resources.tpl

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

packages/apps/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 }}"

packages/apps/postgres/templates/db.yaml

@@ -5,6 +5,12 @@ metadata:
   name: {{ .Release.Name }}
 spec:
   instances: {{ .Values.replicas }}
+  {{- if .Values.resources }}
+  resources: {{- toYaml .Values.resources | nindent 4 }}
+  {{- else if ne .Values.resourcesPreset "none" }}
+  resources: {{- include "resources.preset" (dict "type" .Values.resourcesPreset "Release" .Release) | nindent 4 }}
+  {{- end }}
+
   enableSuperuserAccess: true
   {{- $configMap := lookup "v1" "ConfigMap" "cozy-system" "cozystack-scheduling" }}
   {{- if $configMap }}

packages/apps/postgres/values.schema.json

@@ -101,6 +101,16 @@
                     "default": "ChaXoveekoh6eigh4siesheeda2quai0"
                 }
             }
+        },
+        "resources": {
+            "type": "object",
+            "description": "Resources",
+            "default": {}
+        },
+        "resourcesPreset": {
+            "type": "string",
+            "description": "Set container resources according to one common preset (allowed values: none, nano, micro, small, medium, large, xlarge, 2xlarge). This is ignored if resources is set (resources is recommended for production).",
+            "default": "nano"
         }
     }
 }

packages/apps/postgres/values.yaml

@@ -76,3 +76,16 @@ backup:
   s3AccessKey: oobaiRus9pah8PhohL1ThaeTa4UVa7gu
   s3SecretKey: ju3eum4dekeich9ahM1te8waeGai0oog
   resticPassword: ChaXoveekoh6eigh4siesheeda2quai0
+
+## @param resources Resources
+resources: {}
+ # resources:
+ #   limits:
+ #     cpu: 4000m
+ #     memory: 4Gi
+ #   requests:
+ #     cpu: 100m
+ #     memory: 512Mi
+ 
+## @param resourcesPreset Set container resources according to one common preset (allowed values: none, nano, micro, small, medium, large, xlarge, 2xlarge). This is ignored if resources is set (resources is recommended for production).
+resourcesPreset: "nano"

packages/apps/rabbitmq/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: 0.4.4
+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/rabbitmq/README.md

@@ -22,7 +22,9 @@ The service utilizes official RabbitMQ operator. This ensures the reliability an
 
 ### Configuration parameters
 
-| Name     | Description                 | Value |
-| -------- | --------------------------- | ----- |
-| `users`  | Users configuration         | `{}`  |
-| `vhosts` | Virtual Hosts configuration | `{}`  |
+| Name              | Description                                                                                                                                                                                                       | Value  |
+| ----------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ------ |
+| `users`           | Users configuration                                                                                                                                                                                               | `{}`   |
+| `vhosts`          | Virtual Hosts configuration                                                                                                                                                                                       | `{}`   |
+| `resources`       | Resources                                                                                                                                                                                                         | `{}`   |
+| `resourcesPreset` | Set container resources according to one common preset (allowed values: none, nano, micro, small, medium, large, xlarge, 2xlarge). This is ignored if resources is set (resources is recommended for production). | `nano` |