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

@@ -39,38 +39,82 @@ jobs:
     runs-on: [self-hosted]
     permissions:
       contents: write
-  
+
     if: |
       github.event.pull_request.merged == true &&
       contains(github.event.pull_request.labels.*.name, 'release')
-  
+
     steps:
+      # Extract tag from branch name  (branch = release-X.Y.Z*)
       - name: Extract tag from branch name
         id: get_tag
         uses: actions/github-script@v7
         with:
           script: |
             const branch = context.payload.pull_request.head.ref;
-            const match = branch.match(/^release-(v\d+\.\d+\.\d+(?:[-\w\.]+)?)$/);
-  
-            if (!match) {
-              core.setFailed(`Branch '${branch}' does not match expected format 'release-vX.Y.Z[-suffix]'`);
-            } else {
-              const tag = match[1];
-              core.setOutput('tag', tag);
-              console.log(`✅ Extracted tag: ${tag}`);
+            const m = branch.match(/^release-(\d+\.\d+\.\d+(?:[-\w\.]+)?)$/);
+            if (!m) {
+              core.setFailed(`Branch '${branch}' does not match 'release-X.Y.Z[-suffix]'`);
+              return;
             }
-  
+            const tag = `v${m[1]}`;
+            core.setOutput('tag', tag);
+            console.log(`✅ Tag to publish: ${tag}`);
+
+      # Checkout repo & create / push annotated tag
       - name: Checkout repo
         uses: actions/checkout@v4
         with:
           fetch-depth: 0
-  
-      - name: Create tag on merged commit
+
+      - name: Create tag on merge commit
         run: |
-          git tag ${{ steps.get_tag.outputs.tag }} ${{ github.sha }}
-          git push origin ${{ steps.get_tag.outputs.tag }}
-  
+          git tag -f ${{ steps.get_tag.outputs.tag }} ${{ github.sha }}
+          git push -f origin ${{ steps.get_tag.outputs.tag }}
+
+      # 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 = '${{ steps.semver.outputs.comparison-result }}' === '<';
+            core.setOutput('make_latest', isRc || outdated ? 'false' : 'legacy');
+
+      # Publish draft release with correct flags
       - name: Publish draft release
         uses: actions/github-script@v7
         with:
@@ -78,19 +122,17 @@ jobs:
             const tag = '${{ steps.get_tag.outputs.tag }}';
             const releases = await github.rest.repos.listReleases({
               owner: context.repo.owner,
-              repo: context.repo.repo
+              repo:  context.repo.repo
             });
-  
-            const release = releases.data.find(r => r.tag_name === tag && r.draft);
-            if (!release) {
-              throw new Error(`Draft release with tag ${tag} not found`);
-            }
-  
+            const draft = releases.data.find(r => r.tag_name === tag && r.draft);
+            if (!draft) throw new Error(`Draft release for ${tag} not found`);
             await github.rest.repos.updateRelease({
-              owner: context.repo.owner,
-              repo: context.repo.repo,
-              release_id: release.id,
-              draft: false
+              owner:       context.repo.owner,
+              repo:        context.repo.repo,
+              release_id:  draft.id,
+              draft:       false,
+              prerelease:  ${{ steps.flags.outputs.is_rc }},
+              make_latest: '${{ steps.flags.outputs.make_latest }}'
             });
-  
-            console.log(`✅ Published release for ${tag}`);
+
+            console.log(`🚀 Published release for ${tag}`);

.github/workflows/pull-requests.yaml

@@ -12,9 +12,20 @@ jobs:
       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, 'ok-to-test') &&
-      !contains(github.event.pull_request.labels.*.name, 'release')
+      !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
@@ -30,10 +41,8 @@ jobs:
           password: ${{ secrets.GITHUB_TOKEN }}
           registry: ghcr.io
 
-      - name: make build
-        run: |
-          make build
+      - name: Build
+        run: make build
 
-      - name: make test
-        run: |
-          make test
+      - name: Test
+        run: make test

.github/workflows/tags.yaml

@@ -3,7 +3,7 @@ name: Versioned Tag
 on:
   push:
     tags:
-      - 'v*.*.*'
+      - 'v*.*.*' # vX.Y.Z or vX.Y.Z-rcN
 
 jobs:
   prepare-release:
@@ -15,6 +15,7 @@ jobs:
       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
@@ -23,28 +24,67 @@ jobs:
             const tag = context.ref.replace('refs/tags/', '');
             const releases = await github.rest.repos.listReleases({
               owner: context.repo.owner,
-              repo: context.repo.repo
+              repo:  context.repo.repo
             });
+            const exists = releases.data.some(r => r.tag_name === tag && !r.draft);
+            core.setOutput('skip', exists);
+            console.log(exists ? `Release ${tag} already published` : `No published release ${tag}`);
 
-            const existing = releases.data.find(r => r.tag_name === tag && !r.draft);
-            if (existing) {
-              core.setOutput('skip', 'true');
-            } else {
-              core.setOutput('skip', 'false');
-            }
-
+      # If a published release already exists, skip the rest of the workflow
       - name: Skip if release already exists
         if: steps.check_release.outputs.skip == 'true'
         run: echo "Release already exists, skipping workflow."
 
+      # Parse tag meta‑data (rc?, maintenance line, etc.)
+      - name: Parse tag
+        if: steps.check_release.outputs.skip == 'false'
+        id: tag
+        uses: actions/github-script@v7
+        with:
+          script: |
+            const ref = context.ref.replace('refs/tags/', '');           // e.g. v0.31.5-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
+          fetch-tags:  true
 
-      - name: Login to GitHub Container Registry
+      - name: Login to GHCR
         if: steps.check_release.outputs.skip == 'false'
         uses: docker/login-action@v3
         with:
@@ -52,108 +92,160 @@ jobs:
           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'
-        env:
-          GIT_AUTHOR_NAME: ${{ github.actor }}
-          GIT_AUTHOR_EMAIL: ${{ github.actor }}@users.noreply.github.com
         run: |
-          git config user.name "$GIT_AUTHOR_NAME"
-          git config user.email "$GIT_AUTHOR_EMAIL"
+          git config user.name  "github-actions"
+          git config user.email "github-actions@github.com"
           git add .
           git commit -m "Prepare release ${GITHUB_REF#refs/tags/}" -s || echo "No changes to commit"
+          git push origin HEAD || true
 
+      # Get `latest_version` from latest published release 
+      - name: Get latest published release
+        if: steps.check_release.outputs.skip == 'false'
+        id: latest_release
+        uses: actions/github-script@v7
+        with:
+          script: |
+            try {
+              const rel = await github.rest.repos.getLatestRelease({
+                owner: context.repo.owner,
+                repo:  context.repo.repo
+              });
+              core.setOutput('tag', rel.data.tag_name);
+            } catch (_) {
+              core.setOutput('tag', '');
+            }
+
+      # Compare tag (A) with latest (B)
+      - name: Semver compare
+        if: steps.check_release.outputs.skip == 'false'
+        id: semver
+        uses: madhead/semver-utils@v4.3.0
+        with:
+          version:     ${{ steps.tag.outputs.tag }}            # A
+          compare-to:  ${{ steps.latest_release.outputs.tag }} # B
+
+      # Create or reuse DRAFT GitHub Release
+      - name: Create / reuse draft release
+        if: steps.check_release.outputs.skip == 'false'
+        id: release
+        uses: actions/github-script@v7
+        with:
+          script: |
+            const tag        = '${{ steps.tag.outputs.tag }}';
+            const isRc       = ${{ steps.tag.outputs.is_rc }};
+            const outdated   = '${{ steps.semver.outputs.comparison-result }}' === '<';
+            const makeLatest = outdated ? false : 'legacy';
+            const releases   = await github.rest.repos.listReleases({
+              owner: context.repo.owner,
+              repo:  context.repo.repo
+            });
+            let rel          = releases.data.find(r => r.tag_name === tag);
+            if (!rel) {
+              rel = await github.rest.repos.createRelease({
+                owner: context.repo.owner,
+                repo:  context.repo.repo,
+                tag_name:    tag,
+                name:        tag,
+                draft:       true,
+                prerelease:  isRc,
+                make_latest: makeLatest
+              });
+              console.log(`Draft release created for ${tag}`);
+            } else {
+              console.log(`Re‑using existing release ${tag}`);
+            }
+            core.setOutput('upload_url', rel.upload_url);
+
+      # Build + upload assets (optional)
+      - name: Build & upload assets
+        if: steps.check_release.outputs.skip == 'false'
+        run: |
+          make assets
+          make upload_assets VERSION=${{ steps.tag.outputs.tag }}
+        env:
+          GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+
+      # Ensure long‑lived maintenance branch release‑X.Y
+      - name: Ensure maintenance branch release‑${{ 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 ${context.sha}`);
+            }
+
+      # Create release‑X.Y.Z branch and push (force‑update)
       - name: Create release branch
         if: steps.check_release.outputs.skip == 'false'
         run: |
-          BRANCH_NAME="release-${GITHUB_REF#refs/tags/v}"
-          git branch -f "$BRANCH_NAME"
-          git push origin "$BRANCH_NAME" --force
+          BRANCH="release-${GITHUB_REF#refs/tags/v}"
+          git branch -f "$BRANCH"
+          git push -f origin "$BRANCH"
 
+      # Create pull request into original base branch (if absent)
       - name: Create pull request if not exists
         if: steps.check_release.outputs.skip == 'false'
         uses: actions/github-script@v7
         with:
           script: |
             const version = context.ref.replace('refs/tags/v', '');
-            const branch = `release-${version}`;
-            const base = 'main';
-      
+            const base    = '${{ steps.get_base.outputs.branch }}';
+            const head    = `release-${version}`;
+
             const prs = await github.rest.pulls.list({
               owner: context.repo.owner,
-              repo: context.repo.repo,
-              head: `${context.repo.owner}:${branch}`,
+              repo:  context.repo.repo,
+              head:  `${context.repo.owner}:${head}`,
               base
             });
-      
             if (prs.data.length === 0) {
-              const newPr = await github.rest.pulls.create({
+              const pr = await github.rest.pulls.create({
                 owner: context.repo.owner,
-                repo: context.repo.repo,
-                head: branch,
-                base: base,
+                repo:  context.repo.repo,
+                head,
+                base,
                 title: `Release v${version}`,
-                body:
-                  `This PR prepares the release \`v${version}\`.\n` +
-                  `(Please merge it before releasing draft)`,
+                body:  `This PR prepares the release \`v${version}\`.`,
                 draft: false
               });
-      
-              console.log(`Created pull request #${newPr.data.number} from ${branch} to ${base}`);
-      
               await github.rest.issues.addLabels({
                 owner: context.repo.owner,
-                repo: context.repo.repo,
-                issue_number: newPr.data.number,
-                labels: ['release', 'ok-to-test']
+                repo:  context.repo.repo,
+                issue_number: pr.data.number,
+                labels: ['release']
               });
-      
+              console.log(`Created PR #${pr.data.number}`);
             } else {
-              console.log(`Pull request already exists from ${branch} to ${base}`);
+              console.log(`PR already exists from ${head} to ${base}`);
             }
 
-      - name: Create or reuse draft release
+      # Run tests 
+      - name: Test
         if: steps.check_release.outputs.skip == 'false'
-        id: create_release
-        uses: actions/github-script@v7
-        with:
-          script: |
-            const tag = context.ref.replace('refs/tags/', '');
-            const releases = await github.rest.repos.listReleases({
-              owner: context.repo.owner,
-              repo: context.repo.repo
-            });
-
-            let release = releases.data.find(r => r.tag_name === tag);
-            if (!release) {
-              release = await github.rest.repos.createRelease({
-                owner: context.repo.owner,
-                repo: context.repo.repo,
-                tag_name: tag,
-                name: `${tag}`,
-                draft: true,
-                prerelease: false
-              });
-            }
-            core.setOutput('upload_url', release.upload_url);
-
-      - name: Build assets
-        if: steps.check_release.outputs.skip == 'false'
-        run: make assets
-        env:
-          GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
-
-      - name: Upload assets
-        if: steps.check_release.outputs.skip == 'false'
-        run: make upload_assets VERSION=${GITHUB_REF#refs/tags/}
-        env:
-          GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
-
-      - name: Delete pushed tag
-        if: steps.check_release.outputs.skip == 'false'
-        run: |
-          git push --delete origin ${GITHUB_REF#refs/tags/}
+        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
 

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
@@ -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

@@ -19,21 +19,19 @@ fi
 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 | grep 'refs/tags/v' | sort -k2,2 -rV | awk '{print $1}')
-# add latest main commit to search
-search_commits="${search_commits} $(git rev-parse "origin/main")"
+search_commits=$(git ls-remote --tags origin | awk -F/ '$3 ~ /v[0-9]+.[0-9]+.[0-9]+/ {print}' | sort -k2,2 -rV | awk '{print $1}')
 
 resolved_miss_map=$(
   echo "$miss_map" | while read -r chart version commit; do
     # if version is found in HEAD, it's HEAD
-    if grep -q "^version: $version$" ./${chart}/Chart.yaml; then
+    if [ "$(awk '$1 == "version:" {print $2}' ./${chart}/Chart.yaml)" = "${version}" ]; then
       echo "$chart $version HEAD"
       continue
     fi
 
     # if commit is not HEAD, check if it's valid
-    if [ $commit != "HEAD" ]; then
-      if ! git show "${commit}:./${chart}/Chart.yaml" 2>/dev/null | grep -q "^version: $version$"; then
+    if [ "$commit" != "HEAD" ]; then
+      if [ "$(git show "${commit}:./${chart}/Chart.yaml" | awk '$1 == "version:" {print $2}')" != "${version}" ]; then
         echo "Commit $commit for $chart $version is not valid" >&2
         exit 1
       fi
@@ -46,15 +44,15 @@ resolved_miss_map=$(
     # if commit is HEAD, but version is not found in HEAD, check all tags
     found_tag=""
     for tag in $search_commits; do
-      if git show "${tag}:./${chart}/Chart.yaml" 2>/dev/null | grep -q "^version: $version$"; then
+      if [ "$(git show "${tag}:./${chart}/Chart.yaml" | awk '$1 == "version:" {print $2}')" = "${version}" ]; then
         found_tag=$(git rev-parse --short "${tag}")
         break
       fi
     done
     
     if [ -z "$found_tag" ]; then
-      echo "Can't find $chart $version in any version tag or in the latest main commit" >&2
-      exit 1
+      echo "Can't find $chart $version in any version tag, removing it" >&2
+      continue
     fi
     
     echo "$chart $version $found_tag"

hack/upload-assets.sh

@@ -7,3 +7,5 @@ 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
+	}
+}

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

@@ -1 +1 @@
-ghcr.io/cozystack/cozystack/postgres-backup:0.10.0@sha256:10179ed56457460d95cd5708db2a00130901255fa30c4dd76c65d2ef5622b61f
+ghcr.io/cozystack/cozystack/postgres-backup:0.10.1@sha256:10179ed56457460d95cd5708db2a00130901255fa30c4dd76c65d2ef5622b61f

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

@@ -1 +1 @@
-ghcr.io/cozystack/cozystack/nginx-cache:0.4.0@sha256:0f4d8e6863ed074e90f8a7a8390ccd98dae0220119346aba19e85054bb902e2f
+ghcr.io/cozystack/cozystack/nginx-cache:0.4.0@sha256:4da14241052d2c4bd29d1766c4a569446f808a19538ef7f6acc05a981913df8e

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: 0.17.1
+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/cozystack/cozystack/cluster-autoscaler:0.17.0@sha256:85371c6aabf5a7fea2214556deac930c600e362f92673464fe2443784e2869c3
+ghcr.io/cozystack/cozystack/cluster-autoscaler:0.18.1@sha256:85371c6aabf5a7fea2214556deac930c600e362f92673464fe2443784e2869c3

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

@@ -1 +1 @@
-ghcr.io/cozystack/cozystack/kubevirt-cloud-provider:0.17.0@sha256:53f4734109799da8b27f35a3b1afdb4746b5992f1d7b9d1c132ea6242cdd8cf0
+ghcr.io/cozystack/cozystack/kubevirt-cloud-provider:0.18.1@sha256:795d8e1ef4b2b0df2aa1e09d96cd13476ebb545b4bf4b5779b7547a70ef64cf9

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

@@ -1 +1 @@
-ghcr.io/cozystack/cozystack/kubevirt-csi-driver:0.17.0@sha256:1a6605d3bff6342e12bcc257e852a4f89e97e8af6d3d259930ec07c7ad5f001d
+ghcr.io/cozystack/cozystack/kubevirt-csi-driver:0.18.1@sha256:5717919c75e609902c6d67138311a2a8fd07be822e2173f3802b67cf5f3486e9

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

@@ -1 +1 @@
-ghcr.io/cozystack/cozystack/ubuntu-container-disk:v1.30.1@sha256:d842de4637ea6188999464f133c89f63a3bd13f1cb202c10f1f8c0c1c3c3dbd4
+ghcr.io/cozystack/cozystack/ubuntu-container-disk:v1.30.1@sha256:6359b7877f04c6ac6641c0ebcc2a1d03cabfe1718464cd43f82e97724ad6aad8

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/monitoring-agents.yaml

@@ -38,10 +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/values.yaml

@@ -70,6 +70,13 @@ addons:
     enabled: false
     valuesOverride: {}
 
+  ## VerticalPodAutoscaler
+  ##
+  verticalPodAutoscaler:
+    ## @param addons.verticalPodAutoscaler.valuesOverride Custom values to override
+    ##
+    valuesOverride: {}
+
 ## @section Kamaji control plane
 ##
 kamajiControlPlane:

packages/apps/postgres/Chart.yaml

@@ -16,7 +16,7 @@ type: application
 # This is the chart version. This version number should be incremented each time you make changes
 # to the chart and its templates, including the app version.
 # Versions are expected to follow Semantic Versioning (https://semver.org/)
-version: 0.10.0
+version: 0.10.1
 
 # 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/images/postgres-backup.tag

@@ -1 +1 @@
-ghcr.io/cozystack/cozystack/postgres-backup:0.10.0@sha256:10179ed56457460d95cd5708db2a00130901255fa30c4dd76c65d2ef5622b61f
+ghcr.io/cozystack/cozystack/postgres-backup:0.10.1@sha256:10179ed56457460d95cd5708db2a00130901255fa30c4dd76c65d2ef5622b61f

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/tenant/Chart.yaml

@@ -4,4 +4,4 @@ description: Separated tenant namespace
 icon: /logos/tenant.svg
 
 type: application
-version: 1.9.1
+version: 1.9.2

packages/apps/tenant/templates/networkpolicy.yaml

@@ -24,6 +24,7 @@ spec:
   ingress:
   - fromEntities:
       - world
+      - cluster
   egress:
   - toEntities:
       - world

packages/apps/versions_map

@@ -57,7 +57,9 @@ kubernetes 0.15.1 160e4e2a
 kubernetes 0.15.2 8267072d
 kubernetes 0.16.0 077045b0
 kubernetes 0.17.0 1fbbfcd0
-kubernetes 0.17.1 HEAD
+kubernetes 0.17.1 fd240701
+kubernetes 0.18.0 721c12a7
+kubernetes 0.18.1 HEAD
 mysql 0.1.0 263e47be
 mysql 0.2.0 c24a103f
 mysql 0.3.0 53f2365e
@@ -87,7 +89,8 @@ postgres 0.7.0 4b90bf5a
 postgres 0.7.1 1ec10165
 postgres 0.8.0 4e68e65c
 postgres 0.9.0 8267072d
-postgres 0.10.0 HEAD
+postgres 0.10.0 721c12a7
+postgres 0.10.1 HEAD
 rabbitmq 0.1.0 263e47be
 rabbitmq 0.2.0 53f2365e
 rabbitmq 0.3.0 6c5cf5bf
@@ -128,7 +131,8 @@ tenant 1.6.8 bc95159a
 tenant 1.7.0 24fa7222
 tenant 1.8.0 160e4e2a
 tenant 1.9.0 728743db
-tenant 1.9.1 HEAD
+tenant 1.9.1 721c12a7
+tenant 1.9.2 HEAD
 virtual-machine 0.1.4 f2015d65
 virtual-machine 0.1.5 263e47be
 virtual-machine 0.2.0 c0685f43
@@ -140,7 +144,9 @@ virtual-machine 0.7.0 e23286a3
 virtual-machine 0.7.1 0ab39f20
 virtual-machine 0.8.0 3fa4dd3a
 virtual-machine 0.8.1 93c46161
-virtual-machine 0.8.2 HEAD
+virtual-machine 0.8.2 de19450f
+virtual-machine 0.9.0 721c12a7
+virtual-machine 0.9.1 HEAD
 vm-disk 0.1.0 d971f2ff
 vm-disk 0.1.1 HEAD
 vm-instance 0.1.0 1ec10165
@@ -149,7 +155,9 @@ vm-instance 0.3.0 4e68e65c
 vm-instance 0.4.0 e23286a3
 vm-instance 0.4.1 0ab39f20
 vm-instance 0.5.0 3fa4dd3a
-vm-instance 0.5.1 HEAD
+vm-instance 0.5.1 de19450f
+vm-instance 0.6.0 721c12a7
+vm-instance 0.6.1 HEAD
 vpn 0.1.0 263e47be
 vpn 0.2.0 53f2365e
 vpn 0.3.0 6c5cf5bf

packages/apps/virtual-machine/Chart.yaml

@@ -17,10 +17,10 @@ type: application
 # This is the chart version. This version number should be incremented each time you make changes
 # to the chart and its templates, including the app version.
 # Versions are expected to follow Semantic Versioning (https://semver.org/)
-version: 0.8.2
+version: 0.9.1
 
 # 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
 # follow Semantic Versioning. They should reflect the version the application is using.
 # It is recommended to use it with quotes.
-appVersion: "0.8.2"
+appVersion: 0.9.0

packages/apps/virtual-machine/Makefile

@@ -2,6 +2,7 @@ include ../../../scripts/package.mk
 
 generate:
 	readme-generator -v values.yaml -s values.schema.json -r README.md
+	yq -o json -i '.properties.gpus.items.type = "object" | .properties.gpus.default = []' values.schema.json
 	INSTANCE_TYPES=$$(yq e '.metadata.name' -o=json -r ../../system/kubevirt-instancetypes/templates/instancetypes.yaml | yq 'split(" ") | . + [""]' -o json) \
 	  && yq -i -o json ".properties.instanceType.optional=true | .properties.instanceType.enum = $${INSTANCE_TYPES}" values.schema.json
 	PREFERENCES=$$(yq e '.metadata.name' -o=json -r ../../system/kubevirt-instancetypes/templates/preferences.yaml | yq 'split(" ") | . + [""]' -o json) \

packages/apps/virtual-machine/README.md

@@ -36,22 +36,23 @@ virtctl ssh <user>@<vm>
 
 ### Common parameters
 
-| Name                      | Description                                                                                                | Value            |
-| ------------------------- | ---------------------------------------------------------------------------------------------------------- | ---------------- |
-| `external`                | Enable external access from outside the cluster                                                            | `false`          |
-| `externalMethod`          | specify method to passthrough the traffic to the virtual machine. Allowed values: `WholeIP` and `PortList` | `WholeIP`        |
-| `externalPorts`           | Specify ports to forward from outside the cluster                                                          | `[]`             |
-| `running`                 | Determines if the virtual machine should be running                                                        | `true`           |
-| `instanceType`            | Virtual Machine instance type                                                                              | `u1.medium`      |
-| `instanceProfile`         | Virtual Machine prefferences profile                                                                       | `ubuntu`         |
-| `systemDisk.image`        | The base image for the virtual machine. Allowed values: `ubuntu`, `cirros`, `alpine`, `fedora` and `talos` | `ubuntu`         |
-| `systemDisk.storage`      | The size of the disk allocated for the virtual machine                                                     | `5Gi`            |
-| `systemDisk.storageClass` | StorageClass used to store the data                                                                        | `replicated`     |
-| `resources.cpu`           | The number of CPU cores allocated to the virtual machine                                                   | `""`             |
-| `resources.memory`        | The amount of memory allocated to the virtual machine                                                      | `""`             |
-| `sshKeys`                 | List of SSH public keys for authentication. Can be a single key or a list of keys.                         | `[]`             |
-| `cloudInit`               | cloud-init user data config. See cloud-init documentation for more details.                                | `#cloud-config
-` |
+| Name                      | Description                                                                                                | Value        |
+| ------------------------- | ---------------------------------------------------------------------------------------------------------- | ------------ |
+| `external`                | Enable external access from outside the cluster                                                            | `false`      |
+| `externalMethod`          | specify method to passthrough the traffic to the virtual machine. Allowed values: `WholeIP` and `PortList` | `WholeIP`    |
+| `externalPorts`           | Specify ports to forward from outside the cluster                                                          | `[]`         |
+| `running`                 | Determines if the virtual machine should be running                                                        | `true`       |
+| `instanceType`            | Virtual Machine instance type                                                                              | `u1.medium`  |
+| `instanceProfile`         | Virtual Machine preferences profile                                                                        | `ubuntu`     |
+| `systemDisk.image`        | The base image for the virtual machine. Allowed values: `ubuntu`, `cirros`, `alpine`, `fedora` and `talos` | `ubuntu`     |
+| `systemDisk.storage`      | The size of the disk allocated for the virtual machine                                                     | `5Gi`        |
+| `systemDisk.storageClass` | StorageClass used to store the data                                                                        | `replicated` |
+| `gpus`                    | List of GPUs to attach                                                                                     | `[]`         |
+| `resources.cpu`           | The number of CPU cores allocated to the virtual machine                                                   | `""`         |
+| `resources.memory`        | The amount of memory allocated to the virtual machine                                                      | `""`         |
+| `sshKeys`                 | List of SSH public keys for authentication. Can be a single key or a list of keys.                         | `[]`         |
+| `cloudInit`               | cloud-init user data config. See cloud-init documentation for more details.                                | `""`         |
+| `cloudInitSeed`           | A seed string to generate an SMBIOS UUID for the VM.                                                       | `""`         |
 
 ## U Series
 

packages/apps/virtual-machine/templates/_helpers.tpl

@@ -49,3 +49,23 @@ Selector labels
 app.kubernetes.io/name: {{ include "virtual-machine.name" . }}
 app.kubernetes.io/instance: {{ .Release.Name }}
 {{- end }}
+
+{{/*
+Generate a stable UUID for cloud-init re-initialization upon upgrade.
+*/}}
+{{- define "virtual-machine.stableUuid" -}}
+{{- $source := printf "%s-%s-%s" .Release.Namespace (include "virtual-machine.fullname" .) .Values.cloudInitSeed }}
+{{- $hash := sha256sum $source }}
+{{- $uuid := printf "%s-%s-4%s-9%s-%s" (substr 0 8 $hash) (substr 8 12 $hash) (substr 13 16 $hash) (substr 17 20 $hash) (substr 20 32 $hash) }}
+{{- if eq .Values.cloudInitSeed "" }}
+  {{- /*  Try to save previous uuid to not trigger full cloud-init again if user decided to remove the seed. */}}
+  {{- $vmResource := lookup "kubevirt.io/v1" "VirtualMachine" .Release.Namespace (include "virtual-machine.fullname" .) -}}
+  {{- if $vmResource }}
+    {{- $existingUuid := $vmResource | dig "spec" "template" "spec" "domain" "firmware" "uuid" "" }}
+    {{- if $existingUuid }}
+      {{- $uuid = $existingUuid }}
+    {{- end }}
+  {{- end }}
+{{- end }}
+{{- $uuid }}
+{{- end }}

packages/apps/virtual-machine/templates/vm.yaml

@@ -68,7 +68,16 @@ spec:
           requests:
             memory: {{ .Values.resources.memory | quote }}
         {{- end }}
+        firmware:
+          uuid: {{ include "virtual-machine.stableUuid" . }}
         devices:
+          {{- if .Values.gpus }}
+          gpus:
+          {{- range $i, $gpu := .Values.gpus }}
+          - name: gpu{{ add $i 1 }}
+            deviceName: {{ $gpu.name }}
+          {{- end }}
+          {{- end }}
           disks:
           - disk:
               bus: scsi
@@ -90,6 +99,7 @@ spec:
             secret:
               secretName: {{ include "virtual-machine.fullname" $ }}-ssh-keys
           propagationMethod:
+            # keys will be injected into metadata part of cloud-init disk
             noCloud: {}
       {{- end }}
       terminationGracePeriodSeconds: 30
@@ -100,8 +110,14 @@ spec:
       {{- if or .Values.sshKeys .Values.cloudInit }}
       - name: cloudinitdisk
         cloudInitNoCloud:
+        {{- if .Values.cloudInit }}
           secretRef:
             name: {{ include "virtual-machine.fullname" . }}-cloud-init
+        {{- else }}
+          userData: |
+            #cloud-config
+            final_message: Cloud-init user-data was left blank intentionally.
+        {{- end }}
       {{- end }}
       networks:
       - name: default

packages/apps/virtual-machine/values.schema.json

@@ -88,7 +88,7 @@
     },
     "instanceProfile": {
       "type": "string",
-      "description": "Virtual Machine prefferences profile",
+      "description": "Virtual Machine preferences profile",
       "default": "ubuntu",
       "optional": true,
       "enum": [
@@ -164,6 +164,14 @@
         }
       }
     },
+    "gpus": {
+      "type": "array",
+      "description": "List of GPUs to attach",
+      "default": [],
+      "items": {
+        "type": "object"
+      }
+    },
     "resources": {
       "type": "object",
       "properties": {
@@ -190,7 +198,12 @@
     "cloudInit": {
       "type": "string",
       "description": "cloud-init user data config. See cloud-init documentation for more details.",
-      "default": "#cloud-config\n"
+      "default": ""
+    },
+    "cloudInitSeed": {
+      "type": "string",
+      "description": "A seed string to generate an SMBIOS UUID for the VM.",
+      "default": ""
     }
   }
 }

packages/apps/virtual-machine/values.yaml

@@ -12,7 +12,7 @@ externalPorts:
 running: true
 
 ## @param instanceType Virtual Machine instance type
-## @param instanceProfile Virtual Machine prefferences profile
+## @param instanceProfile Virtual Machine preferences profile
 ##
 instanceType: "u1.medium"
 instanceProfile: ubuntu
@@ -26,6 +26,12 @@ systemDisk:
   storage: 5Gi
   storageClass: replicated
 
+## @param gpus [array] List of GPUs to attach
+## Example:
+## gpus:
+## - name: nvidia.com/GA102GL_A10
+gpus: []
+
 ## @param resources.cpu The number of CPU cores allocated to the virtual machine
 ## @param resources.memory The amount of memory allocated to the virtual machine
 resources:
@@ -49,5 +55,13 @@ sshKeys: []
 ##   password: ubuntu
 ##   chpasswd: { expire: False }
 ##
-cloudInit: |
-  #cloud-config
+cloudInit: ""
+
+## @param cloudInitSeed A seed string to generate an SMBIOS UUID for the VM.
+cloudInitSeed: ""
+## Change it to any new value to force a full cloud-init reconfiguration. Change it when you want to apply
+## to an existing VM settings that are usually written only once, like new SSH keys or new network configuration.
+## An empty value does nothing (and the existing UUID is not reverted). Please note that changing this value
+## does not trigger a VM restart. You must perform the restart separately.
+## Example:
+## cloudInitSeed: "upd1"

packages/apps/vm-instance/Chart.yaml

@@ -17,10 +17,10 @@ type: application
 # This is the chart version. This version number should be incremented each time you make changes
 # to the chart and its templates, including the app version.
 # Versions are expected to follow Semantic Versioning (https://semver.org/)
-version: 0.5.1
+version: 0.6.1
 
 # 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
 # follow Semantic Versioning. They should reflect the version the application is using.
 # It is recommended to use it with quotes.
-appVersion: "0.5.1"
+appVersion: 0.6.0

packages/apps/vm-instance/Makefile

@@ -3,6 +3,7 @@ include ../../../scripts/package.mk
 generate:
 	readme-generator -v values.yaml -s values.schema.json -r README.md
 	yq -o json -i '.properties.disks.items.type = "object" | .properties.disks.default = []' values.schema.json
+	yq -o json -i '.properties.gpus.items.type = "object" | .properties.gpus.default = []' values.schema.json
 	INSTANCE_TYPES=$$(yq e '.metadata.name' -o=json -r ../../system/kubevirt-instancetypes/templates/instancetypes.yaml | yq 'split(" ") | . + [""]' -o json) \
 	  && yq -i -o json ".properties.instanceType.optional=true | .properties.instanceType.enum = $${INSTANCE_TYPES}" values.schema.json
 	PREFERENCES=$$(yq e '.metadata.name' -o=json -r ../../system/kubevirt-instancetypes/templates/preferences.yaml | yq 'split(" ") | . + [""]' -o json) \

packages/apps/vm-instance/README.md

@@ -36,20 +36,21 @@ virtctl ssh <user>@<vm>
 
 ### Common parameters
 
-| Name               | Description                                                                                                | Value            |
-| ------------------ | ---------------------------------------------------------------------------------------------------------- | ---------------- |
-| `external`         | Enable external access from outside the cluster                                                            | `false`          |
-| `externalMethod`   | specify method to passthrough the traffic to the virtual machine. Allowed values: `WholeIP` and `PortList` | `WholeIP`        |
-| `externalPorts`    | Specify ports to forward from outside the cluster                                                          | `[]`             |
-| `running`          | Determines if the virtual machine should be running                                                        | `true`           |
-| `instanceType`     | Virtual Machine instance type                                                                              | `u1.medium`      |
-| `instanceProfile`  | Virtual Machine prefferences profile                                                                       | `ubuntu`         |
-| `disks`            | List of disks to attach                                                                                    | `[]`             |
-| `resources.cpu`    | The number of CPU cores allocated to the virtual machine                                                   | `""`             |
-| `resources.memory` | The amount of memory allocated to the virtual machine                                                      | `""`             |
-| `sshKeys`          | List of SSH public keys for authentication. Can be a single key or a list of keys.                         | `[]`             |
-| `cloudInit`        | cloud-init user data config. See cloud-init documentation for more details.                                | `#cloud-config
-` |
+| Name               | Description                                                                                                | Value       |
+| ------------------ | ---------------------------------------------------------------------------------------------------------- | ----------- |
+| `external`         | Enable external access from outside the cluster                                                            | `false`     |
+| `externalMethod`   | specify method to passthrough the traffic to the virtual machine. Allowed values: `WholeIP` and `PortList` | `WholeIP`   |
+| `externalPorts`    | Specify ports to forward from outside the cluster                                                          | `[]`        |
+| `running`          | Determines if the virtual machine should be running                                                        | `true`      |
+| `instanceType`     | Virtual Machine instance type                                                                              | `u1.medium` |
+| `instanceProfile`  | Virtual Machine preferences profile                                                                        | `ubuntu`    |
+| `disks`            | List of disks to attach                                                                                    | `[]`        |
+| `gpus`             | List of GPUs to attach                                                                                     | `[]`        |
+| `resources.cpu`    | The number of CPU cores allocated to the virtual machine                                                   | `""`        |
+| `resources.memory` | The amount of memory allocated to the virtual machine                                                      | `""`        |
+| `sshKeys`          | List of SSH public keys for authentication. Can be a single key or a list of keys.                         | `[]`        |
+| `cloudInit`        | cloud-init user data config. See cloud-init documentation for more details.                                | `""`        |
+| `cloudInitSeed`    | A seed string to generate an SMBIOS UUID for the VM.                                                       | `""`        |
 
 ## U Series
 

packages/apps/vm-instance/templates/_helpers.tpl

@@ -49,3 +49,23 @@ Selector labels
 app.kubernetes.io/name: {{ include "virtual-machine.name" . }}
 app.kubernetes.io/instance: {{ .Release.Name }}
 {{- end }}
+
+{{/*
+Generate a stable UUID for cloud-init re-initialization upon upgrade.
+*/}}
+{{- define "virtual-machine.stableUuid" -}}
+{{- $source := printf "%s-%s-%s" .Release.Namespace (include "virtual-machine.fullname" .) .Values.cloudInitSeed }}
+{{- $hash := sha256sum $source }}
+{{- $uuid := printf "%s-%s-4%s-9%s-%s" (substr 0 8 $hash) (substr 8 12 $hash) (substr 13 16 $hash) (substr 17 20 $hash) (substr 20 32 $hash) }}
+{{- if eq .Values.cloudInitSeed "" }}
+  {{- /*  Try to save previous uuid to not trigger full cloud-init again if user decided to remove the seed. */}}
+  {{- $vmResource := lookup "kubevirt.io/v1" "VirtualMachine" .Release.Namespace (include "virtual-machine.fullname" .) -}}
+  {{- if $vmResource }}
+    {{- $existingUuid := $vmResource | dig "spec" "template" "spec" "domain" "firmware" "uuid" "" }}
+    {{- if $existingUuid }}
+      {{- $uuid = $existingUuid }}
+    {{- end }}
+  {{- end }}
+{{- end }}
+{{- $uuid }}
+{{- end }}

packages/apps/vm-instance/templates/dashboard-resourcemap.yaml

@@ -22,5 +22,5 @@ spec:
   kind: virtual-machine
   type: virtual-machine
   selector:
-    vm.kubevirt.io/name: {{ $.Release.Name }}
+    {{- include "virtual-machine.selectorLabels" . | nindent 4 }}
   version: {{ $.Chart.Version }}

packages/apps/vm-instance/templates/vm.yaml

@@ -1,8 +1,8 @@
 {{- if and .Values.instanceType (not (lookup "instancetype.kubevirt.io/v1beta1" "VirtualMachineClusterInstancetype" "" .Values.instanceType)) }}
-{{-   fail (printf "Specified instancetype not exists in cluster: %s" .Values.instanceType) }}
+{{-   fail (printf "Specified instanceType does not exist in the cluster: %s" .Values.instanceType) }}
 {{- end }}
 {{- if and .Values.instanceProfile (not (lookup "instancetype.kubevirt.io/v1beta1" "VirtualMachineClusterPreference" "" .Values.instanceProfile)) }}
-{{-   fail (printf "Specified profile not exists in cluster: %s" .Values.instanceProfile) }}
+{{-   fail (printf "Specified instanceProfile does not exist in the cluster: %s" .Values.instanceProfile) }}
 {{- end }}
 
 apiVersion: kubevirt.io/v1
@@ -40,11 +40,20 @@ spec:
           requests:
             memory: {{ .Values.resources.memory | quote }}
         {{- end }}
+        firmware:
+          uuid: {{ include "virtual-machine.stableUuid" . }}
         devices:
+          {{- if .Values.gpus }}
+          gpus:
+          {{- range $i, $gpu := .Values.gpus }}
+          - name: gpu{{ add $i 1 }}
+            deviceName: {{ $gpu.name }}
+          {{- end }}
+          {{- end }}
           disks:
           {{- range $i, $disk := .Values.disks }}
-          - name: disk-{{ .name }}
-            {{- $disk := lookup "cdi.kubevirt.io/v1beta1" "DataVolume" $.Release.Namespace (printf "vm-disk-%s" .name) }}
+          - name: disk-{{ $disk.name }}
+            {{- $disk := lookup "cdi.kubevirt.io/v1beta1" "DataVolume" $.Release.Namespace (printf "vm-disk-%s" $disk.name) }}
             {{- if $disk }}
             {{- if and (hasKey $disk.metadata.annotations "vm-disk.cozystack.io/optical") (eq (index $disk.metadata.annotations "vm-disk.cozystack.io/optical") "true") }}
             cdrom: {}
@@ -75,6 +84,7 @@ spec:
             secret:
               secretName: {{ include "virtual-machine.fullname" $ }}-ssh-keys
           propagationMethod:
+            # keys will be injected into metadata part of cloud-init disk
             noCloud: {}
       {{- end }}
       terminationGracePeriodSeconds: 30
@@ -87,8 +97,14 @@ spec:
       {{- if or .Values.sshKeys .Values.cloudInit }}
       - name: cloudinitdisk
         cloudInitNoCloud:
+        {{- if .Values.cloudInit }}
           secretRef:
             name: {{ include "virtual-machine.fullname" . }}-cloud-init
+        {{- else }}
+          userData: |
+            #cloud-config
+            final_message: Cloud-init user-data was left blank intentionally.
+        {{- end }}
       {{- end }}
       networks:
       - name: default

packages/apps/vm-instance/values.schema.json

@@ -88,7 +88,7 @@
     },
     "instanceProfile": {
       "type": "string",
-      "description": "Virtual Machine prefferences profile",
+      "description": "Virtual Machine preferences profile",
       "default": "ubuntu",
       "optional": true,
       "enum": [
@@ -145,6 +145,14 @@
         "type": "object"
       }
     },
+    "gpus": {
+      "type": "array",
+      "description": "List of GPUs to attach",
+      "default": [],
+      "items": {
+        "type": "object"
+      }
+    },
     "resources": {
       "type": "object",
       "properties": {
@@ -171,7 +179,12 @@
     "cloudInit": {
       "type": "string",
       "description": "cloud-init user data config. See cloud-init documentation for more details.",
-      "default": "#cloud-config\n"
+      "default": ""
+    },
+    "cloudInitSeed": {
+      "type": "string",
+      "description": "A seed string to generate an SMBIOS UUID for the VM.",
+      "default": ""
     }
   }
 }

packages/apps/vm-instance/values.yaml

@@ -12,7 +12,7 @@ externalPorts:
 running: true
 
 ## @param instanceType Virtual Machine instance type
-## @param instanceProfile Virtual Machine prefferences profile
+## @param instanceProfile Virtual Machine preferences profile
 ##
 instanceType: "u1.medium"
 instanceProfile: ubuntu
@@ -24,6 +24,12 @@ instanceProfile: ubuntu
 ## - name: example-data
 disks: []
 
+## @param gpus [array] List of GPUs to attach
+## Example:
+## gpus:
+## - name: nvidia.com/GA102GL_A10
+gpus: []
+
 ## @param resources.cpu The number of CPU cores allocated to the virtual machine
 ## @param resources.memory The amount of memory allocated to the virtual machine
 resources:
@@ -47,5 +53,13 @@ sshKeys: []
 ##   password: ubuntu
 ##   chpasswd: { expire: False }
 ##
-cloudInit: |
-  #cloud-config
+cloudInit: ""
+
+## @param cloudInitSeed A seed string to generate an SMBIOS UUID for the VM.
+cloudInitSeed: ""
+## Change it to any new value to force a full cloud-init reconfiguration. Change it when you want to apply
+## to an existing VM settings that are usually written only once, like new SSH keys or new network configuration.
+## An empty value does nothing (and the existing UUID is not reverted). Please note that changing this value
+## does not trigger a VM restart. You must perform the restart separately.
+## Example:
+## cloudInitSeed: "upd1"

packages/core/installer/Makefile

@@ -59,7 +59,7 @@ image-matchbox:
 		> ../../extra/bootbox/images/matchbox.tag
 	rm -f images/matchbox.json
 
-assets: talos-iso talos-nocloud talos-metal
+assets: talos-iso talos-nocloud talos-metal talos-kernel talos-initramfs
 
 talos-initramfs talos-kernel talos-installer talos-iso talos-nocloud talos-metal:
 	mkdir -p ../../../_out/assets

packages/core/installer/values.yaml

@@ -1,2 +1,2 @@
 cozystack:
-  image: ghcr.io/cozystack/cozystack/installer:v0.29.1@sha256:d63b1cc791ca75d53a7270940189d1401bbeb08f0d54d8ae29dae0ab8a6ef230
+  image: ghcr.io/cozystack/cozystack/installer:v0.30.4@sha256:d474e9c3f90dadb24f2fc325acfa42648053e2b21949c91169769795b8b8217c

packages/core/platform/bundles/paas-full.yaml

@@ -116,7 +116,7 @@ releases:
   chart: cozy-monitoring-agents
   namespace: cozy-monitoring
   privileged: true
-  dependsOn: [cilium,kubeovn,victoria-metrics-operator]
+  dependsOn: [victoria-metrics-operator, vertical-pod-autoscaler-crds]
   values:
     scrapeRules:
       etcd:
@@ -153,6 +153,17 @@ releases:
   namespace: cozy-kubevirt-cdi
   dependsOn: [cilium,kubeovn,kubevirt-cdi-operator]
 
+- name: gpu-operator
+  releaseName: gpu-operator
+  chart: cozy-gpu-operator
+  namespace: cozy-gpu-operator
+  privileged: true
+  optional: true
+  dependsOn: [cilium,kubeovn]
+  valuesFiles:
+  - values.yaml
+  - values-talos.yaml
+
 - name: metallb
   releaseName: metallb
   chart: cozy-metallb
@@ -388,6 +399,13 @@ releases:
   privileged: true
   dependsOn: [monitoring-agents]
 
+- name: vertical-pod-autoscaler-crds
+  releaseName: vertical-pod-autoscaler-crds
+  chart: cozy-vertical-pod-autoscaler-crds
+  namespace: cozy-vertical-pod-autoscaler
+  privileged: true
+  dependsOn: [cilium, kubeovn]
+
 - name: reloader
   releaseName: reloader
   chart: cozy-reloader

packages/core/platform/bundles/paas-hosted.yaml

@@ -69,7 +69,7 @@ releases:
   chart: cozy-monitoring-agents
   namespace: cozy-monitoring
   privileged: true
-  dependsOn: [victoria-metrics-operator]
+  dependsOn: [victoria-metrics-operator, vertical-pod-autoscaler-crds]
   values:
     scrapeRules:
       etcd:
@@ -254,3 +254,10 @@ releases:
   namespace: cozy-vertical-pod-autoscaler
   privileged: true
   dependsOn: [monitoring-agents]
+
+- name: vertical-pod-autoscaler-crds
+  releaseName: vertical-pod-autoscaler-crds
+  chart: cozy-vertical-pod-autoscaler-crds
+  namespace: cozy-vertical-pod-autoscaler
+  privileged: true
+  dependsOn: [cilium, kubeovn]

packages/core/testing/Makefile

@@ -2,7 +2,7 @@ NAMESPACE=cozy-e2e-tests
 NAME := sandbox
 CLEAN := 1
 TESTING_APPS := $(shell find ../../apps -maxdepth 1 -mindepth 1 -type d | awk -F/ '{print $$NF}')
-SANDBOX_NAME := cozy-e2e-sandbox
+SANDBOX_NAME := cozy-e2e-sandbox-$(shell echo "$$(hostname):$$(pwd)" | sha256sum | cut -c -6)
 
 ROOT_DIR = $(dir $(abspath $(firstword $(MAKEFILE_LIST))/../../..))
 

packages/core/testing/images/e2e-sandbox/Dockerfile

@@ -14,3 +14,4 @@ RUN curl -LO "https://dl.k8s.io/release/v${KUBECTL_VERSION}/bin/linux/amd64/kube
  && mv kubectl /usr/local/bin/kubectl
 RUN curl -sSL https://raw.githubusercontent.com/helm/helm/main/scripts/get-helm-3 | bash -s - --version "v${HELM_VERSION}"
 RUN wget https://github.com/mikefarah/yq/releases/download/v4.44.3/yq_linux_amd64 -O /usr/local/bin/yq && chmod +x /usr/local/bin/yq
+RUN curl -s https://fluxcd.io/install.sh | bash

packages/core/testing/values.yaml

@@ -1,2 +1,2 @@
 e2e:
-  image: ghcr.io/cozystack/cozystack/e2e-sandbox:v0.29.1@sha256:f239dc2d06dfe43fb3192531e994bdb10414d42d56d8659b10951bb4fe434f80
+  image: ghcr.io/cozystack/cozystack/e2e-sandbox:v0.30.4@sha256:1f35a80c22b4ae3909216892e44f7ba50b00bd135b64081ffe5296eb936a5ca3

packages/extra/bootbox/images/matchbox.tag

@@ -1 +1 @@
-ghcr.io/cozystack/cozystack/matchbox:v0.29.1@sha256:f0c1d531af04ffde003755df2b6fb2fef9ba0d8355aa55d728de523c623b08a0
+ghcr.io/cozystack/cozystack/matchbox:v0.30.4@sha256:8eb6da7d616bd4f91fbe6a1bf3a4cb5448976c1ade2e1ecca9bf6a2bd1772851

packages/extra/monitoring/Chart.yaml

@@ -3,4 +3,4 @@ name: monitoring
 description: Monitoring and observability stack
 icon: /logos/monitoring.svg
 type: application
-version: 1.9.1
+version: 1.9.2

packages/extra/monitoring/images/grafana.tag

@@ -1 +1 @@
-ghcr.io/cozystack/cozystack/grafana:1.9.1@sha256:24382d445bf7a39ed988ef4dc7a0d9f084db891fcb5f42fd2e64622710b9457e
+ghcr.io/cozystack/cozystack/grafana:1.9.2@sha256:24382d445bf7a39ed988ef4dc7a0d9f084db891fcb5f42fd2e64622710b9457e

packages/extra/monitoring/templates/vlogs/vlogs.yaml

@@ -4,6 +4,8 @@ kind: VLogs
 metadata:
   name: {{ .name }}
 spec:
+  image:
+    tag: v1.17.0-victorialogs
   storage:
     resources:
       requests:

packages/extra/versions_map

@@ -34,7 +34,8 @@ monitoring 1.7.0 2a976afe
 monitoring 1.8.0 8c460528
 monitoring 1.8.1 8267072d
 monitoring 1.9.0 45a7416c
-monitoring 1.9.1 HEAD
+monitoring 1.9.1 fd240701
+monitoring 1.9.2 HEAD
 seaweedfs 0.1.0 71514249
 seaweedfs 0.2.0 5fb9cfe3
 seaweedfs 0.2.1 fde4bcfa

packages/system/bucket/images/s3manager.tag

@@ -1 +1 @@
-ghcr.io/cozystack/cozystack/s3manager:v0.5.0@sha256:6e0a47fb639b27181848d38575577a3cc145486828f50d5fb899e167a3b46c84
+ghcr.io/cozystack/cozystack/s3manager:v0.5.0@sha256:a47d2743d01bff0ce60aa745fdff54f9b7184dff8679b11ab4ecd08ac663012b

packages/system/capi-operator/charts/cluster-api-operator/Chart.yaml

@@ -1,6 +1,6 @@
 apiVersion: v2
-appVersion: 0.17.0
+appVersion: 0.18.1
 description: Cluster API Operator
 name: cluster-api-operator
 type: application
-version: 0.17.0
+version: 0.18.1

packages/system/capi-operator/charts/cluster-api-operator/templates/addon.yaml

@@ -26,8 +26,10 @@ apiVersion: v1
 kind: Namespace
 metadata:
   annotations:
+    {{- if $.Values.enableHelmHook }}
     "helm.sh/hook": "post-install,post-upgrade"
     "helm.sh/hook-weight": "1"
+    {{- end }}
     "argocd.argoproj.io/sync-wave": "1"
   name: {{ $addonNamespace }}
 ---
@@ -37,8 +39,10 @@ metadata:
   name: {{ $addonName }}
   namespace: {{ $addonNamespace }}
   annotations:
+    {{- if $.Values.enableHelmHook }}
     "helm.sh/hook": "post-install,post-upgrade"
     "helm.sh/hook-weight": "2"
+    {{- end }}
     "argocd.argoproj.io/sync-wave": "2"
 {{- if or $addonVersion $.Values.secretName }}
 spec:

packages/system/capi-operator/charts/cluster-api-operator/templates/bootstrap.yaml

@@ -26,8 +26,11 @@ apiVersion: v1
 kind: Namespace
 metadata:
   annotations:
+    {{- if $.Values.enableHelmHook }}
     "helm.sh/hook": "post-install,post-upgrade"
     "helm.sh/hook-weight": "1"
+    {{- end }}
+    "argocd.argoproj.io/sync-wave": "1"
   name: {{ $bootstrapNamespace }}
 ---
 apiVersion: operator.cluster.x-k8s.io/v1alpha2
@@ -36,8 +39,11 @@ metadata:
   name: {{ $bootstrapName }}
   namespace: {{ $bootstrapNamespace }}
   annotations:
+    {{- if $.Values.enableHelmHook }}
     "helm.sh/hook": "post-install,post-upgrade"
     "helm.sh/hook-weight": "2"
+    {{- end }}
+    "argocd.argoproj.io/sync-wave": "2"
 {{- if or $bootstrapVersion $.Values.configSecret.name }}
 spec:
 {{- end}}

packages/system/capi-operator/charts/cluster-api-operator/templates/control-plane.yaml

@@ -26,8 +26,11 @@ apiVersion: v1
 kind: Namespace
 metadata:
   annotations:
+    {{- if $.Values.enableHelmHook }}
     "helm.sh/hook": "post-install,post-upgrade"
     "helm.sh/hook-weight": "1"
+    {{- end }}
+    "argocd.argoproj.io/sync-wave": "1"
   name: {{ $controlPlaneNamespace }}
 ---
 apiVersion: operator.cluster.x-k8s.io/v1alpha2
@@ -36,8 +39,11 @@ metadata:
   name: {{ $controlPlaneName }}
   namespace: {{ $controlPlaneNamespace }}
   annotations:
+    {{- if $.Values.enableHelmHook }}
     "helm.sh/hook": "post-install,post-upgrade"
     "helm.sh/hook-weight": "2"
+    {{- end }}
+    "argocd.argoproj.io/sync-wave": "2"
 {{- if or $controlPlaneVersion $.Values.configSecret.name $.Values.manager }}
 spec:
 {{- end}}

packages/system/capi-operator/charts/cluster-api-operator/templates/core-conditions.yaml

@@ -1,4 +1,4 @@
-{{- if or .Values.addon .Values.bootstrap .Values.controlPlane .Values.infrastructure }}
+{{- if or .Values.addon .Values.bootstrap .Values.controlPlane .Values.infrastructure .Values.ipam }}
 # Deploy core components if not specified
 {{- if not .Values.core }}
 ---
@@ -6,8 +6,11 @@ apiVersion: v1
 kind: Namespace
 metadata:
   annotations:
+    {{- if $.Values.enableHelmHook }}
     "helm.sh/hook": "post-install,post-upgrade"
     "helm.sh/hook-weight": "1"
+    {{- end }}
+    "argocd.argoproj.io/sync-wave": "1"
   name: capi-system
 ---
 apiVersion: operator.cluster.x-k8s.io/v1alpha2
@@ -16,8 +19,11 @@ metadata:
   name: cluster-api
   namespace: capi-system
   annotations:
+    {{- if $.Values.enableHelmHook }}
     "helm.sh/hook": "post-install,post-upgrade"
     "helm.sh/hook-weight": "2"
+    {{- end }}
+    "argocd.argoproj.io/sync-wave": "2"
 {{- with .Values.configSecret }}
 spec:
   configSecret:
@@ -28,4 +34,3 @@ spec:
 {{- end }}
 {{- end }}
 {{- end }}
-

packages/system/capi-operator/charts/cluster-api-operator/templates/core.yaml

@@ -25,8 +25,11 @@ apiVersion: v1
 kind: Namespace
 metadata:
   annotations:
+    {{- if $.Values.enableHelmHook }}
     "helm.sh/hook": "post-install,post-upgrade"
     "helm.sh/hook-weight": "1"
+    {{- end }}
+    "argocd.argoproj.io/sync-wave": "1"
   name: {{ $coreNamespace }}
 ---
 apiVersion: operator.cluster.x-k8s.io/v1alpha2
@@ -35,8 +38,10 @@ metadata:
   name: {{ $coreName }}
   namespace: {{ $coreNamespace }}
   annotations:
+    {{- if $.Values.enableHelmHook }}
     "helm.sh/hook": "post-install,post-upgrade"
     "helm.sh/hook-weight": "2"
+    {{- end }}
     "argocd.argoproj.io/sync-wave": "2"
 {{- if or $coreVersion $.Values.configSecret.name $.Values.manager }}
 spec:
@@ -45,8 +50,8 @@ spec:
   version: {{ $coreVersion }}
 {{- end }}
 {{- if $.Values.manager }}
-  manager:
 {{- if and $.Values.manager.featureGates $.Values.manager.featureGates.core }}
+  manager:
     featureGates:
     {{- range $key, $value := $.Values.manager.featureGates.core }}
       {{ $key }}: {{ $value }}

packages/system/capi-operator/charts/cluster-api-operator/templates/infra-conditions.yaml

@@ -7,8 +7,10 @@ apiVersion: v1
 kind: Namespace
 metadata:
   annotations:
+    {{- if $.Values.enableHelmHook }}
     "helm.sh/hook": "post-install,post-upgrade"
     "helm.sh/hook-weight": "1"
+    {{- end }}
     "argocd.argoproj.io/sync-wave": "1"
   name: capi-kubeadm-bootstrap-system
 ---
@@ -18,8 +20,10 @@ metadata:
   name: kubeadm
   namespace: capi-kubeadm-bootstrap-system
   annotations:
+    {{- if $.Values.enableHelmHook }}
     "helm.sh/hook": "post-install,post-upgrade"
     "helm.sh/hook-weight": "2"
+    {{- end }}
     "argocd.argoproj.io/sync-wave": "2"
 {{- with .Values.configSecret }}
 spec:
@@ -37,8 +41,10 @@ apiVersion: v1
 kind: Namespace
 metadata:
   annotations:
+    {{- if $.Values.enableHelmHook }}
     "helm.sh/hook": "post-install,post-upgrade"
     "helm.sh/hook-weight": "1"
+    {{- end }}
     "argocd.argoproj.io/sync-wave": "1"
   name: capi-kubeadm-control-plane-system
 ---
@@ -48,14 +54,16 @@ metadata:
   name: kubeadm
   namespace: capi-kubeadm-control-plane-system
   annotations:
+    {{- if $.Values.enableHelmHook }}
     "helm.sh/hook": "post-install,post-upgrade"
     "helm.sh/hook-weight": "2"
+    {{- end }}
     "argocd.argoproj.io/sync-wave": "2"
 {{- with .Values.configSecret }}
 spec:
 {{- if $.Values.manager }}
-  manager:
 {{- if and $.Values.manager.featureGates $.Values.manager.featureGates.kubeadm }}
+  manager:
     featureGates:
     {{- range $key, $value := $.Values.manager.featureGates.kubeadm }}
       {{ $key }}: {{ $value }}

packages/system/capi-operator/charts/cluster-api-operator/templates/infra.yaml

@@ -26,8 +26,10 @@ apiVersion: v1
 kind: Namespace
 metadata:
   annotations:
+    {{- if $.Values.enableHelmHook }}
     "helm.sh/hook": "post-install,post-upgrade"
     "helm.sh/hook-weight": "1"
+    {{- end }}
     "argocd.argoproj.io/sync-wave": "1"
   name: {{ $infrastructureNamespace }}
 ---
@@ -37,8 +39,10 @@ metadata:
   name: {{ $infrastructureName }}
   namespace: {{ $infrastructureNamespace }}
   annotations:
+    {{- if $.Values.enableHelmHook }}
     "helm.sh/hook": "post-install,post-upgrade"
     "helm.sh/hook-weight": "2"
+    {{- end }}
     "argocd.argoproj.io/sync-wave": "2"
 {{- if or $infrastructureVersion $.Values.configSecret.name $.Values.manager $.Values.additionalDeployments }}
 spec:
@@ -47,8 +51,8 @@ spec:
   version: {{ $infrastructureVersion }}
 {{- end }}
 {{- if $.Values.manager }}
-  manager:
 {{- if and (kindIs "map" $.Values.manager.featureGates) (hasKey $.Values.manager.featureGates $infrastructureName) }}
+  manager:
 {{- range $key, $value := $.Values.manager.featureGates }}
   {{- if eq $key $infrastructureName }}
     featureGates:

packages/system/capi-operator/charts/cluster-api-operator/templates/ipam.yaml

@@ -26,8 +26,10 @@ apiVersion: v1
 kind: Namespace
 metadata:
   annotations:
+    {{- if $.Values.enableHelmHook }}
     "helm.sh/hook": "post-install,post-upgrade"
     "helm.sh/hook-weight": "1"
+    {{- end }}
     "argocd.argoproj.io/sync-wave": "1"
   name: {{ $ipamNamespace }}
 ---
@@ -37,8 +39,10 @@ metadata:
   name: {{ $ipamName }}
   namespace: {{ $ipamNamespace }}
   annotations:
+    {{- if $.Values.enableHelmHook }}
     "helm.sh/hook": "post-install,post-upgrade"
     "helm.sh/hook-weight": "2"
+    {{- end }}
     "argocd.argoproj.io/sync-wave": "2"
 {{- if or $ipamVersion $.Values.configSecret.name $.Values.manager $.Values.additionalDeployments }}
 spec:
@@ -47,8 +51,8 @@ spec:
   version: {{ $ipamVersion }}
 {{- end }}
 {{- if $.Values.manager }}
-  manager:
 {{- if and (kindIs "map" $.Values.manager.featureGates) (hasKey $.Values.manager.featureGates $ipamName) }}
+  manager:
 {{- range $key, $value := $.Values.manager.featureGates }}
   {{- if eq $key $ipamName }}
     featureGates:

packages/system/capi-operator/charts/cluster-api-operator/values.yaml

@@ -21,7 +21,7 @@ leaderElection:
 image:
   manager:
     repository: registry.k8s.io/capi-operator/cluster-api-operator
-    tag: v0.17.0
+    tag: v0.18.1
     pullPolicy: IfNotPresent
 env:
   manager: []
@@ -69,3 +69,4 @@ volumeMounts:
     - mountPath: /tmp/k8s-webhook-server/serving-certs
       name: cert
       readOnly: true
+enableHelmHook: true

packages/system/capi-providers/templates/providers.yaml

@@ -21,6 +21,9 @@ spec:
         limits:
           cpu: "1"
           memory: 1024Mi
+        requests:
+          cpu: "10m"
+          memory: 128Mi
 ---
 apiVersion: operator.cluster.x-k8s.io/v1alpha2
 kind: BootstrapProvider

packages/system/cilium/charts/cilium/Chart.yaml

@@ -79,7 +79,7 @@ annotations:
     Pod IP Pool\n  description: |\n    CiliumPodIPPool defines an IP pool that can
     be used for pooled IPAM (i.e. the multi-pool IPAM mode).\n"
 apiVersion: v2
-appVersion: 1.17.1
+appVersion: 1.17.2
 description: eBPF-based Networking, Security, and Observability
 home: https://cilium.io/
 icon: https://cdn.jsdelivr.net/gh/cilium/cilium@main/Documentation/images/logo-solo.svg
@@ -95,4 +95,4 @@ kubeVersion: '>= 1.21.0-0'
 name: cilium
 sources:
 - https://github.com/cilium/cilium
-version: 1.17.1
+version: 1.17.2

packages/system/cilium/charts/cilium/README.md

@@ -1,6 +1,6 @@
 # cilium
 
-![Version: 1.17.1](https://img.shields.io/badge/Version-1.17.1-informational?style=flat-square) ![AppVersion: 1.17.1](https://img.shields.io/badge/AppVersion-1.17.1-informational?style=flat-square)
+![Version: 1.17.2](https://img.shields.io/badge/Version-1.17.2-informational?style=flat-square) ![AppVersion: 1.17.2](https://img.shields.io/badge/AppVersion-1.17.2-informational?style=flat-square)
 
 Cilium is open source software for providing and transparently securing
 network connectivity and loadbalancing between application workloads such as
@@ -85,7 +85,7 @@ contributors across the globe, there is almost always someone available to help.
 | authentication.mutual.spire.install.agent.tolerations | list | `[{"effect":"NoSchedule","key":"node.kubernetes.io/not-ready"},{"effect":"NoSchedule","key":"node-role.kubernetes.io/master"},{"effect":"NoSchedule","key":"node-role.kubernetes.io/control-plane"},{"effect":"NoSchedule","key":"node.cloudprovider.kubernetes.io/uninitialized","value":"true"},{"key":"CriticalAddonsOnly","operator":"Exists"}]` | SPIRE agent tolerations configuration By default it follows the same tolerations as the agent itself to allow the Cilium agent on this node to connect to SPIRE. ref: https://kubernetes.io/docs/concepts/scheduling-eviction/taint-and-toleration/ |
 | authentication.mutual.spire.install.enabled | bool | `true` | Enable SPIRE installation. This will only take effect only if authentication.mutual.spire.enabled is true |
 | authentication.mutual.spire.install.existingNamespace | bool | `false` | SPIRE namespace already exists. Set to true if Helm should not create, manage, and import the SPIRE namespace. |
-| authentication.mutual.spire.install.initImage | object | `{"digest":"sha256:a5d0ce49aa801d475da48f8cb163c354ab95cab073cd3c138bd458fc8257fbf1","override":null,"pullPolicy":"IfNotPresent","repository":"docker.io/library/busybox","tag":"1.37.0","useDigest":true}` | init container image of SPIRE agent and server |
+| authentication.mutual.spire.install.initImage | object | `{"digest":"sha256:498a000f370d8c37927118ed80afe8adc38d1edcbfc071627d17b25c88efcab0","override":null,"pullPolicy":"IfNotPresent","repository":"docker.io/library/busybox","tag":"1.37.0","useDigest":true}` | init container image of SPIRE agent and server |
 | authentication.mutual.spire.install.namespace | string | `"cilium-spire"` | SPIRE namespace to install into |
 | authentication.mutual.spire.install.server.affinity | object | `{}` | SPIRE server affinity configuration |
 | authentication.mutual.spire.install.server.annotations | object | `{}` | SPIRE server annotations |
@@ -131,6 +131,8 @@ contributors across the globe, there is almost always someone available to help.
 | bpf.ctTcpMax | int | `524288` | Configure the maximum number of entries in the TCP connection tracking table. |
 | bpf.datapathMode | string | `veth` | Mode for Pod devices for the core datapath (veth, netkit, netkit-l2, lb-only) |
 | bpf.disableExternalIPMitigation | bool | `false` | Disable ExternalIP mitigation (CVE-2020-8554) |
+| bpf.distributedLRU | object | `{"enabled":false}` | Control to use a distributed per-CPU backend memory for the core BPF LRU maps which Cilium uses. This improves performance significantly, but it is also recommended to increase BPF map sizing along with that. |
+| bpf.distributedLRU.enabled | bool | `false` | Enable distributed LRU backend memory. For compatibility with existing installations it is off by default. |
 | bpf.enableTCX | bool | `true` | Attach endpoint programs using tcx instead of legacy tc hooks on supported kernels. |
 | bpf.events | object | `{"default":{"burstLimit":null,"rateLimit":null},"drop":{"enabled":true},"policyVerdict":{"enabled":true},"trace":{"enabled":true}}` | Control events generated by the Cilium datapath exposed to Cilium monitor and Hubble. Helm configuration for BPF events map rate limiting is experimental and might change in upcoming releases. |
 | bpf.events.default | object | `{"burstLimit":null,"rateLimit":null}` | Default settings for all types of events except dbg and pcap. |
@@ -195,7 +197,7 @@ contributors across the globe, there is almost always someone available to help.
 | clustermesh.apiserver.extraVolumeMounts | list | `[]` | Additional clustermesh-apiserver volumeMounts. |
 | clustermesh.apiserver.extraVolumes | list | `[]` | Additional clustermesh-apiserver volumes. |
 | clustermesh.apiserver.healthPort | int | `9880` | TCP port for the clustermesh-apiserver health API. |
-| clustermesh.apiserver.image | object | `{"digest":"sha256:1de22f46bfdd638de72c2224d5223ddc3bbeacda1803cb75799beca3d4bf7a4c","override":null,"pullPolicy":"IfNotPresent","repository":"quay.io/cilium/clustermesh-apiserver","tag":"v1.17.1","useDigest":true}` | Clustermesh API server image. |
+| clustermesh.apiserver.image | object | `{"digest":"sha256:981250ebdc6e66e190992eaf75cfca169113a8f08d5c3793fe15822176980398","override":null,"pullPolicy":"IfNotPresent","repository":"quay.io/cilium/clustermesh-apiserver","tag":"v1.17.2","useDigest":true}` | Clustermesh API server image. |
 | clustermesh.apiserver.kvstoremesh.enabled | bool | `true` | Enable KVStoreMesh. KVStoreMesh caches the information retrieved from the remote clusters in the local etcd instance. |
 | clustermesh.apiserver.kvstoremesh.extraArgs | list | `[]` | Additional KVStoreMesh arguments. |
 | clustermesh.apiserver.kvstoremesh.extraEnv | list | `[]` | Additional KVStoreMesh environment variables. |
@@ -375,7 +377,7 @@ contributors across the globe, there is almost always someone available to help.
 | envoy.healthPort | int | `9878` | TCP port for the health API. |
 | envoy.httpRetryCount | int | `3` | Maximum number of retries for each HTTP request |
 | envoy.idleTimeoutDurationSeconds | int | `60` | Set Envoy upstream HTTP idle connection timeout seconds. Does not apply to connections with pending requests. Default 60s |
-| envoy.image | object | `{"digest":"sha256:fc708bd36973d306412b2e50c924cd8333de67e0167802c9b48506f9d772f521","override":null,"pullPolicy":"IfNotPresent","repository":"quay.io/cilium/cilium-envoy","tag":"v1.31.5-1739264036-958bef243c6c66fcfd73ca319f2eb49fff1eb2ae","useDigest":true}` | Envoy container image. |
+| envoy.image | object | `{"digest":"sha256:377c78c13d2731f3720f931721ee309159e782d882251709cb0fac3b42c03f4b","override":null,"pullPolicy":"IfNotPresent","repository":"quay.io/cilium/cilium-envoy","tag":"v1.31.5-1741765102-efed3defcc70ab5b263a0fc44c93d316b846a211","useDigest":true}` | Envoy container image. |
 | envoy.initialFetchTimeoutSeconds | int | `30` | Time in seconds after which the initial fetch on an xDS stream is considered timed out |
 | envoy.livenessProbe.failureThreshold | int | `10` | failure threshold of liveness probe |
 | envoy.livenessProbe.periodSeconds | int | `30` | interval between checks of the liveness probe |
@@ -392,6 +394,7 @@ contributors across the globe, there is almost always someone available to help.
 | envoy.podLabels | object | `{}` | Labels to be added to envoy pods |
 | envoy.podSecurityContext | object | `{"appArmorProfile":{"type":"Unconfined"}}` | Security Context for cilium-envoy pods. |
 | envoy.podSecurityContext.appArmorProfile | object | `{"type":"Unconfined"}` | AppArmorProfile options for the `cilium-agent` and init containers |
+| envoy.policyRestoreTimeoutDuration | string | `nil` | Max duration to wait for endpoint policies to be restored on restart. Default "3m". |
 | envoy.priorityClassName | string | `nil` | The priority class to use for cilium-envoy. |
 | envoy.prometheus | object | `{"enabled":true,"port":"9964","serviceMonitor":{"annotations":{},"enabled":false,"interval":"10s","labels":{},"metricRelabelings":null,"relabelings":[{"replacement":"${1}","sourceLabels":["__meta_kubernetes_pod_node_name"],"targetLabel":"node"}]}}` | Configure Cilium Envoy Prometheus options. Note that some of these apply to either cilium-agent or cilium-envoy. |
 | envoy.prometheus.enabled | bool | `true` | Enable prometheus metrics for cilium-envoy |
@@ -515,7 +518,7 @@ contributors across the globe, there is almost always someone available to help.
 | hubble.relay.extraVolumes | list | `[]` | Additional hubble-relay volumes. |
 | hubble.relay.gops.enabled | bool | `true` | Enable gops for hubble-relay |
 | hubble.relay.gops.port | int | `9893` | Configure gops listen port for hubble-relay |
-| hubble.relay.image | object | `{"digest":"sha256:397e8fbb188157f744390a7b272a1dec31234e605bcbe22d8919a166d202a3dc","override":null,"pullPolicy":"IfNotPresent","repository":"quay.io/cilium/hubble-relay","tag":"v1.17.1","useDigest":true}` | Hubble-relay container image. |
+| hubble.relay.image | object | `{"digest":"sha256:42a8db5c256c516cacb5b8937c321b2373ad7a6b0a1e5a5120d5028433d586cc","override":null,"pullPolicy":"IfNotPresent","repository":"quay.io/cilium/hubble-relay","tag":"v1.17.2","useDigest":true}` | Hubble-relay container image. |
 | hubble.relay.listenHost | string | `""` | Host to listen to. Specify an empty string to bind to all the interfaces. |
 | hubble.relay.listenPort | string | `"4245"` | Port to listen to. |
 | hubble.relay.nodeSelector | object | `{"kubernetes.io/os":"linux"}` | Node labels for pod assignment ref: https://kubernetes.io/docs/concepts/scheduling-eviction/assign-pod-node/#nodeselector |
@@ -582,7 +585,7 @@ contributors across the globe, there is almost always someone available to help.
 | hubble.ui.backend.extraEnv | list | `[]` | Additional hubble-ui backend environment variables. |
 | hubble.ui.backend.extraVolumeMounts | list | `[]` | Additional hubble-ui backend volumeMounts. |
 | hubble.ui.backend.extraVolumes | list | `[]` | Additional hubble-ui backend volumes. |
-| hubble.ui.backend.image | object | `{"digest":"sha256:0e0eed917653441fded4e7cdb096b7be6a3bddded5a2dd10812a27b1fc6ed95b","override":null,"pullPolicy":"IfNotPresent","repository":"quay.io/cilium/hubble-ui-backend","tag":"v0.13.1","useDigest":true}` | Hubble-ui backend image. |
+| hubble.ui.backend.image | object | `{"digest":"sha256:a034b7e98e6ea796ed26df8f4e71f83fc16465a19d166eff67a03b822c0bfa15","override":null,"pullPolicy":"IfNotPresent","repository":"quay.io/cilium/hubble-ui-backend","tag":"v0.13.2","useDigest":true}` | Hubble-ui backend image. |
 | hubble.ui.backend.livenessProbe.enabled | bool | `false` | Enable liveness probe for Hubble-ui backend (requires Hubble-ui 0.12+) |
 | hubble.ui.backend.readinessProbe.enabled | bool | `false` | Enable readiness probe for Hubble-ui backend (requires Hubble-ui 0.12+) |
 | hubble.ui.backend.resources | object | `{}` | Resource requests and limits for the 'backend' container of the 'hubble-ui' deployment. |
@@ -592,7 +595,7 @@ contributors across the globe, there is almost always someone available to help.
 | hubble.ui.frontend.extraEnv | list | `[]` | Additional hubble-ui frontend environment variables. |
 | hubble.ui.frontend.extraVolumeMounts | list | `[]` | Additional hubble-ui frontend volumeMounts. |
 | hubble.ui.frontend.extraVolumes | list | `[]` | Additional hubble-ui frontend volumes. |
-| hubble.ui.frontend.image | object | `{"digest":"sha256:e2e9313eb7caf64b0061d9da0efbdad59c6c461f6ca1752768942bfeda0796c6","override":null,"pullPolicy":"IfNotPresent","repository":"quay.io/cilium/hubble-ui","tag":"v0.13.1","useDigest":true}` | Hubble-ui frontend image. |
+| hubble.ui.frontend.image | object | `{"digest":"sha256:9e37c1296b802830834cc87342a9182ccbb71ffebb711971e849221bd9d59392","override":null,"pullPolicy":"IfNotPresent","repository":"quay.io/cilium/hubble-ui","tag":"v0.13.2","useDigest":true}` | Hubble-ui frontend image. |
 | hubble.ui.frontend.resources | object | `{}` | Resource requests and limits for the 'frontend' container of the 'hubble-ui' deployment. |
 | hubble.ui.frontend.securityContext | object | `{}` | Hubble-ui frontend security context. |
 | hubble.ui.frontend.server.ipv6 | object | `{"enabled":true}` | Controls server listener for ipv6 |
@@ -622,7 +625,7 @@ contributors across the globe, there is almost always someone available to help.
 | hubble.ui.updateStrategy | object | `{"rollingUpdate":{"maxUnavailable":1},"type":"RollingUpdate"}` | hubble-ui update strategy. |
 | identityAllocationMode | string | `"crd"` | Method to use for identity allocation (`crd`, `kvstore` or `doublewrite-readkvstore` / `doublewrite-readcrd` for migrating between identity backends). |
 | identityChangeGracePeriod | string | `"5s"` | Time to wait before using new identity on endpoint identity change. |
-| image | object | `{"digest":"sha256:8969bfd9c87cbea91e40665f8ebe327268c99d844ca26d7d12165de07f702866","override":null,"pullPolicy":"IfNotPresent","repository":"quay.io/cilium/cilium","tag":"v1.17.1","useDigest":true}` | Agent container image. |
+| image | object | `{"digest":"sha256:3c4c9932b5d8368619cb922a497ff2ebc8def5f41c18e410bcc84025fcd385b1","override":null,"pullPolicy":"IfNotPresent","repository":"quay.io/cilium/cilium","tag":"v1.17.2","useDigest":true}` | Agent container image. |
 | imagePullSecrets | list | `[]` | Configure image pull secrets for pulling container images |
 | ingressController.default | bool | `false` | Set cilium ingress controller to be the default ingress controller This will let cilium ingress controller route entries without ingress class set |
 | ingressController.defaultSecretName | string | `nil` | Default secret name for ingresses without .spec.tls[].secretName set. |
@@ -759,7 +762,7 @@ contributors across the globe, there is almost always someone available to help.
 | operator.hostNetwork | bool | `true` | HostNetwork setting |
 | operator.identityGCInterval | string | `"15m0s"` | Interval for identity garbage collection. |
 | operator.identityHeartbeatTimeout | string | `"30m0s"` | Timeout for identity heartbeats. |
-| operator.image | object | `{"alibabacloudDigest":"sha256:034b479fba340f9d98510e509c7ce1c36e8889a109d5f1c2240fcb0942bc772c","awsDigest":"sha256:da74748057c836471bfdc0e65bb29ba0edb82916ec4b99f6a4f002b2fcc849d6","azureDigest":"sha256:b9e3e3994f5fcf1832e1f344f3b3b544832851b1990f124b2c2c68e3ffe04a9b","genericDigest":"sha256:628becaeb3e4742a1c36c4897721092375891b58bae2bfcae48bbf4420aaee97","override":null,"pullPolicy":"IfNotPresent","repository":"quay.io/cilium/operator","suffix":"","tag":"v1.17.1","useDigest":true}` | cilium-operator image. |
+| operator.image | object | `{"alibabacloudDigest":"sha256:7cb8c23417f65348bb810fe92fb05b41d926f019d77442f3fa1058d17fea7ffe","awsDigest":"sha256:955096183e22a203bbb198ca66e3266ce4dbc2b63f1a2fbd03f9373dcd97893c","azureDigest":"sha256:455fb88b558b1b8ba09d63302ccce76b4930581be89def027184ab04335c20e0","genericDigest":"sha256:81f2d7198366e8dec2903a3a8361e4c68d47d19c68a0d42f0b7b6e3f0523f249","override":null,"pullPolicy":"IfNotPresent","repository":"quay.io/cilium/operator","suffix":"","tag":"v1.17.2","useDigest":true}` | cilium-operator image. |
 | operator.nodeGCInterval | string | `"5m0s"` | Interval for cilium node garbage collection. |
 | operator.nodeSelector | object | `{"kubernetes.io/os":"linux"}` | Node labels for cilium-operator pod assignment ref: https://kubernetes.io/docs/concepts/scheduling-eviction/assign-pod-node/#nodeselector |
 | operator.podAnnotations | object | `{}` | Annotations to be added to cilium-operator pods |
@@ -809,7 +812,7 @@ contributors across the globe, there is almost always someone available to help.
 | preflight.extraEnv | list | `[]` | Additional preflight environment variables. |
 | preflight.extraVolumeMounts | list | `[]` | Additional preflight volumeMounts. |
 | preflight.extraVolumes | list | `[]` | Additional preflight volumes. |
-| preflight.image | object | `{"digest":"sha256:8969bfd9c87cbea91e40665f8ebe327268c99d844ca26d7d12165de07f702866","override":null,"pullPolicy":"IfNotPresent","repository":"quay.io/cilium/cilium","tag":"v1.17.1","useDigest":true}` | Cilium pre-flight image. |
+| preflight.image | object | `{"digest":"sha256:3c4c9932b5d8368619cb922a497ff2ebc8def5f41c18e410bcc84025fcd385b1","override":null,"pullPolicy":"IfNotPresent","repository":"quay.io/cilium/cilium","tag":"v1.17.2","useDigest":true}` | Cilium pre-flight image. |
 | preflight.nodeSelector | object | `{"kubernetes.io/os":"linux"}` | Node labels for preflight pod assignment ref: https://kubernetes.io/docs/concepts/scheduling-eviction/assign-pod-node/#nodeselector |
 | preflight.podAnnotations | object | `{}` | Annotations to be added to preflight pods |
 | preflight.podDisruptionBudget.enabled | bool | `false` | enable PodDisruptionBudget ref: https://kubernetes.io/docs/concepts/workloads/pods/disruptions/ |
@@ -883,7 +886,7 @@ contributors across the globe, there is almost always someone available to help.
 | tls.caBundle.useSecret | bool | `false` | Use a Secret instead of a ConfigMap. |
 | tls.readSecretsOnlyFromSecretsNamespace | string | `nil` | Configure if the Cilium Agent will only look in `tls.secretsNamespace` for    CiliumNetworkPolicy relevant Secrets.    If false, the Cilium Agent will be granted READ (GET/LIST/WATCH) access    to _all_ secrets in the entire cluster. This is not recommended and is    included for backwards compatibility.    This value obsoletes `tls.secretsBackend`, with `true` == `local` in the old    setting, and `false` == `k8s`. |
 | tls.secretSync | object | `{"enabled":null}` | Configures settings for synchronization of TLS Interception Secrets |
-| tls.secretSync.enabled | string | `nil` | Enable synchronization of Secrets for TLS Interception. If disabled and tls.secretsBackend is set to 'k8s', then secrets will be read directly by the agent. |
+| tls.secretSync.enabled | string | `nil` | Enable synchronization of Secrets for TLS Interception. If disabled and tls.readSecretsOnlyFromSecretsNamespace is set to 'false', then secrets will be read directly by the agent. |
 | tls.secretsBackend | string | `nil` | This configures how the Cilium agent loads the secrets used TLS-aware CiliumNetworkPolicies (namely the secrets referenced by terminatingTLS and originatingTLS). This value is DEPRECATED and will be removed in a future version. Use `tls.readSecretsOnlyFromSecretsNamespace` instead. Possible values:   - local   - k8s |
 | tls.secretsNamespace | object | `{"create":true,"name":"cilium-secrets"}` | Configures where secrets used in CiliumNetworkPolicies will be looked for |
 | tls.secretsNamespace.create | bool | `true` | Create secrets namespace for TLS Interception secrets. |
@@ -891,6 +894,7 @@ contributors across the globe, there is almost always someone available to help.
 | tolerations | list | `[{"operator":"Exists"}]` | Node tolerations for agent scheduling to nodes with taints ref: https://kubernetes.io/docs/concepts/scheduling-eviction/taint-and-toleration/ |
 | tunnelPort | int | Port 8472 for VXLAN, Port 6081 for Geneve | Configure VXLAN and Geneve tunnel port. |
 | tunnelProtocol | string | `"vxlan"` | Tunneling protocol to use in tunneling mode and for ad-hoc tunnels. Possible values:   - ""   - vxlan   - geneve |
+| tunnelSourcePortRange | string | 0-0 to let the kernel driver decide the range | Configure VXLAN and Geneve tunnel source port range hint. |
 | updateStrategy | object | `{"rollingUpdate":{"maxUnavailable":2},"type":"RollingUpdate"}` | Cilium agent update strategy |
 | upgradeCompatibility | string | `nil` | upgradeCompatibility helps users upgrading to ensure that the configMap for Cilium will not change critical values to ensure continued operation This flag is not required for new installations. For example: '1.7', '1.8', '1.9' |
 | vtep.cidr | string | `""` | A space separated list of VTEP device CIDRs, for example "1.1.1.0/24 1.1.2.0/24" |

packages/system/cilium/charts/cilium/files/cilium-envoy/configmap/bootstrap-config.yaml

@@ -7,8 +7,15 @@ staticResources:
   - name: "envoy-prometheus-metrics-listener"
     address:
       socketAddress:
-        address: "0.0.0.0"
+        address: {{ .Values.ipv4.enabled | ternary "0.0.0.0" "::" | quote }}
         portValue: {{ .Values.envoy.prometheus.port }}
+    {{- if and .Values.ipv4.enabled .Values.ipv6.enabled }}
+    additionalAddresses:
+    - address:
+        socketAddress:
+          address: "::"
+          portValue: {{ .Values.envoy.prometheus.port }}
+    {{- end }}
     filterChains:
     - filters:
       - name: "envoy.filters.network.http_connection_manager"
@@ -289,7 +296,7 @@ overloadManager:
 applicationLogConfig:
   logFormat:
     {{- if .Values.envoy.log.format_json }}
-    jsonFormat: "{{ .Values.envoy.log.format_json | toJson }}"
+    jsonFormat: {{ .Values.envoy.log.format_json | toJson }}
     {{- else }}
     textFormat: "{{ .Values.envoy.log.format }}"
     {{- end }}

packages/system/cilium/charts/cilium/templates/cilium-agent/daemonset.yaml

@@ -232,7 +232,7 @@ spec:
         resources:
           {{- toYaml . | trim | nindent 10 }}
         {{- end }}
-        {{- if or .Values.prometheus.enabled .Values.hubble.metrics.enabled }}
+        {{- if or .Values.prometheus.enabled (or .Values.hubble.metrics.enabled .Values.hubble.metrics.dynamic.enabled) }}
         ports:
         - name: peer-service
           containerPort: {{ .Values.hubble.peerService.targetPort }}
@@ -364,7 +364,7 @@ spec:
           mountPath: {{ .Values.kubeConfigPath }}
           readOnly: true
         {{- end }}
-        {{- if and .Values.hubble.enabled .Values.hubble.metrics.enabled .Values.hubble.metrics.tls.enabled }}
+        {{- if and .Values.hubble.enabled (or .Values.hubble.metrics.enabled .Values.hubble.metrics.dynamic.enabled) .Values.hubble.metrics.tls.enabled }}
         - name: hubble-metrics-tls
           mountPath: /var/lib/cilium/tls/hubble-metrics
           readOnly: true
@@ -999,7 +999,7 @@ spec:
                 path: client-ca.crt
           {{- end }}
       {{- end }}
-      {{- if and .Values.hubble.enabled .Values.hubble.metrics.enabled .Values.hubble.metrics.tls.enabled }}
+      {{- if and .Values.hubble.enabled (or .Values.hubble.metrics.enabled .Values.hubble.metrics.dynamic.enabled) .Values.hubble.metrics.tls.enabled }}
       - name: hubble-metrics-tls
         projected:
           # note: the leading zero means this number is in octal representation: do not remove it

packages/system/cilium/charts/cilium/templates/cilium-agent/rolebinding.yaml

@@ -39,6 +39,9 @@ metadata:
   {{- end }}
   labels:
     app.kubernetes.io/part-of: cilium
+    {{- with .Values.commonLabels }}
+    {{- toYaml . | nindent 4 }}
+    {{- end }}
 roleRef:
   apiGroup: rbac.authorization.k8s.io
   kind: Role
@@ -62,6 +65,9 @@ metadata:
   {{- end }}
   labels:
     app.kubernetes.io/part-of: cilium
+    {{- with .Values.commonLabels }}
+    {{- toYaml . | nindent 4 }}
+    {{- end }}
 roleRef:
   apiGroup: rbac.authorization.k8s.io
   kind: Role
@@ -85,6 +91,9 @@ metadata:
   {{- end }}
   labels:
     app.kubernetes.io/part-of: cilium
+    {{- with .Values.commonLabels }}
+    {{- toYaml . | nindent 4 }}
+    {{- end }}
 roleRef:
   apiGroup: rbac.authorization.k8s.io
   kind: Role
@@ -104,6 +113,9 @@ metadata:
   namespace: {{ .Values.bgpControlPlane.secretsNamespace.name | quote }}
   labels:
     app.kubernetes.io/part-of: cilium
+    {{- with .Values.commonLabels }}
+    {{- toYaml . | nindent 4 }}
+    {{- end }}
 roleRef:
   apiGroup: rbac.authorization.k8s.io
   kind: Role
@@ -123,6 +135,9 @@ metadata:
   namespace: {{ .Values.tls.secretsNamespace.name | quote }}
   labels:
     app.kubernetes.io/part-of: cilium
+    {{- with .Values.commonLabels }}
+    {{- toYaml . | nindent 4 }}
+    {{- end }}
 roleRef:
   apiGroup: rbac.authorization.k8s.io
   kind: Role

packages/system/cilium/charts/cilium/templates/cilium-agent/service.yaml

@@ -46,6 +46,9 @@ metadata:
     k8s-app: cilium
     app.kubernetes.io/name: cilium-agent
     app.kubernetes.io/part-of: cilium
+    {{- with .Values.commonLabels }}
+    {{- toYaml . | nindent 4 }}
+    {{- end }}
 spec:
   clusterIP: None
   type: ClusterIP

packages/system/cilium/charts/cilium/templates/cilium-configmap.yaml

@@ -403,7 +403,7 @@ data:
 
 {{- if .Values.bpf.authMapMax }}
   # bpf-auth-map-max specifies the maximum number of entries in the auth map
-  bpf-auth-map-max: {{ .Values.bpf.authMapMax | quote }}
+  bpf-auth-map-max: "{{ .Values.bpf.authMapMax | int }}"
 {{- end }}
 {{- if or $bpfCtTcpMax $bpfCtAnyMax }}
   # bpf-ct-global-*-max specifies the maximum number of connections
@@ -419,34 +419,34 @@ data:
   # For users upgrading from Cilium 1.2 or earlier, to minimize disruption
   # during the upgrade process, set bpf-ct-global-tcp-max to 1000000.
 {{- if $bpfCtTcpMax }}
-  bpf-ct-global-tcp-max: {{ $bpfCtTcpMax | quote }}
+  bpf-ct-global-tcp-max: "{{ $bpfCtTcpMax | int }}"
 {{- end }}
 {{- if $bpfCtAnyMax }}
-  bpf-ct-global-any-max: {{ $bpfCtAnyMax | quote }}
+  bpf-ct-global-any-max: "{{ $bpfCtAnyMax | int }}"
 {{- end }}
 {{- end }}
 {{- if .Values.bpf.ctAccounting }}
-  bpf-conntrack-accounting: "{{ .Values.bpf.ctAccounting }}"
+  bpf-conntrack-accounting: "{{ .Values.bpf.ctAccounting | int }}"
 {{- end }}
 {{- if .Values.bpf.natMax }}
   # bpf-nat-global-max specified the maximum number of entries in the
   # BPF NAT table.
-  bpf-nat-global-max: "{{ .Values.bpf.natMax }}"
+  bpf-nat-global-max: "{{ .Values.bpf.natMax | int }}"
 {{- end }}
 {{- if .Values.bpf.neighMax }}
   # bpf-neigh-global-max specified the maximum number of entries in the
   # BPF neighbor table.
-  bpf-neigh-global-max: "{{ .Values.bpf.neighMax }}"
+  bpf-neigh-global-max: "{{ .Values.bpf.neighMax | int }}"
 {{- end }}
 {{- if hasKey .Values.bpf "policyMapMax" }}
   # bpf-policy-map-max specifies the maximum number of entries in endpoint
   # policy map (per endpoint)
-  bpf-policy-map-max: "{{ .Values.bpf.policyMapMax }}"
+  bpf-policy-map-max: "{{ .Values.bpf.policyMapMax | int }}"
 {{- end }}
 {{- if hasKey .Values.bpf "lbMapMax" }}
   # bpf-lb-map-max specifies the maximum number of entries in bpf lb service,
   # backend and affinity maps.
-  bpf-lb-map-max: "{{ .Values.bpf.lbMapMax }}"
+  bpf-lb-map-max: "{{ .Values.bpf.lbMapMax | int }}"
 {{- end }}
 {{- if hasKey .Values.bpf "lbExternalClusterIP" }}
   bpf-lb-external-clusterip: {{ .Values.bpf.lbExternalClusterIP | quote }}
@@ -461,6 +461,7 @@ data:
   bpf-lb-mode-annotation: {{ .Values.bpf.lbModeAnnotation | quote }}
 {{- end }}
 
+  bpf-distributed-lru: {{ .Values.bpf.distributedLRU.enabled | quote }}
   bpf-events-drop-enabled: {{ .Values.bpf.events.drop.enabled | quote }}
   bpf-events-policy-verdict-enabled: {{ .Values.bpf.events.policyVerdict.enabled | quote }}
   bpf-events-trace-enabled: {{ .Values.bpf.events.trace.enabled | quote }}
@@ -513,6 +514,9 @@ data:
 {{- if .Values.tunnelPort }}
   tunnel-port: {{ .Values.tunnelPort | quote }}
 {{- end }}
+{{- if .Values.tunnelSourcePortRange }}
+  tunnel-source-port-range: {{ .Values.tunnelSourcePortRange | quote }}
+{{- end }}
 
 {{- if .Values.serviceNoBackendResponse }}
   service-no-backend-response: "{{ .Values.serviceNoBackendResponse }}"
@@ -927,9 +931,8 @@ data:
   operator-api-serve-addr: {{ $defaultOperatorApiServeAddr | quote }}
 {{- end }}
 
-{{- if .Values.hubble.enabled }}
-  # Enable Hubble gRPC service.
   enable-hubble: {{ .Values.hubble.enabled | quote }}
+{{- if .Values.hubble.enabled }}
   # UNIX domain socket for Hubble server to listen to.
   hubble-socket-path: {{ .Values.hubble.socketPath | quote }}
 {{- if hasKey .Values.hubble "eventQueueSize" }}
@@ -941,7 +944,7 @@ data:
   # Capacity of the buffer to store recent events.
   hubble-event-buffer-capacity: {{ .Values.hubble.eventBufferCapacity | quote }}
 {{- end }}
-{{- if .Values.hubble.metrics.enabled }}
+{{- if or .Values.hubble.metrics.enabled .Values.hubble.metrics.dynamic.enabled}}
   # Address to expose Hubble metrics (e.g. ":7070"). Metrics server will be disabled if this
   # field is not set.
   hubble-metrics-server: ":{{ .Values.hubble.metrics.port }}"
@@ -953,14 +956,20 @@ data:
   hubble-metrics-server-tls-client-ca-files: /var/lib/cilium/tls/hubble-metrics/client-ca.crt
   {{- end }}
   {{- end }}
+{{- end }}
+{{- if .Values.hubble.metrics.enabled }}
   # A space separated list of metrics to enable. See [0] for available metrics.
   #
   # https://github.com/cilium/hubble/blob/master/Documentation/metrics.md
   hubble-metrics: {{- range .Values.hubble.metrics.enabled }}
     {{.}}
+  {{- end}}
+{{- if .Values.hubble.metrics.dynamic.enabled }}
+  hubble-dynamic-metrics-config-path: /dynamic-metrics-config/dynamic-metrics.yaml
 {{- end }}
   enable-hubble-open-metrics: {{ .Values.hubble.metrics.enableOpenMetrics | quote }}
 {{- end }}
+
 {{- if .Values.hubble.redact }}
 {{- if eq .Values.hubble.redact.enabled true }}
   # Enables hubble redact capabilities
@@ -1004,10 +1013,6 @@ data:
   hubble-flowlogs-config-path: /flowlog-config/flowlogs.yaml
 {{- end }}
 {{- end }}
-{{- if .Values.hubble.metrics.dynamic.enabled }}
-  hubble-dynamic-metrics-config-path: /dynamic-metrics-config/dynamic-metrics.yaml
-  hubble-metrics-server: ":{{ .Values.hubble.metrics.port }}"
-{{- end }}
 {{- if hasKey .Values.hubble "listenAddress" }}
   # An additional address for Hubble server to listen to (e.g. ":4244").
   hubble-listen-address: {{ .Values.hubble.listenAddress | quote }}
@@ -1041,8 +1046,8 @@ data:
 {{- else }}
   ipam: {{ $ipam | quote }}
 {{- end }}
-{{- if hasKey .Values.ipam "multiPoolPreAllocation" }}
-  ipam-multi-pool-pre-allocation: {{ .Values.ipam.multiPoolPreAllocation }}
+{{- if .Values.ipam.multiPoolPreAllocation }}
+  ipam-multi-pool-pre-allocation: {{ .Values.ipam.multiPoolPreAllocation | quote }}
 {{- end }}
 
 {{- if .Values.ipam.ciliumNodeUpdateRate }}
@@ -1335,6 +1340,10 @@ data:
   external-envoy-proxy: {{ include "envoyDaemonSetEnabled" . | quote }}
   envoy-base-id: {{ .Values.envoy.baseID | quote }}
 
+{{- if .Values.envoy.policyRestoreTimeoutDuration }}
+  envoy-policy-restore-timeout: {{ .Values.envoy.policyRestoreTimeoutDuration | quote }}
+{{- end }}
+
 {{- if .Values.envoy.log.path }}
   envoy-log: {{ .Values.envoy.log.path | quote }}
 {{- end }}

packages/system/cilium/charts/cilium/templates/cilium-operator/role.yaml

@@ -41,6 +41,9 @@ metadata:
   {{- end }}
   labels:
     app.kubernetes.io/part-of: cilium
+    {{- with .Values.commonLabels }}
+    {{- toYaml . | nindent 4 }}
+    {{- end }}
 rules:
 - apiGroups:
   - ""
@@ -66,6 +69,9 @@ metadata:
   {{- end }}
   labels:
     app.kubernetes.io/part-of: cilium
+    {{- with .Values.commonLabels }}
+    {{- toYaml . | nindent 4 }}
+    {{- end }}
 rules:
 - apiGroups:
   - ""

packages/system/cilium/charts/cilium/templates/cilium-operator/rolebinding.yaml

@@ -7,24 +7,23 @@ kind: RoleBinding
 metadata:
   name: cilium-operator-ingress-secrets
   namespace: {{ .Values.ingressController.secretsNamespace.name | quote }}
-  {{- with .Values.commonLabels }}
   labels:
+    app.kubernetes.io/part-of: cilium
+    {{- with .Values.commonLabels }}
     {{- toYaml . | nindent 4 }}
-  {{- end }}
+    {{- end }}
   {{- with .Values.operator.annotations }}
   annotations:
     {{- toYaml . | nindent 4 }}
   {{- end }}
-  labels:
-    app.kubernetes.io/part-of: cilium
 roleRef:
   apiGroup: rbac.authorization.k8s.io
   kind: Role
   name: cilium-operator-ingress-secrets
 subjects:
-  - kind: ServiceAccount
-    name: {{ .Values.serviceAccounts.operator.name | quote }}
-    namespace: {{ include "cilium.namespace" . }}
+- kind: ServiceAccount
+  name: {{ .Values.serviceAccounts.operator.name | quote }}
+  namespace: {{ include "cilium.namespace" . }}
 {{- end }}
 
 {{- if and .Values.operator.enabled .Values.serviceAccounts.operator.create .Values.gatewayAPI.enabled .Values.gatewayAPI.secretsNamespace.sync .Values.gatewayAPI.secretsNamespace.name }}
@@ -34,12 +33,15 @@ kind: RoleBinding
 metadata:
   name: cilium-operator-gateway-secrets
   namespace: {{ .Values.gatewayAPI.secretsNamespace.name | quote }}
+  labels:
+    app.kubernetes.io/part-of: cilium
+    {{- with .Values.commonLabels }}
+    {{- toYaml . | nindent 4 }}
+    {{- end }}
   {{- with .Values.operator.annotations }}
   annotations:
     {{- toYaml . | nindent 4 }}
   {{- end }}
-  labels:
-    app.kubernetes.io/part-of: cilium
 roleRef:
   apiGroup: rbac.authorization.k8s.io
   kind: Role
@@ -57,12 +59,15 @@ kind: RoleBinding
 metadata:
   name: cilium-operator-tlsinterception-secrets
   namespace: {{ .Values.tls.secretsNamespace.name | quote }}
+  labels:
+    app.kubernetes.io/part-of: cilium
+    {{- with .Values.commonLabels }}
+    {{- toYaml . | nindent 4 }}
+    {{- end }}
   {{- with .Values.operator.annotations }}
   annotations:
     {{- toYaml . | nindent 4 }}
   {{- end }}
-  labels:
-    app.kubernetes.io/part-of: cilium
 roleRef:
   apiGroup: rbac.authorization.k8s.io
   kind: Role

packages/system/cilium/charts/cilium/templates/hubble/servicemonitor.yaml

@@ -1,4 +1,4 @@
-{{- if and .Values.hubble.enabled .Values.hubble.metrics.enabled .Values.hubble.metrics.serviceMonitor.enabled }}
+{{- if and .Values.hubble.enabled (or .Values.hubble.metrics.enabled .Values.hubble.metrics.dynamic.enabled) .Values.hubble.metrics.serviceMonitor.enabled }}
 apiVersion: monitoring.coreos.com/v1
 kind: ServiceMonitor
 metadata:

packages/system/cilium/charts/cilium/templates/spire/server/service.yaml

@@ -4,10 +4,13 @@ kind: Service
 metadata:
   name: spire-server
   namespace: {{ .Values.authentication.mutual.spire.install.namespace }}
-  {{- with .Values.commonLabels }}
   labels:
+    {{- with .Values.commonLabels }}
     {{- toYaml . | nindent 4 }}
-  {{- end }}
+    {{- end }}
+    {{- with .Values.authentication.mutual.spire.install.server.service.labels }}
+    {{- toYaml . | nindent 4 }}
+    {{- end }}
   {{- if or .Values.authentication.mutual.spire.install.server.service.annotations .Values.authentication.mutual.spire.annotations }}
   annotations:
     {{- with .Values.authentication.mutual.spire.annotations }}
@@ -17,10 +20,6 @@ metadata:
       {{- toYaml . | nindent 4 }}
     {{- end }}
   {{- end }}
-  {{- with .Values.authentication.mutual.spire.install.server.service.labels }}
-  labels:
-    {{- toYaml . | nindent 8 }}
-  {{- end }}
 spec:
   type: {{ .Values.authentication.mutual.spire.install.server.service.type }}
   ports:

packages/system/cilium/charts/cilium/templates/spire/server/statefulset.yaml

@@ -4,10 +4,6 @@ kind: StatefulSet
 metadata:
   name: spire-server
   namespace: {{ .Values.authentication.mutual.spire.install.namespace }}
-  {{- with .Values.commonLabels }}
-  labels:
-    {{- toYaml . | nindent 4 }}
-  {{- end }}
   {{- if or .Values.authentication.mutual.spire.install.server.annotations .Values.authentication.mutual.spire.annotations }}
   annotations:
     {{- with .Values.authentication.mutual.spire.annotations }}
@@ -19,9 +15,12 @@ metadata:
   {{- end }}
   labels:
     app: spire-server
-  {{- with .Values.authentication.mutual.spire.install.server.labels }}
+    {{- with .Values.commonLabels }}
     {{- toYaml . | nindent 4 }}
-  {{- end }}
+    {{- end }}
+    {{- with .Values.authentication.mutual.spire.install.server.labels }}
+    {{- toYaml . | nindent 4 }}
+    {{- end }}
 spec:
   replicas: 1
   selector:

packages/system/cilium/charts/cilium/values.schema.json

@@ -519,6 +519,14 @@
         "disableExternalIPMitigation": {
           "type": "boolean"
         },
+        "distributedLRU": {
+          "properties": {
+            "enabled": {
+              "type": "boolean"
+            }
+          },
+          "type": "object"
+        },
         "enableTCX": {
           "type": "boolean"
         },
@@ -2110,6 +2118,12 @@
           },
           "type": "object"
         },
+        "policyRestoreTimeoutDuration": {
+          "type": [
+            "null",
+            "string"
+          ]
+        },
         "priorityClassName": {
           "type": [
             "null",
@@ -5462,6 +5476,9 @@
     "tunnelProtocol": {
       "type": "string"
     },
+    "tunnelSourcePortRange": {
+      "type": "string"
+    },
     "updateStrategy": {
       "properties": {
         "rollingUpdate": {

packages/system/cilium/charts/cilium/values.yaml

@@ -191,10 +191,10 @@ image:
   # @schema
   override: ~
   repository: "quay.io/cilium/cilium"
-  tag: "v1.17.1"
+  tag: "v1.17.2"
   pullPolicy: "IfNotPresent"
   # cilium-digest
-  digest: "sha256:8969bfd9c87cbea91e40665f8ebe327268c99d844ca26d7d12165de07f702866"
+  digest: "sha256:3c4c9932b5d8368619cb922a497ff2ebc8def5f41c18e410bcc84025fcd385b1"
   useDigest: true
 # -- Scheduling configurations for cilium pods
 scheduling:
@@ -495,6 +495,13 @@ bpf:
   # tracking table.
   # @default -- `262144`
   ctAnyMax: ~
+  # -- Control to use a distributed per-CPU backend memory for the core BPF LRU maps
+  # which Cilium uses. This improves performance significantly, but it is also
+  # recommended to increase BPF map sizing along with that.
+  distributedLRU:
+    # -- Enable distributed LRU backend memory. For compatibility with existing
+    # installations it is off by default.
+    enabled: false
   # -- Control events generated by the Cilium datapath exposed to Cilium monitor and Hubble.
   # Helm configuration for BPF events map rate limiting is experimental and might change
   # in upcoming releases.
@@ -1433,9 +1440,9 @@ hubble:
       # @schema
       override: ~
       repository: "quay.io/cilium/hubble-relay"
-      tag: "v1.17.1"
+      tag: "v1.17.2"
       # hubble-relay-digest
-      digest: "sha256:397e8fbb188157f744390a7b272a1dec31234e605bcbe22d8919a166d202a3dc"
+      digest: "sha256:42a8db5c256c516cacb5b8937c321b2373ad7a6b0a1e5a5120d5028433d586cc"
       useDigest: true
       pullPolicy: "IfNotPresent"
     # -- Specifies the resources for the hubble-relay pods
@@ -1684,8 +1691,8 @@ hubble:
         # @schema
         override: ~
         repository: "quay.io/cilium/hubble-ui-backend"
-        tag: "v0.13.1"
-        digest: "sha256:0e0eed917653441fded4e7cdb096b7be6a3bddded5a2dd10812a27b1fc6ed95b"
+        tag: "v0.13.2"
+        digest: "sha256:a034b7e98e6ea796ed26df8f4e71f83fc16465a19d166eff67a03b822c0bfa15"
         useDigest: true
         pullPolicy: "IfNotPresent"
       # -- Hubble-ui backend security context.
@@ -1718,8 +1725,8 @@ hubble:
         # @schema
         override: ~
         repository: "quay.io/cilium/hubble-ui"
-        tag: "v0.13.1"
-        digest: "sha256:e2e9313eb7caf64b0061d9da0efbdad59c6c461f6ca1752768942bfeda0796c6"
+        tag: "v0.13.2"
+        digest: "sha256:9e37c1296b802830834cc87342a9182ccbb71ffebb711971e849221bd9d59392"
         useDigest: true
         pullPolicy: "IfNotPresent"
       # -- Hubble-ui frontend security context.
@@ -2332,6 +2339,11 @@ envoy:
   xffNumTrustedHopsL7PolicyIngress: 0
   # -- Number of trusted hops regarding the x-forwarded-for and related HTTP headers for the egress L7 policy enforcement Envoy listeners.
   xffNumTrustedHopsL7PolicyEgress: 0
+  # @schema
+  # type: [null, string]
+  # @schema
+  # -- Max duration to wait for endpoint policies to be restored on restart. Default "3m".
+  policyRestoreTimeoutDuration: null
   # -- Envoy container image.
   image:
     # @schema
@@ -2339,9 +2351,9 @@ envoy:
     # @schema
     override: ~
     repository: "quay.io/cilium/cilium-envoy"
-    tag: "v1.31.5-1739264036-958bef243c6c66fcfd73ca319f2eb49fff1eb2ae"
+    tag: "v1.31.5-1741765102-efed3defcc70ab5b263a0fc44c93d316b846a211"
     pullPolicy: "IfNotPresent"
-    digest: "sha256:fc708bd36973d306412b2e50c924cd8333de67e0167802c9b48506f9d772f521"
+    digest: "sha256:377c78c13d2731f3720f931721ee309159e782d882251709cb0fac3b42c03f4b"
     useDigest: true
   # -- Additional containers added to the cilium Envoy DaemonSet.
   extraContainers: []
@@ -2605,7 +2617,7 @@ tls:
     # type: [null, boolean]
     # @schema
     # -- Enable synchronization of Secrets for TLS Interception. If disabled and
-    # tls.secretsBackend is set to 'k8s', then secrets will be read directly by the agent.
+    # tls.readSecretsOnlyFromSecretsNamespace is set to 'false', then secrets will be read directly by the agent.
     enabled: ~
   # -- Base64 encoded PEM values for the CA certificate and private key.
   # This can be used as common CA to generate certificates used by hubble and clustermesh components.
@@ -2658,6 +2670,9 @@ routingMode: ""
 # -- Configure VXLAN and Geneve tunnel port.
 # @default -- Port 8472 for VXLAN, Port 6081 for Geneve
 tunnelPort: 0
+# -- Configure VXLAN and Geneve tunnel source port range hint.
+# @default -- 0-0 to let the kernel driver decide the range
+tunnelSourcePortRange: 0-0
 # -- Configure what the response should be to traffic for a service without backends.
 # Possible values:
 #  - reject (default)
@@ -2693,15 +2708,15 @@ operator:
     # @schema
     override: ~
     repository: "quay.io/cilium/operator"
-    tag: "v1.17.1"
+    tag: "v1.17.2"
     # operator-generic-digest
-    genericDigest: "sha256:628becaeb3e4742a1c36c4897721092375891b58bae2bfcae48bbf4420aaee97"
+    genericDigest: "sha256:81f2d7198366e8dec2903a3a8361e4c68d47d19c68a0d42f0b7b6e3f0523f249"
     # operator-azure-digest
-    azureDigest: "sha256:b9e3e3994f5fcf1832e1f344f3b3b544832851b1990f124b2c2c68e3ffe04a9b"
+    azureDigest: "sha256:455fb88b558b1b8ba09d63302ccce76b4930581be89def027184ab04335c20e0"
     # operator-aws-digest
-    awsDigest: "sha256:da74748057c836471bfdc0e65bb29ba0edb82916ec4b99f6a4f002b2fcc849d6"
+    awsDigest: "sha256:955096183e22a203bbb198ca66e3266ce4dbc2b63f1a2fbd03f9373dcd97893c"
     # operator-alibabacloud-digest
-    alibabacloudDigest: "sha256:034b479fba340f9d98510e509c7ce1c36e8889a109d5f1c2240fcb0942bc772c"
+    alibabacloudDigest: "sha256:7cb8c23417f65348bb810fe92fb05b41d926f019d77442f3fa1058d17fea7ffe"
     useDigest: true
     pullPolicy: "IfNotPresent"
     suffix: ""
@@ -2976,9 +2991,9 @@ preflight:
     # @schema
     override: ~
     repository: "quay.io/cilium/cilium"
-    tag: "v1.17.1"
+    tag: "v1.17.2"
     # cilium-digest
-    digest: "sha256:8969bfd9c87cbea91e40665f8ebe327268c99d844ca26d7d12165de07f702866"
+    digest: "sha256:3c4c9932b5d8368619cb922a497ff2ebc8def5f41c18e410bcc84025fcd385b1"
     useDigest: true
     pullPolicy: "IfNotPresent"
   # -- The priority class to use for the preflight pod.
@@ -3125,9 +3140,9 @@ clustermesh:
       # @schema
       override: ~
       repository: "quay.io/cilium/clustermesh-apiserver"
-      tag: "v1.17.1"
+      tag: "v1.17.2"
       # clustermesh-apiserver-digest
-      digest: "sha256:1de22f46bfdd638de72c2224d5223ddc3bbeacda1803cb75799beca3d4bf7a4c"
+      digest: "sha256:981250ebdc6e66e190992eaf75cfca169113a8f08d5c3793fe15822176980398"
       useDigest: true
       pullPolicy: "IfNotPresent"
     # -- TCP port for the clustermesh-apiserver health API.
@@ -3634,7 +3649,7 @@ authentication:
           override: ~
           repository: "docker.io/library/busybox"
           tag: "1.37.0"
-          digest: "sha256:a5d0ce49aa801d475da48f8cb163c354ab95cab073cd3c138bd458fc8257fbf1"
+          digest: "sha256:498a000f370d8c37927118ed80afe8adc38d1edcbfc071627d17b25c88efcab0"
           useDigest: true
           pullPolicy: "IfNotPresent"
         # SPIRE agent configuration

packages/system/cilium/charts/cilium/values.yaml.tmpl

@@ -500,6 +500,13 @@ bpf:
   # tracking table.
   # @default -- `262144`
   ctAnyMax: ~
+  # -- Control to use a distributed per-CPU backend memory for the core BPF LRU maps
+  # which Cilium uses. This improves performance significantly, but it is also
+  # recommended to increase BPF map sizing along with that.
+  distributedLRU:
+      # -- Enable distributed LRU backend memory. For compatibility with existing
+      # installations it is off by default.
+      enabled: false
   # -- Control events generated by the Cilium datapath exposed to Cilium monitor and Hubble.
   # Helm configuration for BPF events map rate limiting is experimental and might change
   # in upcoming releases.
@@ -2351,6 +2358,11 @@ envoy:
   xffNumTrustedHopsL7PolicyIngress: 0
   # -- Number of trusted hops regarding the x-forwarded-for and related HTTP headers for the egress L7 policy enforcement Envoy listeners.
   xffNumTrustedHopsL7PolicyEgress: 0
+  # @schema
+  # type: [null, string]
+  # @schema
+  # -- Max duration to wait for endpoint policies to be restored on restart. Default "3m".
+  policyRestoreTimeoutDuration: null
   # -- Envoy container image.
   image:
     # @schema
@@ -2626,7 +2638,7 @@ tls:
     # type: [null, boolean]
     # @schema
     # -- Enable synchronization of Secrets for TLS Interception. If disabled and
-    # tls.secretsBackend is set to 'k8s', then secrets will be read directly by the agent.
+    # tls.readSecretsOnlyFromSecretsNamespace is set to 'false', then secrets will be read directly by the agent.
     enabled: ~
   # -- Base64 encoded PEM values for the CA certificate and private key.
   # This can be used as common CA to generate certificates used by hubble and clustermesh components.
@@ -2679,6 +2691,9 @@ routingMode: ""
 # -- Configure VXLAN and Geneve tunnel port.
 # @default -- Port 8472 for VXLAN, Port 6081 for Geneve
 tunnelPort: 0
+# -- Configure VXLAN and Geneve tunnel source port range hint.
+# @default -- 0-0 to let the kernel driver decide the range
+tunnelSourcePortRange: 0-0
 # -- Configure what the response should be to traffic for a service without backends.
 # Possible values:
 #  - reject (default)

packages/system/cilium/images/cilium/Dockerfile

@@ -1,2 +1,2 @@
-ARG VERSION=v1.17.1
+ARG VERSION=v1.17.2
 FROM quay.io/cilium/cilium:${VERSION}

packages/system/cilium/values.yaml

@@ -14,7 +14,7 @@ cilium:
     mode: "kubernetes"
   image:
     repository: ghcr.io/cozystack/cozystack/cilium
-    tag: 1.17.1
-    digest: "sha256:ac154cd13711444f9fd1a7c6e947f504c769cc654039b93630ccc0479111f2a3"
+    tag: 1.17.2
+    digest: "sha256:bc6a8ec326188960ac36584873e07801bcbc56cb862e2ec8bf87a7926f66abf1"
   envoy:
     enabled: false

packages/system/cozystack-api/values.yaml

@@ -1,2 +1,2 @@
 cozystackAPI:
-  image: ghcr.io/cozystack/cozystack/cozystack-api:v0.29.1@sha256:3ce1cd4a9c74999b08ee477811bdc048a8b3fc79f214d92db2e81bb3ae0bd516
+  image: ghcr.io/cozystack/cozystack/cozystack-api:v0.30.4@sha256:299b50de88aa945ab90ee41eeb1a0ac7ba20d858adacd1ef125af7d676ce440f

packages/system/cozystack-controller/templates/rbac.yaml

@@ -4,7 +4,7 @@ metadata:
   name: cozystack-controller
 rules:
 - apiGroups: [""]
-  resources: ["configmaps", "pods", "namespaces", "nodes", "services", "persistentvolumes"]
+  resources: ["configmaps", "pods", "namespaces", "nodes", "services", "persistentvolumes", "persistentvolumeclaims"]
   verbs: ["get", "watch", "list"]
 - apiGroups: ['cozystack.io']
   resources: ['*']

packages/system/cozystack-controller/values.yaml

@@ -1,5 +1,5 @@
 cozystackController:
-  image: ghcr.io/cozystack/cozystack/cozystack-controller:v0.29.1@sha256:e06f651a70268d0151c8d475cc1c002a66bb6e60cce7cbe7408403054ed167f7
+  image: ghcr.io/cozystack/cozystack/cozystack-controller:v0.30.4@sha256:a39395a6ce995d91bee8817c4032b8e073e0387f8b1e0de9d78909cb64189f80
   debug: false
   disableTelemetry: false
-  cozystackVersion: "v0.29.1"
+  cozystackVersion: "v0.30.4"

packages/system/dashboard/charts/kubeapps/templates/dashboard/configmap.yaml

@@ -76,7 +76,7 @@ data:
       "kubeappsNamespace": {{ .Release.Namespace | quote }},
       "helmGlobalNamespace": {{ include "kubeapps.helmGlobalPackagingNamespace" . | quote }},
       "carvelGlobalNamespace": {{ .Values.kubeappsapis.pluginConfig.kappController.packages.v1alpha1.globalPackagingNamespace | quote }},
-      "appVersion": "v0.29.1",
+      "appVersion": "v0.30.4",
       "authProxyEnabled": {{ .Values.authProxy.enabled }},
       "oauthLoginURI": {{ .Values.authProxy.oauthLoginURI | quote }},
       "oauthLogoutURI": {{ .Values.authProxy.oauthLogoutURI | quote }},

packages/system/dashboard/values.yaml

@@ -18,14 +18,14 @@ kubeapps:
     image:
       registry: ghcr.io/cozystack/cozystack
       repository: dashboard
-      tag: v0.29.1
+      tag: v0.30.4
       digest: "sha256:a83fe4654f547469cfa469a02bda1273c54bca103a41eb007fdb2e18a7a91e93"
   kubeappsapis:
     image:
       registry: ghcr.io/cozystack/cozystack
       repository: kubeapps-apis
-      tag: v0.29.1
-      digest: "sha256:8cc327760c33a15022b847d3fa8d22b87891e17a74dc56f50f52cae032a81d8c"
+      tag: v0.30.4
+      digest: "sha256:a5ff1d3fdd69c78184554bd07e7675662201d7b27387717b4a70432a81db6301"
     pluginConfig:
       flux:
         packages:

packages/system/gpu-operator/Chart.yaml

@@ -0,0 +1,3 @@
+apiVersion: v2
+name: cozy-gpu-operator
+version: 0.0.0 # Placeholder, the actual version will be automatically set during the build process