remove chaos ai

Signed-off-by: Paige Patton <prubenda@redhat.com>

.coveragerc

@@ -0,0 +1,4 @@
+[run]
+omit =
+    tests/*
+    krkn/tests/**

.github/CODEOWNERS

@@ -0,0 +1 @@
+*   @paigerube14 @tsebastiani @chaitanyaenr

.github/ISSUE_TEMPLATE/bug_report.md

@@ -0,0 +1,43 @@
+---
+name: Bug report
+about: Create a report an issue
+title: "[BUG]"
+labels: bug
+---
+
+# Bug Description
+
+## **Describe the bug**
+
+A clear and concise description of what the bug is.
+
+## **To Reproduce**
+
+Any specific steps used to reproduce the behavior
+
+### Scenario File
+Scenario file(s) that were specified in your config file (can be starred (*) with confidential information )
+```yaml
+<config>
+
+```
+
+### Config File 
+Config file you used when error was seen (the default used is config/config.yaml)
+
+```yaml
+<config>
+
+```
+
+## **Expected behavior**
+
+A clear and concise description of what you expected to happen.
+
+## **Krkn Output**
+
+Krkn output to help show your problem 
+
+## **Additional context**
+
+Add any other context about the problem 

.github/ISSUE_TEMPLATE/feature.md

@@ -0,0 +1,16 @@
+---
+name: New Feature Request
+about: Suggest an idea for this project
+title: ''
+labels: enhancement
+assignees: ''
+---
+
+**Is your feature request related to a problem? Please describe.**
+A clear and concise description of what the problem is. Ex. I'm always frustrated when [...]
+
+**Describe the solution you'd like**
+A clear and concise description of what you want to see added/changed. Ex. new parameter in [xxx] scenario, new scenario that does [xxx]
+
+**Additional context**
+Add any other context about the feature request here.

.github/PULL_REQUEST_TEMPLATE.md

@@ -0,0 +1,47 @@
+# Type of change
+
+- [ ] Refactor
+- [ ] New feature
+- [ ] Bug fix
+- [ ] Optimization
+
+# Description  
+<-- Provide a brief description of the changes made in this PR. -->  
+
+## Related Tickets & Documents
+If no related issue, please create one and start the converasation on wants of 
+
+- Related Issue #: 
+- Closes #: 
+
+# Documentation  
+- [ ] **Is documentation needed for this update?**
+
+If checked, a documentation PR must be created and merged in the [website repository](https://github.com/krkn-chaos/website/).
+
+## Related Documentation PR (if applicable)  
+<-- Add the link to the corresponding documentation PR in the website repository -->  
+
+# Checklist before requesting a review
+[ ] Ensure the changes and proposed solution have been discussed in the relevant issue and have received acknowledgment from the community or maintainers. See [contributing guidelines](https://krkn-chaos.dev/docs/contribution-guidelines/)
+See [testing your changes](https://krkn-chaos.dev/docs/developers-guide/testing-changes/) and run on any Kubernetes or OpenShift cluster to validate your changes
+- [ ] I have performed a self-review of my code by running krkn and specific scenario 
+- [ ] If it is a core feature, I have added thorough unit tests with above 80% coverage
+
+*REQUIRED*:
+Description of combination of tests performed and output of run
+
+```bash
+python run_kraken.py
+...
+<---insert test results output--->
+```
+
+OR
+
+
+```bash
+python -m coverage run -a -m unittest discover -s tests -v
+...
+<---insert test results output--->
+```

.github/release-template.md

@@ -0,0 +1,7 @@
+## Release {VERSION}
+
+### Download Artifacts
+- 📦 Krkn sources (noarch): [krkn-{VERSION}-src.tar.gz](https://krkn-chaos.gateway.scarf.sh/krkn-src-{VERSION}.tar.gz)
+
+### Changes
+{CHANGES}

.github/workflows/release.yml

@@ -0,0 +1,60 @@
+name: Create Release
+on:
+  push:
+    tags:
+      - 'v*'
+jobs:
+  release:
+    permissions:
+      contents: write
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+      - name: calculate previous tag
+        run: |
+          git fetch --tags origin
+          PREVIOUS_TAG=$(git tag --sort=-creatordate | sed -n '2 p')
+          echo $PREVIOUS_TAG 
+          echo "PREVIOUS_TAG=$PREVIOUS_TAG" >> "$GITHUB_ENV"
+
+      - name: generate release notes from template
+        id: release-notes
+        env:
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+        run: |
+          NOTES=$(gh api \
+          --method POST \
+          -H "Accept: application/vnd.github+json" \
+          -H "X-GitHub-Api-Version: 2022-11-28" \
+          /repos/krkn-chaos/krkn/releases/generate-notes \
+          -f "tag_name=${{ github.ref_name }}" -f "target_commitish=main" -f "previous_tag_name=${{ env.PREVIOUS_TAG }}" | jq -r .body)
+          echo "NOTES<<EOF" >> $GITHUB_ENV
+          echo "$NOTES" >> $GITHUB_ENV
+          echo "EOF" >> $GITHUB_ENV
+
+      - name: replace placeholders in template
+        run: |
+          echo "${{ env.NOTES }}"
+          TEMPLATE=$(cat .github/release-template.md)
+          VERSION=${{ github.ref_name }}
+          NOTES="${{ env.NOTES }}"
+          OUTPUT=${TEMPLATE//\{VERSION\}/$VERSION}
+          OUTPUT=${OUTPUT//\{CHANGES\}/$NOTES}
+          echo "$OUTPUT" > release-notes.md
+      - name: create release
+        env:
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+        run: |
+          gh release create ${{ github.ref_name }} --title "${{ github.ref_name }}"  -F release-notes.md
+
+      - name: Install Syft
+        run: |
+          curl -sSfL https://raw.githubusercontent.com/anchore/syft/main/install.sh | sudo sh -s -- -b /usr/local/bin
+
+      - name: Generate SBOM
+        env:
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+        run: |
+          syft . --scope all-layers --output cyclonedx-json > sbom.json
+          echo "SBOM generated successfully!"
+          gh release upload ${{ github.ref_name }} sbom.json

.github/workflows/require-docs.yml

@@ -0,0 +1,45 @@
+name: Require Documentation Update
+on:
+  pull_request:
+    types: [opened, edited, synchronize]
+    branches:
+        - main
+jobs:
+  check-docs:
+    name: Check Documentation Update
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v4
+
+      - name: Check if Documentation is Required
+        id: check_docs
+        run: |
+          echo "Checking PR body for documentation checkbox..."
+          # Read the PR body from the GitHub event payload
+          if echo "${{ github.event.pull_request.body }}" | grep -qi '\[x\].*documentation needed'; then
+            echo "Documentation required detected."
+            echo "docs_required=true" >> $GITHUB_OUTPUT
+          else
+            echo "Documentation not required."
+            echo "docs_required=false" >> $GITHUB_OUTPUT
+          fi
+
+      - name: Enforce Documentation Update (if required)
+        if: steps.check_docs.outputs.docs_required == 'true'
+        env:
+          GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+        run: |
+          # Retrieve feature branch and repository owner from the GitHub context
+          FEATURE_BRANCH="${{ github.head_ref }}"
+          REPO_OWNER="${{ github.repository_owner }}"
+          WEBSITE_REPO="website"
+          echo "Searching for a merged documentation PR for feature branch: $FEATURE_BRANCH in $REPO_OWNER/$WEBSITE_REPO..."
+          MERGED_PR=$(gh pr list --repo "$REPO_OWNER/$WEBSITE_REPO" --state merged --json headRefName,title,url | jq -r \
+            --arg FEATURE_BRANCH "$FEATURE_BRANCH" '.[] | select(.title | contains($FEATURE_BRANCH)) | .url')
+          if [[ -z "$MERGED_PR" ]]; then
+            echo ":x: Documentation PR for branch '$FEATURE_BRANCH' is required and has not been merged."
+            exit 1
+          else
+            echo ":white_check_mark: Found merged documentation PR: $MERGED_PR"
+          fi

.github/workflows/stale.yml

@@ -0,0 +1,52 @@
+name: Manage Stale Issues and Pull Requests
+
+on:
+  schedule:
+    # Run daily at 1:00 AM UTC
+    - cron: '0 1 * * *'
+  workflow_dispatch: 
+
+permissions:
+  issues: write
+  pull-requests: write
+
+jobs:
+  stale:
+    name: Mark and Close Stale Issues and PRs
+    runs-on: ubuntu-latest
+    steps:
+      - name: Mark and close stale issues and PRs
+        uses: actions/stale@v9
+        with:
+          days-before-issue-stale: 60
+          days-before-issue-close: 14
+          stale-issue-label: 'stale'
+          stale-issue-message: |
+            This issue has been automatically marked as stale because it has not had any activity in the last 60 days.
+            It will be closed in 14 days if no further activity occurs.
+            If this issue is still relevant, please leave a comment or remove the stale label.
+            Thank you for your contributions to krkn!
+          close-issue-message: |
+            This issue has been automatically closed due to inactivity.
+            If you believe this issue is still relevant, please feel free to reopen it or create a new issue with updated information.
+            Thank you for your understanding!
+          close-issue-reason: 'not_planned'
+
+          days-before-pr-stale: 90
+          days-before-pr-close: 14
+          stale-pr-label: 'stale'
+          stale-pr-message: |
+            This pull request has been automatically marked as stale because it has not had any activity in the last 90 days.
+            It will be closed in 14 days if no further activity occurs.
+            If this PR is still relevant, please rebase it, address any pending reviews, or leave a comment.
+            Thank you for your contributions to krkn!
+          close-pr-message: |
+            This pull request has been automatically closed due to inactivity.
+            If you believe this PR is still relevant, please feel free to reopen it or create a new pull request with updated changes.
+            Thank you for your understanding!
+
+          # Exempt labels
+          exempt-issue-labels: 'bug,enhancement,good first issue'
+          exempt-pr-labels: 'pending discussions,hold'
+
+          remove-stale-when-updated: true

.github/workflows/tests.yml

@@ -14,46 +14,51 @@ jobs:
         uses: actions/checkout@v3
       - name: Create multi-node KinD cluster
         uses: redhat-chaos/actions/kind@main
-      - name: Install Helm & add repos
-        run: |
-          curl https://raw.githubusercontent.com/helm/helm/main/scripts/get-helm-3 | bash
-          helm repo add prometheus-community https://prometheus-community.github.io/helm-charts
-          helm repo add stable https://charts.helm.sh/stable
-          helm repo update
       - name: Deploy prometheus & Port Forwarding
+        uses: redhat-chaos/actions/prometheus@main
+      - name: Deploy Elasticsearch
+        with:
+          ELASTIC_PORT: ${{ env.ELASTIC_PORT }}
+          RUN_ID: ${{ github.run_id }}
+        uses: redhat-chaos/actions/elastic@main
+      - name: Download elastic password
+        uses: actions/download-artifact@v4
+        with:
+          name: elastic_password_${{ github.run_id }}
+      - name: Set elastic password on env
         run: |
-          kubectl create namespace prometheus-k8s
-          helm install \
-          --wait --timeout 360s \
-          kind-prometheus \
-          prometheus-community/kube-prometheus-stack \
-          --namespace prometheus-k8s \
-          --set prometheus.service.nodePort=30000 \
-          --set prometheus.service.type=NodePort \
-          --set grafana.service.nodePort=31000 \
-          --set grafana.service.type=NodePort \
-          --set alertmanager.service.nodePort=32000 \
-          --set alertmanager.service.type=NodePort \
-          --set prometheus-node-exporter.service.nodePort=32001 \
-          --set prometheus-node-exporter.service.type=NodePort
-
-          SELECTOR=`kubectl -n prometheus-k8s get service kind-prometheus-kube-prome-prometheus -o wide --no-headers=true | awk '{ print $7 }'`
-          POD_NAME=`kubectl -n prometheus-k8s get pods --selector="$SELECTOR" --no-headers=true | awk '{ print $1 }'`
-          kubectl -n prometheus-k8s port-forward $POD_NAME 9090:9090 &
-          sleep 5
+          ELASTIC_PASSWORD=$(cat elastic_password.txt)
+          echo "ELASTIC_PASSWORD=$ELASTIC_PASSWORD" >> "$GITHUB_ENV"
       - name: Install Python
         uses: actions/setup-python@v4
         with:
-          python-version: '3.9'
+          python-version: '3.11'
           architecture: 'x64'
       - name: Install environment
         run: |
           sudo apt-get install build-essential python3-dev
           pip install --upgrade pip
           pip install -r requirements.txt
+          pip install coverage
 
       - name: Deploy test workloads
         run: |
+          es_pod_name=$(kubectl get pods -l "app=elasticsearch-master" -o name)
+          echo "POD_NAME: $es_pod_name"
+          kubectl --namespace default port-forward $es_pod_name 9200 &
+          prom_name=$(kubectl get pods -n monitoring -l "app.kubernetes.io/name=prometheus" -o name)
+          kubectl --namespace monitoring port-forward $prom_name 9090 &
+
+          # Wait for Elasticsearch to be ready
+          echo "Waiting for Elasticsearch to be ready..."
+          for i in {1..30}; do
+            if curl -k -s -u elastic:$ELASTIC_PASSWORD https://localhost:9200/_cluster/health > /dev/null 2>&1; then
+              echo "Elasticsearch is ready!"
+              break
+            fi
+            echo "Attempt $i: Elasticsearch not ready yet, waiting..."
+            sleep 2
+          done
           kubectl apply -f CI/templates/outage_pod.yaml
           kubectl wait --for=condition=ready pod -l scenario=outage --timeout=300s
           kubectl apply -f CI/templates/container_scenario_pod.yaml
@@ -63,31 +68,39 @@ jobs:
           kubectl wait --for=condition=ready pod -l scenario=time-skew --timeout=300s
           kubectl apply -f CI/templates/service_hijacking.yaml
           kubectl wait --for=condition=ready pod -l "app.kubernetes.io/name=proxy" --timeout=300s
+          kubectl apply -f CI/legacy/scenarios/volume_scenario.yaml
+          kubectl wait --for=condition=ready pod kraken-test-pod -n kraken --timeout=300s
       - name: Get Kind nodes
         run: |
           kubectl get nodes --show-labels=true
       # Pull request only steps
       - name: Run unit tests
-        if: github.event_name == 'pull_request'
         run: python -m coverage run -a -m unittest discover -s tests -v
 
-      - name: Setup Pull Request Functional Tests
-        if: |
-          github.event_name == 'pull_request'
+      - name: Setup Functional Tests
         run: |
-            yq -i '.kraken.port="8081"' CI/config/common_test_config.yaml
-            yq -i '.kraken.signal_address="0.0.0.0"' CI/config/common_test_config.yaml
             yq -i '.kraken.performance_monitoring="localhost:9090"' CI/config/common_test_config.yaml
-            echo "test_service_hijacking" > ./CI/tests/functional_tests
+            yq -i '.elastic.elastic_port=9200' CI/config/common_test_config.yaml
+            yq -i '.elastic.elastic_url="https://localhost"' CI/config/common_test_config.yaml
+            yq -i '.elastic.enable_elastic=False' CI/config/common_test_config.yaml
+            yq -i '.elastic.password="${{env.ELASTIC_PASSWORD}}"' CI/config/common_test_config.yaml
+            yq -i '.performance_monitoring.prometheus_url="http://localhost:9090"' CI/config/common_test_config.yaml
             echo "test_app_outages" >> ./CI/tests/functional_tests
-            echo "test_container"      >> ./CI/tests/functional_tests
-            echo "test_namespace"      >> ./CI/tests/functional_tests
-            echo "test_net_chaos"      >> ./CI/tests/functional_tests
-            echo "test_time"           >> ./CI/tests/functional_tests
-            echo "test_arca_cpu_hog" >> ./CI/tests/functional_tests
-            echo "test_arca_memory_hog" >> ./CI/tests/functional_tests
-            echo "test_arca_io_hog" >> ./CI/tests/functional_tests
-
+            echo "test_container" >> ./CI/tests/functional_tests
+            echo "test_cpu_hog" >> ./CI/tests/functional_tests
+            echo "test_customapp_pod" >> ./CI/tests/functional_tests
+            echo "test_io_hog" >> ./CI/tests/functional_tests
+            echo "test_memory_hog" >> ./CI/tests/functional_tests
+            echo "test_namespace" >> ./CI/tests/functional_tests
+            echo "test_net_chaos" >> ./CI/tests/functional_tests
+            echo "test_node" >> ./CI/tests/functional_tests
+            echo "test_pod" >> ./CI/tests/functional_tests
+            echo "test_pod_error" >> ./CI/tests/functional_tests
+            echo "test_service_hijacking" >> ./CI/tests/functional_tests
+            echo "test_pod_network_filter" >> ./CI/tests/functional_tests
+            echo "test_pod_server" >> ./CI/tests/functional_tests
+            echo "test_time" >> ./CI/tests/functional_tests
+            # echo "test_pvc" >> ./CI/tests/functional_tests
 
       # Push on main only steps + all other functional to collect coverage
       # for the badge
@@ -101,22 +114,9 @@ jobs:
       - name: Setup Post Merge Request Functional Tests
         if: github.ref == 'refs/heads/main' && github.event_name == 'push'
         run: |
-          yq -i '.kraken.port="8081"' CI/config/common_test_config.yaml
-          yq -i '.kraken.signal_address="0.0.0.0"' CI/config/common_test_config.yaml
-          yq -i '.kraken.performance_monitoring="localhost:9090"' CI/config/common_test_config.yaml
           yq -i '.telemetry.username="${{secrets.TELEMETRY_USERNAME}}"' CI/config/common_test_config.yaml
           yq -i '.telemetry.password="${{secrets.TELEMETRY_PASSWORD}}"' CI/config/common_test_config.yaml
-          echo "test_telemetry" > ./CI/tests/functional_tests
-          echo "test_service_hijacking" >> ./CI/tests/functional_tests
-          echo "test_app_outages" >> ./CI/tests/functional_tests
-          echo "test_container"      >> ./CI/tests/functional_tests
-          echo "test_namespace"      >> ./CI/tests/functional_tests
-          echo "test_net_chaos"      >> ./CI/tests/functional_tests
-          echo "test_time"           >> ./CI/tests/functional_tests
-          echo "test_arca_cpu_hog" >> ./CI/tests/functional_tests
-          echo "test_arca_memory_hog" >> ./CI/tests/functional_tests
-          echo "test_arca_io_hog" >> ./CI/tests/functional_tests
-
+          echo "test_telemetry" >> ./CI/tests/functional_tests
       # Final common steps
       - name: Run Functional tests
         env:
@@ -126,33 +126,40 @@ jobs:
           cat ./CI/results.markdown >> $GITHUB_STEP_SUMMARY
           echo >> $GITHUB_STEP_SUMMARY
       - name: Upload CI logs
+        if: ${{ always() }}
         uses: actions/upload-artifact@v4
         with:
           name: ci-logs
           path: CI/out
           if-no-files-found: error
       - name: Collect coverage report
+        if: ${{ always() }}
         run: |
           python -m coverage html
           python -m coverage json
       - name: Publish coverage report to job summary
+        if: ${{ always() }}
         run: |
           pip install html2text
           html2text --ignore-images --ignore-links -b 0 htmlcov/index.html >> $GITHUB_STEP_SUMMARY
       - name: Upload coverage data
+        if: ${{ always() }}
         uses: actions/upload-artifact@v4
         with:
           name: coverage
           path: htmlcov
           if-no-files-found: error
       - name: Upload json coverage
+        if: ${{ always() }}
         uses: actions/upload-artifact@v4
         with:
           name: coverage.json
           path: coverage.json
           if-no-files-found: error
       - name: Check CI results
-        run: grep Fail CI/results.markdown && false || true
+        if: ${{ always() }}
+        run: "! grep Fail CI/results.markdown"
+
   badge:
     permissions:
       contents: write
@@ -175,7 +182,7 @@ jobs:
         - name: Set up Python
           uses: actions/setup-python@v4
           with:
-            python-version: 3.9
+            python-version: '3.11'
         - name: Copy badge on GitHub Page Repo
           env:
             COLOR: yellow
@@ -192,7 +199,8 @@ jobs:
             cd krkn-lib-docs
             git add .
             git config user.name "krkn-chaos"
-            git config user.email "<>"
+            git config user.email "krkn-actions@users.noreply.github.com"
             git commit -m "[KRKN] Coverage Badge ${GITHUB_REF##*/}" || echo "no changes to commit"
             git push
       
+      

ADOPTERS.md

@@ -0,0 +1,9 @@
+# Krkn Adopters
+
+This is a list of organizations that have publicly acknowledged usage of Krkn and shared details of how they are leveraging it in their environment for chaos engineering use cases. Do you want to add yourself to this list? Please fork the repository and open a PR with the required change. 
+
+| Organization | Since | Website | Use-Case |
+|:-|:-|:-|:-|
+| MarketAxess | 2024 | https://www.marketaxess.com/ | Kraken enables us to achieve our goal of increasing the reliability of our cloud products on Kubernetes. The tool allows us to automatically run various chaos scenarios, identify resilience and performance bottlenecks, and seamlessly restore the system to its original state once scenarios finish. These chaos scenarios include pod disruptions, node (EC2) outages, simulating availability zone (AZ) outages, and filling up storage spaces like EBS and EFS. The community is highly responsive to requests and works on expanding the tool's capabilities. MarketAxess actively contributes to the project, adding features such as the ability to leverage existing network ACLs and proposing several feature improvements to enhance test coverage. |
+| Red Hat Openshift | 2020 | https://www.redhat.com/ | Kraken is a highly reliable chaos testing tool used to ensure the quality and resiliency of Red Hat Openshift. The engineering team runs all the test scenarios under Kraken on different cloud platforms on both self-managed and cloud services environments prior to the release of a new version of the product. The team also contributes to the Kraken project consistently which helps the test scenarios to keep up with the new features introduced to the product. Inclusion of this test coverage has contributed to gaining the trust of new and existing customers of the product.   |
+| IBM | 2023 | https://www.ibm.com/ | While working on AI for Chaos Testing at IBM Research, we closely collaborated with the Kraken (Krkn) team to advance intelligent chaos engineering. Our contributions included developing AI-enabled chaos injection strategies and integrating reinforcement learning (RL)-based fault search techniques into the Krkn tool, enabling it to identify and explore system vulnerabilities more efficiently. Kraken stands out as one of the most user-friendly and effective tools for chaos engineering, and the Kraken team’s deep technical involvement played a crucial role in the success of this collaboration—helping bridge cutting-edge AI research with practical, real-world system reliability testing.   |

CI/config/common_test_config.yaml

@@ -2,26 +2,30 @@ kraken:
     distribution: kubernetes                                # Distribution can be kubernetes or openshift.
     kubeconfig_path: ~/.kube/config                        # Path to kubeconfig.
     exit_on_failure: False                                 # Exit when a post action scenario fails.
-    litmus_version: v1.13.6                                # Litmus version to install.
-    litmus_uninstall: False                                # If you want to uninstall litmus if failure.
+    publish_kraken_status: True                            # Can be accessed at http://0.0.0.0:8081
+    signal_state: RUN                                      # Will wait for the RUN signal when set to PAUSE before running the scenarios, refer docs/signal.md for more details
+    signal_address: 0.0.0.0                                # Signal listening address
+    port: 8081                                             # Signal port
+    auto_rollback: True                                    # Enable auto rollback for scenarios.
+    rollback_versions_directory: /tmp/kraken-rollback      # Directory to store rollback version files.
     chaos_scenarios:                                       # List of policies/chaos scenarios to load.
         -   $scenario_type:                                # List of chaos pod scenarios to load.
             - $scenario_file
-              $post_config
 cerberus:
     cerberus_enabled: False                                # Enable it when cerberus is previously installed.
     cerberus_url:                                          # When cerberus_enabled is set to True, provide the url where cerberus publishes go/no-go signal.
 
 performance_monitoring:
-    deploy_dashboards: False                               # Install a mutable grafana and load the performance dashboards. Enable this only when running on OpenShift.
-    repo: "https://github.com/cloud-bulldozer/performance-dashboards.git"
     capture_metrics: False
     metrics_profile_path: config/metrics-aggregated.yaml
     prometheus_url:                                        # The prometheus url/route is automatically obtained in case of OpenShift, please set it when the distribution is Kubernetes.
     prometheus_bearer_token:                               # The bearer token is automatically obtained in case of OpenShift, please set it when the distribution is Kubernetes. This is needed to authenticate with prometheus.
     uuid:                                                  # uuid for the run is generated by default if not set.
-    enable_alerts: False                                   # Runs the queries specified in the alert profile and displays the info or exits 1 when severity=error.
-    alert_profile: config/alerts.yaml                           # Path to alert profile with the prometheus queries.
+    enable_alerts: True                                  # Runs the queries specified in the alert profile and displays the info or exits 1 when severity=error
+    enable_metrics: True
+    alert_profile: config/alerts.yaml                          # Path or URL to alert profile with the prometheus queries
+    metrics_profile: config/metrics-report.yaml
+    check_critical_alerts: True                           # Path to alert profile with the prometheus queries.
 
 tunings:
     wait_duration: 6                                       # Duration to wait between each chaos scenario.
@@ -32,13 +36,13 @@ telemetry:
     api_url: https://yvnn4rfoi7.execute-api.us-west-2.amazonaws.com/test #telemetry service endpoint
     username: $TELEMETRY_USERNAME                                      # telemetry service username
     password: $TELEMETRY_PASSWORD                                      # telemetry service password
-    prometheus_namespace: 'prometheus-k8s'                                # prometheus namespace
+    prometheus_namespace: 'monitoring'                                # prometheus namespace
     prometheus_pod_name: 'prometheus-kind-prometheus-kube-prome-prometheus-0'                                 # prometheus pod_name
     prometheus_container_name: 'prometheus'
     prometheus_backup: True                                 # enables/disables prometheus data collection
     full_prometheus_backup: False                           # if is set to False only the /prometheus/wal folder will be downloaded.
     backup_threads: 5                                       # number of telemetry download/upload threads
-    archive_path: /tmp                                      # local path where the archive files will be temporarly stored
+    archive_path: /tmp                                      # local path where the archive files will be temporarily stored
     max_retries: 0                                          # maximum number of upload retries (if 0 will retry forever)
     run_tag: ''                                             # if set, this will be appended to the run folder in the bucket (useful to group the runs)
     archive_size: 10000                                     # the size of the prometheus data archive size in KB. The lower the size of archive is
@@ -52,8 +56,6 @@ telemetry:
     telemetry_group: "funtests"
 elastic:
     enable_elastic: False
-    collect_metrics: False
-    collect_alerts: False
     verify_certs: False
     elastic_url: "https://192.168.39.196"                                         # To track results in elasticsearch, give url to server here; will post telemetry details when url and index not blank
     elastic_port: 32766
@@ -62,3 +64,11 @@ elastic:
     metrics_index: "krkn-metrics"
     alerts_index: "krkn-alerts"
     telemetry_index: "krkn-telemetry"
+
+health_checks:                                              # Utilizing health check endpoints to observe application behavior during chaos injection.
+    interval:                                               # Interval in seconds to perform health checks, default value is 2 seconds
+    config:                                                 # Provide list of health check configurations for applications
+        - url:                                              # Provide application endpoint
+          bearer_token:                                     # Bearer token for authentication if any
+          auth:                                             # Provide authentication credentials (username , password) in tuple format if any, ex:("admin","secretpassword")
+          exit_on_failure:                                  # If value is True exits when health check failed for application, values can be True/False

CI/legacy/scenarios/volume_scenario.yaml

@@ -45,15 +45,45 @@ metadata:
   name: kraken-test-pod
   namespace: kraken
 spec:
+  securityContext:
+    fsGroup: 1001
+  # initContainer to fix permissions on the mounted volume
+  initContainers:
+    - name: fix-permissions
+      image: 'quay.io/centos7/httpd-24-centos7:centos7'
+      command:
+        - sh
+        - -c
+        - |
+          echo "Setting up permissions for /home/kraken..."
+          # Create the directory if it doesn't exist
+          mkdir -p /home/kraken
+          # Set ownership to user 1001 and group 1001
+          chown -R 1001:1001 /home/kraken
+          # Set permissions to allow read/write
+          chmod -R 755 /home/kraken
+          rm -rf /home/kraken/*
+          echo "Permissions fixed. Current state:"
+          ls -la /home/kraken
+      volumeMounts:
+        - mountPath: "/home/kraken"
+          name: kraken-test-pv
+      securityContext:
+        runAsUser: 0  # Run as root to fix permissions
   volumes:
     - name: kraken-test-pv
       persistentVolumeClaim:
         claimName: kraken-test-pvc
   containers:
     - name: kraken-test-container
-      image: 'quay.io/centos7/httpd-24-centos7:latest'
-      volumeMounts:
-        - mountPath: "/home/krake-dir/"
-          name: kraken-test-pv
+      image: 'quay.io/centos7/httpd-24-centos7:centos7'
       securityContext:
-        privileged: true
+        runAsUser: 1001
+        runAsNonRoot: true
+        allowPrivilegeEscalation: false
+        capabilities:
+          drop:
+            - ALL
+      volumeMounts:
+        - mountPath: "/home/kraken"
+          name: kraken-test-pv

CI/templates/outage_pod.yaml

@@ -8,9 +8,9 @@ spec:
   hostNetwork: true
   containers:
   - name: fedtools
-    image: docker.io/fedora/tools
+    image: quay.io/krkn-chaos/krkn:tools
     command:
     - /bin/sh
     - -c
     - |
-      sleep infinity
+      sleep infinity

CI/templates/pod_network_filter.yaml

@@ -0,0 +1,29 @@
+apiVersion: v1
+kind: Pod
+metadata:
+  name: pod-network-filter-test
+  labels:
+    app.kubernetes.io/name: pod-network-filter
+spec:
+  containers:
+  - name: nginx
+    image: quay.io/krkn-chaos/krkn-funtests:pod-network-filter
+    ports:
+      - containerPort: 5000
+        name: pod-network-prt
+
+---
+apiVersion: v1
+kind: Service
+metadata:
+  name: pod-network-filter-service
+spec:
+  selector:
+    app.kubernetes.io/name: pod-network-filter
+  type: NodePort
+  ports:
+  - name: pod-network-filter-svc
+    protocol: TCP
+    port: 80
+    targetPort: pod-network-prt
+    nodePort: 30037

CI/templates/time_pod.yaml

@@ -8,9 +8,9 @@ spec:
   hostNetwork: true
   containers:
   - name: fedtools
-    image: docker.io/fedora/tools
+    image: quay.io/krkn-chaos/krkn:tools
     command:
     - /bin/sh
     - -c
     - |
-      sleep infinity
+      sleep infinity

CI/tests/test_app_outages.sh

@@ -13,7 +13,13 @@ function functional_test_app_outage {
   export scenario_type="application_outages_scenarios"
   export scenario_file="scenarios/openshift/app_outage.yaml"
   export post_config=""
+
+  kubectl get services -A 
+
+  kubectl get pods 
   envsubst < CI/config/common_test_config.yaml > CI/config/app_outage.yaml
+  cat $scenario_file
+  cat CI/config/app_outage.yaml
   python3 -m coverage run -a run_kraken.py -c CI/config/app_outage.yaml
   echo "App outage scenario test: Success"
 }

CI/tests/test_arca_cpu_hog.sh

@@ -1,19 +0,0 @@
-set -xeEo pipefail
-
-source CI/tests/common.sh
-
-trap error ERR
-trap finish EXIT
-
-
-function functional_test_arca_cpu_hog {
-  yq -i '.input_list[0].node_selector={"kubernetes.io/hostname":"kind-worker2"}' scenarios/kube/cpu-hog/input.yaml
-  export scenario_type="hog_scenarios"
-  export scenario_file="scenarios/kube/cpu-hog/input.yaml"
-  export post_config=""
-  envsubst < CI/config/common_test_config.yaml > CI/config/arca_cpu_hog.yaml
-  python3 -m coverage run -a run_kraken.py -c CI/config/arca_cpu_hog.yaml
-  echo "Arcaflow CPU Hog: Success"
-}
-
-functional_test_arca_cpu_hog

CI/tests/test_arca_io_hog.sh

@@ -1,19 +0,0 @@
-set -xeEo pipefail
-
-source CI/tests/common.sh
-
-trap error ERR
-trap finish EXIT
-
-
-function functional_test_arca_io_hog {
-  yq -i '.input_list[0].node_selector={"kubernetes.io/hostname":"kind-worker2"}' scenarios/kube/io-hog/input.yaml
-  export scenario_type="hog_scenarios"
-  export scenario_file="scenarios/kube/io-hog/input.yaml"
-  export post_config=""
-  envsubst < CI/config/common_test_config.yaml > CI/config/arca_io_hog.yaml
-  python3 -m coverage run -a run_kraken.py -c CI/config/arca_io_hog.yaml
-  echo "Arcaflow IO Hog: Success"
-}
-
-functional_test_arca_io_hog

CI/tests/test_arca_memory_hog.sh

@@ -1,19 +0,0 @@
-set -xeEo pipefail
-
-source CI/tests/common.sh
-
-trap error ERR
-trap finish EXIT
-
-
-function functional_test_arca_memory_hog {
-  yq -i '.input_list[0].node_selector={"kubernetes.io/hostname":"kind-worker2"}' scenarios/kube/memory-hog/input.yaml
-  export scenario_type="hog_scenarios"
-  export scenario_file="scenarios/kube/memory-hog/input.yaml"
-  export post_config=""
-  envsubst < CI/config/common_test_config.yaml > CI/config/arca_memory_hog.yaml
-  python3 -m coverage run -a run_kraken.py -c CI/config/arca_memory_hog.yaml
-  echo "Arcaflow Memory Hog: Success"
-}
-
-functional_test_arca_memory_hog

CI/tests/test_container.sh

@@ -16,8 +16,10 @@ function functional_test_container_crash {
   export post_config=""
   envsubst < CI/config/common_test_config.yaml > CI/config/container_config.yaml
 
-  python3 -m coverage run -a run_kraken.py -c CI/config/container_config.yaml
+  python3 -m coverage run -a run_kraken.py -c CI/config/container_config.yaml -d True
   echo "Container scenario test: Success"
+
+  kubectl get pods -n kube-system -l component=etcd
 }
 
 functional_test_container_crash

CI/tests/test_cpu_hog.sh

@@ -0,0 +1,20 @@
+set -xeEo pipefail
+
+source CI/tests/common.sh
+
+trap error ERR
+trap finish EXIT
+
+
+function functional_test_cpu_hog {
+  yq -i '."node-selector"="kubernetes.io/hostname=kind-worker2"' scenarios/kube/cpu-hog.yml
+
+  export scenario_type="hog_scenarios"
+  export scenario_file="scenarios/kube/cpu-hog.yml"
+  export post_config=""
+  envsubst < CI/config/common_test_config.yaml > CI/config/cpu_hog.yaml
+  python3 -m coverage run -a run_kraken.py -c CI/config/cpu_hog.yaml
+  echo "CPU Hog: Success"
+}
+
+functional_test_cpu_hog

CI/tests/test_customapp_pod.sh

@@ -0,0 +1,18 @@
+set -xeEo pipefail
+
+source CI/tests/common.sh
+
+trap error ERR
+trap finish EXIT
+
+function functional_test_customapp_pod_node_selector {
+  export scenario_type="pod_disruption_scenarios"
+  export scenario_file="scenarios/openshift/customapp_pod.yaml"
+  export post_config=""
+  envsubst < CI/config/common_test_config.yaml > CI/config/customapp_pod_config.yaml
+
+  python3 -m coverage run -a run_kraken.py -c CI/config/customapp_pod_config.yaml -d True
+  echo "Pod disruption with node_label_selector test: Success"
+}
+
+functional_test_customapp_pod_node_selector

CI/tests/test_io_hog.sh

@@ -0,0 +1,20 @@
+set -xeEo pipefail
+
+source CI/tests/common.sh
+
+trap error ERR
+trap finish EXIT
+
+function functional_test_io_hog {
+  yq -i '."node-selector"="kubernetes.io/hostname=kind-worker2"' scenarios/kube/io-hog.yml
+  export scenario_type="hog_scenarios"
+  export scenario_file="scenarios/kube/io-hog.yml"
+  export post_config=""
+
+  cat $scenario_file
+  envsubst < CI/config/common_test_config.yaml > CI/config/io_hog.yaml
+  python3 -m coverage run -a run_kraken.py -c CI/config/io_hog.yaml
+  echo "IO Hog: Success"
+}
+
+functional_test_io_hog

CI/tests/test_memory_hog.sh

@@ -0,0 +1,19 @@
+set -xeEo pipefail
+
+source CI/tests/common.sh
+
+trap error ERR
+trap finish EXIT
+
+
+function functional_test_memory_hog {
+  yq -i '."node-selector"="kubernetes.io/hostname=kind-worker2"' scenarios/kube/memory-hog.yml
+  export scenario_type="hog_scenarios"
+  export scenario_file="scenarios/kube/memory-hog.yml"
+  export post_config=""
+  envsubst < CI/config/common_test_config.yaml > CI/config/memory_hog.yaml
+  python3 -m coverage run -a run_kraken.py -c CI/config/memory_hog.yaml
+  echo "Memory Hog: Success"
+}
+
+functional_test_memory_hog

CI/tests/test_node.sh

@@ -0,0 +1,18 @@
+uset -xeEo pipefail
+
+source CI/tests/common.sh
+
+trap error ERR
+trap finish EXIT
+
+function functional_test_node_stop_start {
+  export scenario_type="node_scenarios"
+  export scenario_file="scenarios/kind/node_scenarios_example.yml"
+  export post_config=""
+  envsubst < CI/config/common_test_config.yaml > CI/config/node_config.yaml
+  cat CI/config/node_config.yaml
+  python3 -m coverage run -a run_kraken.py -c CI/config/node_config.yaml
+  echo "Node Stop/Start scenario test: Success"
+}
+
+functional_test_node_stop_start

CI/tests/test_pod.sh

@@ -0,0 +1,20 @@
+set -xeEo pipefail
+
+source CI/tests/common.sh
+
+trap error ERR
+trap finish EXIT
+
+function functional_test_pod_crash {
+  export scenario_type="pod_disruption_scenarios"
+  export scenario_file="scenarios/kind/pod_etcd.yml"
+  export post_config=""
+  envsubst < CI/config/common_test_config.yaml > CI/config/pod_config.yaml
+
+  python3 -m coverage run -a run_kraken.py -c CI/config/pod_config.yaml
+  echo "Pod disruption scenario test: Success"
+  date
+  kubectl get pods -n kube-system -l component=etcd -o yaml
+}
+
+functional_test_pod_crash

CI/tests/test_pod_error.sh

@@ -0,0 +1,28 @@
+
+source CI/tests/common.sh
+
+trap error ERR
+trap finish EXIT
+
+function functional_test_pod_error {
+  export scenario_type="pod_disruption_scenarios"
+  export scenario_file="scenarios/kind/pod_etcd.yml"
+  export post_config=""
+  yq -i '.[0].config.kill=5' scenarios/kind/pod_etcd.yml
+  envsubst < CI/config/common_test_config.yaml > CI/config/pod_config.yaml
+  cat CI/config/pod_config.yaml
+
+  cat scenarios/kind/pod_etcd.yml
+  python3 -m coverage run -a run_kraken.py -c CI/config/pod_config.yaml
+  
+  ret=$?
+  echo "\n\nret $ret"
+  if [[ $ret -ge 1 ]]; then
+      echo "Pod disruption error scenario test: Success"
+  else 
+    echo "Pod disruption error scenario test: Failure"
+    exit 1
+  fi
+}
+
+functional_test_pod_error

CI/tests/test_pod_network_filter.sh

@@ -0,0 +1,62 @@
+function functional_pod_network_filter {
+  export SERVICE_URL="http://localhost:8889"
+  export scenario_type="network_chaos_ng_scenarios"
+  export scenario_file="scenarios/kube/pod-network-filter.yml"
+  export post_config=""
+  envsubst < CI/config/common_test_config.yaml > CI/config/pod_network_filter.yaml
+  yq -i '.[0].test_duration=10' scenarios/kube/pod-network-filter.yml
+  yq -i '.[0].label_selector=""' scenarios/kube/pod-network-filter.yml
+  yq -i '.[0].ingress=false' scenarios/kube/pod-network-filter.yml
+  yq -i '.[0].egress=true' scenarios/kube/pod-network-filter.yml
+  yq -i '.[0].target="pod-network-filter-test"' scenarios/kube/pod-network-filter.yml
+  yq -i '.[0].protocols=["tcp"]' scenarios/kube/pod-network-filter.yml
+  yq -i '.[0].ports=[443]' scenarios/kube/pod-network-filter.yml
+  yq -i '.performance_monitoring.check_critical_alerts=False' CI/config/pod_network_filter.yaml
+
+  ## Test webservice deployment
+  kubectl apply -f ./CI/templates/pod_network_filter.yaml
+  COUNTER=0
+  while true
+   do
+    curl $SERVICE_URL
+    EXITSTATUS=$?
+    if [ "$EXITSTATUS" -eq "0" ]
+      then
+        break
+    fi
+    sleep 1
+    COUNTER=$((COUNTER+1))
+    [ $COUNTER -eq "100" ] && echo "maximum number of retry reached, test failed" && exit 1
+  done
+
+  cat scenarios/kube/pod-network-filter.yml
+
+  python3 -m coverage run -a run_kraken.py -c CI/config/pod_network_filter.yaml > krkn_pod_network.out 2>&1 &
+  PID=$!
+
+  # wait until the dns resolution starts failing and the service returns 400
+  DNS_FAILURE_STATUS=0
+  while true
+   do
+    OUT_STATUS_CODE=$(curl -X GET -s -o /dev/null -I -w "%{http_code}" $SERVICE_URL)
+    if [ "$OUT_STATUS_CODE" -eq "404" ]
+      then
+        DNS_FAILURE_STATUS=404
+    fi
+
+    if [ "$DNS_FAILURE_STATUS" -eq "404" ] && [ "$OUT_STATUS_CODE" -eq "200" ]
+      then
+        echo "service restored"
+        break
+    fi
+    COUNTER=$((COUNTER+1))
+    [ $COUNTER -eq "100" ] && echo "maximum number of retry reached, test failed" && exit 1
+    sleep 2
+  done
+
+  wait $PID
+
+}
+
+functional_pod_network_filter
+

CI/tests/test_pod_server.sh

@@ -0,0 +1,35 @@
+set -xeEo pipefail
+
+source CI/tests/common.sh
+
+trap error ERR
+trap finish EXIT
+
+function functional_test_pod_server {
+  export scenario_type="pod_disruption_scenarios"
+  export scenario_file="scenarios/kind/pod_etcd.yml"
+  export post_config=""
+
+  envsubst < CI/config/common_test_config.yaml > CI/config/pod_config.yaml
+  yq -i '.[0].config.kill=1' scenarios/kind/pod_etcd.yml
+  
+  yq -i '.tunings.daemon_mode=True' CI/config/pod_config.yaml
+  cat CI/config/pod_config.yaml
+  python3 -m coverage run -a run_kraken.py -c CI/config/pod_config.yaml & 
+  sleep 15
+  curl -X POST http:/0.0.0.0:8081/STOP
+
+  wait
+
+  yq -i '.kraken.signal_state="PAUSE"' CI/config/pod_config.yaml
+  yq -i '.tunings.daemon_mode=False' CI/config/pod_config.yaml
+  cat CI/config/pod_config.yaml
+  python3 -m coverage run -a run_kraken.py -c CI/config/pod_config.yaml & 
+  sleep 5
+  curl -X POST http:/0.0.0.0:8081/RUN
+  wait
+
+  echo "Pod disruption with server scenario test: Success"
+}
+
+functional_test_pod_server

CI/tests/test_pvc.sh

@@ -0,0 +1,18 @@
+set -xeEo pipefail
+
+source CI/tests/common.sh
+
+trap error ERR
+trap finish EXIT
+
+function functional_test_pvc_fill {
+  export scenario_type="pvc_scenarios"
+  export scenario_file="scenarios/kind/pvc_scenario.yaml"
+  export post_config=""
+  envsubst < CI/config/common_test_config.yaml > CI/config/pvc_config.yaml
+  cat CI/config/pvc_config.yaml
+  python3 -m coverage run -a run_kraken.py -c CI/config/pvc_config.yaml --debug True
+  echo "PVC Fill scenario test: Success"
+}
+
+functional_test_pvc_fill

CI/tests/test_service_hijacking.sh

@@ -39,7 +39,7 @@ function functional_test_service_hijacking {
   export scenario_file="scenarios/kube/service_hijacking.yaml"
   export post_config=""
   envsubst < CI/config/common_test_config.yaml > CI/config/service_hijacking.yaml
-  python3 -m coverage run -a run_kraken.py -c CI/config/service_hijacking.yaml  > /dev/null 2>&1 &
+  python3 -m coverage run -a run_kraken.py -c CI/config/service_hijacking.yaml  > /tmp/krkn.log 2>&1 &
   PID=$!
   #Waiting the hijacking to have effect
   COUNTER=0
@@ -100,8 +100,13 @@ function functional_test_service_hijacking {
   [ "${PAYLOAD_PATCH_2//[$'\t\r\n ']}" == "${OUT_PATCH//[$'\t\r\n ']}" ] && echo "Step 2 PATCH Payload OK" || (echo "Step 2 PATCH Payload did not match. Test failed." && exit 1)
   [ "$OUT_STATUS_CODE" == "$STATUS_CODE_PATCH_2" ] && echo "Step 2 PATCH Status Code OK" || (echo "Step 2 PATCH status code did not match. Test failed." && exit 1)
   [ "$OUT_CONTENT" == "$TEXT_MIME" ] && echo "Step 2 PATCH MIME OK" || (echo " Step 2 PATCH MIME did not match. Test failed." && exit 1)
+
+
+
   wait $PID
 
+  cat /tmp/krkn.log
+
   # now checking  if service has been restore correctly and nginx responds correctly
   curl -s  $SERVICE_URL | grep nginx! && echo "BODY: Service restored!" || (echo "BODY: failed to restore service" && exit 1)
   OUT_STATUS_CODE=`curl -X GET -s -o /dev/null -I -w "%{http_code}" $SERVICE_URL`

CI/tests/test_telemetry.sh

@@ -18,8 +18,9 @@ function functional_test_telemetry {
   yq -i '.performance_monitoring.prometheus_url="http://localhost:9090"' CI/config/common_test_config.yaml
   yq -i '.telemetry.run_tag=env(RUN_TAG)' CI/config/common_test_config.yaml
 
-  export scenario_type="hog_scenarios"
-  export scenario_file="scenarios/kube/cpu-hog/input.yaml"
+  export scenario_type="pod_disruption_scenarios"
+  export scenario_file="scenarios/kind/pod_etcd.yml"
+
   export post_config=""
   envsubst < CI/config/common_test_config.yaml > CI/config/telemetry.yaml
   retval=$(python3 -m coverage run -a run_kraken.py -c CI/config/telemetry.yaml)

CLAUDE.md

@@ -0,0 +1,273 @@
+# CLAUDE.md - Krkn Chaos Engineering Framework
+
+## Project Overview
+
+Krkn (Kraken) is a chaos engineering tool for Kubernetes/OpenShift clusters. It injects deliberate failures to validate cluster resilience. Plugin-based architecture with multi-cloud support (AWS, Azure, GCP, IBM Cloud, VMware, Alibaba, OpenStack).
+
+## Repository Structure
+
+```
+krkn/
+├── krkn/
+│   ├── scenario_plugins/        # Chaos scenario plugins (pod, node, network, hogs, etc.)
+│   ├── utils/                   # Utility functions
+│   ├── rollback/                # Rollback management
+│   ├── prometheus/              # Prometheus integration
+│   └── cerberus/                # Health monitoring
+├── tests/                       # Unit tests (unittest framework)
+├── scenarios/                   # Example scenario configs (openshift/, kube/, kind/)
+├── config/                      # Configuration files
+└── CI/                          # CI/CD test scripts
+```
+
+## Quick Start
+
+```bash
+# Setup (ALWAYS use virtual environment)
+python3 -m venv venv
+source venv/bin/activate
+pip install -r requirements.txt
+
+# Run Krkn
+python run_kraken.py --config config/config.yaml
+
+# Note: Scenarios are specified in config.yaml under kraken.chaos_scenarios
+# There is no --scenario flag; edit config/config.yaml to select scenarios
+
+# Run tests
+python -m unittest discover -s tests -v
+python -m coverage run -a -m unittest discover -s tests -v
+```
+
+## Critical Requirements
+
+### Python Environment
+- **Python 3.9+** required
+- **NEVER install packages globally** - always use virtual environment
+- **CRITICAL**: `docker` must be <7.0 and `requests` must be <2.32 (Unix socket compatibility)
+
+### Key Dependencies
+- **krkn-lib** (5.1.13): Core library for Kubernetes/OpenShift operations
+- **kubernetes** (34.1.0): Kubernetes Python client
+- **docker** (<7.0), **requests** (<2.32): DO NOT upgrade without verifying compatibility
+- Cloud SDKs: boto3 (AWS), azure-mgmt-* (Azure), google-cloud-compute (GCP), ibm_vpc (IBM), pyVmomi (VMware)
+
+## Plugin Architecture (CRITICAL)
+
+**Strictly enforced naming conventions:**
+
+### Naming Rules
+- **Module files**: Must end with `_scenario_plugin.py` and use snake_case
+  - Example: `pod_disruption_scenario_plugin.py`
+- **Class names**: Must be CamelCase and end with `ScenarioPlugin`
+  - Example: `PodDisruptionScenarioPlugin`
+  - Must match module filename (snake_case ↔ CamelCase)
+- **Directory structure**: Plugin dirs CANNOT contain "scenario" or "plugin"
+  - Location: `krkn/scenario_plugins/<plugin_name>/`
+
+### Plugin Implementation
+Every plugin MUST:
+1. Extend `AbstractScenarioPlugin`
+2. Implement `run()` method
+3. Implement `get_scenario_types()` method
+
+```python
+from krkn.scenario_plugins import AbstractScenarioPlugin
+
+class PodDisruptionScenarioPlugin(AbstractScenarioPlugin):
+    def run(self, config, scenarios_list, kubeconfig_path, wait_duration):
+        pass
+    
+    def get_scenario_types(self):
+        return ["pod_scenarios", "pod_outage"]
+```
+
+### Creating a New Plugin
+1. Create directory: `krkn/scenario_plugins/<plugin_name>/`
+2. Create module: `<plugin_name>_scenario_plugin.py`
+3. Create class: `<PluginName>ScenarioPlugin` extending `AbstractScenarioPlugin`
+4. Implement `run()` and `get_scenario_types()`
+5. Create unit test: `tests/test_<plugin_name>_scenario_plugin.py`
+6. Add example scenario: `scenarios/<platform>/<scenario>.yaml`
+
+**DO NOT**: Violate naming conventions (factory will reject), include "scenario"/"plugin" in directory names, create plugins without tests.
+
+## Testing
+
+### Unit Tests
+```bash
+# Run all tests
+python -m unittest discover -s tests -v
+
+# Specific test
+python -m unittest tests.test_pod_disruption_scenario_plugin
+
+# With coverage
+python -m coverage run -a -m unittest discover -s tests -v
+python -m coverage html
+```
+
+**Test requirements:**
+- Naming: `test_<module>_scenario_plugin.py`
+- Mock external dependencies (Kubernetes API, cloud providers)
+- Test success, failure, and edge cases
+- Keep tests isolated and independent
+
+### Functional Tests
+Located in `CI/tests/`. Can be run locally on a kind cluster with Prometheus and Elasticsearch set up.
+
+**Setup for local testing:**
+1. Deploy Prometheus and Elasticsearch on your kind cluster:
+   - Prometheus setup: https://krkn-chaos.dev/docs/developers-guide/testing-changes/#prometheus
+   - Elasticsearch setup: https://krkn-chaos.dev/docs/developers-guide/testing-changes/#elasticsearch
+
+2. Or disable monitoring features in `config/config.yaml`:
+   ```yaml
+   performance_monitoring:
+       enable_alerts: False
+       enable_metrics: False
+       check_critical_alerts: False
+   ```
+
+**Note:** Functional tests run automatically in CI with full monitoring enabled.
+
+## Cloud Provider Implementations
+
+Node chaos scenarios are cloud-specific. Each in `krkn/scenario_plugins/node_actions/<provider>_node_scenarios.py`:
+- AWS, Azure, GCP, IBM Cloud, VMware, Alibaba, OpenStack, Bare Metal
+
+Implement: stop, start, reboot, terminate instances.
+
+**When modifying**: Maintain consistency with other providers, handle API errors, add logging, update tests.
+
+### Adding Cloud Provider Support
+1. Create: `krkn/scenario_plugins/node_actions/<provider>_node_scenarios.py`
+2. Extend: `abstract_node_scenarios.AbstractNodeScenarios`
+3. Implement: `stop_instances`, `start_instances`, `reboot_instances`, `terminate_instances`
+4. Add SDK to `requirements.txt`
+5. Create unit test with mocked SDK
+6. Add example scenario: `scenarios/openshift/<provider>_node_scenarios.yml`
+
+## Configuration
+
+**Main config**: `config/config.yaml`
+- `kraken`: Core settings
+- `cerberus`: Health monitoring
+- `performance_monitoring`: Prometheus
+- `elastic`: Elasticsearch telemetry
+
+**Scenario configs**: `scenarios/` directory
+```yaml
+- config:
+    scenario_type: <type>  # Must match plugin's get_scenario_types()
+```
+
+## Code Style
+
+- **Import order**: Standard library, third-party, local imports
+- **Naming**: snake_case (functions/variables), CamelCase (classes)
+- **Logging**: Use Python's `logging` module
+- **Error handling**: Return appropriate exit codes
+- **Docstrings**: Required for public functions/classes
+
+## Exit Codes
+
+Krkn uses specific exit codes to communicate execution status:
+
+- `0`: Success - all scenarios passed, no critical alerts
+- `1`: Scenario failure - one or more scenarios failed
+- `2`: Critical alerts fired during execution
+- `3+`: Health check failure (Cerberus monitoring detected issues)
+
+**When implementing scenarios:**
+- Return `0` on success
+- Return `1` on scenario-specific failures
+- Propagate health check failures appropriately
+- Log exit code reasons clearly
+
+## Container Support
+
+Krkn can run inside a container. See `containers/` directory.
+
+**Building custom image:**
+```bash
+cd containers
+./compile_dockerfile.sh  # Generates Dockerfile from template
+docker build -t krkn:latest .
+```
+
+**Running containerized:**
+```bash
+docker run -v ~/.kube:/root/.kube:Z \
+  -v $(pwd)/config:/config:Z \
+  -v $(pwd)/scenarios:/scenarios:Z \
+  krkn:latest
+```
+
+## Git Workflow
+
+- **NEVER commit directly to main**
+- **NEVER use `--force` without approval**
+- **ALWAYS create feature branches**: `git checkout -b feature/description`
+- **ALWAYS run tests before pushing**
+
+**Conventional commits**: `feat:`, `fix:`, `test:`, `docs:`, `refactor:`
+
+```bash
+git checkout main && git pull origin main
+git checkout -b feature/your-feature-name
+# Make changes, write tests
+python -m unittest discover -s tests -v
+git add <specific-files>
+git commit -m "feat: description"
+git push -u origin feature/your-feature-name
+```
+
+## Environment Variables
+
+- `KUBECONFIG`: Path to kubeconfig
+- `AWS_*`, `AZURE_*`, `GOOGLE_APPLICATION_CREDENTIALS`: Cloud credentials
+- `PROMETHEUS_URL`, `ELASTIC_URL`, `ELASTIC_PASSWORD`: Monitoring config
+
+**NEVER commit credentials or API keys.**
+
+## Common Pitfalls
+
+1. Missing virtual environment - always activate venv
+2. Running functional tests without cluster setup
+3. Ignoring exit codes
+4. Modifying krkn-lib directly (it's a separate package)
+5. Upgrading docker/requests beyond version constraints
+
+## Before Writing Code
+
+1. Check for existing implementations
+2. Review existing plugins as examples
+3. Maintain consistency with cloud provider patterns
+4. Plan rollback logic
+5. Write tests alongside code
+6. Update documentation
+
+## When Adding Dependencies
+
+1. Check if functionality exists in krkn-lib or current dependencies
+2. Verify compatibility with existing versions
+3. Pin specific versions in `requirements.txt`
+4. Check for security vulnerabilities
+5. Test thoroughly for conflicts
+
+## Common Development Tasks
+
+### Modifying Existing Plugin
+1. Read plugin code and corresponding test
+2. Make changes
+3. Update/add unit tests
+4. Run: `python -m unittest tests.test_<plugin>_scenario_plugin`
+
+### Writing Unit Tests
+1. Create: `tests/test_<module>_scenario_plugin.py`
+2. Import `unittest` and plugin class
+3. Mock external dependencies
+4. Test success, failure, and edge cases
+5. Run: `python -m unittest tests.test_<module>_scenario_plugin`
+

GOVERNANCE.md

@@ -0,0 +1,83 @@
+
+
+
+The governance model adopted here is heavily influenced by a set of CNCF projects, especially drew
+reference from [Kubernetes governance](https://github.com/kubernetes/community/blob/master/governance.md).
+*For similar structures some of the same wordings from kubernetes governance are borrowed to adhere
+to the originally construed meaning.*
+
+## Principles
+
+- **Open**: Krkn is open source community.
+- **Welcoming and respectful**: See [Code of Conduct](https://github.com/cncf/foundation/blob/master/code-of-conduct.md).
+- **Transparent and accessible**: Work and collaboration should be done in public.
+  Changes to the Krkn organization, Krkn code repositories, and CNCF related activities (e.g.
+  level, involvement, etc) are done in public.
+- **Merit**: Ideas and contributions are accepted according to their technical merit
+  and alignment with project objectives, scope and design principles.
+
+## Code of Conduct
+
+Krkn follows the [CNCF Code of Conduct](https://github.com/cncf/foundation/blob/master/code-of-conduct.md).
+Here is an excerpt:
+
+>  As contributors and maintainers of this project, and in the interest of fostering an open and welcoming community, we pledge to respect all people who contribute through reporting issues, posting feature requests, updating documentation, submitting pull requests or patches, and other activities.
+
+## Maintainer Levels
+
+### Contributor
+Contributors contribute to the community. Anyone can become a contributor by participating in discussions, reporting bugs, or contributing code or documentation.
+
+#### Responsibilities:
+
+Be active in the community and adhere to the Code of Conduct.
+
+Report bugs and suggest new features.
+
+Contribute high-quality code and documentation.
+
+
+### Member
+Members are active contributors to the community. Members have demonstrated a strong understanding of the project's codebase and conventions.
+
+#### Responsibilities:
+
+Review pull requests for correctness, quality, and adherence to project standards.
+
+Provide constructive and timely feedback to contributors.
+
+Ensure that all contributions are well-tested and documented.
+
+Work with maintainers to ensure a smooth and efficient release process.
+
+### Maintainer
+Maintainers are responsible for the overall health and direction of the project. They are long-standing contributors who have shown a deep commitment to the project's success.
+
+#### Responsibilities:
+
+Set the technical direction and vision for the project.
+
+Manage releases and ensure the stability of the main branch.
+
+Make decisions on feature inclusion and project priorities.
+
+Mentor other contributors and help grow the community.
+
+Resolve disputes and make final decisions when consensus cannot be reached.
+
+### Owner
+Owners have administrative access to the project and are the final decision-makers.
+
+#### Responsibilities:
+
+Manage the core team of maintainers and approvers.
+
+Set the overall vision and strategy for the project.
+
+Handle administrative tasks, such as managing the project's repository and other resources.
+
+Represent the project in the broader open-source community.
+
+
+# Credits
+Sections of this document have been borrowed from [Kubernetes governance](https://github.com/kubernetes/community/blob/master/governance.md)

MAINTAINERS.md

@@ -1,12 +1,34 @@
 ## Overview
 
 This document contains a list of maintainers in this repo.
+This file lists the maintainers and committers of the Krkn project.
+
+In short, maintainers are people who are in charge of the maintenance of the Krkn project. Committers are active community members who have shown that they are committed to the continuous development of the project through ongoing engagement with the community.
+
+For detailed description of the roles, see [Governance](./GOVERNANCE.md) page.
 
 ## Current Maintainers
 
-| Maintainer          | GitHub ID                                                 | Email                   |
-|---------------------| --------------------------------------------------------- | ----------------------- |
-| Ravi Elluri         | [chaitanyaenr](https://github.com/chaitanyaenr)           | nelluri@redhat.com      |
-| Pradeep Surisetty   | [psuriset](https://github.com/psuriset)                   | psuriset@redhat.com     |
-| Paige Rubendall     | [paigerube14](https://github.com/paigerube14)             | prubenda@redhat.com     |
-| Tullio Sebastiani   | [tsebastiani](https://github.com/tsebastiani)             | tsebasti@redhat.com     |
+| Maintainer          | GitHub ID                                                 | Email                   | Contribution Level     | 
+|---------------------| --------------------------------------------------------- | ----------------------- | ---------------------- | 
+| Ravi Elluri         | [chaitanyaenr](https://github.com/chaitanyaenr)           | nelluri@redhat.com      | Owner | 
+| Pradeep Surisetty   | [psuriset](https://github.com/psuriset)                   | psuriset@redhat.com     | Owner | 
+| Paige Patton     | [paigerube14](https://github.com/paigerube14)                | prubenda@redhat.com     | Maintainer | 
+| Tullio Sebastiani   | [tsebastiani](https://github.com/tsebastiani)             | tsebasti@redhat.com     | Maintainer | 
+| Yogananth Subramanian  | [yogananth-subramanian](https://github.com/yogananth-subramanian)             | ysubrama@redhat.com     |Maintainer | 
+| Sahil Shah  | [shahsahil264](https://github.com/shahsahil264)                   | sahshah@redhat.com   |  Member | 
+
+
+Note : It is mandatory for all Krkn community members to follow our [Code of Conduct](./CODE_OF_CONDUCT.md)
+
+
+## Contributor Ladder
+This project follows a contributor ladder model, where contributors can take on more responsibilities as they gain experience and demonstrate their commitment to the project. 
+The roles are:
+* Contributor: A contributor to the community whether it be with code, docs or issues
+
+* Member: A contributor who is active in the community and reviews pull requests.
+
+* Maintainer: A contributor who is responsible for the overall health and direction of the project.
+
+* Owner: A contributor who has administrative ownership of the project.

README.md

@@ -2,6 +2,7 @@
 ![Workflow-Status](https://github.com/krkn-chaos/krkn/actions/workflows/docker-image.yml/badge.svg)
 ![coverage](https://krkn-chaos.github.io/krkn-lib-docs/coverage_badge_krkn.svg)
 ![action](https://github.com/krkn-chaos/krkn/actions/workflows/tests.yml/badge.svg)
+[![OpenSSF Best Practices](https://www.bestpractices.dev/projects/10548/badge)](https://www.bestpractices.dev/projects/10548)
 
 ![Krkn logo](media/logo.png)
 
@@ -10,102 +11,21 @@ Kraken injects deliberate failures into Kubernetes clusters to check if it is re
 
 
 ### Workflow
-![Kraken workflow](media/kraken-workflow.png)
-
-### Demo
-[![Kraken demo](media/KrakenStarting.png)](https://youtu.be/LN-fZywp_mo "Kraken Demo - Click to Watch!")
+![Kraken workflow](media/kraken-workflow.png) 
 
 
-### Chaos Testing Guide
-[Guide](docs/index.md) encapsulates:
-- Test methodology that needs to be embraced.
-- Best practices that an Kubernetes cluster, platform and applications running on top of it should take into account for best user experience, performance, resilience and reliability.
-- Tooling.
-- Scenarios supported.
-- Test environment recommendations as to how and where to run chaos tests.
-- Chaos testing in practice.
-
-The guide is hosted at https://krkn-chaos.github.io/krkn.
+<!-- ### Demo
+[![Kraken demo](media/KrakenStarting.png)](https://youtu.be/LN-fZywp_mo "Kraken Demo - Click to Watch!") -->
 
 
 ### How to Get Started
-Instructions on how to setup, configure and run Kraken can be found at [Installation](docs/installation.md).
-
-You may consider utilizing the chaos recommendation tool prior to initiating the chaos runs to profile the application service(s) under test. This tool discovers a list of Krkn scenarios with a high probability of causing failures or disruptions to your application service(s). The tool can be accessed at [Chaos-Recommender](utils/chaos_recommender/README.md).
-
-See the [getting started doc](docs/getting_started.md) on support on how to get started with your own custom scenario or editing current scenarios for your specific usage.
-
-After installation, refer back to the below sections for supported scenarios and how to tweak the kraken config to load them on your cluster.
+Instructions on how to setup, configure and run Kraken can be found in the [documentation](https://krkn-chaos.dev/docs/).
 
 
-#### Running Kraken with minimal configuration tweaks
-For cases where you want to run Kraken with minimal configuration changes, refer to [krkn-hub](https://github.com/krkn-chaos/krkn-hub). One use case is CI integration where you do not want to carry around different configuration files for the scenarios.
+### Blogs, podcasts and interviews
+Additional resources, including blog posts, podcasts, and community interviews, can be found on the [website](https://krkn-chaos.dev/blog)
 
 
-### Config
-Instructions on how to setup the config and the options supported can be found at [Config](docs/config.md).
-
-
-### Kubernetes chaos scenarios supported
-
-Scenario type               | Kubernetes    
---------------------------- | ------------- | 
-[Pod Scenarios](docs/pod_scenarios.md) | :heavy_check_mark: |
-[Pod Network Scenarios](docs/pod_network_scenarios.md) | :x: |
-[Container Scenarios](docs/container_scenarios.md) | :heavy_check_mark: |
-[Node Scenarios](docs/node_scenarios.md) | :heavy_check_mark: |
-[Time Scenarios](docs/time_scenarios.md) | :heavy_check_mark: |
-[Hog Scenarios: CPU, Memory](docs/arcaflow_scenarios.md) | :heavy_check_mark: |
-[Cluster Shut Down Scenarios](docs/cluster_shut_down_scenarios.md) | :heavy_check_mark: |
-[Service Disruption Scenarios](docs/service_disruption_scenarios.md.md) | :heavy_check_mark: |
-[Zone Outage Scenarios](docs/zone_outage.md) | :heavy_check_mark: |
-[Application_outages](docs/application_outages.md) | :heavy_check_mark: |
-[PVC scenario](docs/pvc_scenario.md) | :heavy_check_mark: |
-[Network_Chaos](docs/network_chaos.md) | :heavy_check_mark: |
-[ManagedCluster Scenarios](docs/managedcluster_scenarios.md) | :heavy_check_mark: |
-[Service Hijacking Scenarios](docs/service_hijacking_scenarios.md) | :heavy_check_mark: |
-[SYN Flood Scenarios](docs/syn_flood_scenarios.md) | :heavy_check_mark: |
-
-
-### Kraken scenario pass/fail criteria and report
-It is important to make sure to check if the targeted component recovered from the chaos injection and also if the Kubernetes cluster is healthy as failures in one component can have an adverse impact on other components. Kraken does this by:
-- Having built in checks for pod and node based scenarios to ensure the expected number of replicas and nodes are up. It also supports running custom scripts with the checks.
-- Leveraging [Cerberus](https://github.com/krkn-chaos/cerberus) to monitor the cluster under test and consuming the aggregated go/no-go signal to determine pass/fail post chaos. It is highly recommended to turn on the Cerberus health check feature available in Kraken. Instructions on installing and setting up Cerberus can be found [here](https://github.com/openshift-scale/cerberus#installation) or can be installed from Kraken using the [instructions](https://github.com/krkn-chaos/krkn#setting-up-infrastructure-dependencies). Once Cerberus is up and running, set cerberus_enabled to True and cerberus_url to the url where Cerberus publishes go/no-go signal in the Kraken config file. Cerberus can monitor [application routes](https://github.com/redhat-chaos/cerberus/blob/main/docs/config.md#watch-routes) during the chaos and fails the run if it encounters downtime as it is a potential downtime in a customers, or users environment as well. It is especially important during the control plane chaos scenarios including the API server, Etcd, Ingress etc. It can be enabled by setting `check_applicaton_routes: True` in the [Kraken config](https://github.com/redhat-chaos/krkn/blob/main/config/config.yaml) provided application routes are being monitored in the [cerberus config](https://github.com/redhat-chaos/krkn/blob/main/config/cerberus.yaml).
-- Leveraging built-in alert collection feature to fail the runs in case of critical alerts.
-
-### Signaling
-In CI runs or any external job it is useful to stop Kraken once a certain test or state gets reached. We created a way to signal to kraken to pause the chaos or stop it completely using a signal posted to a port of your choice.
-
-For example if we have a test run loading the cluster running and kraken separately running; we want to be able to know when to start/stop the kraken run based on when the test run completes or gets to a certain loaded state.
-
-More detailed information on enabling and leveraging this feature can be found [here](docs/signal.md).
-
-
-### Performance monitoring
-Monitoring the Kubernetes/OpenShift cluster to observe the impact of Kraken chaos scenarios on various components is key to find out the bottlenecks as it is important to make sure the cluster is healthy in terms if both recovery as well as performance during/after the failure has been injected. Instructions on enabling it can be found [here](docs/performance_dashboards.md).
-
-
-### SLOs validation during and post chaos
-- In addition to checking the recovery and health of the cluster and components under test, Kraken takes in a profile with the Prometheus expressions to validate and alerts, exits with a non-zero return code depending on the severity set. This feature can be used to determine pass/fail or alert on abnormalities observed in the cluster based on the metrics. 
-- Kraken also provides ability to check if any critical alerts are firing in the cluster post chaos and pass/fail's. 
-
-Information on enabling and leveraging this feature can be found [here](docs/SLOs_validation.md)
-
-
-### OCM / ACM integration
-
-Kraken supports injecting faults into [Open Cluster Management (OCM)](https://open-cluster-management.io/) and [Red Hat Advanced Cluster Management for Kubernetes (ACM)](https://www.krkn.com/en/technologies/management/advanced-cluster-management) managed clusters through [ManagedCluster Scenarios](docs/managedcluster_scenarios.md).
-
-
-### Blogs and other useful resources
-- Blog post on introduction to Kraken: https://www.openshift.com/blog/introduction-to-kraken-a-chaos-tool-for-openshift/kubernetes
-- Discussion and demo on how Kraken can be leveraged to ensure OpenShift is reliable, performant and scalable: https://www.youtube.com/watch?v=s1PvupI5sD0&ab_channel=OpenShift
-- Blog post emphasizing the importance of making Chaos part of Performance and Scale runs to mimic the production environments: https://www.openshift.com/blog/making-chaos-part-of-kubernetes/openshift-performance-and-scalability-tests
-- Blog post on findings from Chaos test runs: https://cloud.redhat.com/blog/openshift/kubernetes-chaos-stories
-- Discussion with CNCF TAG App Delivery on Krkn workflow, features and addition to CNCF sandbox: [Github](https://github.com/cncf/sandbox/issues/44), [Tracker](https://github.com/cncf/tag-app-delivery/issues/465), [recording](https://www.youtube.com/watch?v=nXQkBFK_MWc&t=722s)
-- Blog post on supercharging chaos testing using AI integration in Krkn: https://www.redhat.com/en/blog/supercharging-chaos-testing-using-ai
-- Blog post announcing Krkn joining CNCF Sandbox: https://www.redhat.com/en/blog/krknchaos-joining-cncf-sandbox
-
 ### Roadmap
 Enhancements being planned can be found in the [roadmap](ROADMAP.md).
 
@@ -113,17 +33,8 @@ Enhancements being planned can be found in the [roadmap](ROADMAP.md).
 ### Contributions
 We are always looking for more enhancements, fixes to make it better, any contributions are most welcome. Feel free to report or work on the issues filed on github.
 
-[More information on how to Contribute](docs/contribute.md)
+[More information on how to Contribute](https://krkn-chaos.dev/docs/contribution-guidelines/)
 
-If adding a new scenario or tweaking the main config, be sure to add in updates into the CI to be sure the CI is up to date.
-Please read [this file]((CI/README.md#adding-a-test-case)) for more information on updates.
-
-
-### Scenario Plugin Development
-
-If you're gearing up to develop new scenarios, take a moment to review our 
-[Scenario Plugin API Documentation](docs/scenario_plugin_api.md). 
-It’s the perfect starting point to tap into your chaotic creativity!
 
 ### Community
 Key Members(slack_usernames/full name): paigerube14/Paige Rubendall, mffiedler/Mike Fiedler, tsebasti/Tullio Sebastiani, yogi/Yogananth Subramanian, sahil/Sahil Shah, pradeep/Pradeep Surisetty and ravielluri/Naga Ravi Chaitanya Elluri.

RELEASE.md

@@ -0,0 +1,55 @@
+### Release Protocol: The Community-First Cycle
+
+This document outlines the project's release protocol, a methodology designed to ensure a responsive and transparent development process that is closely aligned with the needs of our users and contributors. This protocol is tailored for projects in their early stages, prioritizing agility and community feedback over a rigid, time-boxed schedule.
+
+#### 1. Key Principles
+
+* **Community as the Compass:** The primary driver for all development is feedback from our user and contributor community.
+* **Prioritization by Impact:** Tasks are prioritized based on their impact on user experience, the urgency of bug fixes, and the value of community-contributed features.
+* **Event-Driven Releases:** Releases are not bound by a fixed calendar. New versions are published when a significant body of work is complete, a critical issue is resolved, or a new feature is ready for adoption.
+* **Transparency and Communication:** All development decisions, progress, and plans are communicated openly through our issue tracker, pull requests, and community channels.
+
+#### 2. The Release Lifecycle
+
+The release cycle is a continuous flow of activities rather than a series of sequential phases.
+
+**2.1. Discovery & Prioritization**
+* New features and bug fixes are identified through user feedback on our issue tracker, community discussions, and direct contributions.
+* The core maintainers, in collaboration with the community, continuously evaluate and tag issues to create an open and dynamic backlog.
+
+**2.2. Development & Code Review**
+* Work is initiated based on the highest-priority items in the backlog.
+* All code contributions are made via pull requests (PRs).
+* PRs are reviewed by maintainers and other contributors to ensure code quality, adherence to project standards, and overall stability.
+
+**2.3. Release Readiness**
+A new release is considered ready when one of the following conditions is met:
+* A major new feature has been completed and thoroughly tested.
+* A critical security vulnerability or bug has been addressed.
+* A sufficient number of smaller improvements and fixes have been merged, providing meaningful value to users.
+
+**2.4. Versioning**
+We adhere to [**Semantic Versioning 2.0.0**](https://semver.org/).
+* **Major version (`X.y.z`)**: Reserved for releases that introduce breaking changes.
+* **Minor version (`x.Y.z`)**: Used for new features or significant non-breaking changes.
+* **Patch version (`x.y.Z`)**: Used for bug fixes and small, non-functional improvements.
+
+#### 3. Roles and Responsibilities
+
+* **Members:** The [core team](https://github.com/krkn-chaos/krkn/blob/main/MAINTAINERS.md) responsible for the project's health. Their duties include:
+    * Reviewing pull requests.
+    * Contributing code and documentation via pull requests.
+    * Engaging in discussions and providing feedback.
+* **Maintainers and Owners:** The [core team](https://github.com/krkn-chaos/krkn/blob/main/MAINTAINERS.md) responsible for the project's health. Their duties include:
+    * Facilitating community discussions and prioritization.
+    * Reviewing and merging pull requests.
+    * Cutting and announcing official releases.
+* **Contributors:** The community. Their duties include:
+    * Reporting bugs and suggesting new features.
+    * Contributing code and documentation via pull requests.
+    * Engaging in discussions and providing feedback.
+
+#### 4. Adoption and Future Evolution
+
+This protocol is designed for the current stage of the project. As the project matures and the contributor base grows, the maintainers will evaluate the need for a more structured methodology to ensure continued scalability and stability.
+

ROADMAP.md

@@ -2,11 +2,11 @@
 
 Following are a list of enhancements that we are planning to work on adding support in Krkn. Of course any help/contributions are greatly appreciated.
 
-- [ ] [Ability to run multiple chaos scenarios in parallel under load to mimic real world outages](https://github.com/krkn-chaos/krkn/issues/424)
+- [x] [Ability to run multiple chaos scenarios in parallel under load to mimic real world outages](https://github.com/krkn-chaos/krkn/issues/424)
 - [x] [Centralized storage for chaos experiments artifacts](https://github.com/krkn-chaos/krkn/issues/423)
-- [ ] [Support for causing DNS outages](https://github.com/krkn-chaos/krkn/issues/394)
+- [x] [Support for causing DNS outages](https://github.com/krkn-chaos/krkn/issues/394)
 - [x] [Chaos recommender](https://github.com/krkn-chaos/krkn/tree/main/utils/chaos-recommender) to suggest scenarios having probability of impacting the service under test using profiling results 
-- [] Chaos AI integration to improve test coverage while reducing fault space to save costs and execution time
+- [x] Chaos AI integration to improve test coverage while reducing fault space to save costs and execution time [krkn-chaos-ai](https://github.com/krkn-chaos/krkn-chaos-ai)
 - [x] [Support for pod level network traffic shaping](https://github.com/krkn-chaos/krkn/issues/393)
 - [ ] [Ability to visualize the metrics that are being captured by Kraken and stored in Elasticsearch](https://github.com/krkn-chaos/krkn/issues/124)
 - [x] Support for running all the scenarios of Kraken on Kubernetes distribution - see https://github.com/krkn-chaos/krkn/issues/185, https://github.com/redhat-chaos/krkn/issues/186
@@ -14,3 +14,7 @@ Following are a list of enhancements that we are planning to work on adding supp
 - [x] [Switch documentation references to Kubernetes](https://github.com/krkn-chaos/krkn/issues/495)
 - [x] [OCP and Kubernetes functionalities segregation](https://github.com/krkn-chaos/krkn/issues/497)
 - [x] [Krknctl - client for running Krkn scenarios with ease](https://github.com/krkn-chaos/krknctl)
+- [x] [AI Chat bot to help get started with Krkn and commands](https://github.com/krkn-chaos/krkn-lightspeed)
+- [ ] [Ability to roll back cluster to original state if chaos fails](https://github.com/krkn-chaos/krkn/issues/804)
+- [ ] Add recovery time metrics to each scenario for better regression analysis
+- [ ] [Add resiliency scoring to chaos scenarios ran on cluster](https://github.com/krkn-chaos/krkn/issues/125)

SECURITY.md

@@ -0,0 +1,43 @@
+# Security Policy
+
+We attach great importance to code security. We are very grateful to the users, security vulnerability researchers, etc. for reporting security vulnerabilities to the Krkn community. All reported security vulnerabilities will be carefully assessed and addressed in a timely manner.
+
+
+## Security Checks
+
+Krkn leverages [Snyk](https://snyk.io/) to ensure that any security vulnerabilities found 
+in the code base and dependencies are fixed and published in the latest release. Security 
+vulnerability checks are enabled for each pull request to enable developers to get insights 
+and proactively fix them.
+
+ 
+## Reporting a Vulnerability
+
+The Krkn project treats security vulnerabilities seriously, so we
+strive to take action quickly when required.
+
+The project requests that security issues be disclosed in a responsible
+manner to allow adequate time to respond.  If a security issue or
+vulnerability has been found, please disclose the details to our
+dedicated email address:
+
+cncf-krkn-maintainers@lists.cncf.io
+
+You can also use the [GitHub vulnerability report mechanism](https://docs.github.com/en/code-security/security-advisories/guidance-on-reporting-and-writing-information-about-vulnerabilities/privately-reporting-a-security-vulnerability#privately-reporting-a-security-vulnerability) to report the security vulnerability.
+
+Please include as much information as possible with the report. The
+following details assist with analysis efforts:
+  - Description of the vulnerability
+  - Affected component (version, commit, branch etc)
+  - Affected code (file path, line numbers)
+  - Exploit code
+
+
+## Security Team
+
+The security team currently consists of the [Maintainers of Krkn](https://github.com/krkn-chaos/krkn/blob/main/MAINTAINERS.md)
+
+
+## Process and Supported Releases
+
+The Krkn security team will investigate and provide a fix in a timely manner depending on the severity. The fix will be included in the new release of Krkn and details will be included in the release notes.

config/cerberus.yaml

@@ -39,7 +39,7 @@ cerberus:
         Sunday:
     slack_team_alias:                                    # The slack team alias to be tagged while reporting failures in the slack channel when no watcher is assigned
 
-    custom_checks:                                       # Relative paths of files conataining additional user defined checks
+    custom_checks:                                       # Relative paths of files containing additional user defined checks
 
 tunings:
     timeout: 3                                          # Number of seconds before requests fail

config/config.yaml

@@ -1,75 +1,74 @@
 kraken:
-    distribution: kubernetes                                # Distribution can be kubernetes or openshift
     kubeconfig_path: ~/.kube/config                     # Path to kubeconfig
     exit_on_failure: False                                 # Exit when a post action scenario fails
+    auto_rollback: True                                    # Enable auto rollback for scenarios.
+    rollback_versions_directory: /tmp/kraken-rollback      # Directory to store rollback version files.
     publish_kraken_status: True                            # Can be accessed at http://0.0.0.0:8081
     signal_state: RUN                                      # Will wait for the RUN signal when set to PAUSE before running the scenarios, refer docs/signal.md for more details
     signal_address: 0.0.0.0                                # Signal listening address
     port: 8081                                             # Signal port
     chaos_scenarios:
-        # List of policies/chaos scenarios to load
-        - hog_scenarios:
-            - scenarios/kube/cpu-hog/input.yaml
-            - scenarios/kube/memory-hog/input.yaml
-            - scenarios/kube/io-hog/input.yaml
-            - scenarios/kube/io-hog/input.yaml
-        - application_outages_scenarios:
-            - scenarios/openshift/app_outage.yaml
-        - container_scenarios:                             # List of chaos pod scenarios to load
-            - scenarios/openshift/container_etcd.yml
-        - pod_network_scenarios:
-              - scenarios/openshift/network_chaos_ingress.yml
-              - scenarios/openshift/pod_network_outage.yml
-        - pod_disruption_scenarios:
-            - scenarios/openshift/etcd.yml
-            - scenarios/openshift/regex_openshift_pod_kill.yml
-            - scenarios/openshift/prom_kill.yml
-            - scenarios/openshift/openshift-apiserver.yml
-            - scenarios/openshift/openshift-kube-apiserver.yml
-        - vmware_node_scenarios:
-            - scenarios/openshift/vmware_node_scenarios.yml
-        - ibmcloud_node_scenarios:
-            - scenarios/openshift/ibmcloud_node_scenarios.yml
-        - node_scenarios:                                  # List of chaos node scenarios to load
-            - scenarios/openshift/aws_node_scenarios.yml
-        - time_scenarios:                                  # List of chaos time scenarios to load
-            - scenarios/openshift/time_scenarios_example.yml
-        - cluster_shut_down_scenarios:
-            - scenarios/openshift/cluster_shut_down_scenario.yml
-        - service_disruption_scenarios:
-             - scenarios/openshift/regex_namespace.yaml
-             - scenarios/openshift/ingress_namespace.yaml
-        - zone_outages_scenarios:
-            - scenarios/openshift/zone_outage.yaml
-        - pvc_scenarios:
-            - scenarios/openshift/pvc_scenario.yaml
-        - network_chaos_scenarios:
-            - scenarios/openshift/network_chaos.yaml
-        - service_hijacking_scenarios:
-              - scenarios/kube/service_hijacking.yaml
-        - syn_flood_scenarios:
-              - scenarios/kube/syn_flood.yaml
+       # List of policies/chaos scenarios to load
+       - hog_scenarios:
+           - scenarios/kube/cpu-hog.yml
+           - scenarios/kube/memory-hog.yml
+           - scenarios/kube/io-hog.yml
+       - application_outages_scenarios:
+           - scenarios/openshift/app_outage.yaml
+       - container_scenarios:                             # List of chaos pod scenarios to load
+           - scenarios/openshift/container_etcd.yml
+       - pod_network_scenarios:
+             - scenarios/openshift/network_chaos_ingress.yml
+             - scenarios/openshift/pod_network_outage.yml
+       - pod_disruption_scenarios:
+           - scenarios/openshift/etcd.yml
+           - scenarios/openshift/regex_openshift_pod_kill.yml
+           - scenarios/openshift/prom_kill.yml
+           - scenarios/openshift/openshift-apiserver.yml
+           - scenarios/openshift/openshift-kube-apiserver.yml
+       - node_scenarios:                                  # List of chaos node scenarios to load
+           - scenarios/openshift/aws_node_scenarios.yml
+           - scenarios/openshift/vmware_node_scenarios.yml
+           - scenarios/openshift/ibmcloud_node_scenarios.yml
+       - time_scenarios:                                  # List of chaos time scenarios to load
+           - scenarios/openshift/time_scenarios_example.yml
+       - cluster_shut_down_scenarios:
+           - scenarios/openshift/cluster_shut_down_scenario.yml
+       - service_disruption_scenarios:
+            - scenarios/openshift/regex_namespace.yaml
+            - scenarios/openshift/ingress_namespace.yaml
+       - zone_outages_scenarios:
+           - scenarios/openshift/zone_outage.yaml
+       - pvc_scenarios:
+           - scenarios/openshift/pvc_scenario.yaml
+       - network_chaos_scenarios:
+           - scenarios/openshift/network_chaos.yaml
+       - service_hijacking_scenarios:
+             - scenarios/kube/service_hijacking.yaml
+       - syn_flood_scenarios:
+             - scenarios/kube/syn_flood.yaml
+       - network_chaos_ng_scenarios:
+               - scenarios/kube/pod-network-filter.yml
+               - scenarios/kube/node-network-filter.yml
+       -  kubevirt_vm_outage:
+              - scenarios/kubevirt/kubevirt-vm-outage.yaml
 
 cerberus:
     cerberus_enabled: False                                # Enable it when cerberus is previously installed
     cerberus_url:                                          # When cerberus_enabled is set to True, provide the url where cerberus publishes go/no-go signal
-    check_applicaton_routes: False                         # When enabled will look for application unavailability using the routes specified in the cerberus config and fails the run
+    check_application_routes: False                         # When enabled will look for application unavailability using the routes specified in the cerberus config and fails the run
 
 performance_monitoring:
-    deploy_dashboards: False                              # Install a mutable grafana and load the performance dashboards. Enable this only when running on OpenShift
-    repo: "https://github.com/cloud-bulldozer/performance-dashboards.git"
-    prometheus_url: ''                                      # The prometheus url/route is automatically obtained in case of OpenShift, please set it when the distribution is Kubernetes.
+    prometheus_url: ''                                    # The prometheus url/route is automatically obtained in case of OpenShift, please set it when the distribution is Kubernetes.
     prometheus_bearer_token:                              # The bearer token is automatically obtained in case of OpenShift, please set it when the distribution is Kubernetes. This is needed to authenticate with prometheus.
     uuid:                                                 # uuid for the run is generated by default if not set
     enable_alerts: False                                  # Runs the queries specified in the alert profile and displays the info or exits 1 when severity=error
     enable_metrics: False
     alert_profile: config/alerts.yaml                          # Path or URL to alert profile with the prometheus queries
-    metrics_profile: config/metrics.yaml
+    metrics_profile: config/metrics-report.yaml
     check_critical_alerts: False                          # When enabled will check prometheus for critical alerts firing post chaos
 elastic:
     enable_elastic: False
-    collect_metrics: False
-    collect_alerts: False
     verify_certs: False
     elastic_url: ""                                         # To track results in elasticsearch, give url to server here; will post telemetry details when url and index not blank
     elastic_port: 32766
@@ -80,7 +79,7 @@ elastic:
     telemetry_index: "krkn-telemetry"
 
 tunings:
-    wait_duration: 60                                      # Duration to wait between each chaos scenario
+    wait_duration: 1                                      # Duration to wait between each chaos scenario
     iterations: 1                                          # Number of times to execute the scenarios
     daemon_mode: False                                     # Iterations are set to infinity which means that the kraken will cause chaos forever
 telemetry:
@@ -94,7 +93,7 @@ telemetry:
     prometheus_pod_name: ""                                 # name of the prometheus pod (if distribution is kubernetes)
     full_prometheus_backup: False                           # if is set to False only the /prometheus/wal folder will be downloaded.
     backup_threads: 5                                       # number of telemetry download/upload threads
-    archive_path: /tmp                                      # local path where the archive files will be temporarly stored
+    archive_path: /tmp                                      # local path where the archive files will be temporarily stored
     max_retries: 0                                          # maximum number of upload retries (if 0 will retry forever)
     run_tag: ''                                             # if set, this will be appended to the run folder in the bucket (useful to group the runs)
     archive_size: 500000
@@ -113,7 +112,20 @@ telemetry:
     oc_cli_path: /usr/bin/oc                                # optional, if not specified will be search in $PATH
     events_backup: True                                     # enables/disables cluster events collection
 
+health_checks:                                              # Utilizing health check endpoints to observe application behavior during chaos injection.
+    interval:                                               # Interval in seconds to perform health checks, default value is 2 seconds
+    config:                                                 # Provide list of health check configurations for applications
+        - url:                                              # Provide application endpoint
+          bearer_token:                                     # Bearer token for authentication if any
+          auth:                                             # Provide authentication credentials (username , password) in tuple format if any, ex:("admin","secretpassword")
+          exit_on_failure:                                  # If value is True exits when health check failed for application, values can be True/False
 
-
-
-
+kubevirt_checks:                                            # Utilizing virt check endpoints to observe ssh ability to VMI's during chaos injection.
+    interval: 2                                             # Interval in seconds to perform virt checks, default value is 2 seconds
+    namespace:                                              # Namespace where to find VMI's
+    name:                                                   # Regex Name style of VMI's to watch, optional, will watch all VMI names in the namespace if left blank
+    only_failures: False                                    # Boolean of whether to show all VMI's failures and successful ssh connection (False), or only failure status' (True) 
+    disconnected: False                                     # Boolean of how to try to connect to the VMIs; if True will use the ip_address to try ssh from within a node, if false will use the name and uses virtctl to try to connect; Default is False
+    ssh_node: ""                                            # If set, will be a backup way to ssh to a node. Will want to set to a node that isn't targeted in chaos
+    node_names: ""
+    exit_on_failure:                                        # If value is True and VMI's are failing post chaos returns failure, values can be True/False

config/config_kind.yaml

@@ -7,26 +7,33 @@ kraken:
     signal_state: RUN                                      # Will wait for the RUN signal when set to PAUSE before running the scenarios, refer docs/signal.md for more details
     signal_address: 0.0.0.0                                # Signal listening address
     chaos_scenarios:                                       # List of policies/chaos scenarios to load
-        - plugin_scenarios:
-            - scenarios/kind/scheduler.yml
-        - node_scenarios:
-            - scenarios/kind/node_scenarios_example.yml        
+        - pod_disruption_scenarios:
+            - scenarios/kube/pod.yml
 
 cerberus:
     cerberus_enabled: False                                # Enable it when cerberus is previously installed
     cerberus_url:                                          # When cerberus_enabled is set to True, provide the url where cerberus publishes go/no-go signal
-    check_applicaton_routes: False                         # When enabled will look for application unavailability using the routes specified in the cerberus config and fails the run
+    check_application_routes: False                         # When enabled will look for application unavailability using the routes specified in the cerberus config and fails the run
 
 performance_monitoring:
-    deploy_dashboards: False                              # Install a mutable grafana and load the performance dashboards. Enable this only when running on OpenShift
-    repo: "https://github.com/cloud-bulldozer/performance-dashboards.git"
     prometheus_url:                                       # The prometheus url/route is automatically obtained in case of OpenShift, please set it when the distribution is Kubernetes.
     prometheus_bearer_token:                              # The bearer token is automatically obtained in case of OpenShift, please set it when the distribution is Kubernetes. This is needed to authenticate with prometheus.
     uuid:                                                 # uuid for the run is generated by default if not set
     enable_alerts: False                                  # Runs the queries specified in the alert profile and displays the info or exits 1 when severity=error
     alert_profile: config/alerts.yaml                          # Path to alert profile with the prometheus queries
 
+elastic:
+    enable_elastic: False
+
 tunings:
     wait_duration: 60                                      # Duration to wait between each chaos scenario
     iterations: 1                                          # Number of times to execute the scenarios
     daemon_mode: False                                     # Iterations are set to infinity which means that the kraken will cause chaos forever
+
+telemetry:
+    enabled: False                                         # enable/disables the telemetry collection feature
+    archive_path: /tmp                                     # local path where the archive files will be temporarily stored
+    events_backup: False                                   # enables/disables cluster events collection
+    logs_backup: False
+
+health_checks:                                             # Utilizing health check endpoints to observe application behavior during chaos injection.

config/config_kubernetes.yaml

@@ -14,11 +14,9 @@ kraken:
 cerberus:
     cerberus_enabled: False                                # Enable it when cerberus is previously installed
     cerberus_url:                                          # When cerberus_enabled is set to True, provide the url where cerberus publishes go/no-go signal
-    check_applicaton_routes: False                         # When enabled will look for application unavailability using the routes specified in the cerberus config and fails the run
+    check_application_routes: False                         # When enabled will look for application unavailability using the routes specified in the cerberus config and fails the run
 
 performance_monitoring:
-    deploy_dashboards: False                              # Install a mutable grafana and load the performance dashboards. Enable this only when running on OpenShift
-    repo: "https://github.com/cloud-bulldozer/performance-dashboards.git"
     prometheus_url:                                       # The prometheus url/route is automatically obtained in case of OpenShift, please set it when the distribution is Kubernetes.
     prometheus_bearer_token:                              # The bearer token is automatically obtained in case of OpenShift, please set it when the distribution is Kubernetes. This is needed to authenticate with prometheus.
     uuid:                                                 # uuid for the run is generated by default if not set

config/config_performance.yaml

@@ -35,7 +35,7 @@ kraken:
 cerberus:
     cerberus_enabled: True                                # Enable it when cerberus is previously installed
     cerberus_url: http://0.0.0.0:8080                     # When cerberus_enabled is set to True, provide the url where cerberus publishes go/no-go signal
-    check_applicaton_routes: False                        # When enabled will look for application unavailability using the routes specified in the cerberus config and fails the run
+    check_application_routes: False                        # When enabled will look for application unavailability using the routes specified in the cerberus config and fails the run
 
 performance_monitoring:
     deploy_dashboards: True                               # Install a mutable grafana and load the performance dashboards. Enable this only when running on OpenShift
@@ -61,7 +61,7 @@ telemetry:
     prometheus_backup: True                                 # enables/disables prometheus data collection
     full_prometheus_backup: False                           # if is set to False only the /prometheus/wal folder will be downloaded.
     backup_threads: 5                                       # number of telemetry download/upload threads
-    archive_path: /tmp                                      # local path where the archive files will be temporarly stored
+    archive_path: /tmp                                      # local path where the archive files will be temporarily stored
     max_retries: 0                                          # maximum number of upload retries (if 0 will retry forever)
     run_tag: ''                                             # if set, this will be appended to the run folder in the bucket (useful to group the runs)
     archive_size: 500000                                     # the size of the prometheus data archive size in KB. The lower the size of archive is

config/metrics-aggregated.yaml

@@ -1,133 +1,126 @@
 metrics:
 # API server
-  - query: histogram_quantile(0.99, sum(rate(apiserver_request_duration_seconds_bucket{apiserver="kube-apiserver", verb!~"WATCH", subresource!="log"}[2m])) by (verb,resource,subresource,instance,le)) > 0
-    metricName: API99thLatency
-
   - query: sum(irate(apiserver_request_total{apiserver="kube-apiserver",verb!="WATCH",subresource!="log"}[2m])) by (verb,instance,resource,code) > 0
     metricName: APIRequestRate
+    instant: True
 
   - query: sum(apiserver_current_inflight_requests{}) by (request_kind) > 0
     metricName: APIInflightRequests
+    instant: True
+
+  - query: histogram_quantile(0.99, rate(apiserver_current_inflight_requests[5m]))
+    metricName: APIInflightRequests
+    instant: True
 
 # Container & pod metrics
   - query: (sum(container_memory_rss{name!="",container!="POD",namespace=~"openshift-(etcd|oauth-apiserver|.*apiserver|ovn-kubernetes|sdn|ingress|authentication|.*controller-manager|.*scheduler)"}) by (container, pod, namespace, node) and on (node) kube_node_role{role="master"}) > 0
     metricName: containerMemory-Masters
+    instant: true
 
   - query: (sum(irate(container_cpu_usage_seconds_total{name!="",container!="POD",namespace=~"openshift-(etcd|oauth-apiserver|sdn|ovn-kubernetes|.*apiserver|authentication|.*controller-manager|.*scheduler)"}[2m]) * 100) by (container, pod, namespace, node) and on (node) kube_node_role{role="master"}) > 0
     metricName: containerCPU-Masters
+    instant: true
 
   - query: (sum(irate(container_cpu_usage_seconds_total{pod!="",container="prometheus",namespace="openshift-monitoring"}[2m]) * 100) by (container, pod, namespace, node) and on (node) kube_node_role{role="infra"}) > 0
     metricName: containerCPU-Prometheus
+    instant: true
 
   - query: (avg(irate(container_cpu_usage_seconds_total{name!="",container!="POD",namespace=~"openshift-(sdn|ovn-kubernetes|ingress)"}[2m]) * 100 and on (node) kube_node_role{role="worker"}) by (namespace, container)) > 0
     metricName: containerCPU-AggregatedWorkers
+    instant: true
 
   - query: (avg(irate(container_cpu_usage_seconds_total{name!="",container!="POD",namespace=~"openshift-(sdn|ovn-kubernetes|ingress|monitoring|image-registry|logging)"}[2m]) * 100 and on (node) kube_node_role{role="infra"}) by (namespace, container)) > 0
     metricName: containerCPU-AggregatedInfra
 
   - query: (sum(container_memory_rss{pod!="",namespace="openshift-monitoring",name!="",container="prometheus"}) by (container, pod, namespace, node) and on (node) kube_node_role{role="infra"}) > 0
     metricName: containerMemory-Prometheus
+    instant: True
 
   - query: avg(container_memory_rss{name!="",container!="POD",namespace=~"openshift-(sdn|ovn-kubernetes|ingress)"} and on (node) kube_node_role{role="worker"}) by (container, namespace)
     metricName: containerMemory-AggregatedWorkers
+    instant: True
 
   - query: avg(container_memory_rss{name!="",container!="POD",namespace=~"openshift-(sdn|ovn-kubernetes|ingress|monitoring|image-registry|logging)"} and on (node) kube_node_role{role="infra"}) by (container, namespace)
     metricName: containerMemory-AggregatedInfra
+    instant: True
 
 # Node metrics
   - query: (sum(irate(node_cpu_seconds_total[2m])) by (mode,instance) and on (instance) label_replace(kube_node_role{role="master"}, "instance", "$1", "node", "(.+)")) > 0
     metricName: nodeCPU-Masters
+    instant: True
+
+  - query: max(max_over_time(sum(irate(node_cpu_seconds_total{mode!="idle", mode!="steal"}[2m]) and on (instance) label_replace(kube_node_role{role="master"}, "instance", "$1", "node", "(.+)")) by (instance)[.elapsed:]))
+    metricName: maxCPU-Masters
+    instant: true
+  
+  - query: avg(avg_over_time((node_memory_MemTotal_bytes - node_memory_MemAvailable_bytes)[.elapsed:]) and on (instance) label_replace(kube_node_role{role="master"}, "instance", "$1", "node", "(.+)"))
+    metricName: nodeMemory-Masters
+    instant: true
 
   - query: (avg((sum(irate(node_cpu_seconds_total[2m])) by (mode,instance) and on (instance) label_replace(kube_node_role{role="worker"}, "instance", "$1", "node", "(.+)"))) by (mode)) > 0
     metricName: nodeCPU-AggregatedWorkers
+    instant: True
 
   - query: (avg((sum(irate(node_cpu_seconds_total[2m])) by (mode,instance) and on (instance) label_replace(kube_node_role{role="infra"}, "instance", "$1", "node", "(.+)"))) by (mode)) > 0
     metricName: nodeCPU-AggregatedInfra
+    instant: True
 
-  - query: avg(node_memory_MemAvailable_bytes) by (instance) and on (instance) label_replace(kube_node_role{role="master"}, "instance", "$1", "node", "(.+)")
-    metricName: nodeMemoryAvailable-Masters
+  - query: avg(avg_over_time((node_memory_MemTotal_bytes - node_memory_MemAvailable_bytes)[.elapsed:]) and on (instance) label_replace(kube_node_role{role="master"}, "instance", "$1", "node", "(.+)"))
+    metricName: nodeMemory-Masters
+    instant: true
+
+  - query: max(max_over_time((node_memory_MemTotal_bytes - node_memory_MemAvailable_bytes)[.elapsed:]) and on (instance) label_replace(kube_node_role{role="master"}, "instance", "$1", "node", "(.+)"))
+    metricName: maxMemory-Masters
+    instant: true
 
   - query: avg(node_memory_MemAvailable_bytes and on (instance) label_replace(kube_node_role{role="worker"}, "instance", "$1", "node", "(.+)"))
     metricName: nodeMemoryAvailable-AggregatedWorkers
+    instant: True
+
+  - query: max(max_over_time(sum(irate(node_cpu_seconds_total{mode!="idle", mode!="steal"}[2m]) and on (instance) label_replace(kube_node_role{role="worker"}, "instance", "$1", "node", "(.+)")) by (instance)[.elapsed:]))
+    metricName: maxCPU-Workers
+    instant: true
+  
+  - query: max(max_over_time((node_memory_MemTotal_bytes - node_memory_MemAvailable_bytes)[.elapsed:]) and on (instance) label_replace(kube_node_role{role="worker"}, "instance", "$1", "node", "(.+)"))
+    metricName: maxMemory-Workers
+    instant: true
 
   - query: avg(node_memory_MemAvailable_bytes and on (instance) label_replace(kube_node_role{role="infra"}, "instance", "$1", "node", "(.+)"))
     metricName: nodeMemoryAvailable-AggregatedInfra
+    instant: True
 
   - query: avg(node_memory_Active_bytes) by (instance) and on (instance) label_replace(kube_node_role{role="master"}, "instance", "$1", "node", "(.+)")
     metricName: nodeMemoryActive-Masters
+    instant: True
 
   - query: avg(node_memory_Active_bytes and on (instance) label_replace(kube_node_role{role="worker"}, "instance", "$1", "node", "(.+)"))
     metricName: nodeMemoryActive-AggregatedWorkers
+    instant: True
 
   - query: avg(avg(node_memory_Active_bytes) by (instance) and on (instance) label_replace(kube_node_role{role="infra"}, "instance", "$1", "node", "(.+)"))
     metricName: nodeMemoryActive-AggregatedInfra
-
-  - query: avg(node_memory_Cached_bytes) by (instance) + avg(node_memory_Buffers_bytes) by (instance) and on (instance) label_replace(kube_node_role{role="master"}, "instance", "$1", "node", "(.+)")
-    metricName: nodeMemoryCached+nodeMemoryBuffers-Masters
-
-  - query: avg(node_memory_Cached_bytes + node_memory_Buffers_bytes and on (instance) label_replace(kube_node_role{role="worker"}, "instance", "$1", "node", "(.+)"))
-    metricName: nodeMemoryCached+nodeMemoryBuffers-AggregatedWorkers
-
-  - query: avg(node_memory_Cached_bytes + node_memory_Buffers_bytes and on (instance) label_replace(kube_node_role{role="infra"}, "instance", "$1", "node", "(.+)"))
-    metricName: nodeMemoryCached+nodeMemoryBuffers-AggregatedInfra
-
-  - query: irate(node_network_receive_bytes_total{device=~"^(ens|eth|bond|team).*"}[2m]) and on (instance) label_replace(kube_node_role{role="master"}, "instance", "$1", "node", "(.+)")
-    metricName: rxNetworkBytes-Masters
-
-  - query: avg(irate(node_network_receive_bytes_total{device=~"^(ens|eth|bond|team).*"}[2m]) and on (instance) label_replace(kube_node_role{role="worker"}, "instance", "$1", "node", "(.+)")) by (device)
-    metricName: rxNetworkBytes-AggregatedWorkers
-
-  - query: avg(irate(node_network_receive_bytes_total{device=~"^(ens|eth|bond|team).*"}[2m]) and on (instance) label_replace(kube_node_role{role="infra"}, "instance", "$1", "node", "(.+)")) by (device)
-    metricName: rxNetworkBytes-AggregatedInfra
-
-  - query: irate(node_network_transmit_bytes_total{device=~"^(ens|eth|bond|team).*"}[2m]) and on (instance) label_replace(kube_node_role{role="master"}, "instance", "$1", "node", "(.+)")
-    metricName: txNetworkBytes-Masters
-
-  - query: avg(irate(node_network_transmit_bytes_total{device=~"^(ens|eth|bond|team).*"}[2m]) and on (instance) label_replace(kube_node_role{role="worker"}, "instance", "$1", "node", "(.+)")) by (device)
-    metricName: txNetworkBytes-AggregatedWorkers
-
-  - query: avg(irate(node_network_transmit_bytes_total{device=~"^(ens|eth|bond|team).*"}[2m]) and on (instance) label_replace(kube_node_role{role="infra"}, "instance", "$1", "node", "(.+)")) by (device)
-    metricName: txNetworkBytes-AggregatedInfra
-
-  - query: rate(node_disk_written_bytes_total{device!~"^(dm|rb).*"}[2m]) and on (instance) label_replace(kube_node_role{role="master"}, "instance", "$1", "node", "(.+)")
-    metricName: nodeDiskWrittenBytes-Masters
-
-  - query: avg(rate(node_disk_written_bytes_total{device!~"^(dm|rb).*"}[2m]) and on (instance) label_replace(kube_node_role{role="worker"}, "instance", "$1", "node", "(.+)")) by (device)
-    metricName: nodeDiskWrittenBytes-AggregatedWorkers
-
-  - query: avg(rate(node_disk_written_bytes_total{device!~"^(dm|rb).*"}[2m]) and on (instance) label_replace(kube_node_role{role="infra"}, "instance", "$1", "node", "(.+)")) by (device)
-    metricName: nodeDiskWrittenBytes-AggregatedInfra
-
-  - query: rate(node_disk_read_bytes_total{device!~"^(dm|rb).*"}[2m]) and on (instance) label_replace(kube_node_role{role="master"}, "instance", "$1", "node", "(.+)")
-    metricName: nodeDiskReadBytes-Masters
-
-  - query: avg(rate(node_disk_read_bytes_total{device!~"^(dm|rb).*"}[2m]) and on (instance) label_replace(kube_node_role{role="worker"}, "instance", "$1", "node", "(.+)")) by (device)
-    metricName: nodeDiskReadBytes-AggregatedWorkers
-
-  - query: avg(rate(node_disk_read_bytes_total{device!~"^(dm|rb).*"}[2m]) and on (instance) label_replace(kube_node_role{role="infra"}, "instance", "$1", "node", "(.+)")) by (device)
-    metricName: nodeDiskReadBytes-AggregatedInfra
+    instant: True
 
 # Etcd metrics
   - query: sum(rate(etcd_server_leader_changes_seen_total[2m]))
     metricName: etcdLeaderChangesRate
+    instant: True
 
   - query: etcd_server_is_leader > 0
     metricName: etcdServerIsLeader
+    instant: True
 
   - query: histogram_quantile(0.99, rate(etcd_disk_backend_commit_duration_seconds_bucket[2m]))
     metricName: 99thEtcdDiskBackendCommitDurationSeconds
+    instant: True
 
   - query: histogram_quantile(0.99, rate(etcd_disk_wal_fsync_duration_seconds_bucket[2m]))
     metricName: 99thEtcdDiskWalFsyncDurationSeconds
+    instant: True
 
   - query: histogram_quantile(0.99, rate(etcd_network_peer_round_trip_time_seconds_bucket[5m]))
     metricName: 99thEtcdRoundTripTimeSeconds
-
-  - query: etcd_mvcc_db_total_size_in_bytes
-    metricName: etcdDBPhysicalSizeBytes
-
-  - query: etcd_mvcc_db_total_size_in_use_in_bytes
-    metricName: etcdDBLogicalSizeBytes
+    instant: True
 
   - query: sum by (cluster_version)(etcd_cluster_version)
     metricName: etcdVersion
@@ -135,83 +128,16 @@ metrics:
 
   - query: sum(rate(etcd_object_counts{}[5m])) by (resource) > 0
     metricName: etcdObjectCount
+    instant: True
 
   - query: histogram_quantile(0.99,sum(rate(etcd_request_duration_seconds_bucket[2m])) by (le,operation,apiserver)) > 0
     metricName: P99APIEtcdRequestLatency
-
-  - query: sum(grpc_server_started_total{namespace="openshift-etcd",grpc_service="etcdserverpb.Watch",grpc_type="bidi_stream"}) - sum(grpc_server_handled_total{namespace="openshift-etcd",grpc_service="etcdserverpb.Watch",grpc_type="bidi_stream"})
-    metricName: ActiveWatchStreams
-
-  - query: sum(grpc_server_started_total{namespace="openshift-etcd",grpc_service="etcdserverpb.Lease",grpc_type="bidi_stream"}) - sum(grpc_server_handled_total{namespace="openshift-etcd",grpc_service="etcdserverpb.Lease",grpc_type="bidi_stream"})
-    metricName: ActiveLeaseStreams
-
-  - query: sum(rate(etcd_debugging_snap_save_total_duration_seconds_sum{namespace="openshift-etcd"}[2m]))
-    metricName: snapshotSaveLatency
-
-  - query: sum(rate(etcd_server_heartbeat_send_failures_total{namespace="openshift-etcd"}[2m]))
-    metricName: HeartBeatFailures
-
-  - query: sum(rate(etcd_server_health_failures{namespace="openshift-etcd"}[2m]))
-    metricName: HealthFailures
-
-  - query: sum(rate(etcd_server_slow_apply_total{namespace="openshift-etcd"}[2m]))
-    metricName: SlowApplies
-
-  - query: sum(rate(etcd_server_slow_read_indexes_total{namespace="openshift-etcd"}[2m]))
-    metricName: SlowIndexRead
-
-  - query: sum(etcd_server_proposals_pending)
-    metricName: PendingProposals
-
-  - query: histogram_quantile(1.0, sum(rate(etcd_debugging_mvcc_db_compaction_pause_duration_milliseconds_bucket[1m])) by (le, instance))
-    metricName: CompactionMaxPause
+    instant: True
 
   - query: sum by (instance) (apiserver_storage_objects)
     metricName: etcdTotalObjectCount 
+    instant: True
 
   - query: topk(500, max by(resource) (apiserver_storage_objects))
     metricName: etcdTopObectCount    
-
-# Cluster metrics
-  - query: count(kube_namespace_created)
-    metricName: namespaceCount
-
-  - query: sum(kube_pod_status_phase{}) by (phase)
-    metricName: podStatusCount
-
-  - query: count(kube_secret_info{})
-    metricName: secretCount
-
-  - query: count(kube_deployment_labels{})
-    metricName: deploymentCount
-
-  - query: count(kube_configmap_info{})
-    metricName: configmapCount
-
-  - query: count(kube_service_info{})
-    metricName: serviceCount
-
-  - query: kube_node_role
-    metricName: nodeRoles
-    instant: true
-
-  - query: sum(kube_node_status_condition{status="true"}) by (condition)
-    metricName: nodeStatus
-
-  - query: (sum(rate(container_fs_writes_bytes_total{container!="",device!~".+dm.+"}[5m])) by (device, container, node) and on (node) kube_node_role{role="master"}) > 0
-    metricName: containerDiskUsage
-
-  - query: cluster_version{type="completed"}
-    metricName: clusterVersion
-    instant: true
-
-# Golang metrics
-
-  - query: go_memstats_heap_alloc_bytes{job=~"apiserver|api|etcd"}
-    metricName: goHeapAllocBytes
-
-  - query: go_memstats_heap_inuse_bytes{job=~"apiserver|api|etcd"}
-    metricName: goHeapInuseBytes
-
-  - query: go_gc_duration_seconds{job=~"apiserver|api|etcd",quantile="1"}
-    metricName: goGCDurationSeconds
+    instant: True

config/metrics-report.yaml

@@ -0,0 +1,248 @@
+metrics:
+
+# API server
+- query: sum(apiserver_current_inflight_requests{}) by (request_kind) > 0
+  metricName: APIInflightRequests
+  instant: true
+
+# Kubelet & CRI-O
+
+# Average and max of the CPU usage from all worker's kubelet
+- query: avg(avg_over_time(irate(process_cpu_seconds_total{service="kubelet",job="kubelet"}[2m])[.elapsed:]) and on (node) kube_node_role{role="worker"})
+  metricName: cpu-kubelet
+  instant: true
+
+- query: max(max_over_time(irate(process_cpu_seconds_total{service="kubelet",job="kubelet"}[2m])[.elapsed:]) and on (node) kube_node_role{role="worker"})
+  metricName: max-cpu-kubelet
+  instant: true
+
+# Average of the memory usage from all worker's kubelet
+- query: avg(avg_over_time(process_resident_memory_bytes{service="kubelet",job="kubelet"}[.elapsed:]) and on (node) kube_node_role{role="worker"})
+  metricName: memory-kubelet
+  instant: true
+
+# Max of the memory usage from all worker's kubelet
+- query: max(max_over_time(process_resident_memory_bytes{service="kubelet",job="kubelet"}[.elapsed:]) and on (node) kube_node_role{role="worker"})
+  metricName: max-memory-kubelet
+  instant: true
+
+- query: max_over_time(sum(process_resident_memory_bytes{service="kubelet",job="kubelet"} and on (node) kube_node_role{role="worker"})[.elapsed:])
+  metricName: max-memory-sum-kubelet
+  instant: true
+
+# Average and max of the CPU usage from all worker's CRI-O
+- query: avg(avg_over_time(irate(process_cpu_seconds_total{service="kubelet",job="crio"}[2m])[.elapsed:]) and on (node) kube_node_role{role="worker"})
+  metricName: cpu-crio
+  instant: true
+
+- query: max(max_over_time(irate(process_cpu_seconds_total{service="kubelet",job="crio"}[2m])[.elapsed:]) and on (node) kube_node_role{role="worker"})
+  metricName: max-cpu-crio
+  instant: true
+
+# Average of the memory usage from all worker's CRI-O
+- query: avg(avg_over_time(process_resident_memory_bytes{service="kubelet",job="crio"}[.elapsed:]) and on (node) kube_node_role{role="worker"})
+  metricName: memory-crio
+  instant: true
+
+# Max of the memory usage from all worker's CRI-O
+- query: max(max_over_time(process_resident_memory_bytes{service="kubelet",job="crio"}[.elapsed:]) and on (node) kube_node_role{role="worker"})
+  metricName: max-memory-crio
+  instant: true
+
+# Etcd
+
+- query: avg(avg_over_time(histogram_quantile(0.99, rate(etcd_disk_backend_commit_duration_seconds_bucket[2m]))[.elapsed:]))
+  metricName: 99thEtcdDiskBackendCommit
+  instant: true
+
+- query: avg(avg_over_time(histogram_quantile(0.99, rate(etcd_disk_wal_fsync_duration_seconds_bucket[2m]))[.elapsed:]))
+  metricName: 99thEtcdDiskWalFsync
+  instant: true
+
+- query: avg(avg_over_time(histogram_quantile(0.99, irate(etcd_network_peer_round_trip_time_seconds_bucket[2m]))[.elapsed:]))
+  metricName: 99thEtcdRoundTripTime
+  instant: true
+
+# Control-plane
+
+- query: avg(avg_over_time(topk(1, sum(irate(container_cpu_usage_seconds_total{name!="", namespace="openshift-kube-controller-manager"}[2m])) by (pod))[.elapsed:]))
+  metricName: cpu-kube-controller-manager
+  instant: true
+
+- query: max(max_over_time(topk(1, sum(irate(container_cpu_usage_seconds_total{name!="", namespace="openshift-kube-controller-manager"}[2m])) by (pod))[.elapsed:]))
+  metricName: max-cpu-kube-controller-manager
+  instant: true
+
+- query: avg(avg_over_time(topk(1, sum(container_memory_rss{name!="", namespace="openshift-kube-controller-manager"}) by (pod))[.elapsed:]))
+  metricName: memory-kube-controller-manager
+  instant: true
+
+- query: max(max_over_time(topk(1, sum(container_memory_rss{name!="", namespace="openshift-kube-controller-manager"}) by (pod))[.elapsed:]))
+  metricName: max-memory-kube-controller-manager
+  instant: true
+
+- query: avg(avg_over_time(topk(3, sum(irate(container_cpu_usage_seconds_total{name!="", namespace="openshift-kube-apiserver"}[2m])) by (pod))[.elapsed:]))
+  metricName: cpu-kube-apiserver
+  instant: true
+
+- query: avg(avg_over_time(topk(3, sum(container_memory_rss{name!="", namespace="openshift-kube-apiserver"}) by (pod))[.elapsed:]))
+  metricName: memory-kube-apiserver
+  instant: true
+
+- query: avg(avg_over_time(topk(3, sum(irate(container_cpu_usage_seconds_total{name!="", namespace="openshift-apiserver"}[2m])) by (pod))[.elapsed:]))
+  metricName: cpu-openshift-apiserver
+  instant: true
+
+- query: avg(avg_over_time(topk(3, sum(container_memory_rss{name!="", namespace="openshift-apiserver"}) by (pod))[.elapsed:]))
+  metricName: memory-openshift-apiserver
+  instant: true
+
+- query: avg(avg_over_time(topk(3, sum(irate(container_cpu_usage_seconds_total{name!="", namespace="openshift-etcd"}[2m])) by (pod))[.elapsed:]))
+  metricName: cpu-etcd
+  instant: true
+
+- query: avg(avg_over_time(topk(3,sum(container_memory_rss{name!="", namespace="openshift-etcd"}) by (pod))[.elapsed:]))
+  metricName: memory-etcd
+  instant: true
+
+- query: avg(avg_over_time(topk(1, sum(irate(container_cpu_usage_seconds_total{name!="", namespace="openshift-controller-manager"}[2m])) by (pod))[.elapsed:]))
+  metricName: cpu-openshift-controller-manager
+  instant: true
+
+- query: avg(avg_over_time(topk(1, sum(container_memory_rss{name!="", namespace="openshift-controller-manager"}) by (pod))[.elapsed:]))
+  metricName: memory-openshift-controller-manager
+  instant: true
+
+ # multus
+
+- query: avg(avg_over_time(irate(container_cpu_usage_seconds_total{name!="", namespace="openshift-multus", pod=~"(multus).+", container!="POD"}[2m])[.elapsed:])) by (container)
+  metricName: cpu-multus
+  instant: true
+
+- query: avg(avg_over_time(container_memory_rss{name!="", namespace="openshift-multus", pod=~"(multus).+", container!="POD"}[.elapsed:])) by (container)
+  metricName: memory-multus
+  instant: true
+
+# OVNKubernetes - standard & IC
+
+- query: avg(avg_over_time(irate(container_cpu_usage_seconds_total{name!="", namespace="openshift-ovn-kubernetes", pod=~"(ovnkube-master|ovnkube-control-plane).+", container!="POD"}[2m])[.elapsed:])) by (container)
+  metricName: cpu-ovn-control-plane
+  instant: true
+
+- query: avg(avg_over_time(container_memory_rss{name!="", namespace="openshift-ovn-kubernetes", pod=~"(ovnkube-master|ovnkube-control-plane).+", container!="POD"}[.elapsed:])) by (container)
+  metricName: memory-ovn-control-plane
+  instant: true
+
+- query: avg(avg_over_time(irate(container_cpu_usage_seconds_total{name!="", namespace="openshift-ovn-kubernetes", pod=~"ovnkube-node.+", container!="POD"}[2m])[.elapsed:])) by (container)
+  metricName: cpu-ovnkube-node
+  instant: true
+
+- query: avg(avg_over_time(container_memory_rss{name!="", namespace="openshift-ovn-kubernetes", pod=~"ovnkube-node.+", container!="POD"}[.elapsed:])) by (container)
+  metricName: memory-ovnkube-node
+  instant: true
+
+# Nodes
+
+- query: avg(avg_over_time(sum(irate(node_cpu_seconds_total{mode!="idle", mode!="steal"}[2m]) and on (instance) label_replace(kube_node_role{role="master"}, "instance", "$1", "node", "(.+)")) by (instance)[.elapsed:]))
+  metricName: cpu-masters
+  instant: true
+
+- query: avg(avg_over_time((node_memory_MemTotal_bytes - node_memory_MemAvailable_bytes)[.elapsed:]) and on (instance) label_replace(kube_node_role{role="master"}, "instance", "$1", "node", "(.+)"))
+  metricName: memory-masters
+  instant: true
+
+- query: max(max_over_time((node_memory_MemTotal_bytes - node_memory_MemAvailable_bytes)[.elapsed:]) and on (instance) label_replace(kube_node_role{role="master"}, "instance", "$1", "node", "(.+)"))
+  metricName: max-memory-masters
+  instant: true
+
+- query: avg(avg_over_time(sum(irate(node_cpu_seconds_total{mode!="idle", mode!="steal"}[2m]) and on (instance) label_replace(kube_node_role{role="worker"}, "instance", "$1", "node", "(.+)")) by (instance)[.elapsed:]))
+  metricName: cpu-workers
+  instant: true
+
+- query: max(max_over_time(sum(irate(node_cpu_seconds_total{mode!="idle", mode!="steal"}[2m]) and on (instance) label_replace(kube_node_role{role="worker"}, "instance", "$1", "node", "(.+)")) by (instance)[.elapsed:]))
+  metricName: max-cpu-workers
+  instant: true
+
+- query: avg(avg_over_time((node_memory_MemTotal_bytes - node_memory_MemAvailable_bytes)[.elapsed:]) and on (instance) label_replace(kube_node_role{role="worker"}, "instance", "$1", "node", "(.+)"))
+  metricName: memory-workers
+  instant: true
+
+- query: max(max_over_time((node_memory_MemTotal_bytes - node_memory_MemAvailable_bytes)[.elapsed:]) and on (instance) label_replace(kube_node_role{role="worker"}, "instance", "$1", "node", "(.+)"))
+  metricName: max-memory-workers
+  instant: true
+
+- query: sum( (node_memory_MemTotal_bytes - node_memory_MemAvailable_bytes) and on (instance) label_replace(kube_node_role{role="worker"}, "instance", "$1", "node", "(.+)") )
+  metricName: memory-sum-workers
+  instant: true
+
+
+- query: avg(avg_over_time(sum(irate(node_cpu_seconds_total{mode!="idle", mode!="steal"}[2m]) and on (instance) label_replace(kube_node_role{role="infra"}, "instance", "$1", "node", "(.+)")) by (instance)[.elapsed:]))
+  metricName: cpu-infra
+  instant: true
+
+- query: max(max_over_time(sum(irate(node_cpu_seconds_total{mode!="idle", mode!="steal"}[2m]) and on (instance) label_replace(kube_node_role{role="infra"}, "instance", "$1", "node", "(.+)")) by (instance)[.elapsed:]))
+  metricName: max-cpu-infra
+  instant: true
+
+- query: avg(avg_over_time((node_memory_MemTotal_bytes - node_memory_MemAvailable_bytes)[.elapsed:]) and on (instance) label_replace(kube_node_role{role="infra"}, "instance", "$1", "node", "(.+)"))
+  metricName: memory-infra
+  instant: true
+
+- query: max(max_over_time((node_memory_MemTotal_bytes - node_memory_MemAvailable_bytes)[.elapsed:]) and on (instance) label_replace(kube_node_role{role="infra"}, "instance", "$1", "node", "(.+)"))
+  metricName: max-memory-infra
+  instant: true
+
+- query: max_over_time(sum((node_memory_MemTotal_bytes - node_memory_MemAvailable_bytes) and on (instance) label_replace(kube_node_role{role="infra"}, "instance", "$1", "node", "(.+)"))[.elapsed:])
+  metricName: max-memory-sum-infra
+  instant: true
+
+# Monitoring and ingress
+
+- query: avg(avg_over_time(sum(irate(container_cpu_usage_seconds_total{name!="", namespace="openshift-monitoring", pod=~"prometheus-k8s.+"}[2m])) by (pod)[.elapsed:]))
+  metricName: cpu-prometheus
+  instant: true
+
+- query: max(max_over_time(sum(irate(container_cpu_usage_seconds_total{name!="", namespace="openshift-monitoring", pod=~"prometheus-k8s.+"}[2m])) by (pod)[.elapsed:]))
+  metricName: max-cpu-prometheus
+  instant: true
+
+- query: avg(avg_over_time(sum(container_memory_rss{name!="", namespace="openshift-monitoring", pod=~"prometheus-k8s.+"}) by (pod)[.elapsed:]))
+  metricName: memory-prometheus
+  instant: true
+
+- query: max(max_over_time(sum(container_memory_rss{name!="", namespace="openshift-monitoring", pod=~"prometheus-k8s.+"}) by (pod)[.elapsed:]))
+  metricName: max-memory-prometheus
+  instant: true
+
+- query: avg(avg_over_time(sum(irate(container_cpu_usage_seconds_total{name!="", namespace="openshift-ingress", pod=~"router-default.+"}[2m])) by (pod)[.elapsed:]))
+  metricName: cpu-router
+  instant: true
+
+- query: avg(avg_over_time(sum(container_memory_rss{name!="", namespace="openshift-ingress", pod=~"router-default.+"}) by (pod)[.elapsed:]))
+  metricName: memory-router
+  instant: true
+
+# Cluster
+
+- query: avg_over_time(cluster:memory_usage:ratio[.elapsed:])
+  metricName: memory-cluster-usage-ratio
+  instant: true
+
+- query: avg_over_time(cluster:node_cpu:ratio[.elapsed:])
+  metricName: cpu-cluster-usage-ratio
+  instant: true
+
+# Retain the raw CPU seconds totals for comparison
+- query: sum(node_cpu_seconds_total and on (instance) label_replace(kube_node_role{role="worker",role!="infra"}, "instance", "$1", "node", "(.+)")) by (mode)
+  metricName: nodeCPUSeconds-Workers
+  instant: true
+
+
+- query: sum(node_cpu_seconds_total and on (instance) label_replace(kube_node_role{role="master"}, "instance", "$1", "node", "(.+)")) by (mode)
+  metricName: nodeCPUSeconds-Masters
+  instant: true
+
+
+- query: sum(node_cpu_seconds_total and on (instance) label_replace(kube_node_role{role="infra"}, "instance", "$1", "node", "(.+)")) by (mode)
+  metricName: nodeCPUSeconds-Infra
+  instant: true

config/metrics.yaml

@@ -1,13 +1,7 @@
 metrics:
 # API server
-  - query: histogram_quantile(0.99, sum(rate(apiserver_request_duration_seconds_bucket{apiserver="kube-apiserver", verb!~"WATCH", subresource!="log"}[2m])) by (verb,resource,subresource,instance,le)) > 0
-    metricName: API99thLatency
-
-  - query: sum(irate(apiserver_request_total{apiserver="kube-apiserver",verb!="WATCH",subresource!="log"}[2m])) by (verb,instance,resource,code) > 0
-    metricName: APIRequestRate
-
-  - query: sum(apiserver_current_inflight_requests{}) by (request_kind) > 0
-    metricName: APIInflightRequests
+  - query: irate(apiserver_request_total{verb="POST", resource="pods", subresource="binding",code="201"}[2m]) > 0
+    metricName: schedulingThroughput
 
 # Containers & pod metrics
   - query: sum(irate(container_cpu_usage_seconds_total{name!="",namespace=~"openshift-(etcd|oauth-apiserver|.*apiserver|ovn-kubernetes|sdn|ingress|authentication|.*controller-manager|.*scheduler|monitoring|logging|image-registry)"}[2m]) * 100) by (pod, namespace, node)
@@ -33,8 +27,17 @@ metrics:
     metricName: crioMemory
 
 # Node metrics
-  - query: sum(irate(node_cpu_seconds_total[2m])) by (mode,instance) > 0
-    metricName: nodeCPU
+  - query: (sum(irate(node_cpu_seconds_total[2m])) by (mode,instance) and on (instance) label_replace(kube_node_role{role="master"}, "instance", "$1", "node", "(.+)")) > 0
+    metricName: nodeCPU-Masters
+
+  - query: (avg_over_time((node_memory_MemTotal_bytes - node_memory_MemAvailable_bytes)[.elapsed:]) and on (instance) label_replace(kube_node_role{role="master"}, "instance", "$1", "node", "(.+)"))
+    metricName: nodeMemory-Masters
+  
+  - query: (sum(irate(node_cpu_seconds_total[2m])) by (mode,instance) and on (instance) label_replace(kube_node_role{role="worker"}, "instance", "$1", "node", "(.+)")) > 0
+    metricName: nodeCPU-Workers
+  
+  - query: (avg_over_time((node_memory_MemTotal_bytes - node_memory_MemAvailable_bytes)[2m:]) and on (instance) label_replace(kube_node_role{role="worker"}, "instance", "$1", "node", "(.+)"))
+    metricName: nodeMemory-Workers
 
   - query: avg(node_memory_MemAvailable_bytes) by (instance)
     metricName: nodeMemoryAvailable
@@ -42,6 +45,9 @@ metrics:
   - query: avg(node_memory_Active_bytes) by (instance)
     metricName: nodeMemoryActive
 
+  - query: max(max_over_time((node_memory_MemTotal_bytes - node_memory_MemAvailable_bytes)[.elapsed:]) and on (instance) label_replace(kube_node_role{role="master"}, "instance", "$1", "node", "(.+)"))
+    metricName: maxMemory-Masters
+
   - query: avg(node_memory_Cached_bytes) by (instance) + avg(node_memory_Buffers_bytes) by (instance)
     metricName: nodeMemoryCached+nodeMemoryBuffers
 
@@ -84,34 +90,4 @@ metrics:
 
   - query: sum by (cluster_version)(etcd_cluster_version)
     metricName: etcdVersion
-    instant: true
-
-# Cluster metrics
-  - query: count(kube_namespace_created)
-    metricName: namespaceCount
-
-  - query: sum(kube_pod_status_phase{}) by (phase)
-    metricName: podStatusCount
-
-  - query: count(kube_secret_info{})
-    metricName: secretCount
-
-  - query: count(kube_deployment_labels{})
-    metricName: deploymentCount
-
-  - query: count(kube_configmap_info{})
-    metricName: configmapCount
-
-  - query: count(kube_service_info{})
-    metricName: serviceCount
-
-  - query: kube_node_role
-    metricName: nodeRoles
-    instant: true
-
-  - query: sum(kube_node_status_condition{status="true"}) by (condition)
-    metricName: nodeStatus
-
-  - query: cluster_version{type="completed"}
-    metricName: clusterVersion
-    instant: true
+    instant: true

containers/Dockerfile.template

@@ -1,17 +1,35 @@
 # oc build
-FROM golang:1.22.5 AS oc-build
+FROM golang:1.24.9 AS oc-build
 RUN apt-get update && apt-get install -y --no-install-recommends libkrb5-dev
 WORKDIR /tmp
+# oc build
 RUN git clone --branch release-4.18 https://github.com/openshift/oc.git
 WORKDIR /tmp/oc
-RUN go mod edit -go 1.22.5 &&\
-    go get github.com/moby/buildkit@v0.12.5 &&\
-    go get github.com/containerd/containerd@v1.7.11&&\
-    go get github.com/docker/docker@v25.0.6&&\
-    go get github.com/opencontainers/runc@v1.1.14&&\
+RUN go mod edit -go 1.24.9 &&\
+    go mod edit -require github.com/moby/buildkit@v0.12.5 &&\
+    go mod edit -require github.com/containerd/containerd@v1.7.29&&\
+    go mod edit -require github.com/docker/docker@v27.5.1+incompatible&&\
+    go mod edit -require github.com/opencontainers/runc@v1.2.8&&\
+    go mod edit -require github.com/go-git/go-git/v5@v5.13.0&&\
+    go mod edit -require github.com/opencontainers/selinux@v1.13.0&&\
+    go mod edit -require github.com/ulikunitz/xz@v0.5.15&&\
+    go mod edit -require golang.org/x/net@v0.38.0&&\
+    go mod edit -require github.com/containerd/containerd@v1.7.27&&\
+    go mod edit -require golang.org/x/oauth2@v0.27.0&&\
+    go mod edit -require golang.org/x/crypto@v0.35.0&&\
+    go mod edit -replace github.com/containerd/containerd@v1.7.27=github.com/containerd/containerd@v1.7.29&&\
     go mod tidy && go mod vendor
+
 RUN make GO_REQUIRED_MIN_VERSION:= oc
 
+# virtctl build
+WORKDIR /tmp
+RUN git clone https://github.com/kubevirt/kubevirt.git
+WORKDIR /tmp/kubevirt
+RUN go mod edit -go 1.24.9 &&\
+    go work use &&\
+    go build -o virtctl ./cmd/virtctl/
+
 FROM fedora:40
 ARG PR_NUMBER
 ARG TAG
@@ -20,23 +38,23 @@ RUN dnf update -y
 
 ENV KUBECONFIG /home/krkn/.kube/config
 
-# install kubectl
-RUN curl -LO "https://dl.k8s.io/release/$(curl -L -s https://dl.k8s.io/release/stable.txt)/bin/linux/amd64/kubectl" &&\
-    cp kubectl /usr/local/bin/kubectl && chmod +x /usr/local/bin/kubectl &&\
-    cp kubectl /usr/bin/kubectl && chmod +x /usr/bin/kubectl
 
 # This overwrites any existing configuration in /etc/yum.repos.d/kubernetes.repo
 RUN dnf update && dnf install -y --setopt=install_weak_deps=False \
-    git python39 jq yq gettext wget which &&\
+    git python3.11 jq yq gettext wget which ipmitool openssh-server &&\
     dnf clean all
 
 # copy oc client binary from oc-build image
 COPY --from=oc-build /tmp/oc/oc /usr/bin/oc
+COPY --from=oc-build /tmp/kubevirt/virtctl /usr/bin/virtctl
 
 # krkn build
 RUN git clone https://github.com/krkn-chaos/krkn.git /home/krkn/kraken && \
     mkdir -p /home/krkn/.kube
 
+RUN mkdir -p /home/krkn/.ssh && \
+    chmod 700 /home/krkn/.ssh
+
 WORKDIR /home/krkn/kraken
 
 # default behaviour will be to build main
@@ -45,16 +63,28 @@ RUN if [ -n "$PR_NUMBER" ]; then git fetch origin pull/${PR_NUMBER}/head:pr-${PR
 # if it is a TAG trigger checkout the tag
 RUN if [ -n "$TAG" ]; then git checkout "$TAG";fi
 
-RUN python3.9 -m ensurepip
-RUN pip3.9 install -r requirements.txt
-RUN pip3.9 install jsonschema
+RUN python3.11 -m ensurepip --upgrade --default-pip
+RUN python3.11 -m pip install --upgrade pip setuptools==78.1.1
 
-LABEL krknctl.title="Krkn Base Image"
-LABEL krknctl.description="This is the krkn base image."
-LABEL krknctl.input_fields='$KRKNCTL_INPUT'
+# removes the the vulnerable versions of setuptools and pip
+RUN rm -rf "$(pip cache dir)"
+RUN rm -rf /tmp/*
+RUN rm -rf /usr/local/lib/python3.11/ensurepip/_bundled
+RUN pip3.11 install -r requirements.txt
+RUN pip3.11 install jsonschema
 
+LABEL krknctl.title.global="Krkn Base Image"
+LABEL krknctl.description.global="This is the krkn base image."
+LABEL krknctl.input_fields.global='$KRKNCTL_INPUT'
+
+# SSH setup script
+RUN chmod +x /home/krkn/kraken/containers/setup-ssh.sh
+
+# Main entrypoint script
+RUN chmod +x /home/krkn/kraken/containers/entrypoint.sh
 
 RUN chown -R krkn:krkn /home/krkn && chmod 755 /home/krkn
 USER krkn
-ENTRYPOINT ["python3.9", "run_kraken.py"]
+
+ENTRYPOINT ["/bin/bash", "/home/krkn/kraken/containers/entrypoint.sh"]
 CMD ["--config=config/config.yaml"]

containers/README.md

@@ -6,7 +6,7 @@ Container image gets automatically built by quay.io at [Kraken image](https://qu
 
 ### Run containerized version
 
-Refer [instructions](https://github.com/redhat-chaos/krkn/blob/main/docs/installation.md#run-containerized-version) for information on how to run the containerized version of kraken.
+Refer [instructions](https://krkn-chaos.dev/docs/installation/) for information on how to run the containerized version of kraken.
 
 
 ### Run Custom Kraken Image

containers/entrypoint.sh

@@ -0,0 +1,7 @@
+#!/bin/bash
+# Run SSH setup
+./containers/setup-ssh.sh
+# Change to kraken directory
+
+# Execute the main command
+exec python3.9 run_kraken.py "$@"

containers/krknctl-input.json

@@ -31,6 +31,24 @@
     "separator": ",",
     "required": "false"
   },
+  {
+    "name": "ssh-public-key",
+    "short_description": "Krkn ssh public key path",
+    "description": "Sets the path where krkn will search for ssh public key (in container)",
+    "variable": "KRKN_SSH_PUBLIC",
+    "type": "string",
+    "default": "",
+    "required": "false"
+  },
+  {
+    "name": "ssh-private-key",
+    "short_description": "Krkn ssh private key path",
+    "description": "Sets the path where krkn will search for ssh private key (in container)",
+    "variable": "KRKN_SSH_PRIVATE",
+    "type": "string",
+    "default": "",
+    "required": "false"
+  },
   {
     "name": "krkn-kubeconfig",
     "short_description": "Krkn kubeconfig path",
@@ -67,6 +85,24 @@
     "default": "False",
     "required": "false"
   },
+  {
+    "name": "prometheus-url",
+    "short_description": "Prometheus url",
+    "description": "Prometheus url for when running on kuberenetes",
+    "variable": "PROMETHEUS_URL",
+    "type": "string",
+    "default": "",
+    "required": "false"
+  },
+  {
+    "name": "prometheus-token",
+    "short_description": "Prometheus bearer token",
+    "description": "Prometheus bearer token for prometheus url authentication",
+    "variable": "PROMETHEUS_TOKEN",
+    "type": "string",
+    "default": "",
+    "required": "false"
+  },
   {
     "name": "uuid",
     "short_description": "Sets krkn run uuid",
@@ -101,12 +137,21 @@
   {
     "name": "alerts-path",
     "short_description": "Cluster alerts path file (in container)",
-    "description": "Enables cluster alerts check",
+    "description": "Allows to specify a different alert file path",
     "variable": "ALERTS_PATH",
     "type": "string",
     "default": "config/alerts.yaml",
     "required": "false"
   },
+  {
+    "name": "metrics-path",
+    "short_description": "Cluster metrics path file (in container)",
+    "description": "Allows to specify a different metrics file path",
+    "variable": "METRICS_PATH",
+    "type": "string",
+    "default": "config/metrics-aggregated.yaml",
+    "required": "false"
+  },
   {
     "name": "enable-es",
     "short_description": "Enables elastic search data collection",
@@ -125,7 +170,6 @@
     "variable": "ES_SERVER",
     "type": "string",
     "default": "http://0.0.0.0",
-    "validator": "^(http|https):\/\/.*",
     "required": "false"
   },
   {
@@ -166,28 +210,6 @@
     "default": "False",
     "required": "false"
   },
-  {
-    "name": "es-collect-metrics",
-    "short_description": "Enables metrics collection on elastic search",
-    "description": "Enables metrics collection on elastic search",
-    "variable": "ES_COLLECT_METRICS",
-    "type": "enum",
-    "allowed_values": "True,False",
-    "separator": ",",
-    "default": "False",
-    "required": "false"
-  },
-  {
-    "name": "es-collect-alerts",
-    "short_description": "Enables alerts collection on elastic search",
-    "description": "Enables alerts collection on elastic search",
-    "variable": "ES_COLLECT_ALERTS",
-    "type": "enum",
-    "allowed_values": "True,False",
-    "separator": ",",
-    "default": "False",
-    "required": "false"
-  },
   {
     "name": "es-metrics-index",
     "short_description": "Elasticsearch metrics index",
@@ -381,6 +403,142 @@
     "default": "True",
     "required": "false"
   },
+  {
+    "name": "health-check-interval",
+    "short_description": "Heath check interval",
+    "description": "How often to check the health check urls",
+    "variable": "HEALTH_CHECK_INTERVAL",
+    "type": "number",
+    "default": "2",
+    "required": "false"
+  },
+  {
+    "name": "health-check-url",
+    "short_description": "Health check url",
+    "description": "Url to check the health of",
+    "variable": "HEALTH_CHECK_URL",
+    "type": "string",
+    "default": "",
+    "required": "false"
+  },
+  {
+    "name": "health-check-auth",
+    "short_description": "Health check authentication tuple",
+    "description": "Authentication tuple to authenticate into health check URL",
+    "variable": "HEALTH_CHECK_AUTH",
+    "type": "string",
+    "default": "",
+    "required": "false"
+  },
+  {
+    "name": "health-check-bearer-token",
+    "short_description": "Health check bearer token",
+    "description": "Bearer token to authenticate into health check URL",
+    "variable": "HEALTH_CHECK_BEARER_TOKEN",
+    "type": "string",
+    "default": "",
+    "required": "false"
+  },
+  {
+    "name": "health-check-exit",
+    "short_description": "Health check exit on failure",
+    "description": "Exit on failure when health check URL is not able to connect",
+    "variable": "HEALTH_CHECK_EXIT_ON_FAILURE",
+    "type": "enum",
+    "allowed_values": "True,False",
+    "separator": ",",
+    "default": "False",
+    "required": "false"
+  },
+  {
+    "name": "health-check-verify",
+    "short_description": "SSL Verification of health check url",
+    "description": "SSL Verification to authenticate into health check URL",
+    "variable": "HEALTH_CHECK_VERIFY",
+    "type": "enum",
+    "allowed_values": "True,False",
+    "separator": ",",
+    "default": "False",
+    "required": "false"
+  },
+  {
+    "name": "kubevirt-check-interval",
+    "short_description": "Kube Virt check interval",
+    "description": "How often to check the kube virt check Vms ssh status",
+    "variable": "KUBE_VIRT_CHECK_INTERVAL",
+    "type": "number",
+    "default": "2",
+    "required": "false"
+  },
+  {
+    "name": "kubevirt-namespace",
+    "short_description": "KubeVirt namespace to check",
+    "description": "KubeVirt namespace to check the health of",
+    "variable": "KUBE_VIRT_NAMESPACE",
+    "type": "string",
+    "default": "",
+    "required": "false"
+  },
+  {
+    "name": "kubevirt-name",
+    "short_description": "KubeVirt regex names to watch",
+    "description": "KubeVirt regex names to check VMs",
+    "variable": "KUBE_VIRT_NAME",
+    "type": "string",
+    "default": "",
+    "required": "false"
+  },
+  {
+    "name": "kubevirt-only-failures",
+    "short_description": "KubeVirt checks only report if failure occurs",
+    "description": "KubeVirt checks only report if failure occurs",
+    "variable": "KUBE_VIRT_FAILURES",
+    "type": "enum",
+    "allowed_values": "True,False,true,false",
+    "separator": ",",
+    "default": "False",
+    "required": "false"
+  },
+  {
+    "name": "kubevirt-disconnected",
+    "short_description": "KubeVirt checks in disconnected mode",
+    "description": "KubeVirt checks in disconnected mode, bypassing the clusters Api",
+    "variable": "KUBE_VIRT_DISCONNECTED",
+    "type": "enum",
+    "allowed_values": "True,False,true,false",
+    "separator": ",",
+    "default": "False",
+    "required": "false"
+  },
+  {
+    "name": "kubevirt-ssh-node",
+    "short_description": "KubeVirt node to ssh from",
+    "description": "KubeVirt node to ssh from, should be available whole chaos run",
+    "variable": "KUBE_VIRT_SSH_NODE",
+    "type": "string",
+    "default": "",
+    "required": "false"
+  },
+  {
+    "name": "kubevirt-exit-on-failure",
+    "short_description": "KubeVirt fail if failed vms at end of run",
+    "description": "KubeVirt fails run if vms still have false status",
+    "variable": "KUBE_VIRT_EXIT_ON_FAIL",
+    "type": "enum",
+    "allowed_values": "True,False,true,false",
+    "separator": ",",
+    "default": "False",
+    "required": "false"
+  },
+  {
+    "name": "kubevirt-node-node",
+    "short_description": "KubeVirt node to filter vms on",
+    "description": "Only track VMs in KubeVirt on given node name",
+    "variable": "KUBE_VIRT_NODE_NAME",
+    "type": "string",
+    "default": "",
+    "required": "false"
+  },
   {
     "name": "krkn-debug",
     "short_description": "Krkn debug mode",
@@ -392,5 +550,4 @@
     "default": "False",
     "required": "false"
   }
-]
-
+]

containers/setup-ssh.sh

@@ -0,0 +1,73 @@
+#!/bin/bash
+# Setup SSH key if mounted
+# Support multiple mount locations
+MOUNTED_PRIVATE_KEY_ALT="/secrets/id_rsa"
+MOUNTED_PRIVATE_KEY="/home/krkn/.ssh/id_rsa"
+MOUNTED_PUBLIC_KEY="/home/krkn/.ssh/id_rsa.pub"
+WORKING_KEY="/home/krkn/.ssh/id_rsa.key"
+
+# Determine which source to use
+SOURCE_KEY=""
+if [ -f "$MOUNTED_PRIVATE_KEY_ALT" ]; then
+    SOURCE_KEY="$MOUNTED_PRIVATE_KEY_ALT"
+    echo "Found SSH key at alternative location: $SOURCE_KEY"
+elif [ -f "$MOUNTED_PRIVATE_KEY" ]; then
+    SOURCE_KEY="$MOUNTED_PRIVATE_KEY"
+    echo "Found SSH key at default location: $SOURCE_KEY"
+fi
+
+# Setup SSH private key and create config for outbound connections
+if [ -n "$SOURCE_KEY" ]; then
+    echo "Setting up SSH private key from: $SOURCE_KEY"
+
+    # Check current permissions and ownership
+    ls -la "$SOURCE_KEY"
+
+    # Since the mounted key might be owned by root and we run as krkn user,
+    # we cannot modify it directly. Copy to a new location we can control.
+    echo "Copying SSH key to working location: $WORKING_KEY"
+
+    # Try to copy - if readable by anyone, this will work
+    if cp "$SOURCE_KEY" "$WORKING_KEY" 2>/dev/null || cat "$SOURCE_KEY" > "$WORKING_KEY" 2>/dev/null; then
+        chmod 600 "$WORKING_KEY"
+        echo "SSH key copied successfully"
+        ls -la "$WORKING_KEY"
+
+        # Verify the key is readable
+        if ssh-keygen -y -f "$WORKING_KEY" > /dev/null 2>&1; then
+            echo "SSH private key verified successfully"
+        else
+            echo "Warning: SSH key verification failed, but continuing anyway"
+        fi
+
+        # Create SSH config to use the working key
+        cat > /home/krkn/.ssh/config <<EOF
+Host *
+    IdentityFile $WORKING_KEY
+    StrictHostKeyChecking no
+    UserKnownHostsFile /dev/null
+EOF
+        chmod 600 /home/krkn/.ssh/config
+        echo "SSH config created with default identity: $WORKING_KEY"
+    else
+        echo "ERROR: Cannot read SSH key at $SOURCE_KEY"
+        echo "Key is owned by: $(stat -c '%U:%G' "$SOURCE_KEY" 2>/dev/null || stat -f '%Su:%Sg' "$SOURCE_KEY" 2>/dev/null)"
+        echo ""
+        echo "Solutions:"
+        echo "1. Mount with world-readable permissions (less secure): chmod 644 /path/to/key"
+        echo "2. Mount to /secrets/id_rsa instead of /home/krkn/.ssh/id_rsa"
+        echo "3. Change ownership on host: chown \$(id -u):\$(id -g) /path/to/key"
+        exit 1
+    fi
+fi
+
+# Setup SSH public key if mounted (for inbound server access)
+if [ -f "$MOUNTED_PUBLIC_KEY" ]; then
+    echo "SSH public key already present at $MOUNTED_PUBLIC_KEY"
+    # Try to fix permissions (will fail silently if file is mounted read-only or owned by another user)
+    chmod 600 "$MOUNTED_PUBLIC_KEY" 2>/dev/null
+    if [ ! -f "/home/krkn/.ssh/authorized_keys" ]; then
+        cp "$MOUNTED_PUBLIC_KEY" /home/krkn/.ssh/authorized_keys
+        chmod 600 /home/krkn/.ssh/authorized_keys
+    fi
+fi

docs/SLOs_validation.md

@@ -1,48 +0,0 @@
-## SLOs validation
-
-Pass/fail based on metrics captured from the cluster is important in addition to checking the health status and recovery. Kraken supports:
-
-###  Checking for critical alerts post chaos 
-If enabled, the check runs at the end of each scenario ( post chaos ) and Kraken exits in case critical alerts are firing to allow user to debug. You can enable it in the config:
-
-```
-performance_monitoring:
-    check_critical_alerts: False                          # When enabled will check prometheus for critical alerts firing post chaos
-```
-
-### Validation and alerting based on the queries defined by the user during chaos
-Takes PromQL queries as input and modifies the return code of the run to determine pass/fail. It's especially useful in case of automated runs in CI where user won't be able to monitor the system. This feature can be enabled in the [config](https://github.com/redhat-chaos/krkn/blob/main/config/config.yaml) by setting the following:
-
-```
-performance_monitoring:
-    prometheus_url:                                       # The prometheus url/route is automatically obtained in case of OpenShift, please set it when the distribution is Kubernetes.
-    prometheus_bearer_token:                              # The bearer token is automatically obtained in case of OpenShift, please set it when the distribution is Kubernetes. This is needed to authenticate with prometheus.
-    enable_alerts: True                                   # Runs the queries specified in the alert profile and displays the info or exits 1 when severity=error.
-    alert_profile: config/alerts.yaml                          # Path to alert profile with the prometheus queries.
-```
-
-#### Alert profile
-A couple of [alert profiles](https://github.com/redhat-chaos/krkn/tree/main/config) [alerts](https://github.com/redhat-chaos/krkn/blob/main/config/alerts.yaml) are shipped by default and can be tweaked to add more queries to alert on. User can provide a URL or path to the file in the [config](https://github.com/redhat-chaos/krkn/blob/main/config/config.yaml). The following are a few alerts examples:
-
-```
-- expr: avg_over_time(histogram_quantile(0.99, rate(etcd_disk_wal_fsync_duration_seconds_bucket[2m]))[5m:]) > 0.01
-  description: 5 minutes avg. etcd fsync latency on {{$labels.pod}} higher than 10ms {{$value}}
-  severity: error
-
-- expr: avg_over_time(histogram_quantile(0.99, rate(etcd_network_peer_round_trip_time_seconds_bucket[5m]))[5m:]) > 0.1
-  description: 5 minutes avg. etcd network peer round trip on {{$labels.pod}} higher than 100ms {{$value}}
-  severity: info
-
-- expr: increase(etcd_server_leader_changes_seen_total[2m]) > 0
-  description: etcd leader changes observed
-  severity: critical
-```
-
-Krkn supports setting the severity for the alerts with each one having different effects:
-
-```
-info: Prints an info message with the alarm description to stdout. By default all expressions have this severity.
-warning: Prints a warning message with the alarm description to stdout.
-error: Prints a error message with the alarm description to stdout and sets Krkn rc = 1
-critical: Prints a fatal message with the alarm description to stdout and exits execution inmediatly with rc != 0
-```

docs/_config.yml

@@ -1 +0,0 @@
-theme: jekyll-theme-cayman

docs/application_outages.md

@@ -1,17 +0,0 @@
-### Application outages
-Scenario to block the traffic ( Ingress/Egress ) of an application matching the labels for the specified duration of time to understand the behavior of the service/other services which depend on it during downtime. This helps with planning the requirements accordingly, be it improving the timeouts or tweaking the alerts etc.
-
-##### Sample scenario config
-```
-application_outage:                                  # Scenario to create an outage of an application by blocking traffic
-  duration: 600                                      # Duration in seconds after which the routes will be accessible
-  namespace: <namespace-with-application>            # Namespace to target - all application routes will go inaccessible if pod selector is empty
-  pod_selector: {app: foo}                            # Pods to target
-  block: [Ingress, Egress]                           # It can be Ingress or Egress or Ingress, Egress
-```
-
-##### Debugging steps in case of failures
-Kraken creates a network policy blocking the ingress/egress traffic to create an outage, in case of failures before reverting back the network policy, you can delete it manually by executing the following commands to stop the outage:
-```
-$ oc delete networkpolicy/kraken-deny -n <targeted-namespace>
-```

docs/arcaflow_scenarios.md

@@ -1,70 +0,0 @@
-## Arcaflow Scenarios
-Arcaflow is a workflow engine in development which provides the ability to execute workflow steps in sequence, in parallel, repeatedly, etc. The main difference to competitors such as Netflix Conductor is the ability to run ad-hoc workflows without an infrastructure setup required.
-
-The engine uses containers to execute plugins and runs them either locally in Docker/Podman or remotely on a Kubernetes cluster. The workflow system is strongly typed and allows for generating JSON schema and OpenAPI documents for all data formats involved.
-
-### Available Scenarios
-#### Hog scenarios:
-- [CPU Hog](arcaflow_scenarios/cpu_hog.md)
-- [Memory Hog](arcaflow_scenarios/memory_hog.md)
-- [I/O Hog](arcaflow_scenarios/io_hog.md)
-
-
-### Prequisites
-Arcaflow supports three deployment technologies:
-- Docker
-- Podman
-- Kubernetes
-
-#### Docker
-In order to run Arcaflow Scenarios with the Docker deployer, be sure that:
-- Docker is correctly installed in your Operating System (to find instructions on how to install docker please refer to [Docker Documentation](https://www.docker.com/))
-- The Docker daemon is running
-
-#### Podman
-The podman deployer is built around the podman CLI and doesn't need necessarily to be run along with the podman daemon.
-To run Arcaflow Scenarios in your Operating system be sure that:
-- podman is correctly installed in your Operating System (to find instructions on how to install podman refer to [Podman Documentation](https://podman.io/))
-- the podman CLI is in your shell PATH
-
-#### Kubernetes
-The kubernetes deployer integrates directly the Kubernetes API Client and needs only a valid kubeconfig file and a reachable Kubernetes/OpenShift Cluster.
-
-### Usage
-
-To enable arcaflow scenarios edit the kraken config file, go to the section `kraken -> chaos_scenarios` of the yaml structure
-and add a new element to the list named `arcaflow_scenarios` then add the desired scenario
-pointing to the `input.yaml` file.
-```
-kraken:
-    ...
-    chaos_scenarios:
-        - arcaflow_scenarios:
-            - scenarios/arcaflow/cpu-hog/input.yaml
-```
-
-#### input.yaml
-The implemented scenarios can be found in *scenarios/arcaflow/<scenario_name>* folder.
-The entrypoint of each scenario is the *input.yaml* file. 
-In this file there are all the options to set up the scenario accordingly to the desired target 
-### config.yaml
-The arcaflow config file. Here you can set the arcaflow deployer and the arcaflow log level.
-The supported deployers are:
-- Docker
-- Podman (podman daemon not needed, suggested option)
-- Kubernetes
-
-The supported log levels are:
-- debug
-- info
-- warning
-- error
-### workflow.yaml
-This file contains the steps that will be executed to perform the scenario against the target.
-Each step is represented by a container that will be executed from the deployer and its options.
-Note that we provide the scenarios as a template, but they can be manipulated to define more complex workflows.
-To have more details regarding the arcaflow workflows architecture and syntax it is suggested to refer to the [Arcaflow Documentation](https://arcalot.io/arcaflow/).
-
-This edit is no longer in quay image
-Working on fix in ticket: https://issues.redhat.com/browse/CHAOS-494
-This will effect all versions 4.12 and higher of OpenShift

docs/arcaflow_scenarios/cpu_hog.md

@@ -1,19 +0,0 @@
-# CPU Hog
-This scenario is based on the arcaflow [arcaflow-plugin-stressng](https://github.com/arcalot/arcaflow-plugin-stressng) plugin. 
-The purpose of this scenario is to create cpu pressure on a particular node of the Kubernetes/OpenShift cluster for a time span.
-To enable this plugin add the pointer to the scenario input file `scenarios/arcaflow/cpu-hog/input.yaml` as described in the 
-Usage section.
-This scenario takes a list of objects named `input_list` with the following properties:
-
-- **kubeconfig :** *string* the kubeconfig needed by the deployer to deploy the sysbench plugin in the target cluster
-- **namespace :** *string* the namespace where the scenario container will be deployed
-**Note:** this parameter will be automatically filled by kraken if the `kubeconfig_path` property is correctly set
-- **node_selector :** *key-value map* the node label that will be used as `nodeSelector` by the pod to target a specific cluster node
-- **duration :** *string* stop  stress  test  after  N  seconds.  One  can  also specify the units of time in seconds, minutes, hours, days or years with the suffix s, m, h, d or y.
-- **cpu_count :** *int* the number of CPU cores to be used (0 means all)
-- **cpu_method :** *string* a fine-grained control of which cpu stressors to use (ackermann, cfloat etc. see [manpage](https://manpages.org/sysbench) for all the cpu_method options)
-- **cpu_load_percentage :** *int* the CPU load by percentage
-
-To perform several load tests in the same run simultaneously (eg. stress two or more nodes in the same run) add another item
-to the `input_list` with the same properties (and eventually different values eg. different node_selectors 
-to schedule the pod on different nodes). To reduce (or increase) the parallelism change the value `parallelism` in `workload.yaml` file 

docs/arcaflow_scenarios/io_hog.md

@@ -1,21 +0,0 @@
-# I/O Hog
-This scenario is based on the arcaflow [arcaflow-plugin-stressng](https://github.com/arcalot/arcaflow-plugin-stressng) plugin. 
-The purpose of this scenario is to create disk pressure on a particular node of the Kubernetes/OpenShift cluster for a time span.
-The scenario allows to attach a node path to the pod as a `hostPath` volume.
-To enable this plugin add the pointer to the scenario input file `scenarios/arcaflow/io-hog/input.yaml` as described in the 
-Usage section.
-This scenario takes a list of objects named `input_list` with the following properties:
-
-- **kubeconfig :** *string* the kubeconfig needed by the deployer to deploy the sysbench plugin in the target cluster
-- **namespace :** *string* the namespace where the scenario container will be deployed
-**Note:** this parameter will be automatically filled by kraken if the `kubeconfig_path` property is correctly set
-- **node_selector :** *key-value map* the node label that will be used as `nodeSelector` by the pod to target a specific cluster node
-- **duration :** *string* stop  stress  test  after  N  seconds.  One  can  also specify the units of time in seconds, minutes, hours, days or years with the suffix s, m, h, d or y.
-- **target_pod_folder :** *string* the path in the pod where the volume is mounted
-- **target_pod_volume :** *object* the `hostPath` volume definition in the [Kubernetes/OpenShift](https://docs.openshift.com/container-platform/3.11/install_config/persistent_storage/using_hostpath.html) format, that will be attached to the pod as a volume
-- **io_write_bytes :** *string* writes N bytes for each hdd process. The size can be expressed as % of free space on the file system or in units of Bytes, KBytes, MBytes and GBytes using the suffix b, k, m or g
-- **io_block_size :** *string* size of each write in bytes. Size can be from 1 byte to 4m.
-
-To perform several load tests in the same run simultaneously (eg. stress two or more nodes in the same run) add another item
-to the `input_list` with the same properties (and eventually different values eg. different node_selectors 
-to schedule the pod on different nodes). To reduce (or increase) the parallelism change the value `parallelism` in `workload.yaml` file 

docs/arcaflow_scenarios/memory_hog.md

@@ -1,18 +0,0 @@
-# Memory Hog
-This scenario is based on the arcaflow [arcaflow-plugin-stressng](https://github.com/arcalot/arcaflow-plugin-stressng) plugin. 
-The purpose of this scenario is to create Virtual Memory pressure on a particular node of the Kubernetes/OpenShift cluster for a time span.
-To enable this plugin add the pointer to the scenario input file `scenarios/arcaflow/memory-hog/input.yaml` as described in the 
-Usage section.
-This scenario takes a list of objects named `input_list` with the following properties:
-
-- **kubeconfig :** *string* the kubeconfig needed by the deployer to deploy the sysbench plugin in the target cluster
-- **namespace :** *string* the namespace where the scenario container will be deployed
-**Note:** this parameter will be automatically filled by kraken if the `kubeconfig_path` property is correctly set
-- **node_selector :** *key-value map* the node label that will be used as `nodeSelector` by the pod to target a specific cluster node
-- **duration :** *string* stop  stress  test  after  N  seconds.  One  can  also specify the units of time in seconds, minutes, hours, days or years with the suffix s, m, h, d or y.
-- **vm_bytes :** *string* N bytes per vm process or percentage of memory used (using the % symbol). The size can be expressed in units of Bytes, KBytes, MBytes and GBytes using the suffix b, k, m or g.
-- **vm_workers :** *int* Number of VM stressors to be run (0 means 1 stressor per CPU)
-
-To perform several load tests in the same run simultaneously (eg. stress two or more nodes in the same run) add another item
-to the `input_list` with the same properties (and eventually different values eg. different node_selectors 
-to schedule the pod on different nodes). To reduce (or increase) the parallelism change the value `parallelism` in `workload.yaml` file 

docs/cloud_setup.md

@@ -1,102 +0,0 @@
-Supported Cloud Providers:
-
-- [AWS](#aws)
-- [GCP](#gcp)
-- [Openstack](#openstack)
-- [Azure](#azure)
-- [Alibaba](#alibaba)
-- [VMware](#vmware)
-- [IBMCloud](#ibmcloud)
-
-## AWS
-
-**NOTE**: For clusters with AWS make sure [AWS CLI](https://docs.aws.amazon.com/cli/latest/userguide/getting-started-install.html) is installed and properly [configured](https://docs.aws.amazon.com/cli/latest/userguide/cli-configure-quickstart.html) using an AWS account
-
-## GCP
-
-In order to set up Application Default Credentials (ADC) for use by Cloud Client Libraries, you can provide either service account credentials or the credentials associated with your user acccount:
-
-- Using service account credentials:
-
-  A google service account is required to give proper authentication to GCP for node actions. See [here](https://cloud.google.com/docs/authentication/getting-started) for how to create a service account.
-
-  **NOTE**: A user with 'resourcemanager.projects.setIamPolicy' permission is required to grant project-level permissions to the service account.
-
-  After creating the service account you will need to enable the account using the following: ```export GOOGLE_APPLICATION_CREDENTIALS="<serviceaccount.json>"```
-
-- Using the credentials associated with your user acccount:
-
-  1. Make sure that the [GCP CLI](https://cloud.google.com/sdk/docs/install#linux) is installed and [initialized](https://cloud.google.com/sdk/docs/initializing) by running:
-
-     ```gcloud init```
-
-  2. Create local authentication credentials for your user account:
-
-     ```gcloud auth application-default login```
-
-## Openstack
-
-**NOTE**: For clusters with Openstack Cloud, ensure to create and source the [OPENSTACK RC file](https://docs.openstack.org/newton/user-guide/common/cli-set-environment-variables-using-openstack-rc.html) to set the OPENSTACK environment variables from the server where Kraken runs.
-
-## Azure
-
-**NOTE**: You will need to create a service principal and give it the correct access, see [here](https://docs.openshift.com/container-platform/4.5/installing/installing_azure/installing-azure-account.html) for creating the service principal and setting the proper permissions.
-
-To properly run the service principal requires “Azure Active Directory Graph/Application.ReadWrite.OwnedBy” api permission granted and “User Access Administrator”.
-
-Before running you will need to set the following:
-
-1. ```export AZURE_SUBSCRIPTION_ID=<subscription_id>```
-
-2. ```export AZURE_TENANT_ID=<tenant_id>```
-
-3. ```export AZURE_CLIENT_SECRET=<client secret>```
-
-4. ```export AZURE_CLIENT_ID=<client id>```
-
-## Alibaba
-
-See the [Installation guide](https://www.alibabacloud.com/help/en/alibaba-cloud-cli/latest/installation-guide) to install alicloud cli.
-
-1. ```export ALIBABA_ID=<access_key_id>```
-
-2. ```export ALIBABA_SECRET=<access key secret>```
-
-3. ```export ALIBABA_REGION_ID=<region id>```
-
-Refer to [region and zone page](https://www.alibabacloud.com/help/en/elastic-compute-service/latest/regions-and-zones#concept-2459516) to get the region id for the region you are running on.
-
-Set cloud_type to either alibaba or alicloud in your node scenario yaml file.
-
-## VMware
-
-Set the following environment variables
-
-1. ```export VSPHERE_IP=<vSphere_client_IP_address>```
-
-2. ```export VSPHERE_USERNAME=<vSphere_client_username>```
-
-3. ```export VSPHERE_PASSWORD=<vSphere_client_password>```
-
-These are the credentials that you would normally use to access the vSphere client.
-
-## IBMCloud
-
-If no API key is set up with proper VPC resource permissions, use the following to create it:
-
-* Access group
-* Service id with the following access
-  * With policy **VPC Infrastructure Services**
-  * Resources = All
-  * Roles: 
-    * Editor
-    * Administrator 
-    * Operator  
-    * Viewer
-* API Key
-
-Set the following environment variables
-
-1. ```export IBMC_URL=https://<region>.iaas.cloud.ibm.com/v1```
-
-2. ```export IBMC_APIKEY=<ibmcloud_api_key>```

docs/cluster_shut_down_scenarios.md

@@ -1,19 +0,0 @@
-#### Kubernetes cluster shut down scenario
-Scenario to shut down all the nodes including the masters and restart them after specified duration. Cluster shut down scenario can be injected by placing the shut_down config file under cluster_shut_down_scenario option in the kraken config. Refer to [cluster_shut_down_scenario](https://github.com/krkn-chaos/krkn/blob/main/scenarios/cluster_shut_down_scenario.yml) config file.
-
-Refer to [cloud setup](cloud_setup.md) to configure your cli properly for the cloud provider of the cluster you want to shut down.
-
-Current accepted cloud types:
-* [Azure](cloud_setup.md#azure)
-* [GCP](cloud_setup.md#gcp)
-* [AWS](cloud_setup.md#aws)
-* [Openstack](cloud_setup.md#openstack)
-* [IBMCloud](cloud_setup.md#ibmcloud)
-
-
-```
-cluster_shut_down_scenario:                          # Scenario to stop all the nodes for specified duration and restart the nodes.
-  runs: 1                                            # Number of times to execute the cluster_shut_down scenario.
-  shut_down_duration: 120                            # Duration in seconds to shut down the cluster.
-  cloud_type: aws                                    # Cloud type on which Kubernetes/OpenShift runs.
-```

docs/config.md

@@ -1,65 +0,0 @@
-### Config
-Set the scenarios to inject and the tunings like duration to wait between each scenario in the config file located at [config/config.yaml](https://github.com/redhat-chaos/krkn/blob/main/config/config.yaml).
-
-**NOTE**: [config](https://github.com/redhat-chaos/krkn/blob/main/config/config_performance.yaml) can be used if leveraging the [automated way](https://github.com/redhat-chaos/krkn#setting-up-infrastructure-dependencies) to install the infrastructure pieces.
-
-Config components: 
-* [Kraken](#kraken)
-* [Cerberus](#cerberus)
-* [Performance Monitoring](#performance-monitoring)
-* [Tunings](#tunings)
-
-# Kraken 
-This section defines scenarios and specific data to the chaos run 
-
-## Distribution
-Either **openshift** or **kubernetes** depending on the type of cluster you want to run chaos on. 
-The prometheus url/route and bearer token are automatically obtained in case of OpenShift, please set it when the distribution is Kubernetes.
-
-## Exit on failure
-**exit_on_failure**:  Exit when a post action check or cerberus run fails
-
-## Publish kraken status
-**publish_kraken_status**: Can be accessed at http://0.0.0.0:8081 (or what signal_address and port you set in signal address section)
-**signal_state**: State you want kraken to start at; will wait for the RUN signal to start running a chaos iteration. When set to PAUSE before running the scenarios, refer to [signal.md](signal.md) for more details
-
-## Signal Address 
-**signal_address**: Address to listen/post the signal state to
-**port**: port to listen/post the signal state to
-
-## Chaos Scenarios 
-
-**chaos_scenarios**: List of different types of chaos scenarios you want to run with paths to their specific yaml file configurations
-
-If a scenario has a post action check script, it will be run before and after each scenario to validate the component under test starts and ends at the same state
-
-Currently the scenarios are run one after another (in sequence) and will exit if one of the scenarios fail, without moving onto the next one
-
-Chaos scenario types: 
-- container_scenarios     
-- plugin_scenarios
-- node_scenarios
-- time_scenarios
-- cluster_shut_down_scenarios
-- namespace_scenarios
-- zone_outages
-- application_outages
-- pvc_scenarios
-- network_chaos
-
-
-# Cerberus 
-Parameters to set for enabling of cerberus checks at the end of each executed scenario. The given url will pinged after the scenario and post action check have been completed for each scenario and iteration.
-**cerberus_enabled**: Enable it when cerberus is previously installed
-**cerberus_url**: When cerberus_enabled is set to True, provide the url where cerberus publishes go/no-go signal
-**check_applicaton_routes**:  When enabled will look for application unavailability using the routes specified in the cerberus config and fails the run
-
-
-# Performance Monitoring 
-There are 2 main sections defined in this part of the config [metrics](metrics.md) and [alerts](alerts.md); read more about each of these configurations in their respective docs 
-
-# Tunings
-**wait_duration**: Duration to wait between each chaos scenario
-**iterations**: Number of times to execute the scenarios
-**daemon_mode**: True or False; If true, iterations are set to infinity which means that the kraken will cause chaos forever and number of iterations is ignored
-

docs/container_scenarios.md

@@ -1,40 +0,0 @@
-### Container Scenarios
-Kraken uses the `oc exec` command to `kill` specific containers in a pod.
-This can be based on the pods namespace or labels. If you know the exact object you want to kill, you can also specify the specific container name or pod name in the scenario yaml file.
-These scenarios are in a simple yaml format that you can manipulate to run your specific tests or use the pre-existing scenarios to see how it works.
-
-####  Example Config
-The following are the components of Kubernetes for which a basic chaos scenario config exists today.
-
-```
-scenarios:
-- name: "<name of scenario>"
-  namespace: "<specific namespace>" # can specify "*" if you want to find in all namespaces
-  label_selector: "<label of pod(s)>"
-  container_name: "<specific container name>"  # This is optional, can take out and will kill all containers in all pods found under namespace and label
-  pod_names:  # This is optional, can take out and will select all pods with given namespace and label
-  - <pod_name>
-  count: <number of containers to disrupt, default=1>
-  action: <kill signal to run. For example 1 ( hang up ) or 9. Default is set to 1>
-  expected_recovery_time: <number of seconds to wait for container to be running again> (defaults to 120seconds)
-```
-
-#### Post Action
-In all scenarios we do a post chaos check to wait and verify the specific component.
-
-Here there are two options:
-1. Pass a custom script in the main config scenario list that will run before the chaos and verify the output matches post chaos scenario.
-
-See [scenarios/post_action_etcd_container.py](https://github.com/krkn-chaos/krkn/blob/main/scenarios/post_action_etcd_container.py) for an example.
-```
--   container_scenarios:                                 # List of chaos pod scenarios to load.
-            - -    scenarios/container_etcd.yml
-              -    scenarios/post_action_etcd_container.py
-```
-
-2. Allow kraken to wait and check the killed containers until they become ready again. Kraken keeps a list of the specific
-containers that were killed as well as the namespaces and pods to verify all containers that were affected recover properly.
-
-```
-expected_recovery_time: <seconds to wait for container to recover>
-```

docs/contribute.md

@@ -1,95 +0,0 @@
-# How to contribute
-
-Contributions are always appreciated.
-
-How to:
-* [Submit Pull Request](#pull-request)
-* [Fix Formatting](#fix-formatting)
-* [Squash Commits](#squash-commits)
-* [Rebase Upstream](#rebase-with-upstream)
-
-## Pull request
-
-In order to submit a change or a PR, please fork the project and follow these instructions:
-```bash
-$ git clone http://github.com/<me>/krkn
-$ cd krkn
-$ git checkout -b <branch_name>
-$ <make change>
-$ git add <changes>
-$ git commit -a
-$ <insert good message>
-$ git push
-```
-
-## Fix Formatting
-Kraken uses [pre-commit](https://pre-commit.com) framework to maintain the code linting and python code styling.
-The CI would run the pre-commit check on each pull request.
-We encourage our contributors to follow the same pattern while contributing to the code.
-
-The pre-commit configuration file is present in the repository `.pre-commit-config.yaml`.
-It contains the different code styling and linting guides which we use for the application.
-
-The following command can be used to run the pre-commit:
-`pre-commit run --all-files`
-
-If pre-commit is not installed in your system, it can be installed with `pip install pre-commit`.
-
-## Squash Commits
-If there are multiple commits, please rebase/squash multiple commits
-before creating the PR by following:
-
-```bash
-$ git checkout <my-working-branch>
-$ git rebase -i HEAD~<num_of_commits_to_merge>
-   -OR-
-$ git rebase -i <commit_id_of_first_change_commit>
-```
-
-In the interactive rebase screen, set the first commit to `pick`, and all others to `squash`, or whatever else you may need to do.
-
-
-Push your rebased commits (you may need to force), then issue your PR.
-
-```
-$ git push origin <my-working-branch> --force
-```
-
-## Rebase with Upstream
-
-If changes go into the main repository while you're working on your code it is best to rebase your code with the
- upstream, so you stay up to date with all changes and fix any conflicting code changes.
-
-If not already configured, set the upstream url for kraken.
-```
- git remote add upstream https://github.com/krkn-chaos/krkn.git
-```
-
-Rebase to upstream master branch.
-```
-git fetch upstream
-git rebase upstream/master
-git push origin <branch_name> --force
-```
-
-If any errors occur, it will list off any files that have merge issues.
-Edit the files with the code you want to keep. See below for detailed help from Git.
-1. Vi <file(s)>
-2. Resolving-a-merge-conflict-using-the-command-line
-3. git add <all files you edit>
-4. git rebase --continue
-5. Might need to repeat steps 2 through 4 until rebase complete
-6. git status <this will also tell you if you have other files to edit>
-7. git push origin <branch_name> --force  [push the changes to github remote]
-
-
-Merge Conflicts Example
-```
-1. git rebase upstream/kraken
-2. vi run_kraken.py [edit at the indicated places, get rid of arrowed lines and dashes, and apply correct changes]
-3. git add run_kraken.py
-4. git rebase --continue
-5. repeat 2-4 until done
-6. git status <this will also tell you if you have other files to edit>
-7. git push origin <branch_name> --force  [push the changes to github remote]
-```

docs/getting_started.md

@@ -1,51 +0,0 @@
-## Getting Started Running Chaos Scenarios
-
-#### Adding New Scenarios
-Adding a new scenario is as simple as adding a new config file under [scenarios directory](https://github.com/redhat-chaos/krkn/tree/main/scenarios) and defining it in the main kraken [config](https://github.com/redhat-chaos/krkn/blob/main/config/config.yaml#L8).
-You can either copy an existing yaml file and make it your own, or fill in one of the templates below to suit your needs.
-
-### Templates
-#### Pod Scenario Yaml Template
-For example, for adding a pod level scenario for a new application, refer to the sample scenario below to know what fields are necessary and what to add in each location:
-```
-# yaml-language-server: $schema=../plugin.schema.json
-- id: kill-pods
-  config:
-    namespace_pattern: ^<namespace>$
-    label_selector: <pod label>
-    kill: <number of pods to kill>
-    krkn_pod_recovery_time: <expected time for the pod to become ready>
-```
-
-#### Node Scenario Yaml Template
-
-```
-node_scenarios:
-  - actions:  # Node chaos scenarios to be injected.
-    - <chaos scenario>
-    - <chaos scenario>
-    node_name: <node name>  # Can be left blank.
-    label_selector: <node label>
-    instance_kill_count: <number of nodes on which to perform action>
-    timeout: <duration to wait for completion>
-    cloud_type: <cloud provider>
-```
-
-
-#### Time Chaos Scenario Template
-```
-time_scenarios:
-  - action: 'skew_time' or 'skew_date'
-    object_type: 'pod' or 'node'
-    label_selector: <label of pod or node>
-```
-
-
-### Common Scenario Edits
-If you just want to make small changes to pre-existing scenarios, feel free to edit the scenario file itself.
-
-#### Example of Quick Pod Scenario Edit:
-If you want to kill 2 pods instead of 1 in any of the pre-existing scenarios, you can either edit the number located at filters -> randomSample -> size or the runs under the config -> runStrategy section.
-
-#### Example of Quick Nodes Scenario Edit:
-If your cluster is build on GCP instead of AWS, just change the cloud type in the node_scenarios_example.yml file.

docs/index.md

@@ -1,310 +0,0 @@
-## Chaos Testing Guide
-
-
-### Table of Contents
-* [Introduction](#introduction)
-* [Test Stratagies and Methodology](#test-strategies-and-methodology)
-* [Best Practices](#best-practices)
-* [Tooling](#tooling)
-  * [Workflow](#workflow)
-  * [Cluster recovery checks, metrics evaluation and pass/fail criteria](#cluster-recovery-checks-metrics-evaluation-and-passfail-criteria)
-* [Scenarios](#scenarios)
-* [Test Environment Recommendations - how and where to run chaos tests](#test-environment-recommendations---how-and-where-to-run-chaos-tests)
-* [Chaos testing in Practice](#chaos-testing-in-practice)
-  * [OpenShift organization](#openshift-organization)
-  * [startx-lab](#startx-lab)
-
-
-### Introduction
-There are a couple of false assumptions that users might have when operating and running their applications in distributed systems:
-
-The network is reliable.
-There is zero latency.
-Bandwidth is infinite.
-The network is secure.
-Topology never changes.
-The network is homogeneous.
-Consistent resource usage with no spikes.
-All shared resources are available from all places.
-
-Various assumptions led to a number of outages in production environments in the past.  The services suffered from poor performance or were inaccessible to the customers, leading to missing Service Level Agreement uptime promises, revenue loss, and a degradation in the perceived reliability of said services.
-
-How can we best avoid this from happening? This is where Chaos testing can add value.
-
-
-
-### Test Strategies and Methodology
-Failures in production are costly. To help mitigate risk to service health, consider the following strategies and approaches to service testing:
-
-- Be proactive vs reactive. We have different types of test suites in place - unit, integration and end-to-end - that help expose bugs in code in a controlled environment.  Through implementation of a chaos engineering strategy, we can discover potential causes of service degradation. We need to understand the systems' behavior under unpredictable conditions in order to find the areas to harden, and use performance data points to size the clusters to handle failures in order to keep downtime to a minimum.
-
-- Test the resiliency of a system under turbulent conditions by running tests that are designed to disrupt while monitoring the systems adaptability and performance:
-  - Establish and define your steady state and metrics - understand the behavior and performance under stable conditions and define the metrics that will be used to evaluate the system’s behavior.  Then decide on acceptable outcomes before injecting chaos.
-  - Analyze the statuses and metrics of all components during the chaos test runs.
-  - Improve the areas that are not resilient and performant by comparing the key metrics and Service Level Objectives (SLOs) to the stable conditions before the chaos.
-  For example: evaluating the API server latency or application uptime to see if the key performance indicators and service level indicators are still within acceptable limits.
-
-
-
-
-### Best Practices
-Now that we understand the test methodology, let us take a look at the best practices for an Kubernetes cluster.  On that platform there are user applications and cluster workloads that need to be designed for stability and to provide the best user experience possible:
-
-- Alerts with appropriate severity should get fired.
-  - Alerts are key to identify when a component starts degrading, and can help focus the investigation effort on affected system components.
-  - Alerts should have proper severity, description, notification policy, escalation policy, and SOP in order to reduce MTTR for responding SRE or Ops resources.
-  - Detailed information on the alerts consistency can be found [here](https://github.com/openshift/enhancements/blob/master/enhancements/monitoring/alerting-consistency.md).
-
-- Minimal performance impact - Network, CPU, Memory, Disk, Throughput etc.
-  - The system, as well as the applications, should be designed to have minimal performance impact during disruptions to ensure stability and also to avoid hogging resources that other applications can use.
-We want to look at this in terms of CPU, Memory, Disk, Throughput, Network etc.
-  - We want to look at this in terms of CPU, Memory, Disk, Throughput, Network etc.
-
-- Appropriate CPU/Memory limits set to avoid performance throttling and OOM kills.
-  - There might be rogue applications hogging resources ( CPU/Memory ) on the nodes which might lead to applications underperforming or worse getting OOM killed. It is important to ensure that applications and system components have reserved resources for the kube-scheduler to take into consideration in order to keep them performing at the expected levels.
-
-- Services dependent on the system under test need to handle the failure gracefully to avoid performance degradation and downtime - appropriate timeouts.
-  - In a distributed system, services deployed coordinate with each other and might have external dependencies. Each of the services deployed as a deployment, pod, or container, need to handle the downtime of other dependent services gracefully instead of crashing due to not having appropriate timeouts, fallback logic etc.
-
-- Proper node sizing to avoid cascading failures and ensure cluster stability especially when the cluster is large and dense
-  - The platform needs to be sized taking into account the resource usage spikes that might occur during chaotic events. For example, if one of the main nodes goes down, the other two main nodes need to have enough resources to handle the load. The resource usage depends on the load or number of objects that are running being managed by the Control Plane ( Api Server, Etcd, Controller and Scheduler ). As such, it’s critical to test such conditions, understand the behavior, and leverage the data to size the platform appropriately. This can help keep the applications stable during unplanned events without the control plane undergoing cascading failures which can potentially bring down the entire cluster.
-
-- Proper node sizing to avoid application failures and maintain stability.
-  - An application pod might use more resources during reinitialization after a crash, so it is important to take that into account for sizing the nodes in the cluster to accommodate it. For example, monitoring solutions like Prometheus need high amounts of memory to replay the write ahead log ( WAL ) when it restarts. As such, it’s critical to test such conditions, understand the behavior, and leverage the data to size the platform appropriately. This can help keep the application stable during unplanned events without undergoing degradation in performance or even worse hog the resources on the node which can impact other applications and system pods.
-
-
-- Minimal initialization time and fast recovery logic.
-  - The controller watching the component should recognize a failure as soon as possible. The component needs to have minimal initialization time to avoid extended downtime or overloading the replicas if it is a highly available configuration. The cause of failure can be because of issues with the infrastructure on top of which it is running, application failures, or because of service failures that it depends on.
-
-- High Availability deployment strategy.
-  - There should be multiple replicas ( both Kubernetes and application control planes ) running preferably in different availability zones to survive outages while still serving the user/system requests. Avoid single points of failure.
-- Backed by persistent storage
-  - It is important to have the system/application backed by persistent storage. This is especially important in cases where the application is a database or a stateful application given that a node, pod, or container failure will wipe off the data.
-
-- There should be fallback routes to the backend in case of using CDN, for example, Akamai in case of console.redhat.com - a managed service deployed on top of Kubernetes dedicated:
-  - Content delivery networks (CDNs) are commonly used to host resources such as images, JavaScript files, and CSS. The average web page is nearly 2 MB in size, and offloading heavy resources to third-parties is extremely effective for reducing backend server traffic and latency. However, this makes each CDN an additional point of failure for every site that relies on it. If the CDN fails, its customers could also fail.
-  - To test how the application reacts to failures, drop all network traffic between the system and CDN. The application should still serve the content to the user irrespective of the failure.
-
-- Appropriate caching and Content Delivery Network should be enabled to be performant and usable when there is a latency on the client side.
-  - Not every user or machine has access to unlimited bandwidth, there might be a delay on the user side ( client ) to access the API’s due to limited bandwidth, throttling or latency depending on the geographic location. It is important to inject latency between the client and API calls to understand the behavior and optimize things including caching wherever possible, using CDN’s or opting for different protocols like HTTP/2 or HTTP/3 vs HTTP.
-
-
-
-
-### Tooling
-Now that we looked at the best practices, In this section, we will go through how [Kraken](https://github.com/redhat-chaos/krkn) - a chaos testing framework can help test the resilience of Kubernetes and make sure the applications and services are following the best practices.
-
-#### Workflow
-Let us start by understanding the workflow of kraken: the user will start by running kraken by pointing to a specific Kubernetes cluster using kubeconfig to be able to talk to the platform on top of which the Kubernetes cluster is hosted. This can be done by either the oc/kubectl API or the cloud API. Based on the configuration of kraken, it will inject specific chaos scenarios as shown below, talk to [Cerberus](https://github.com/redhat-chaos/cerberus) to get the go/no-go signal representing the overall health of the cluster ( optional - can be turned off ), scrapes metrics from in-cluster prometheus given a metrics profile with the promql queries and stores them long term in Elasticsearch configured  ( optional - can be turned off ), evaluates the promql expressions specified in the alerts profile ( optional - can be turned off ) and aggregated everything to set the pass/fail i.e. exits 0 or 1. More about the metrics collection, cerberus and metrics evaluation can be found in the next section.
-
-![Kraken workflow](../media/kraken-workflow.png)
-
-#### Cluster recovery checks, metrics evaluation and pass/fail criteria
-- Most of the scenarios have built in checks to verify if the targeted component recovered from the failure after the specified duration of time but there might be cases where other components might have an impact because of a certain failure and it’s extremely important to make sure that the system/application is healthy as a whole post chaos. This is exactly where [Cerberus](https://github.com/redhat-chaos/cerberus) comes to the rescue.
-If the monitoring tool, cerberus is enabled it will consume the signal and continue running chaos or not based on that signal.
-
-- Apart from checking the recovery and cluster health status, it’s equally important to evaluate the performance metrics like latency, resource usage spikes, throughput, etcd health like disk fsync, leader elections etc. To help with this, Kraken has a way to evaluate promql expressions from the incluster prometheus and set the exit status to 0 or 1 based on the severity set for each of the query. Details on how to use this feature can be found [here](https://github.com/redhat-chaos/krkn#alerts).
-
-- The overall pass or fail of kraken is based on the recovery of the specific component (within a certain amount of time), the cerberus health signal which tracks the health of the entire cluster and metrics evaluation from incluster prometheus.
-
-
-
-
-### Scenarios
-
-Let us take a look at how to run the chaos scenarios on your Kubernetes clusters using Kraken-hub - a lightweight wrapper around Kraken to ease the runs by providing the ability to run them by just running container images using podman with parameters set as environment variables. This eliminates the need to carry around and edit configuration files and makes it easy for any CI framework integration. Here are the scenarios supported:
-
-- Pod Scenarios ([Documentation](https://github.com/redhat-chaos/krkn-hub/blob/main/docs/pod-scenarios.md))
-  - Disrupts Kubernetes/Kubernetes and applications deployed as pods:
-    - Helps understand the availability of the application, the initialization timing and recovery status.
-  - [Demo](https://asciinema.org/a/452351?speed=3&theme=solarized-dark)
-
-- Container Scenarios ([Documentation](https://github.com/redhat-chaos/krkn-hub/blob/main/docs/container-scenarios.md))
-  - Disrupts Kubernetes/Kubernetes and applications deployed as containers running as part of a pod(s) using a specified kill signal to mimic failures:
-    - Helps understand the impact and recovery timing when the program/process running in the containers are disrupted - hangs, paused, killed etc., using various kill signals, i.e. SIGHUP, SIGTERM, SIGKILL etc.
-  - [Demo](https://asciinema.org/a/BXqs9JSGDSEKcydTIJ5LpPZBM?speed=3&theme=solarized-dark)
-
-- Node Scenarios ([Documentation](https://github.com/redhat-chaos/krkn-hub/blob/main/docs/node-scenarios.md))
-  - Disrupts nodes as part of the cluster infrastructure by talking to the cloud API. AWS, Azure, GCP, OpenStack and Baremetal are the supported platforms as of now. Possible disruptions include:
-    - Terminate nodes
-    - Fork bomb inside the node
-    - Stop the node
-    - Crash the kubelet running on the node
-    - etc.
-  - [Demo](https://asciinema.org/a/ANZY7HhPdWTNaWt4xMFanF6Q5)
-
-- Zone Outages ([Documentation](https://github.com/redhat-chaos/krkn-hub/blob/main/docs/zone-outages.md))
-  - Creates outage of availability zone(s) in a targeted region in the public cloud where the Kubernetes cluster is running by tweaking the network acl of the zone to simulate the failure, and that in turn will stop both ingress and egress traffic from all nodes in a particular zone for the specified duration and reverts it back to the previous state.
-    - Helps understand the impact on both Kubernetes/Kubernetes control plane as well as applications and services running on the worker nodes in that zone.
-    - Currently, only set up for AWS cloud platform: 1 VPC and multiples subnets within the VPC can be specified.
-    - [Demo](https://asciinema.org/a/452672?speed=3&theme=solarized-dark)
-
-- Application Outages ([Documentation](https://github.com/redhat-chaos/krkn-hub/blob/main/docs/application-outages.md))
-  - Scenario to block the traffic ( Ingress/Egress ) of an application matching the labels for the specified duration of time to understand the behavior of the service/other services which depend on it during the downtime.
-    - Helps understand how the dependent services react to the unavailability.
-    - [Demo](https://asciinema.org/a/452403?speed=3&theme=solarized-dark)
-
-- Power Outages ([Documentation](https://github.com/redhat-chaos/krkn-hub/blob/main/docs/power-outages.md))
-  - This scenario imitates a power outage by shutting down of the entire cluster for a specified duration of time, then restarts all the nodes after the specified time and checks the health of the cluster.
-    - There are various use cases in the customer environments. For example, when some of the clusters are shutdown in cases where the applications are not needed to run in a particular time/season in order to save costs.
-    - The nodes are stopped in parallel to mimic a power outage i.e., pulling off the plug
-  - [Demo](https://asciinema.org/a/r0zLbh70XK7gnc4s5v0ZzSXGo)
-
-- Resource Hog
-  - Hogs CPU, Memory and IO on the targeted nodes
-    - Helps understand if the application/system components have reserved resources to not get disrupted because of rogue applications, or get performance throttled.
-      - CPU Hog ([Documentation](https://github.com/redhat-chaos/krkn-hub/blob/main/docs/node-cpu-hog.md), [Demo](https://asciinema.org/a/452762))
-      - Memory Hog ([Documentation](https://github.com/redhat-chaos/krkn-hub/blob/main/docs/node-memory-hog.md), [Demo](https://asciinema.org/a/452742?speed=3&theme=solarized-dark))
-
-- Time Skewing ([Documentation](https://github.com/redhat-chaos/krkn-hub/blob/main/docs/time-scenarios.md))
-  - Manipulate the system time and/or date of specific pods/nodes.
-    - Verify scheduling of objects so they continue to work.
-    - Verify time gets reset properly.
-
-- Namespace Failures ([Documentation](https://github.com/redhat-chaos/krkn-hub/blob/main/docs/namespace-scenarios.md))
-  - Delete namespaces for the specified duration.
-    - Helps understand the impact on other components and tests/improves recovery time of the components in the targeted namespace.
-
-- Persistent Volume Fill ([Documentation](https://github.com/redhat-chaos/krkn-hub/blob/main/docs/pvc-scenarios.md))
-  - Fills up the persistent volumes, up to a given percentage, used by the pod for the specified duration.
-    - Helps understand how an application deals when it is no longer able to write data to the disk. For example, kafka’s behavior when it is not able to commit data to the disk.
-
-- Network Chaos ([Documentation](https://github.com/redhat-chaos/krkn-hub/blob/main/docs/network-chaos.md))
-  - Scenarios supported includes:
-    - Network latency
-    - Packet loss
-    - Interface flapping
-    - DNS errors
-    - Packet corruption
-    - Bandwidth limitation
-
-
-
-
-### Test Environment Recommendations - how and where to run chaos tests
-
-Let us take a look at few recommendations on how and where to run the chaos tests:
-
-- Run the chaos tests continuously in your test pipelines:
-  - Software, systems, and infrastructure does change – and the condition/health of each can change pretty rapidly. A good place to run tests is in your CI/CD pipeline running on a regular cadence.
-
-- Run the chaos tests manually to learn from the system:
-  - When running a Chaos scenario or Fault tests, it is more important to understand how the system responds and reacts, rather than mark the execution as pass or fail.
-  - It is important to define the scope of the test before the execution to avoid some issues from masking others.
-
-- Run the chaos tests in production environments or mimic the load in staging environments:
-  - As scary as a thought about testing in production is, production is the environment that users are in and traffic spikes/load are real. To fully test the robustness/resilience of a production system, running Chaos Engineering experiments in a production environment will provide needed insights. A couple of things to keep in mind:
-    - Minimize blast radius and have a backup plan in place to make sure the users and customers do not undergo downtime.
-    - Mimic the load in a staging environment in case Service Level Agreements  are too tight to cover any downtime.
-
-- Enable Observability:
-  - Chaos Engineering Without Observability ... Is Just Chaos.
-  - Make sure to have logging and monitoring installed on the cluster to help with understanding the behaviour as to why it is happening. In case of running the tests in the CI where it is not humanly possible to monitor the cluster all the time, it is recommended to leverage Cerberus to capture the state during the runs and metrics collection in Kraken to store metrics long term even after the cluster is gone.
-  - Kraken ships with dashboards that will help understand API, Etcd and Kubernetes cluster level stats and performance metrics.
-  - Pay attention to Prometheus alerts. Check if they are firing as expected.
-
-- Run multiple chaos tests at once to mimic the production outages:
-  - For example, hogging both IO and Network at the same time instead of running them separately to observe the impact.
-  - You might have existing test cases, be it related to Performance, Scalability or QE. Run the chaos in the background during the test runs to observe the impact. Signaling feature in Kraken can help with coordinating the chaos runs i.e., start, stop, pause the scenarios based on the state of the other test jobs.
-
-
-#### Chaos testing in Practice
-
-##### OpenShift organization
-Within the OpenShift organization we use kraken to perform chaos testing throughout a release before the code is available to customers.
-
-    1. We execute kraken during our regression test suite.
-
-        i. We cover each of the chaos scenarios across different clouds.
-
-            a. Our testing is predominantly done on AWS, Azure and GCP.
-
-    2. We run the chaos scenarios during a long running reliability test.
-
-        i. During this test we perform different types of tasks by different users on the cluster.
-
-        ii. We have added the execution of kraken to perform at certain times throughout the long running test and monitor the health of the cluster.
-
-        iii. This test can be seen here: https://github.com/openshift/svt/tree/master/reliability-v2
-
-    3. We are starting to add in test cases that perform chaos testing during an upgrade (not many iterations of this have been completed).
-
-
-##### startx-lab
-
-**NOTE**: Requests for enhancements and any issues need to be filed at the mentioned links given that they are not natively supported in Kraken.
-
-The following content covers the implementation details around how Startx is leveraging Kraken:
-
-* Using kraken as part of a tekton pipeline
-
-You can find on [artifacthub.io](https://artifacthub.io/packages/search?kind=7&ts_query_web=kraken) the 
-[kraken-scenario](https://artifacthub.io/packages/tekton-task/startx-tekton-catalog/kraken-scenario) `tekton-task`
-which can be used to start a kraken chaos scenarios as part of a chaos pipeline.
-
-To use this task, you must have :
-
-  - Openshift pipeline enabled (or tekton CRD loaded for Kubernetes clusters)
-  - 1 Secret named `kraken-aws-creds` for scenarios using aws
-  - 1 ConfigMap named `kraken-kubeconfig` with credentials to the targeted cluster
-  - 1 ConfigMap named `kraken-config-example` with kraken configuration file (config.yaml)
-  - 1 ConfigMap named `kraken-common-example` with all kraken related files
-  - The `pipeline` SA with be autorized to run with priviveged SCC
-
-You can create theses resources using the following sequence :
-
-```bash
-oc project default
-oc adm policy add-scc-to-user privileged -z pipeline
-oc apply -f https://github.com/startxfr/tekton-catalog/raw/stable/task/kraken-scenario/0.1/samples/common.yaml
-```
-
-Then you must change content of `kraken-aws-creds` secret, `kraken-kubeconfig` and `kraken-config-example` configMap
-to reflect your cluster configuration. Refer to the [kraken configuration](https://github.com/redhat-chaos/krkn/blob/main/config/config.yaml)
-and [configuration examples](https://github.com/startxfr/tekton-catalog/blob/stable/task/kraken-scenario/0.1/samples/) 
-for details on how to configure theses resources.
-
-* Start as a single taskrun
-
-```bash
-oc apply -f https://github.com/startxfr/tekton-catalog/raw/stable/task/kraken-scenario/0.1/samples/taskrun.yaml
-```
-
-* Start as a pipelinerun
-
-```yaml
-oc apply -f https://github.com/startxfr/tekton-catalog/raw/stable/task/kraken-scenario/0.1/samples/pipelinerun.yaml
-```
-
-* Deploying kraken using a helm-chart
-
-You can find on [artifacthub.io](https://artifacthub.io/packages/search?kind=0&ts_query_web=kraken) the
-[chaos-kraken](https://artifacthub.io/packages/helm/startx/chaos-kraken) `helm-chart`
-which can be used to deploy a kraken chaos scenarios.
-
-Default configuration create the following resources :
-
-  - 1 project named **chaos-kraken**
-  - 1 scc with privileged context for kraken deployment
-  - 1 configmap with kraken 21 generic scenarios, various scripts and configuration
-  - 1 configmap with kubeconfig of the targeted cluster
-  - 1 job named kraken-test-xxx
-  - 1 service to the kraken pods
-  - 1 route to the kraken service
-
-```bash
-# Install the startx helm repository
-helm repo add startx https://startxfr.github.io/helm-repository/packages/
-# Install the kraken project
-helm install --set project.enabled=true chaos-kraken-project  startx/chaos-kraken
-# Deploy the kraken instance
-helm install \
---set kraken.enabled=true \
---set kraken.aws.credentials.region="eu-west-3" \
---set kraken.aws.credentials.key_id="AKIAXXXXXXXXXXXXXXXX" \
---set kraken.aws.credentials.secret="xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx" \
---set kraken.kubeconfig.token.server="https://api.mycluster:6443" \
---set kraken.kubeconfig.token.token="sha256~XXXXXXXXXX_PUT_YOUR_TOKEN_HERE_XXXXXXXXXXXX" \
--n chaos-kraken \
-chaos-kraken-instance startx/chaos-kraken
-```

docs/installation.md

@@ -1,45 +0,0 @@
-## Installation
-
-The following ways are supported to run Kraken:
-
-- Standalone python program through Git.
-- Containerized version using either Podman or Docker as the runtime via [Krkn-hub](https://github.com/krkn-chaos/krkn-hub)
-- Kubernetes or OpenShift deployment ( unsupported )
-
-**NOTE**: It is recommended to run Kraken external to the cluster ( Standalone or Containerized ) hitting the Kubernetes/OpenShift API as running it internal to the cluster might be disruptive to itself and also might not report back the results if the chaos leads to cluster's API server instability.
-
-**NOTE**: To run Kraken on Power (ppc64le) architecture, build and run a containerized version by following the
- instructions given [here](https://github.com/krkn-chaos/krkn/blob/main/containers/build_own_image-README.md).
-
-**NOTE**: Helper functions for interactions in Krkn are part of [krkn-lib](https://github.com/redhat-chaos/krkn-lib). 
-Please feel free to reuse and expand them as you see fit when adding a new scenario or expanding 
-the capabilities of the current supported scenarios.
-
-
-### Git
-
-#### Clone the repository
-Pick the latest stable release to install [here](https://github.com/krkn-chaos/krkn/releases).
-```
-$ git clone https://github.com/krkn-chaos/krkn.git --branch <release version>
-$ cd krkn
-```
-
-#### Install the dependencies
-```
-$ python3.9 -m venv chaos
-$ source chaos/bin/activate
-$ pip3.9 install -r requirements.txt
-```
-
-**NOTE**: Make sure python3-devel and latest pip versions are installed on the system. The dependencies install has been tested with pip >= 21.1.3 versions.
-
-#### Run
-```
-$ python3.9 run_kraken.py --config <config_file_location>
-```
-
-### Run containerized version
-[Krkn-hub](https://github.com/krkn-chaos/krkn-hub) is a wrapper that allows running Krkn chaos scenarios via podman or docker runtime with scenario parameters/configuration defined as environment variables.
-
-Refer [instructions](https://github.com/krkn-chaos/krkn-hub#supported-chaos-scenarios) to get started.

docs/managedcluster_scenarios.md

@@ -1,36 +0,0 @@
-### ManagedCluster Scenarios
-
-[ManagedCluster](https://open-cluster-management.io/concepts/managedcluster/) scenarios provide a way to integrate kraken with [Open Cluster Management (OCM)](https://open-cluster-management.io/) and [Red Hat Advanced Cluster Management for Kubernetes (ACM)](https://www.redhat.com/en/technologies/management/advanced-cluster-management).
-
-ManagedCluster scenarios leverage [ManifestWorks](https://open-cluster-management.io/concepts/manifestwork/) to inject faults into the ManagedClusters.
-
-The following ManagedCluster chaos scenarios are supported:
-
-1. **managedcluster_start_scenario**: Scenario to start the ManagedCluster instance.
-2. **managedcluster_stop_scenario**: Scenario to stop the ManagedCluster instance.
-3. **managedcluster_stop_start_scenario**: Scenario to stop and then start the ManagedCluster instance.
-4. **start_klusterlet_scenario**: Scenario to start the klusterlet of the ManagedCluster instance.
-5. **stop_klusterlet_scenario**: Scenario to stop the klusterlet of the ManagedCluster instance.
-6. **stop_start_klusterlet_scenario**: Scenario to stop and start the klusterlet of the ManagedCluster instance.
-
-ManagedCluster scenarios can be injected by placing the ManagedCluster scenarios config files under `managedcluster_scenarios` option in the Kraken config. Refer to [managedcluster_scenarios_example](https://github.com/redhat-chaos/krkn/blob/main/scenarios/kube/managedcluster_scenarios_example.yml) config file.
-
-```
-managedcluster_scenarios:
-  - actions:                                                        # ManagedCluster chaos scenarios to be injected
-    - managedcluster_stop_start_scenario
-    managedcluster_name: cluster1                                   # ManagedCluster on which scenario has to be injected; can set multiple names separated by comma
-    # label_selector:                                               # When managedcluster_name is not specified, a ManagedCluster with matching label_selector is selected for ManagedCluster chaos scenario injection
-    instance_count: 1                                               # Number of managedcluster to perform action/select that match the label selector
-    runs: 1                                                         # Number of times to inject each scenario under actions (will perform on same ManagedCluster each time)
-    timeout: 420                                                    # Duration to wait for completion of ManagedCluster scenario injection
-                                                                    # For OCM to detect a ManagedCluster as unavailable, have to wait 5*leaseDurationSeconds
-                                                                    # (default leaseDurationSeconds = 60 sec)
-  - actions:
-    - stop_start_klusterlet_scenario
-    managedcluster_name: cluster1
-    # label_selector:
-    instance_count: 1
-    runs: 1
-    timeout: 60
-```

docs/network_chaos.md

@@ -1,49 +0,0 @@
-### Network chaos
-Scenario to introduce network latency, packet loss, and bandwidth restriction in the Node's host network interface. The purpose of this scenario is to observe faults caused by random variations in the network.
-
-##### Sample scenario config for egress traffic shaping
-```
-network_chaos:                                    # Scenario to create an outage by simulating random variations in the network.
-  duration: 300                                   # In seconds - duration network chaos will be applied.
-  node_name:                                      # Comma separated node names on which scenario has to be injected.
-  label_selector: node-role.kubernetes.io/master  # When node_name is not specified, a node with matching label_selector is selected for running the scenario.
-  instance_count: 1                               # Number of nodes in which to execute network chaos.
-  interfaces:                                     # List of interface on which to apply the network restriction.
-  - "ens5"                                        # Interface name would be the Kernel host network interface name.
-  execution: serial|parallel                      # Execute each of the egress options as a single scenario(parallel) or as separate scenario(serial).
-  egress:
-    latency: 500ms
-    loss: 50%                                    # percentage
-    bandwidth: 10mbit
-```
-
-##### Sample scenario config for ingress traffic shaping (using a plugin)
-```
-- id: network_chaos
-  config:
-    node_interface_name:                            # Dictionary with key as node name(s) and value as a list of its interfaces to test
-      ip-10-0-128-153.us-west-2.compute.internal:
-        - ens5
-        - genev_sys_6081
-    label_selector: node-role.kubernetes.io/master  # When node_interface_name is not specified, nodes with matching label_selector is selected for node chaos scenario injection
-    instance_count: 1                               # Number of nodes to perform action/select that match the label selector
-    kubeconfig_path: ~/.kube/config                 # Path to kubernetes config file. If not specified, it defaults to ~/.kube/config
-    execution_type: parallel                        # Execute each of the ingress options as a single scenario(parallel) or as separate scenario(serial).
-    network_params:
-        latency: 500ms
-        loss: '50%'
-        bandwidth: 10mbit
-    wait_duration: 120
-    test_duration: 60
-```
-
-  Note: For ingress traffic shaping, ensure that your node doesn't have any [IFB](https://wiki.linuxfoundation.org/networking/ifb) interfaces already present. The scenario relies on creating IFBs to do the shaping, and they are deleted at the end of the scenario.
-
-
-##### Steps
- - Pick the nodes to introduce the network anomaly either from node_name or label_selector.
- - Verify interface list in one of the nodes or use the interface with a default route, as test interface, if no interface is specified by the user.
- - Set traffic shaping config on node's interface using tc and netem.
- - Wait for the duration time.
- - Remove traffic shaping config on node's interface.
- - Remove the job that spawned the pod.

docs/node_scenarios.md

@@ -1,121 +0,0 @@
-### Node Scenarios
-
-The following node chaos scenarios are supported:
-
-1. **node_start_scenario**: Scenario to stop the node instance.
-2. **node_stop_scenario**: Scenario to stop the node instance.
-3. **node_stop_start_scenario**: Scenario to stop the node instance for specified duration and then start the node instance. Not supported on VMware.
-4. **node_termination_scenario**: Scenario to terminate the node instance.
-5. **node_reboot_scenario**: Scenario to reboot the node instance.
-6. **stop_kubelet_scenario**: Scenario to stop the kubelet of the node instance.
-7. **stop_start_kubelet_scenario**: Scenario to stop and start the kubelet of the node instance.
-8. **restart_kubelet_scenario**: Scenario to restart the kubelet of the node instance.
-9. **node_crash_scenario**: Scenario to crash the node instance.
-10. **stop_start_helper_node_scenario**: Scenario to stop and start the helper node and check service status.
-11. **node_disk_detach_attach_scenario**: Scenario to detach node disk for specified duration.
-
-
-**NOTE**: If the node does not recover from the node_crash_scenario injection, reboot the node to get it back to Ready state.
-
-**NOTE**: node_start_scenario, node_stop_scenario, node_stop_start_scenario, node_termination_scenario
-, node_reboot_scenario and stop_start_kubelet_scenario are supported on AWS, Azure, OpenStack, BareMetal, GCP
-, VMware and Alibaba.
-
-**NOTE**: node_disk_detach_attach_scenario is supported only on AWS and cannot detach root disk.
-
-
-#### AWS
-
-Cloud setup instructions can be found [here](cloud_setup.md#aws). Sample scenario config can be found [here](https://github.com/krkn-chaos/krkn/blob/main/scenarios/openshift/aws_node_scenarios.yml).
-
-
-
-#### Baremetal
-
-Sample scenario config can be found [here](https://github.com/krkn-chaos/krkn/blob/main/scenarios/openshift/baremetal_node_scenarios.yml).
-
-**NOTE**: Baremetal requires setting the IPMI user and password to power on, off, and reboot nodes, using the config options `bm_user` and `bm_password`. It can either be set in the root of the entry in the scenarios config, or it can be set per machine.
-
-If no per-machine addresses are specified, kraken attempts to use the BMC value in the BareMetalHost object. To list them, you can do 'oc get bmh -o wide --all-namespaces'. If the BMC values are blank, you must specify them per-machine using the config option 'bmc_addr' as specified below.
-
-For per-machine settings, add a "bmc_info" section to the entry in the scenarios config. Inside there, add a configuration section using the node name. In that, add per-machine settings. Valid settings are 'bmc_user', 'bmc_password', and 'bmc_addr'.
-See the example node scenario or the example below.
-
-**NOTE**: Baremetal requires oc (openshift client) be installed on the machine running Kraken.
-
-**NOTE**: Baremetal machines are fragile. Some node actions can occasionally corrupt the filesystem if it does not shut down properly, and sometimes the kubelet does not start properly.
-
-
-
-#### Docker
-
-The Docker provider can be used to run node scenarios against kind clusters.
-
-[kind](https://kind.sigs.k8s.io/) is a tool for running local Kubernetes clusters using Docker container "nodes".
-
-kind was primarily designed for testing Kubernetes itself, but may be used for local development or CI.
-
-
-
-#### GCP
-Cloud setup instructions can be found [here](cloud_setup.md#gcp). Sample scenario config can be found [here](https://github.com/krkn-chaos/krkn/blob/main/scenarios/openshift/gcp_node_scenarios.yml).
-
-NOTE: The parallel option is not available for GCP, the api doesn't perform processes at the same time
-
-
-#### Openstack
-
-How to set up Openstack cli to run node scenarios is defined [here](cloud_setup.md#openstack).
-
-The supported node level chaos scenarios on an OPENSTACK cloud are `node_stop_start_scenario`, `stop_start_kubelet_scenario` and `node_reboot_scenario`.
-
-**NOTE**: For `stop_start_helper_node_scenario`,  visit [here](https://github.com/redhat-cop/ocp4-helpernode) to learn more about the helper node and its usage.
-
-To execute the scenario, ensure the value for `ssh_private_key` in the node scenarios config file is set with the correct private key file path for ssh connection to the helper node. Ensure passwordless ssh is configured on the host running Kraken and the helper node to avoid connection errors.
-
-
-
-#### Azure
-
-Cloud setup instructions can be found [here](cloud_setup.md#azure). Sample scenario config can be found [here](https://github.com/krkn-chaos/krkn/blob/main/scenarios/openshift/azure_node_scenarios.yml).
-
-
-
-#### Alibaba
-
-How to set up Alibaba cli to run node scenarios is defined [here](cloud_setup.md#alibaba).
-
-**NOTE**: There is no "terminating" idea in Alibaba, so any scenario with terminating will "release" the node
-. Releasing a node is 2 steps, stopping the node and then releasing it.
-
-
-
-#### VMware
-How to set up VMware vSphere to run node scenarios is defined [here](cloud_setup.md#vmware)
-
-This cloud type uses a different configuration style, see actions below and [example config file](../scenarios/openshift/vmware_node_scenarios.yml)
-
-- vmware-node-terminate
-- vmware-node-reboot
-- vmware-node-stop
-- vmware-node-start
-
-
-
-#### IBMCloud
-How to set up IBMCloud to run node scenarios is defined [here](cloud_setup.md#ibmcloud)
-
-This cloud type uses a different configuration style, see actions below and [example config file](../scenarios/openshift/ibmcloud_node_scenarios.yml)
-
-- ibmcloud-node-terminate
-- ibmcloud-node-reboot
-- ibmcloud-node-stop
-- ibmcloud-node-start
-
-
-
-#### General
-
-**NOTE**: The `node_crash_scenario` and `stop_kubelet_scenario` scenario is supported independent of the cloud platform.
-
-Use 'generic' or do not add the 'cloud_type' key to your scenario if your cluster is not set up using one of the current supported cloud types.

docs/performance_dashboards.md

@@ -1,12 +0,0 @@
-## Performance dashboards
-
-Kraken supports installing a mutable grafana on the cluster with the dashboards loaded to help with monitoring the cluster for things like resource usage to find the outliers, API stats, Etcd health, Critical alerts etc. It can be deployed by enabling the following in the config:
-
-```
-performance_monitoring:
-    deploy_dashboards: True
-```
-
-The route and credentials to access the dashboards will be printed on the stdout before Kraken starts creating chaos. The dashboards can be edited/modified to include your queries of interest.
-
-**NOTE**: The dashboards leverage Prometheus for scraping the metrics off of the cluster and currently only supports OpenShift since Prometheus is setup on the cluster by default and leverages routes object to expose the grafana dashboards externally.

docs/pod_network_scenarios.md

@@ -1,46 +0,0 @@
-## Pod network Scenarios
-
-### Pod outage
-Scenario to block the traffic ( Ingress/Egress ) of a pod matching the labels for the specified duration of time to understand the behavior of the service/other services which depend on it during downtime. This helps with planning the requirements accordingly, be it improving the timeouts or tweaking the alerts etc.
-With the current network policies, it is not possible to explicitly block ports which are enabled by allowed network policy rule. This chaos scenario addresses this issue by using OVS flow rules to block ports related to the pod. It supports OpenShiftSDN and OVNKubernetes based networks.
-
-##### Sample scenario config (using a plugin)
-```
-- id: pod_network_outage
-  config:
-    namespace: openshift-console   # Required - Namespace of the pod to which filter need to be applied
-    direction:                     # Optioinal - List of directions to apply filters
-        - ingress                  # Blocks ingress traffic, Default both egress and ingress
-    ingress_ports:                 # Optional - List of ports to block traffic on
-        - 8443                     # Blocks 8443, Default [], i.e. all ports.
-    label_selector: 'component=ui' # Blocks access to openshift console
-```
-### Pod Network shaping
-Scenario to introduce network latency, packet loss, and bandwidth restriction in the Pod's network interface. The purpose of this scenario is to observe faults caused by random variations in the network.
-
-##### Sample scenario config for egress traffic shaping (using plugin)
-```
-- id: pod_egress_shaping
-  config:
-    namespace: openshift-console   # Required - Namespace of the pod to which filter need to be applied.
-    label_selector: 'component=ui' # Applies traffic shaping to access openshift console.
-    network_params:
-        latency: 500ms             # Add 500ms latency to egress traffic from the pod.
-```
-##### Sample scenario config for ingress traffic shaping (using plugin)
-```
-- id: pod_ingress_shaping
-  config:
-    namespace: openshift-console   # Required - Namespace of the pod to which filter need to be applied.
-    label_selector: 'component=ui' # Applies traffic shaping to access openshift console.
-    network_params:
-        latency: 500ms             # Add 500ms latency to egress traffic from the pod.
-```
-
-##### Steps
- - Pick the pods to introduce the network anomaly either from label_selector or pod_name.
- - Identify the pod interface name on the node.
- - Set traffic shaping config on pod's interface using tc and netem.
- - Wait for the duration time.
- - Remove traffic shaping config on pod's interface.
- - Remove the job that spawned the pod.

docs/pod_scenarios.md

@@ -1,37 +0,0 @@
-### Pod Scenarios
-
-Krkn recently replaced PowerfulSeal with its own internal pod scenarios using a plugin system. You can run pod scenarios by adding the following config to Krkn:
-
-```yaml
-kraken:
-  chaos_scenarios:
-    - plugin_scenarios:
-      - path/to/scenario.yaml
-```
-
-You can then create the scenario file with the following contents:
-
-```yaml
-# yaml-language-server: $schema=../plugin.schema.json
-- id: kill-pods
-  config:
-    namespace_pattern: ^kube-system$
-    label_selector: k8s-app=kube-scheduler
-    krkn_pod_recovery_time: 120
-    
-```
-
-Please adjust the schema reference to point to the [schema file](../scenarios/plugin.schema.json). This file will give you code completion and documentation for the available options in your IDE.
-
-#### Pod Chaos Scenarios
-
-The following are the components of Kubernetes/OpenShift for which a basic chaos scenario config exists today.
-
-| Component                | Description | Working  |
-| ------------------------ |-------------| -------- |
-| [Basic pod scenario](../scenarios/kube/pod.yml) | Kill a pod. | :heavy_check_mark: |
-| [Etcd](../scenarios/openshift/etcd.yml) | Kills a single/multiple etcd replicas. | :heavy_check_mark: |
-| [Kube ApiServer](../scenarios/openshift/openshift-kube-apiserver.yml)| Kills a single/multiple kube-apiserver replicas. | :heavy_check_mark: |
-| [ApiServer](../scenarios/openshift/openshift-apiserver.yml) | Kills a single/multiple apiserver replicas. | :heavy_check_mark: |
-| [Prometheus](../scenarios/openshift/prometheus.yml) | Kills a single/multiple prometheus replicas. | :heavy_check_mark: |
-| [OpenShift System Pods](../scenarios/openshift/regex_openshift_pod_kill.yml) | Kills random pods running in the OpenShift system namespaces. | :heavy_check_mark: |

docs/pvc_scenario.md

@@ -1,26 +0,0 @@
-### PVC scenario
-Scenario to fill up a given PersistenVolumeClaim by creating a temp file on the PVC from a pod associated with it. The purpose of this scenario is to fill up a volume to understand faults caused by the application using this volume.
-
-##### Sample scenario config
-```
-pvc_scenario:
-  pvc_name: <pvc_name>          # Name of the target PVC.
-  pod_name: <pod_name>          # Name of the pod where the PVC is mounted. It will be ignored if the pvc_name is defined.
-  namespace: <namespace_name>   # Namespace where the PVC is.
-  fill_percentage: 50           # Target percentage to fill up the cluster. Value must be higher than current percentage. Valid values are between 0 and 99.
-  duration: 60                  # Duration in seconds for the fault.
-```
-
-##### Steps
- - Get the pod name where the PVC is mounted.
- - Get the volume name mounted in the container pod.
- - Get the container name where the PVC is mounted.
- - Get the mount path where the PVC is mounted in the pod.
- - Get the PVC capacity and current used capacity.
- - Calculate file size to fill the PVC to the target fill_percentage.
- - Connect to the pod.
- - Create a temp file `kraken.tmp` with random data on the mount path:
-    - `dd bs=1024 count=$file_size </dev/urandom > /mount_path/kraken.tmp`
- - Wait for the duration time.
- - Remove the temp file created:
-    - `rm kraken.tmp`

docs/scenario_plugin_api.md

@@ -1,136 +0,0 @@
-# Scenario Plugin API:
-
-This API enables seamless integration of Scenario Plugins for Krkn. Plugins are automatically 
-detected and loaded by the plugin loader, provided they extend the `AbstractPluginScenario` 
-abstract class, implement the required methods, and adhere to the specified [naming conventions](#naming-conventions).
-
-## Plugin folder:
-
-The plugin loader automatically loads plugins found in the `krkn/scenario_plugins` directory, 
-relative to the Krkn root folder. Each plugin must reside in its own directory and can consist 
-of one or more Python files. The entry point for each plugin is a Python class that extends the 
-[AbstractPluginScenario](../krkn/scenario_plugins/abstract_scenario_plugin.py) abstract class and implements its required methods.
-
-## `AbstractPluginScenario` abstract class:
-
-This [abstract class](../krkn/scenario_plugins/abstract_scenario_plugin.py) defines the contract between the plugin and krkn.
-It consists of two methods:
-- `run(...)`
-- `get_scenario_type()`
-
-Most IDEs can automatically suggest and implement the abstract methods defined in `AbstractPluginScenario`:
-![pycharm](scenario_plugin_pycharm.gif)
-_(IntelliJ PyCharm)_
-
-### `run(...)`
-
-```python
-    def run(
-        self,
-        run_uuid: str,
-        scenario: str,
-        krkn_config: dict[str, any],
-        lib_telemetry: KrknTelemetryOpenshift,
-        scenario_telemetry: ScenarioTelemetry,
-    ) -> int:
-
-```
-
-This method represents the entry point of the plugin and the first method 
-that will be executed.
-#### Parameters:
-
-- `run_uuid`:
-  - the uuid of the chaos run generated by krkn for every single run.
-- `scenario`:
-  - the config file of the scenario that is currently executed
-- `krkn_config`:
-  - the full dictionary representation of the `config.yaml`
-- `lib_telemetry`
-  - it is a composite object of all the [krkn-lib](https://krkn-chaos.github.io/krkn-lib-docs/modules.html) objects and methods needed by a krkn plugin to run.
-- `scenario_telemetry`
-  - the `ScenarioTelemetry` object of the scenario that is currently executed
- 
-### Return value:
-Returns 0 if the scenario succeeds and 1 if it fails.
-> [!WARNING]
-> All the exception must be handled __inside__ the run method and not propagated.
-
-### `get_scenario_types()`:
-
-```python    def get_scenario_types(self) -> list[str]:```
-
-Indicates the scenario types specified in the `config.yaml`. For the plugin to be properly
-loaded, recognized and executed, it must be implemented and must return one or more
-strings matching `scenario_type` strings set in the config.
-> [!WARNING]
-> Multiple strings can map to a *single*  `ScenarioPlugin` but the same string cannot map
-> to different plugins, an exception will be thrown for scenario_type redefinition.
-
-> [!Note]  
-> The `scenario_type` strings must be unique across all plugins; otherwise, an exception will be thrown.
-
-## Naming conventions:
-A key requirement for developing a plugin that will be properly loaded 
-by the plugin loader is following the established naming conventions. 
-These conventions are enforced to maintain a uniform and readable codebase, 
-making it easier to onboard new developers from the community.
-
-### plugin folder:
-- the plugin folder must be placed in the `krkn/scenario_plugin` folder starting from the krkn root folder
-- the plugin folder __cannot__ contain the words
-  - `plugin`
-  - `scenario`
-### plugin file name and class name:
-- the plugin file containing the main plugin class must be named in _snake case_ and must have the suffix `_scenario_plugin`: 
-  - `example_scenario_plugin.py`
-- the main plugin class must named in _capital camel case_ and must have the suffix `ScenarioPlugin` : 
-  - `ExampleScenarioPlugin`
-- the file name must match the class name in the respective syntax:
-  - `example_scenario_plugin.py` -> `ExampleScenarioPlugin`
-
-### scenario type:
-- the scenario type __must__ be unique between all the scenarios.
-
-### logging:
-If your new scenario does not adhere to the naming conventions, an error log will be generated in the Krkn standard output,
-providing details about the issue:
-
-```commandline
-2024-10-03 18:06:31,136 [INFO] 📣 `ScenarioPluginFactory`: types from config.yaml mapped to respective classes for execution:
-2024-10-03 18:06:31,136 [INFO]   ✅ type: application_outages_scenarios ➡️ `ApplicationOutageScenarioPlugin` 
-2024-10-03 18:06:31,136 [INFO]   ✅ types: [hog_scenarios, arcaflow_scenario] ➡️ `ArcaflowScenarioPlugin` 
-2024-10-03 18:06:31,136 [INFO]   ✅ type: container_scenarios ➡️ `ContainerScenarioPlugin` 
-2024-10-03 18:06:31,136 [INFO]   ✅ type: managedcluster_scenarios ➡️ `ManagedClusterScenarioPlugin` 
-2024-10-03 18:06:31,137 [INFO]   ✅ types: [pod_disruption_scenarios, pod_network_scenario, vmware_node_scenarios, ibmcloud_node_scenarios] ➡️ `NativeScenarioPlugin` 
-2024-10-03 18:06:31,137 [INFO]   ✅ type: network_chaos_scenarios ➡️ `NetworkChaosScenarioPlugin` 
-2024-10-03 18:06:31,137 [INFO]   ✅ type: node_scenarios ➡️ `NodeActionsScenarioPlugin` 
-2024-10-03 18:06:31,137 [INFO]   ✅ type: pvc_scenarios ➡️ `PvcScenarioPlugin` 
-2024-10-03 18:06:31,137 [INFO]   ✅ type: service_disruption_scenarios ➡️ `ServiceDisruptionScenarioPlugin` 
-2024-10-03 18:06:31,137 [INFO]   ✅ type: service_hijacking_scenarios ➡️ `ServiceHijackingScenarioPlugin` 
-2024-10-03 18:06:31,137 [INFO]   ✅ type: cluster_shut_down_scenarios ➡️ `ShutDownScenarioPlugin` 
-2024-10-03 18:06:31,137 [INFO]   ✅ type: syn_flood_scenarios ➡️ `SynFloodScenarioPlugin` 
-2024-10-03 18:06:31,137 [INFO]   ✅ type: time_scenarios ➡️ `TimeActionsScenarioPlugin` 
-2024-10-03 18:06:31,137 [INFO]   ✅ type: zone_outages_scenarios ➡️ `ZoneOutageScenarioPlugin`
-
-2024-09-18 14:48:41,735 [INFO] Failed to load Scenario Plugins:
-
-2024-09-18 14:48:41,735 [ERROR] ⛔ Class: ExamplePluginScenario Module: krkn.scenario_plugins.example.example_scenario_plugin
-2024-09-18 14:48:41,735 [ERROR] ⚠️ scenario plugin class name must start with a capital letter, end with `ScenarioPlugin`, and cannot be just `ScenarioPlugin`.
-```
-
->[!NOTE]
->If you're trying to understand how the scenario types in the config.yaml are mapped to 
-> their corresponding plugins, this log will guide you! 
-> Each scenario plugin class mentioned can be found in the `krkn/scenario_plugin` folder
-> simply convert the camel case notation and remove the ScenarioPlugin suffix from the class name
-> e.g `ShutDownScenarioPlugin` class can be found in the `krkn/scenario_plugin/shut_down` folder.
-
-## ExampleScenarioPlugin
-The [ExampleScenarioPlugin](../krkn/tests/test_classes/example_scenario_plugin.py) class included in the tests folder can be used as a scaffolding for new plugins and it is considered
-part of the documentation.
-
-For any questions or further guidance, feel free to reach out to us on the 
-[Kubernetes workspace](https://kubernetes.slack.com/) in the `#krkn` channel. 
-We’re happy to assist. Now, __release the Krkn!__
-

docs/service_disruption_scenarios.md

@@ -1,63 +0,0 @@
-###  Service Disruption Scenarios (Previously Delete Namespace Scenario)
-
-Using this type of scenario configuration one is able to delete crucial objects in a specific namespace, or a namespace matching a certain regex string.
-
-Configuration Options:
-
-**namespace:** Specific namespace or regex style namespace of what you want to delete. Gets all namespaces if not specified; set to "" if you want to use the label_selector field.
-
-Set to '^.*$' and label_selector to "" to randomly select any namespace in your cluster.
-
-**label_selector:** Label on the namespace you want to delete. Set to "" if you are using the namespace variable.
-
-**delete_count:** Number of namespaces to kill in each run. Based on matching namespace and label specified, default is 1.
-
-**runs:** Number of runs/iterations to kill namespaces, default is 1.
-
-**sleep:** Number of seconds to wait between each iteration/count of killing namespaces. Defaults to 10 seconds if not set
-
-Refer to [namespace_scenarios_example](https://github.com/krkn-chaos/krkn/blob/main/scenarios/regex_namespace.yaml) config file.
-
-```
-scenarios:
-- namespace: "^.*$"
-  runs: 1
-- namespace: "^.*ingress.*$"
-  runs: 1
-  sleep: 15
-```
-
-
-### Steps
-
-This scenario will select a namespace (or multiple) dependent on the configuration and will kill all of the below object types in that namespace and will wait for them to be Running in the post action 
-1. Services 
-2. Daemonsets
-3. Statefulsets
-4. Replicasets
-5. Deployments 
-
-
-#### Post Action
-
-We do a post chaos check to wait and verify the specific objects in each namespace are Ready
-
-Here there are two options:
-
-1. Pass a custom script in the main config scenario list that will run before the chaos and verify the output matches post chaos scenario.
-
-See [scenarios/post_action_namespace.py](https://github.com/cloud-bulldozer/kraken/tree/master/scenarios/post_action_namespace.py) for an example
-
-```
--   namespace_scenarios:
-     - -    scenarios/regex_namespace.yaml
-       -    scenarios/post_action_namespace.py
-```
-
-
-1. Allow kraken to wait and check all killed objects in the namespaces become 'Running' again. Kraken keeps a list of the specific
-objects in namespaces that were killed to verify all that were affected recover properly.
-
-```
-wait_time: <seconds to wait for namespace to recover>
-```

docs/service_hijacking_scenarios.md

@@ -1,80 +0,0 @@
-### Service Hijacking Scenarios
-
-Service Hijacking Scenarios aim to simulate fake HTTP responses from a workload targeted by a 
-`Service` already deployed in the cluster. 
-This scenario is executed by deploying a custom-made web service and modifying the target `Service`
-selector to direct traffic to this web service for a specified duration.
-
-The web service's source code is available [here](https://github.com/krkn-chaos/krkn-service-hijacking). 
-It employs a time-based test plan from the scenario configuration file, which specifies the behavior of resources during the chaos scenario as follows:
-
-```yaml
-service_target_port: http-web-svc # The port of the service to be hijacked (can be named or numeric, based on the workload and service configuration).
-service_name: nginx-service # The name of the service that will be hijacked.
-service_namespace: default # The namespace where the target service is located.
-image: quay.io/krkn-chaos/krkn-service-hijacking:v0.1.3 # Image of the krkn web service to be deployed to receive traffic.
-chaos_duration: 30 # Total duration of the chaos scenario in seconds.
-plan:
-  - resource: "/list/index.php" # Specifies the resource or path to respond to in the scenario. For paths, both the path and query parameters are captured but ignored. For resources, only query parameters are captured.
-
-    steps:                      # A time-based plan consisting of steps can be defined for each resource.
-      GET:                      # One or more HTTP methods can be specified for each step. Note: Non-standard methods are supported for fully custom web services (e.g., using NONEXISTENT instead of POST).
-
-        - duration: 15          # Duration in seconds for this step before moving to the next one, if defined. Otherwise, this step will continue until the chaos scenario ends.
-
-          status: 500           # HTTP status code to be returned in this step.
-          mime_type: "application/json" # MIME type of the response for this step.
-          payload: |            # The response payload for this step.
-            {
-              "status":"internal server error"
-            }
-        - duration: 15
-          status: 201
-          mime_type: "application/json"
-          payload: |
-            {
-              "status":"resource created"
-            }
-      POST:
-        - duration: 15
-          status: 401
-          mime_type: "application/json"
-          payload: |
-            {
-               "status": "unauthorized"
-            }
-        - duration: 15
-          status: 404
-          mime_type: "text/plain"
-          payload: "not found"
-
-
-```
-The scenario will focus on the `service_name` within the `service_namespace`, 
-substituting the selector with a randomly generated one, which is added as a label in the mock service manifest.
-This allows multiple scenarios to be executed in the same namespace, each targeting different services without 
-causing conflicts.
-
-The newly deployed mock web service will expose a `service_target_port`, 
-which can be either a named or numeric port based on the service configuration. 
-This ensures that the Service correctly routes HTTP traffic to the mock web service during the chaos run.
-
-Each step will last for `duration` seconds from the deployment of the mock web service in the cluster. 
-For each HTTP resource, defined as a top-level YAML property of the plan 
-(it could be a specific resource, e.g., /list/index.php, or a path-based resource typical in MVC frameworks), 
-one or more HTTP request methods can be specified. Both standard and custom request methods are supported.
-
-During this time frame, the web service will respond with:
-
-- `status`: The [HTTP status code](https://datatracker.ietf.org/doc/html/rfc7231#section-6) (can be standard or custom).
-- `mime_type`: The [MIME type](https://developer.mozilla.org/en-US/docs/Web/HTTP/Basics_of_HTTP/MIME_types) (can be standard or custom).
-- `payload`: The response body to be returned to the client.
-
-At the end of the step `duration`, the web service will proceed to the next step (if available) until 
-the global `chaos_duration` concludes. At this point, the original service will be restored, 
-and the custom web service and its resources will be undeployed.
-
-__NOTE__: Some clients (e.g., cURL, jQuery) may optimize queries using lightweight methods (like HEAD or OPTIONS) 
-to probe API behavior. If these methods are not defined in the test plan, the web service may respond with 
-a `405` or `404` status code. If you encounter unexpected behavior, consider this use case.
-

docs/signal.md

@@ -1,71 +0,0 @@
-### Signaling to Kraken
-This functionality allows a user to be able to pause or stop the kraken run at any time no matter the number of iterations or daemon_mode set in the config.
-
-If publish_kraken_status is set to True in the config, kraken will start up a connection to a url at a certain port to decide if it should continue running.
-
-By default, it will get posted to http://0.0.0.0:8081/
-
-An example use case for this feature would be coordinating kraken runs based on the status of the service installation or load on the cluster.
-
-
-
-#### States
-There are 3 states in the kraken status:
-
-```PAUSE```: When the Kraken signal is 'PAUSE', this will pause the kraken test and wait for the wait_duration until the signal returns to RUN.
-
-```STOP```: When the Kraken signal is 'STOP', end the kraken run and print out report.
-
-```RUN```: When the Kraken signal is 'RUN', continue kraken run based on iterations.
-
-
-
-#### Configuration
-
-In the config you need to set these parameters to tell kraken which port to post the kraken run status to.
-As well if you want to publish and stop running based on the kraken status or not.
-The signal is set to `RUN` by default, meaning it will continue to run the scenarios. It can set to `PAUSE` for Kraken to act as listener and wait until set to `RUN` before injecting chaos.
-```
-    port: 8081
-    publish_kraken_status: True
-    signal_state: RUN
-```
-
-
-#### Setting Signal
-
-You can reset the kraken status during kraken execution with a `set_stop_signal.py` script with the following contents:
-
-```
-import http.client as cli
-
-conn = cli.HTTPConnection("0.0.0.0", "<port>")
-
-conn.request("POST", "/STOP", {})
-
-# conn.request('POST', '/PAUSE', {})
-
-# conn.request('POST', '/RUN', {})
-
-response = conn.getresponse()
-print(response.read().decode())
-```
-
-Make sure to set the correct port number in your set_stop_signal script.
-
-##### Url Examples
-To stop run:
-
-```
-curl -X POST http:/0.0.0.0:8081/STOP
-```
-
-To pause run:
-```
-curl -X POST http:/0.0.0.0:8081/PAUSE
-```
-
-To start running again:
-```
-curl -X POST http:/0.0.0.0:8081/RUN
-```

docs/syn_flood_scenarios.md

@@ -1,33 +0,0 @@
-### SYN Flood Scenarios
-
-This scenario generates a substantial amount of TCP traffic directed at one or more Kubernetes services within 
-the cluster to test the server's resiliency under extreme traffic conditions. 
-It can also target hosts outside the cluster by specifying a reachable IP address or hostname. 
-This scenario leverages the distributed nature of Kubernetes clusters to instantiate multiple instances 
-of the same pod against a single host, significantly increasing the effectiveness of the attack. 
-The configuration also allows for the specification of multiple node selectors, enabling Kubernetes to schedule 
-the attacker pods on a user-defined subset of nodes to make the test more realistic.
-
- ```yaml
-packet-size: 120 # hping3 packet size
-window-size: 64 # hping 3 TCP window size
-duration: 10 # chaos scenario duration
-namespace: default # namespace where the target service(s) are deployed
-target-service: target-svc # target service name (if set target-service-label must be empty)
-target-port: 80 # target service TCP port
-target-service-label : "" # target service label, can be used to target multiple target at the same time
-                          # if they have the same label set (if set target-service must be empty)
-number-of-pods: 2 # number of attacker pod instantiated per each target
-image: quay.io/krkn-chaos/krkn-syn-flood # syn flood attacker container image
-attacker-nodes: # this will set the node affinity to schedule the attacker node. Per each node label selector
-                # can be specified multiple values in this way the kube scheduler will schedule the attacker pods
-                # in the best way possible based on the provided labels. Multiple labels can be specified
-  kubernetes.io/hostname:
-    - host_1
-    - host_2
-  kubernetes.io/os:
-    - linux
-
- ```
-
-The attacker container source code is available [here](https://github.com/krkn-chaos/krkn-syn-flood).

docs/test_your_changes.md

@@ -1,44 +0,0 @@
-# How to Test Your Changes/Additions
-
-## Current list of Scenario Types
-
-Scenario Types:
-* pod-scenarios
-* node-scenarios
-* zone-outages
-* time-scenarios
-* cluster-shutdown
-* container-scenarios
-* node-cpu-hog
-* node-io-hog
-* node-memory-hog
-* application-outages
-
-## Adding a New Scenario
-1. Create folder under [kraken/kraken](../kraken) with name pertinent to your scenario name.
-
-2. Create a python file that will have a generic run function to be the base of your scenario.
-
-    a. See [shut_down.py](../kraken/shut_down/common_shut_down_func.py) for example.
-
-3. Add in a scenario yaml file to run your specific scenario under [scenarios](../scenarios).
-
-    a. Try to add as many parameters as possible and be sure to give them default values in your run function.
-
-4. Add all functionality and helper functions in file you made above (Step 2).
-
-5. Add in caller to new scenario type in [run_kraken.py](../run_kraken.py) (around line 154).
-
-    a. This will also require you to add the new scenario python script to your imports.
-
-6. Add scenario type and scenario yaml to the scenario list in [config](../config/config.yaml) and [config_performance](../config/config_performance.yaml).
-
-7. Update this doc and main README with new scenario type.
-
-8. Add CI test for new scenario.
-
-    a. Refer to test [Readme](../CI/README.md#adding-a-test-case) for more details.
-
-## Follow Contribute guide
-
-Once all you are happy with your changes, follow the [contribution](#docs/contribute.md) guide on how to create your own branch and squash your commits.

docs/time_scenarios.md

@@ -1,33 +0,0 @@
-###  Time/Date Skew Scenarios
-
-Using this type of scenario configuration, one is able to change the time and/or date of the system for pods or nodes.
-
-Configuration Options:
-
-**action:** skew_time or skew_date.
-
-**object_type:** pod or node.
-
-**namespace:** namespace of the pods you want to skew. Needs to be set if setting a specific pod name.
-
-**label_selector:** Label on the nodes or pods you want to skew.
-
-**container_name:** Container name in pod you want to reset time on. If left blank it will randomly select one.
-
-**object_name:** List of the names of pods or nodes you want to skew.
-
-Refer to [time_scenarios_example](https://github.com/krkn-chaos/krkn/blob/main/scenarios/time_scenarios_example.yml) config file.
-
-```
-time_scenarios:
-  - action: skew_time
-    object_type: pod
-    object_name:
-      - apiserver-868595fcbb-6qnsc
-      - apiserver-868595fcbb-mb9j5
-    namespace: openshift-apiserver
-    container_name: openshift-apiserver
-  - action: skew_date
-    object_type: node
-    label_selector: node-role.kubernetes.io/worker
-```

docs/zone_outage.md

@@ -1,28 +0,0 @@
-### Zone outage scenario
-Scenario to create outage in a targeted zone in the public cloud to understand the impact on both Kubernetes/OpenShift control plane as well as applications running on the worker nodes in that zone. It tweaks the network acl of the zone to simulate the failure and that in turn will stop both ingress and egress traffic from all the nodes in a particular zone for the specified duration and reverts it back to the previous state. Zone outage can be injected by placing the zone_outage config file under zone_outages option in the [kraken config](https://github.com/redhat-chaos/krkn/blob/main/config/config.yaml). Refer to [zone_outage_scenario](https://github.com/redhat-chaos/krkn/blob/main/scenarios/zone_outage.yaml) config file for the parameters that need to be defined.
-
-Refer to [cloud setup](cloud_setup.md) to configure your cli properly for the cloud provider of the cluster you want to shut down.
-
-##### Current accepted cloud types:
-* [AWS](cloud_setup.md#aws)
-
-##### Sample scenario config
-```
-zone_outage:                                         # Scenario to create an outage of a zone by tweaking network ACL.
-  cloud_type: aws                                    # Cloud type on which Kubernetes/OpenShift runs. aws is the only platform supported currently for this scenario.
-  duration: 600                                      # Duration in seconds after which the zone will be back online.
-  vpc_id:                                            # Cluster virtual private network to target.
-  subnet_id: [subnet1, subnet2]                      # List of subnet-id's to deny both ingress and egress traffic.
-  default_acl_id: acl-xxxxxxxx                       # (Optional) ID of an existing network ACL to use instead of creating a new one. If provided, this ACL will not be deleted after the scenario.
-```
-
-**NOTE**: vpc_id and subnet_id can be obtained from the cloud web console by selecting one of the instances in the targeted zone ( us-west-2a for example ).
-**NOTE**: Multiple zones will experience downtime in case of targeting multiple subnets which might have an impact on the cluster health especially if the zones have control plane components deployed.
-**NOTE**: default_acl_id can be obtained from the AWS VPC Console by selecting "Network ACLs" from the left sidebar ( the ID will be in the format 'acl-xxxxxxxx' ). Make sure the selected ACL has the desired ingress/egress rules for your outage scenario ( i.e., deny all ).
-
-##### Debugging steps in case of failures
-In case of failures during the steps which revert back the network acl to allow traffic and bring back the cluster nodes in the zone, the nodes in the particular zone will be in `NotReady` condition. Here is how to fix it:
-- OpenShift by default deploys the nodes in different zones for fault tolerance, for example us-west-2a, us-west-2b, us-west-2c. The cluster is associated with a virtual private network and each zone has its own subnet with a network acl which defines the ingress and egress traffic rules at the zone level unlike security groups which are at an instance level.
-- From the cloud web console, select one of the instances in the zone which is down and go to the subnet_id specified in the config.
-- Look at the network acl associated with the subnet and you will see both ingress and egress traffic being denied which is expected as Kraken deliberately injects it.
-- Kraken just switches the network acl while still keeping the original or default network acl around, switching to the default network acl from the drop-down menu will get back the nodes in the targeted zone into Ready state.

kind-config.yml

@@ -5,6 +5,8 @@ nodes:
     extraPortMappings:
       - containerPort: 30036
         hostPort: 8888
+      - containerPort: 30037
+        hostPort: 8889
   - role: control-plane
   - role: control-plane
   - role: worker

krkn/cerberus/setup.py

@@ -14,7 +14,7 @@ def get_status(config, start_time, end_time):
     if config["cerberus"]["cerberus_enabled"]:
         cerberus_url = config["cerberus"]["cerberus_url"]
         check_application_routes = \
-            config["cerberus"]["check_applicaton_routes"]
+            config["cerberus"]["check_application_routes"]
         if not cerberus_url:
             logging.error(
                 "url where Cerberus publishes True/False signal "

krkn/chaos_recommender/analysis.py

@@ -29,9 +29,9 @@ def calculate_zscores(data):
 
 
 def identify_outliers(data, threshold):
-    outliers_cpu = data[data["CPU"] > threshold]["Service"].tolist()
-    outliers_memory = data[data["Memory"] > threshold]["Service"].tolist()
-    outliers_network = data[data["Network"] > threshold]["Service"].tolist()
+    outliers_cpu = data[data["CPU"] > float(threshold)]["Service"].tolist()
+    outliers_memory = data[data["Memory"] > float(threshold)]["Service"].tolist()
+    outliers_network = data[data["Network"] > float(threshold)]["Service"].tolist()
 
     return outliers_cpu, outliers_memory, outliers_network
 
@@ -39,13 +39,13 @@ def identify_outliers(data, threshold):
 def get_services_above_heatmap_threshold(dataframe, cpu_threshold, mem_threshold):
     # Filter the DataFrame based on CPU_HEATMAP and MEM_HEATMAP thresholds
     filtered_df = dataframe[
-        ((dataframe["CPU"] / dataframe["CPU_LIMITS"]) > cpu_threshold)
+        ((dataframe["CPU"] / dataframe["CPU_LIMITS"]) > float(cpu_threshold))
     ]
     # Get the lists of services
     cpu_services = filtered_df["service"].tolist()
 
     filtered_df = dataframe[
-        ((dataframe["MEM"] / dataframe["MEM_LIMITS"]) > mem_threshold)
+        ((dataframe["MEM"] / dataframe["MEM_LIMITS"]) > float(mem_threshold))
     ]
     mem_services = filtered_df["service"].tolist()
 

krkn/invoke/command.py

@@ -15,13 +15,11 @@ def invoke(command, timeout=None):
 
 
 # Invokes a given command and returns the stdout
-def invoke_no_exit(command, timeout=None):
+def invoke_no_exit(command, timeout=15):
     output = ""
     try:
-        output = subprocess.check_output(command, shell=True, universal_newlines=True, timeout=timeout)
-        logging.info("output " + str(output))
+        output = subprocess.check_output(command, shell=True, universal_newlines=True, timeout=timeout, stderr=subprocess.DEVNULL)
     except Exception as e:
-        logging.error("Failed to run %s, error: %s" % (command, e))
         return str(e)
     return output
 

krkn/performance_dashboards/setup.py

@@ -1,28 +0,0 @@
-import subprocess
-import logging
-import git
-import sys
-
-
-# Installs a mutable grafana on the Kubernetes/OpenShift cluster and loads the performance dashboards
-def setup(repo, distribution):
-    if distribution == "kubernetes":
-        command = "cd performance-dashboards/dittybopper && ./k8s-deploy.sh"
-    elif distribution == "openshift":
-        command = "cd performance-dashboards/dittybopper && ./deploy.sh"
-    else:
-        logging.error("Provided distribution: %s is not supported" % (distribution))
-        sys.exit(1)
-    delete_repo = "rm -rf performance-dashboards || exit 0"
-    logging.info(
-        "Cloning, installing mutable grafana on the cluster and loading the dashboards"
-    )
-    try:
-        # delete repo to clone the latest copy if exists
-        subprocess.run(delete_repo, shell=True, universal_newlines=True, timeout=45)
-        # clone the repo
-        git.Repo.clone_from(repo, "performance-dashboards")
-        # deploy performance dashboards
-        subprocess.run(command, shell=True, universal_newlines=True)
-    except Exception as e:
-        logging.error("Failed to install performance-dashboards, error: %s" % (e))

krkn/prometheus/client.py

@@ -2,11 +2,14 @@ from __future__ import annotations
 
 import datetime
 import os.path
+import math
 from typing import Optional, List, Dict, Any
 
-import urllib3
 import logging
+import urllib3
 import sys
+import json
+import tempfile
 
 import yaml
 from krkn_lib.elastic.krkn_elastic import KrknElastic
@@ -25,8 +28,7 @@ def alerts(
     start_time,
     end_time,
     alert_profile,
-    elastic_collect_alerts,
-    elastic_alerts_index,
+    elastic_alerts_index
 ):
 
     if alert_profile is None or os.path.exists(alert_profile) is False:
@@ -46,6 +48,7 @@ def alerts(
         for alert in profile_yaml:
             if list(alert.keys()).sort() != ["expr", "description", "severity"].sort():
                 logging.error(f"wrong alert {alert}, skipping")
+                continue
 
             processed_alert = prom_cli.process_alert(
                 alert,
@@ -56,7 +59,6 @@ def alerts(
                 processed_alert[0]
                 and processed_alert[1]
                 and elastic
-                and elastic_collect_alerts
             ):
                 elastic_alert = ElasticAlert(
                     run_uuid=run_uuid,
@@ -73,10 +75,12 @@ def alerts(
 def critical_alerts(
     prom_cli: KrknPrometheus,
     summary: ChaosRunAlertSummary,
+    elastic: KrknElastic,
     run_id,
     scenario,
     start_time,
     end_time,
+    elastic_alerts_index
 ):
     summary.scenario = scenario
     summary.run_id = run_id
@@ -111,7 +115,6 @@ def critical_alerts(
             summary.chaos_alerts.append(alert)
 
     post_critical_alerts = prom_cli.process_query(query)
-
     for alert in post_critical_alerts:
         if "metric" in alert:
             alertname = (
@@ -134,6 +137,21 @@ def critical_alerts(
             )
             alert = ChaosRunAlert(alertname, alertstate, namespace, severity)
             summary.post_chaos_alerts.append(alert)
+            if elastic:
+                elastic_alert = ElasticAlert(
+                    run_uuid=run_id,
+                    severity=severity,
+                    alert=alertname,
+                    created_at=end_time,
+                    namespace=namespace,
+                    alertstate=alertstate,
+                    phase="post_chaos"
+                )
+                result = elastic.push_alert(elastic_alert, elastic_alerts_index)
+                if result == -1:
+                    logging.error("failed to save alert on ElasticSearch")
+                pass
+
 
     during_critical_alerts_count = len(during_critical_alerts)
     post_critical_alerts_count = len(post_critical_alerts)
@@ -147,8 +165,8 @@ def critical_alerts(
 
     if not firing_alerts:
         logging.info("No critical alerts are firing!!")
-
-
+    
+   
 def metrics(
     prom_cli: KrknPrometheus,
     elastic: KrknElastic,
@@ -156,15 +174,16 @@ def metrics(
     start_time,
     end_time,
     metrics_profile,
-    elastic_collect_metrics,
     elastic_metrics_index,
+    telemetry_json
 ) -> list[dict[str, list[(int, float)] | str]]:
-    metrics_list: list[dict[str, list[(int, float)] | str]] = []
+   
     if metrics_profile is None or os.path.exists(metrics_profile) is False:
         logging.error(f"{metrics_profile} alert profile does not exist")
         sys.exit(1)
     with open(metrics_profile) as profile:
         profile_yaml = yaml.safe_load(profile)
+
         if not profile_yaml["metrics"] or not isinstance(profile_yaml["metrics"], list):
             logging.error(
                 f"{metrics_profile} wrong file format, alert profile must be "
@@ -172,34 +191,114 @@ def metrics(
                 f"expr, description, severity"
             )
             sys.exit(1)
-
+        elapsed_ceil = math.ceil((end_time - start_time)/ 60 )
+        elapsed_time = str(elapsed_ceil) + "m"
+        metrics_list: list[dict[str, int | float | str]] = []
         for metric_query in profile_yaml["metrics"]:
-            if (
+            query = metric_query['query']
+            
+            # calculate elapsed time
+            if ".elapsed" in metric_query["query"]:
+                query = metric_query['query'].replace(".elapsed", elapsed_time)
+            if "instant" in list(metric_query.keys()) and metric_query['instant']:
+                metrics_result = prom_cli.process_query(
+                   query
+                )
+            elif (
                 list(metric_query.keys()).sort()
-                != ["query", "metricName", "instant"].sort()
+                == ["query", "metricName"].sort()
             ):
-                logging.error(f"wrong alert {metric_query}, skipping")
-            metrics_result = prom_cli.process_prom_query_in_range(
-                metric_query["query"],
-                start_time=datetime.datetime.fromtimestamp(start_time),
-                end_time=datetime.datetime.fromtimestamp(end_time),
-            )
-
-            metric = {"name": metric_query["metricName"], "values": []}
+                metrics_result = prom_cli.process_prom_query_in_range(
+                    query,
+                    start_time=datetime.datetime.fromtimestamp(start_time),
+                    end_time=datetime.datetime.fromtimestamp(end_time), granularity=30
+                )
+            else: 
+                logging.info("didn't match keys")
+                continue
+            
             for returned_metric in metrics_result:
-                if "values" in returned_metric:
+                metric = {"query": query, "metricName": metric_query['metricName']}
+                for k,v in returned_metric['metric'].items():
+                    metric[k] = v
+                
+                if "values" in returned_metric: 
                     for value in returned_metric["values"]:
                         try:
-                            metric["values"].append((value[0], float(value[1])))
+                            metric['timestamp'] = str(datetime.datetime.fromtimestamp(value[0]))
+                            metric["value"] = float(value[1])
+                            # want double array of the known details and the metrics specific to each call                    
+                            metrics_list.append(metric.copy())
                         except ValueError:
                             pass
-            metrics_list.append(metric)
+                elif "value" in returned_metric:
+                    try:
+                        value = returned_metric["value"]
+                        metric['timestamp'] = str(datetime.datetime.fromtimestamp(value[0]))
+                        metric["value"] = float(value[1])
 
-        if elastic_collect_metrics and elastic:
+                        # want double array of the known details and the metrics specific to each call
+                        metrics_list.append(metric.copy())
+                    except ValueError:
+                        pass
+        telemetry_json = json.loads(telemetry_json)
+        for scenario in telemetry_json['scenarios']:
+            for k,v in scenario["affected_pods"].items():
+                metric_name = "affected_pods_recovery"
+                metric = {"metricName": metric_name, "type": k}
+                if type(v) is list:
+                    for pod in v:
+                        for k,v in pod.items():
+                            metric[k] = v
+                            metric['timestamp'] = str(datetime.datetime.now())
+                        print('adding pod' + str(metric))
+                        metrics_list.append(metric.copy())
+            for affected_node in scenario["affected_nodes"]:
+                metric_name = "affected_nodes_recovery"
+                metric = {"metricName": metric_name}
+                for k,v in affected_node.items():
+                    metric[k] = v
+                    metric['timestamp'] = str(datetime.datetime.now())
+                metrics_list.append(metric.copy())
+        if telemetry_json['health_checks']:
+            for health_check in telemetry_json["health_checks"]:
+                    metric_name = "health_check_recovery"
+                    metric = {"metricName": metric_name}
+                    for k,v in health_check.items():
+                        metric[k] = v
+                        metric['timestamp'] = str(datetime.datetime.now())
+                    metrics_list.append(metric.copy())
+        if telemetry_json['virt_checks']:
+            for virt_check in telemetry_json["virt_checks"]:
+                    metric_name = "virt_check_recovery"
+                    metric = {"metricName": metric_name}
+                    for k,v in virt_check.items():
+                        metric[k] = v
+                        metric['timestamp'] = str(datetime.datetime.now())
+                    metrics_list.append(metric.copy())
+
+        save_metrics = False
+        if elastic is not None and elastic_metrics_index is not None:
             result = elastic.upload_metrics_to_elasticsearch(
                 run_uuid=run_uuid, index=elastic_metrics_index, raw_data=metrics_list
             )
             if result == -1:
                 logging.error("failed to save metrics on ElasticSearch")
+                save_metrics = True
+        else:
+            save_metrics = True
+        if save_metrics:
+            local_dir = os.path.join(tempfile.gettempdir(), "krkn_metrics")
+            os.makedirs(local_dir, exist_ok=True)
+            local_file = os.path.join(local_dir, f"{elastic_metrics_index}_{run_uuid}.json")
 
+            try:
+                with open(local_file, "w") as f:
+                    json.dump({
+                        "run_uuid": run_uuid,
+                        "metrics": metrics_list
+                }, f, indent=2)
+                logging.info(f"Metrics saved to {local_file}")
+            except Exception as e:
+                logging.error(f"Failed to save metrics to {local_file}: {e}")
     return metrics_list

krkn/rollback/command.py

@@ -0,0 +1,113 @@
+import os
+import logging
+from typing import Optional, TYPE_CHECKING
+
+from krkn.rollback.config import RollbackConfig
+from krkn.rollback.handler import execute_rollback_version_files
+
+
+
+if TYPE_CHECKING:
+    from krkn_lib.telemetry.ocp import KrknTelemetryOpenshift
+    
+
+def list_rollback(run_uuid: Optional[str]=None, scenario_type: Optional[str]=None):
+    """
+    List rollback version files in a tree-like format.
+    
+    :param cfg: Configuration file path
+    :param run_uuid: Optional run UUID to filter by
+    :param scenario_type: Optional scenario type to filter by
+    :return: Exit code (0 for success, 1 for error)
+    """
+    logging.info("Listing rollback version files")
+
+    versions_directory = RollbackConfig().versions_directory
+    
+    logging.info(f"Rollback versions directory: {versions_directory}")
+    
+    # Check if the directory exists first
+    if not os.path.exists(versions_directory):
+        logging.info(f"Rollback versions directory does not exist: {versions_directory}")
+        return 0
+    
+    # List all directories and files
+    try:
+        # Get all run directories
+        run_dirs = []
+        for item in os.listdir(versions_directory):
+            item_path = os.path.join(versions_directory, item)
+            if os.path.isdir(item_path):
+                # Apply run_uuid filter if specified
+                if run_uuid is None or run_uuid in item:
+                    run_dirs.append(item)
+        
+        if not run_dirs:
+            if run_uuid:
+                logging.info(f"No rollback directories found for run_uuid: {run_uuid}")
+            else:
+                logging.info("No rollback directories found")
+            return 0
+        
+        # Sort directories for consistent output
+        run_dirs.sort()
+        
+        print(f"\n{versions_directory}/")
+        for i, run_dir in enumerate(run_dirs):
+            is_last_dir = (i == len(run_dirs) - 1)
+            dir_prefix = "└── " if is_last_dir else "├── "
+            print(f"{dir_prefix}{run_dir}/")
+            
+            # List files in this directory
+            run_dir_path = os.path.join(versions_directory, run_dir)
+            try:
+                files = []
+                for file in os.listdir(run_dir_path):
+                    file_path = os.path.join(run_dir_path, file)
+                    if os.path.isfile(file_path):
+                        # Apply scenario_type filter if specified
+                        if scenario_type is None or file.startswith(scenario_type):
+                            files.append(file)
+                
+                files.sort()
+                for j, file in enumerate(files):
+                    is_last_file = (j == len(files) - 1)
+                    file_prefix = "    └── " if is_last_dir else "│   └── " if is_last_file else ("│   ├── " if not is_last_dir else "    ├── ")
+                    print(f"{file_prefix}{file}")
+                    
+            except PermissionError:
+                file_prefix = "    └── " if is_last_dir else "│   └── "
+                print(f"{file_prefix}[Permission Denied]")
+                
+    except Exception as e:
+        logging.error(f"Error listing rollback directory: {e}")
+        return 1
+    
+    return 0
+
+
+def execute_rollback(telemetry_ocp: "KrknTelemetryOpenshift", run_uuid: Optional[str]=None, scenario_type: Optional[str]=None):
+    """
+    Execute rollback version files and cleanup if successful.
+    
+    :param telemetry_ocp: Instance of KrknTelemetryOpenshift
+    :param run_uuid: Optional run UUID to filter by
+    :param scenario_type: Optional scenario type to filter by
+    :return: Exit code (0 for success, 1 for error)
+    """
+    logging.info("Executing rollback version files")
+    logging.info(f"Executing rollback for run_uuid={run_uuid  or '*'}, scenario_type={scenario_type or '*'}")
+
+    try:
+        # Execute rollback version files
+        execute_rollback_version_files(
+            telemetry_ocp,
+            run_uuid,
+            scenario_type,
+            ignore_auto_rollback_config=True
+        )
+        return 0
+        
+    except Exception as e:
+        logging.error(f"Error during rollback execution: {e}")
+        return 1

krkn/rollback/config.py

@@ -0,0 +1,259 @@
+from __future__ import annotations
+
+from dataclasses import dataclass
+from typing import Callable, TYPE_CHECKING, Optional
+from typing_extensions import TypeAlias
+import time
+import os
+import logging
+
+from krkn_lib.utils import get_random_string
+
+logger = logging.getLogger(__name__)
+
+if TYPE_CHECKING:
+    from krkn_lib.telemetry.ocp import KrknTelemetryOpenshift
+
+RollbackCallable: TypeAlias = Callable[
+    ["RollbackContent", "KrknTelemetryOpenshift"], None
+]
+
+
+if TYPE_CHECKING:
+    from krkn_lib.telemetry.ocp import KrknTelemetryOpenshift
+
+RollbackCallable: TypeAlias = Callable[
+    ["RollbackContent", "KrknTelemetryOpenshift"], None
+]
+
+
+class SingletonMeta(type):
+    _instances = {}
+
+    def __call__(cls, *args, **kwargs):
+        if cls not in cls._instances:
+            cls._instances[cls] = super().__call__(*args, **kwargs)
+        return cls._instances[cls]
+
+
+@dataclass(frozen=True)
+class RollbackContent:
+    """
+    RollbackContent is a dataclass that defines the necessary fields for rollback operations.
+    """
+
+    resource_identifier: str
+    namespace: Optional[str] = None
+
+    def __str__(self):
+        namespace = f'"{self.namespace}"' if self.namespace else "None"
+        resource_identifier = f'"{self.resource_identifier}"'
+        return f"RollbackContent(namespace={namespace}, resource_identifier={resource_identifier})"
+
+
+class RollbackContext(str):
+    """
+    RollbackContext is a string formatted as '<timestamp (s) >-<run_uuid>'.
+    It represents the context for rollback operations, uniquely identifying a run.
+    """
+
+    def __new__(cls, run_uuid: str):
+        return super().__new__(cls, f"{time.time_ns()}-{run_uuid}")
+
+
+class RollbackConfig(metaclass=SingletonMeta):
+    """Configuration for the rollback scenarios."""
+
+    def __init__(self):
+        self._auto = False
+        self._versions_directory = ""
+        self._registered = False
+
+    @property
+    def auto(self):
+        return self._auto
+
+    @auto.setter
+    def auto(self, value):
+        if self._registered:
+            raise AttributeError("Can't modify 'auto' after registration")
+        self._auto = value
+
+    @property
+    def versions_directory(self):
+        return self._versions_directory
+
+    @versions_directory.setter
+    def versions_directory(self, value):
+        if self._registered:
+            raise AttributeError("Can't modify 'versions_directory' after registration")
+        self._versions_directory = value
+    @classmethod
+    def register(cls, auto=False, versions_directory=""):
+        """Initialize and return the singleton instance with given configuration."""
+        instance = cls()
+        instance.auto = auto
+        instance.versions_directory = versions_directory
+        instance._registered = True
+        return instance
+
+    @classmethod
+    def get_rollback_versions_directory(cls, rollback_context: RollbackContext) -> str:
+        """
+        Get the rollback context directory for a given rollback context.
+
+        :param rollback_context: The rollback context string.
+        :return: The path to the rollback context directory.
+        """
+        return f"{cls().versions_directory}/{rollback_context}"
+    
+    @classmethod
+    def is_rollback_version_file_format(cls, file_name: str, expected_scenario_type: str | None = None) -> bool:
+        """
+        Validate the format of a rollback version file name.
+
+        Expected format: <scenario_type>_<timestamp>_<hash_suffix>.py
+        where:
+            - scenario_type: string (can include underscores)
+            - timestamp: integer (nanoseconds since epoch)
+            - hash_suffix: alphanumeric string (length 8)
+            - .py: file extension
+
+        :param file_name: The name of the file to validate.
+        :param expected_scenario_type: The expected scenario type (if any) to validate against.
+        :return: True if the file name matches the expected format, False otherwise.
+        """
+        if not file_name.endswith(".py"):
+            return False
+
+        parts = file_name.split("_")
+        if len(parts) < 3:
+            return False
+
+        scenario_type = "_".join(parts[:-2])
+        timestamp_str = parts[-2]
+        hash_suffix_with_ext = parts[-1]
+        hash_suffix = hash_suffix_with_ext[:-3]
+
+        if expected_scenario_type and scenario_type != expected_scenario_type:
+            return False
+
+        if not timestamp_str.isdigit():
+            return False
+
+        if len(hash_suffix) != 8 or not hash_suffix.isalnum():
+            return False
+
+        return True
+    
+    @classmethod
+    def is_rollback_context_directory_format(cls, directory_name: str, expected_run_uuid: str | None = None) -> bool:
+        """
+        Validate the format of a rollback context directory name.
+
+        Expected format: <timestamp>-<run_uuid>
+        where:
+            - timestamp: integer (nanoseconds since epoch)
+            - run_uuid: alphanumeric string
+
+        :param directory_name: The name of the directory to validate.
+        :param expected_run_uuid: The expected run UUID (if any) to validate against.
+        :return: True if the directory name matches the expected format, False otherwise.
+        """
+        parts = directory_name.split("-", 1)
+        if len(parts) != 2:
+            return False
+
+        timestamp_str, run_uuid = parts
+
+        # Validate timestamp is numeric
+        if not timestamp_str.isdigit():
+            return False
+
+        # Validate run_uuid
+        if expected_run_uuid and expected_run_uuid != run_uuid:
+            return False
+
+        return True
+
+    @classmethod
+    def search_rollback_version_files(cls, run_uuid: str | None = None, scenario_type: str | None = None) -> list[str]:
+        """
+        Search for rollback version files based on run_uuid and scenario_type.
+
+        1. Search directories with "run_uuid" in name under "cls.versions_directory".
+        2. Search files in those directories that start with "scenario_type" in matched directories in step 1.
+
+        :param run_uuid: Unique identifier for the run.
+        :param scenario_type: Type of the scenario.
+        :return: List of version file paths.
+        """
+
+        if not os.path.exists(cls().versions_directory):
+            return []
+
+        rollback_context_directories = []
+        for dir in os.listdir(cls().versions_directory):
+            if cls.is_rollback_context_directory_format(dir, run_uuid):
+                rollback_context_directories.append(dir)
+            else:
+                logger.warning(f"Directory {dir} does not match expected pattern of <timestamp>-<run_uuid>")
+
+        if not rollback_context_directories:
+            logger.warning(f"No rollback context directories found for run UUID {run_uuid}")
+            return []
+
+
+        version_files = []
+        for rollback_context_dir in rollback_context_directories:
+            rollback_context_dir = os.path.join(cls().versions_directory, rollback_context_dir)
+
+            for file in os.listdir(rollback_context_dir):
+                # Skip known non-rollback files/directories
+                if file == "__pycache__" or file.endswith(".executed"):
+                    continue
+
+                if cls.is_rollback_version_file_format(file, scenario_type):
+                    version_files.append(
+                        os.path.join(rollback_context_dir, file)
+                    )
+                else:
+                    logger.warning(
+                        f"File {file} does not match expected pattern of <{scenario_type or '*'}>_<timestamp>_<hash_suffix>.py"
+                    )
+        return version_files
+
+@dataclass(frozen=True)
+class Version:
+    scenario_type: str
+    rollback_context: RollbackContext
+    timestamp: int = time.time_ns()  # Get current timestamp in nanoseconds
+    hash_suffix: str = get_random_string(8)  # Generate a random string of 8 characters
+
+    @property
+    def version_file_name(self) -> str:
+        """
+        Generate a version file name based on the timestamp and hash suffix.
+        :return: The generated version file name.
+        """
+        return f"{self.scenario_type}_{self.timestamp}_{self.hash_suffix}.py"
+
+    @property
+    def version_file_full_path(self) -> str:
+        """
+        Get the full path for the version file based on the version object and current context.
+
+        :return: The generated version file full path.
+        """
+        return f"{RollbackConfig.get_rollback_versions_directory(self.rollback_context)}/{self.version_file_name}"
+
+    @staticmethod
+    def new_version(scenario_type: str, rollback_context: RollbackContext) -> "Version":
+        """
+        Get the current version of the rollback configuration.
+        :return: An instance of Version with the current timestamp and hash suffix.
+        """
+        return Version(
+            scenario_type=scenario_type,
+            rollback_context=rollback_context,
+        )

krkn/rollback/handler.py

@@ -0,0 +1,255 @@
+from __future__ import annotations
+
+import logging
+from typing import cast, TYPE_CHECKING
+import os
+import importlib.util
+import inspect
+
+from krkn.rollback.config import RollbackConfig, RollbackContext, Version
+
+
+logger = logging.getLogger(__name__)
+
+
+if TYPE_CHECKING:
+    from krkn_lib.telemetry.ocp import KrknTelemetryOpenshift
+
+    from krkn.scenario_plugins.abstract_scenario_plugin import AbstractScenarioPlugin
+    from krkn.rollback.config import RollbackContent, RollbackCallable
+    from krkn.rollback.serialization import Serializer
+
+
+def set_rollback_context_decorator(func):
+    """
+    Decorator to automatically set and clear rollback context.
+    It extracts run_uuid from the function arguments and sets the context in rollback_handler
+    before executing the function, and clears it after execution.
+
+    Usage:
+
+    .. code-block:: python
+        from krkn.rollback.handler import set_rollback_context_decorator
+        # for any scenario plugin that inherits from AbstractScenarioPlugin
+        @set_rollback_context_decorator
+        def run(
+            self,
+            run_uuid: str,
+            scenario: str,
+            krkn_config: dict[str, any],
+            lib_telemetry: KrknTelemetryOpenshift,
+            scenario_telemetry: ScenarioTelemetry,
+        ):
+            # Your scenario logic here
+            pass
+    """
+
+    def wrapper(self, *args, **kwargs):
+        self = cast("AbstractScenarioPlugin", self)
+        # Since `AbstractScenarioPlugin.run_scenarios` will call `self.run` and pass all parameters as `kwargs`
+        logger.debug(f"kwargs of ScenarioPlugin.run: {kwargs}")
+        run_uuid = kwargs.get("run_uuid", None)
+        # so we can safely assume that `run_uuid` will be present in `kwargs`
+        assert run_uuid is not None, "run_uuid must be provided in kwargs"
+
+        # Set context if run_uuid is available and rollback_handler exists
+        if run_uuid and hasattr(self, "rollback_handler"):
+            self.rollback_handler = cast("RollbackHandler", self.rollback_handler)
+            self.rollback_handler.set_context(run_uuid)
+
+        try:
+            # Execute the `run` method with the original arguments
+            result = func(self, *args, **kwargs)
+            return result
+        finally:
+            # Clear context after function execution, regardless of success or failure
+            if hasattr(self, "rollback_handler"):
+                self.rollback_handler = cast("RollbackHandler", self.rollback_handler)
+                self.rollback_handler.clear_context()
+
+    return wrapper
+
+def _parse_rollback_module(version_file_path: str) -> tuple[RollbackCallable, RollbackContent]:
+    """
+    Parse a rollback module to extract the rollback function and RollbackContent.
+    
+    :param version_file_path: Path to the rollback version file
+    :return: Tuple of (rollback_callable, rollback_content)
+    """
+    
+    # Create a unique module name based on the file path
+    module_name = f"rollback_module_{os.path.basename(version_file_path).replace('.py', '').replace('-', '_')}"
+    
+    # Load the module using importlib
+    spec = importlib.util.spec_from_file_location(module_name, version_file_path)
+    if spec is None or spec.loader is None:
+        raise ImportError(f"Could not load module from {version_file_path}")
+    
+    module = importlib.util.module_from_spec(spec)
+    spec.loader.exec_module(module)
+    
+    # Find the rollback function
+    rollback_callable = None
+    for name, obj in inspect.getmembers(module):
+        if inspect.isfunction(obj) and name.startswith('rollback_'):
+            # Check function signature
+            sig = inspect.signature(obj)
+            params = list(sig.parameters.values())
+            if (len(params) == 2 and 
+                'RollbackContent' in str(params[0].annotation) and 
+                'KrknTelemetryOpenshift' in str(params[1].annotation)):
+                rollback_callable = obj
+                logger.debug(f"Found rollback function: {name}")
+                break
+    
+    if rollback_callable is None:
+        raise ValueError(f"No valid rollback function found in {version_file_path}")
+    
+    # Find the rollback_content variable
+    if not hasattr(module, 'rollback_content'):
+        raise ValueError("Could not find variable named 'rollback_content' in the module")
+    
+    rollback_content = getattr(module, 'rollback_content', None)
+    if rollback_content is None:
+        raise ValueError("Variable 'rollback_content' is None")
+    
+    logger.debug(f"Found rollback_content variable in module: {rollback_content}")
+    return rollback_callable, rollback_content
+
+
+def execute_rollback_version_files(
+    telemetry_ocp: "KrknTelemetryOpenshift",
+    run_uuid: str | None = None,
+    scenario_type: str | None = None,
+    ignore_auto_rollback_config: bool = False
+):
+    """
+    Execute rollback version files for the given run_uuid and scenario_type.
+    This function is called when a signal is received to perform rollback operations.
+    
+    :param run_uuid: Unique identifier for the run.
+    :param scenario_type: Type of the scenario being rolled back.
+    :param ignore_auto_rollback_config: Flag to ignore auto rollback configuration. Will be set to True for manual execute-rollback calls.
+    """
+    if not ignore_auto_rollback_config and RollbackConfig().auto is False:
+            logger.warning(f"Auto rollback is disabled, skipping execution for run_uuid={run_uuid or '*'}, scenario_type={scenario_type or '*'}")
+            return
+
+    # Get the rollback versions directory
+    version_files = RollbackConfig.search_rollback_version_files(run_uuid, scenario_type)
+    if not version_files:
+        logger.warning(f"Skip execution for run_uuid={run_uuid or '*'}, scenario_type={scenario_type or '*'}")
+        return
+
+    # Execute all version files in the directory
+    logger.info(f"Executing rollback version files for run_uuid={run_uuid or '*'}, scenario_type={scenario_type or '*'}")
+    for version_file in version_files:
+        try:
+            logger.info(f"Executing rollback version file: {version_file}")
+            
+            # Parse the rollback module to get function and content
+            rollback_callable, rollback_content = _parse_rollback_module(version_file)
+            # Execute the rollback function
+            logger.info('Executing rollback callable...')
+            rollback_callable(rollback_content, telemetry_ocp)
+            logger.info('Rollback completed.')
+            success = True
+        except Exception as e:
+            success = False
+            logger.error(f"Failed to execute rollback version file {version_file}: {e}")
+            raise
+
+        # Rename the version file with .executed suffix if successful
+        if success:
+            try:
+                executed_file = f"{version_file}.executed"
+                os.rename(version_file, executed_file)
+                logger.info(f"Renamed {version_file} to {executed_file} successfully.")
+            except Exception as e:
+                logger.error(f"Failed to rename rollback version file {version_file}: {e}")
+                raise
+
+def cleanup_rollback_version_files(run_uuid: str, scenario_type: str):
+    """
+    Cleanup rollback version files for the given run_uuid and scenario_type.
+    This function is called to remove the rollback version files after successful scenario execution in run_scenarios.
+    
+    :param run_uuid: Unique identifier for the run.
+    :param scenario_type: Type of the scenario being rolled back.
+    """
+
+    # Get the rollback versions directory
+    version_files = RollbackConfig.search_rollback_version_files(run_uuid, scenario_type)
+    if not version_files:
+        logger.warning(f"Skip cleanup for run_uuid={run_uuid}, scenario_type={scenario_type or '*'}")
+        return
+
+    # Remove all version files in the directory
+    logger.info(f"Cleaning up rollback version files for run_uuid={run_uuid}, scenario_type={scenario_type}")
+    for version_file in version_files:
+        try:
+            os.remove(version_file)
+            logger.info(f"Removed {version_file} successfully.")
+        except Exception as e:
+            logger.error(f"Failed to remove rollback version file {version_file}: {e}")
+            raise
+
+class RollbackHandler:
+    def __init__(
+        self,
+        scenario_type: str,
+        serializer: "Serializer",
+    ):
+        self.scenario_type = scenario_type
+        self.serializer = serializer
+        self.rollback_context: RollbackContext | None = (
+            None  # will be set when `set_context` is called
+        )
+
+    def set_context(self, run_uuid: str):
+        """
+        Set the context for the rollback handler.
+        :param run_uuid: Unique identifier for the run.
+        """
+        self.rollback_context = RollbackContext(run_uuid)
+        logger.info(
+            f"Set rollback_context: {self.rollback_context} for scenario_type: {self.scenario_type} RollbackHandler"
+        )
+
+    def clear_context(self):
+        """
+        Clear the run_uuid context for the rollback handler.
+        """
+        logger.debug(
+            f"Clear rollback_context {self.rollback_context} for scenario type {self.scenario_type} RollbackHandler"
+        )
+        self.rollback_context = None
+
+    def set_rollback_callable(
+        self,
+        callable: "RollbackCallable",
+        rollback_content: "RollbackContent",
+    ):
+        """
+        Set the rollback callable to be executed after the scenario is finished.
+
+        :param callable: The rollback callable to be set.
+        :param rollback_content: The rollback content for the callable.
+        """
+        logger.debug(
+            f"Rollback callable set to {callable.__name__} for version directory {RollbackConfig.get_rollback_versions_directory(self.rollback_context)}"
+        )
+
+        version: Version = Version.new_version(
+            scenario_type=self.scenario_type,
+            rollback_context=self.rollback_context,
+        )
+
+        # Serialize the callable to a file
+        try:
+            version_file = self.serializer.serialize_callable(
+                callable, rollback_content, version
+            )
+            logger.info(f"Rollback callable serialized to {version_file}")
+        except Exception as e:
+            logger.error(f"Failed to serialize rollback callable: {e}")

krkn/rollback/serialization.py

@@ -0,0 +1,123 @@
+import inspect
+import os
+import logging
+from typing import TYPE_CHECKING
+
+from jinja2 import Environment, FileSystemLoader
+
+if TYPE_CHECKING:
+    from krkn.rollback.config import RollbackCallable, RollbackContent, Version
+
+logger = logging.getLogger(__name__)
+
+
+class Serializer:
+    def __init__(self, scenario_type: str):
+        self.scenario_type = scenario_type
+        # Set up Jinja2 environment to load templates from the rollback directory
+        template_dir = os.path.join(os.path.dirname(__file__))
+        env = Environment(loader=FileSystemLoader(template_dir))
+        self.template = env.get_template("version_template.j2")
+
+    def _parse_rollback_callable_code(
+        self, rollback_callable: "RollbackCallable"
+    ) -> tuple[str, str]:
+        """
+        Parse the rollback callable code to extract its implementation.
+        :param rollback_callable: The callable function to parse (can be staticmethod or regular function).
+        :return: A tuple containing (function_name, function_code).
+        """
+        # Get the implementation code of the rollback_callable
+        rollback_callable_code = inspect.getsource(rollback_callable)
+
+        # Split into lines for processing
+        code_lines = rollback_callable_code.split("\n")
+        cleaned_lines = []
+        function_name = None
+
+        # Find the function definition line and extract function name
+        def_line_index = None
+        for i, line in enumerate(code_lines):
+            # Skip decorators (including @staticmethod)
+            if line.strip().startswith("@"):
+                continue
+
+            # Look for function definition
+            if line.strip().startswith("def "):
+                def_line_index = i
+                # Extract function name from the def line
+                def_line = line.strip()
+                if "(" in def_line:
+                    function_name = def_line.split("def ")[1].split("(")[0].strip()
+                break
+
+        if def_line_index is None or function_name is None:
+            raise ValueError(
+                "Could not find function definition in callable source code"
+            )
+
+        # Get the base indentation level from the def line
+        def_line = code_lines[def_line_index]
+        base_indent_level = len(def_line) - len(def_line.lstrip())
+
+        # Process all lines starting from the def line
+        for i in range(def_line_index, len(code_lines)):
+            line = code_lines[i]
+
+            # Handle empty lines
+            if not line.strip():
+                cleaned_lines.append("")
+                continue
+
+            # Calculate current line's indentation
+            current_indent = len(line) - len(line.lstrip())
+
+            # Remove the base indentation to normalize to function level
+            if current_indent >= base_indent_level:
+                # Remove base indentation
+                normalized_line = line[base_indent_level:]
+                cleaned_lines.append(normalized_line)
+            else:
+                # This shouldn't happen in well-formed code, but handle it gracefully
+                cleaned_lines.append(line.lstrip())
+
+        # Reconstruct the code and clean up trailing whitespace
+        function_code = "\n".join(cleaned_lines).rstrip()
+
+        return function_name, function_code
+
+    def serialize_callable(
+        self,
+        rollback_callable: "RollbackCallable",
+        rollback_content: "RollbackContent",
+        version: "Version",
+    ) -> str:
+        """
+        Serialize a callable function to a file with its arguments and keyword arguments.
+        :param rollback_callable: The callable to serialize.
+        :param rollback_content: The rollback content for the callable.
+        :param version: The version representing the rollback context and file path for the rollback.
+        :return: Path to the serialized callable file.
+        """
+
+        rollback_callable_name, rollback_callable_code = (
+            self._parse_rollback_callable_code(rollback_callable)
+        )
+
+        # Render the template with the required variables
+        file_content = self.template.render(
+            rollback_callable_name=rollback_callable_name,
+            rollback_callable_code=rollback_callable_code,
+            rollback_content=str(rollback_content),
+        )
+
+        # Write the file to the version directory
+        os.makedirs(os.path.dirname(version.version_file_full_path), exist_ok=True)
+
+        logger.debug("Creating version file at %s", version.version_file_full_path)
+        logger.debug("Version file content:\n%s", file_content)
+        with open(version.version_file_full_path, "w") as f:
+            f.write(file_content)
+        logger.info(f"Serialized callable written to {version.version_file_full_path}")
+
+        return version.version_file_full_path

krkn/rollback/signal.py

@@ -0,0 +1,106 @@
+from typing import Dict, Any, Optional
+import threading
+import signal
+import sys
+import logging
+from contextlib import contextmanager
+
+from krkn_lib.telemetry.ocp import KrknTelemetryOpenshift
+
+from krkn.rollback.handler import execute_rollback_version_files
+
+logger = logging.getLogger(__name__)
+
+class SignalHandler:
+    # Class-level variables for signal handling (shared across all instances)
+    _signal_handlers_installed = False  # No need for thread-safe variable due to _signal_lock
+    _original_handlers: Dict[int, Any] = {}
+    _signal_lock = threading.Lock()
+    
+    # Thread-local storage for context
+    _local = threading.local()
+
+    @classmethod
+    def _set_context(cls, run_uuid: str, scenario_type: str, telemetry_ocp: KrknTelemetryOpenshift):
+        """Set the current execution context for this thread."""
+        cls._local.run_uuid = run_uuid
+        cls._local.scenario_type = scenario_type
+        cls._local.telemetry_ocp = telemetry_ocp
+        logger.debug(f"Set signal context set for thread {threading.current_thread().name} - run_uuid={run_uuid}, scenario_type={scenario_type}")
+
+    @classmethod
+    def _get_context(cls) -> tuple[Optional[str], Optional[str], Optional[KrknTelemetryOpenshift]]:
+        """Get the current execution context for this thread."""
+        run_uuid = getattr(cls._local, 'run_uuid', None)
+        scenario_type = getattr(cls._local, 'scenario_type', None)
+        telemetry_ocp = getattr(cls._local, 'telemetry_ocp', None)
+        return run_uuid, scenario_type, telemetry_ocp
+
+    @classmethod
+    def _signal_handler(cls, signum: int, frame):
+        """Handle signals with current thread context information."""
+        signal_name = signal.Signals(signum).name
+        run_uuid, scenario_type, telemetry_ocp = cls._get_context()
+        if not run_uuid or not scenario_type or not telemetry_ocp:
+            logger.warning(f"Signal {signal_name} received without complete context, skipping rollback.")
+            return
+
+        # Clear the context for the next signal, as another signal may arrive before the rollback completes.
+        # This ensures that the rollback is performed only once.
+        cls._set_context(None, None, telemetry_ocp)
+        
+        # Perform rollback
+        logger.info(f"Performing rollback for signal {signal_name} with run_uuid={run_uuid}, scenario_type={scenario_type}")
+        execute_rollback_version_files(telemetry_ocp, run_uuid, scenario_type)
+        
+        # Call original handler if it exists
+        if signum not in cls._original_handlers:
+            logger.info(f"Signal {signal_name} has no registered handler, exiting...")
+            return
+
+        original_handler = cls._original_handlers[signum]
+        if callable(original_handler):
+            logger.info(f"Calling original handler for {signal_name}")
+            original_handler(signum, frame)
+        elif original_handler == signal.SIG_DFL:
+            # Restore default behavior
+            logger.info(f"Restoring default signal handler for {signal_name}")
+            signal.signal(signum, signal.SIG_DFL)
+            signal.raise_signal(signum)
+
+    @classmethod
+    def _register_signal_handler(cls):
+        """Register signal handlers once (called by first instance)."""
+        with cls._signal_lock:  # Lock protects _signal_handlers_installed from race conditions
+            if cls._signal_handlers_installed:
+                return
+                
+            signals_to_handle = [signal.SIGINT, signal.SIGTERM]
+            if hasattr(signal, 'SIGHUP'):
+                signals_to_handle.append(signal.SIGHUP)
+            
+            for sig in signals_to_handle:
+                try:
+                    original_handler = signal.signal(sig, cls._signal_handler)
+                    cls._original_handlers[sig] = original_handler
+                    logger.debug(f"SignalHandler: Registered signal handler for {signal.Signals(sig).name}")
+                except (OSError, ValueError) as e:
+                    logger.warning(f"AbstractScenarioPlugin: Could not register handler for signal {sig}: {e}")
+            
+            cls._signal_handlers_installed = True
+            logger.info("Signal handlers registered globally")
+
+    @classmethod
+    @contextmanager
+    def signal_context(cls, run_uuid: str, scenario_type: str, telemetry_ocp: KrknTelemetryOpenshift):
+        """Context manager to set the signal context for the current thread."""
+        cls._set_context(run_uuid, scenario_type, telemetry_ocp)
+        cls._register_signal_handler()
+        try:
+            yield
+        finally:
+            # Clear context after exiting the context manager
+            cls._set_context(None, None, telemetry_ocp)
+
+
+signal_handler = SignalHandler()

krkn/rollback/version_template.j2

@@ -0,0 +1,55 @@
+# This file is auto-generated by krkn-lib.
+# It contains the rollback callable and its arguments for the scenario plugin.
+
+from dataclasses import dataclass
+import os
+import logging
+from typing import Optional
+
+from krkn_lib.utils import SafeLogger
+from krkn_lib.ocp import KrknOpenshift
+from krkn_lib.telemetry.ocp import KrknTelemetryOpenshift
+
+@dataclass(frozen=True)
+class RollbackContent:
+    resource_identifier: str
+    namespace: Optional[str] = None
+
+# Actual rollback callable
+{{ rollback_callable_code }}
+
+# Create necessary variables for execution
+lib_openshift = None
+lib_telemetry = None
+rollback_content = {{ rollback_content }}
+
+
+# Main entry point for execution
+if __name__ == '__main__':
+    # setup logging
+    logging.basicConfig(
+        level=logging.INFO,
+        format="%(asctime)s [%(levelname)s] %(message)s",
+        handlers=[
+            logging.StreamHandler(),
+        ]
+    )
+
+    # setup logging and get kubeconfig path
+    kubeconfig_path = os.getenv("KUBECONFIG", "~/.kube/config")
+    log_directory = os.path.dirname(os.path.abspath(__file__))
+    os.makedirs(os.path.join(log_directory, 'logs'), exist_ok=True)
+    # setup SafeLogger for telemetry
+    telemetry_log_path = os.path.join(log_directory, 'logs', 'telemetry.log')
+    safe_logger = SafeLogger(telemetry_log_path)
+    # setup krkn-lib objects
+    lib_openshift = KrknOpenshift(kubeconfig_path=kubeconfig_path)
+    lib_telemetry = KrknTelemetryOpenshift(safe_logger=safe_logger, lib_openshift=lib_openshift)
+
+    # execute
+    logging.info('Executing rollback callable...')
+    {{ rollback_callable_name }}(
+        rollback_content,
+        lib_telemetry
+    )
+    logging.info('Rollback completed.')

krkn/scenario_plugins/abstract_scenario_plugin.py

@@ -5,9 +5,26 @@ from krkn_lib.models.telemetry import ScenarioTelemetry
 from krkn_lib.telemetry.ocp import KrknTelemetryOpenshift
 
 from krkn import utils
-
+from krkn.rollback.handler import (
+    RollbackHandler,
+    execute_rollback_version_files,
+    cleanup_rollback_version_files
+)
+from krkn.rollback.signal import signal_handler
+from krkn.rollback.serialization import Serializer
 
 class AbstractScenarioPlugin(ABC):
+
+    def __init__(self, scenario_type: str = "placeholder_scenario_type"):
+        """Initializes the AbstractScenarioPlugin with the scenario type and rollback configuration.
+        
+        :param scenario_type: the scenario type defined in the config.yaml
+        """
+        serializer = Serializer(
+            scenario_type=scenario_type,
+        )
+        self.rollback_handler = RollbackHandler(scenario_type, serializer)
+
     @abstractmethod
     def run(
         self,
@@ -56,6 +73,7 @@ class AbstractScenarioPlugin(ABC):
         scenario_telemetries: list[ScenarioTelemetry] = []
         failed_scenarios = []
         wait_duration = krkn_config["tunings"]["wait_duration"]
+        events_backup = krkn_config["telemetry"]["events_backup"]
         for scenario_config in scenarios_list:
             if isinstance(scenario_config, list):
                 logging.error(
@@ -67,29 +85,45 @@ class AbstractScenarioPlugin(ABC):
 
             scenario_telemetry = ScenarioTelemetry()
             scenario_telemetry.scenario = scenario_config
+            scenario_telemetry.scenario_type = self.get_scenario_types()[0]
             scenario_telemetry.start_timestamp = time.time()
             parsed_scenario_config = telemetry.set_parameters_base64(
                 scenario_telemetry, scenario_config
             )
 
-            try:
-                logging.info(
-                    f"Running {self.__class__.__name__}: {self.get_scenario_types()} -> {scenario_config}"
-                )
-                return_value = self.run(
-                    run_uuid,
-                    scenario_config,
-                    krkn_config,
-                    telemetry,
-                    scenario_telemetry,
-                )
-            except Exception as e:
-                logging.error(
-                    f"uncaught exception on scenario `run()` method: {e} "
-                    f"please report an issue on https://github.com/krkn-chaos/krkn"
-                )
-                return_value = 1
+            with signal_handler.signal_context(
+                run_uuid=run_uuid,
+                scenario_type=scenario_telemetry.scenario_type,
+                telemetry_ocp=telemetry
+            ):
+                try:
+                    logging.info(
+                        f"Running {self.__class__.__name__}: {self.get_scenario_types()} -> {scenario_config}"
+                    )
+                    # pass all the parameters by kwargs to make `set_rollback_context_decorator` get the `run_uuid` and `scenario_type`
+                    return_value = self.run(
+                        run_uuid=run_uuid,
+                        scenario=scenario_config,
+                        krkn_config=krkn_config,
+                        lib_telemetry=telemetry,
+                        scenario_telemetry=scenario_telemetry,
+                    )
+                except Exception as e:
+                    logging.error(
+                        f"uncaught exception on scenario `run()` method: {e} "
+                        f"please report an issue on https://github.com/krkn-chaos/krkn"
+                    )
+                    return_value = 1
 
+            if return_value == 0:
+                cleanup_rollback_version_files(
+                    run_uuid, scenario_telemetry.scenario_type
+                )
+            else:
+                # execute rollback files based on the return value
+                execute_rollback_version_files(
+                    telemetry, run_uuid, scenario_telemetry.scenario_type
+                )
             scenario_telemetry.exit_status = return_value
             scenario_telemetry.end_timestamp = time.time()
             utils.collect_and_put_ocp_logs(
@@ -99,17 +133,21 @@ class AbstractScenarioPlugin(ABC):
                 int(scenario_telemetry.start_timestamp),
                 int(scenario_telemetry.end_timestamp),
             )
-            utils.populate_cluster_events(
-                scenario_telemetry,
-                parsed_scenario_config,
-                telemetry.get_lib_kubernetes(),
-                int(scenario_telemetry.start_timestamp),
-                int(scenario_telemetry.end_timestamp),
-            )
+
+            if events_backup: 
+                utils.populate_cluster_events(
+                    krkn_config,
+                    parsed_scenario_config,
+                    telemetry.get_lib_kubernetes(),
+                    int(scenario_telemetry.start_timestamp),
+                    int(scenario_telemetry.end_timestamp),
+                )
 
             if scenario_telemetry.exit_status != 0:
                 failed_scenarios.append(scenario_config)
             scenario_telemetries.append(scenario_telemetry)
-            logging.info(f"wating {wait_duration} before running the next scenario")
+            logging.info(f"waiting {wait_duration} before running the next scenario")
             time.sleep(wait_duration)
         return failed_scenarios, scenario_telemetries
+
+    

krkn/scenario_plugins/application_outage/application_outage_scenario_plugin.py

@@ -3,13 +3,16 @@ import time
 import yaml
 from krkn_lib.models.telemetry import ScenarioTelemetry
 from krkn_lib.telemetry.ocp import KrknTelemetryOpenshift
-from krkn_lib.utils import get_yaml_item_value
+from krkn_lib.utils import get_yaml_item_value, get_random_string
 from jinja2 import Template
 from krkn import cerberus
 from krkn.scenario_plugins.abstract_scenario_plugin import AbstractScenarioPlugin
+from krkn.rollback.config import RollbackContent
+from krkn.rollback.handler import set_rollback_context_decorator
 
 
 class ApplicationOutageScenarioPlugin(AbstractScenarioPlugin):
+    @set_rollback_context_decorator
     def run(
         self,
         run_uuid: str,
@@ -31,27 +34,66 @@ class ApplicationOutageScenarioPlugin(AbstractScenarioPlugin):
                 )
                 namespace = get_yaml_item_value(scenario_config, "namespace", "")
                 duration = get_yaml_item_value(scenario_config, "duration", 60)
+                exclude_label = get_yaml_item_value(
+                    scenario_config, "exclude_label", None
+                )
+                match_expressions = self._build_exclude_expressions(exclude_label)
+                if match_expressions:
+                    # Log the format being used for better clarity
+                    format_type = "dict" if isinstance(exclude_label, dict) else "string"
+                    logging.info(
+                        "Excluding pods with labels (%s format): %s",
+                        format_type,
+                        ", ".join(
+                            f"{expr['key']} NOT IN {expr['values']}"
+                            for expr in match_expressions
+                        ),
+                    )
 
                 start_time = int(time.time())
+                policy_name = f"krkn-deny-{get_random_string(5)}"
 
-                network_policy_template = """---
+                network_policy_template = (
+                    """---
         apiVersion: networking.k8s.io/v1
         kind: NetworkPolicy
         metadata:
-          name: kraken-deny
+          name: {{ policy_name }}
         spec:
           podSelector:
             matchLabels: {{ pod_selector }}
+{% if match_expressions %}
+            matchExpressions:
+{% for expression in match_expressions %}
+              - key: {{ expression["key"] }}
+                operator: NotIn
+                values:
+{% for value in expression["values"] %}
+                  - {{ value }}
+{% endfor %}
+{% endfor %}
+{% endif %}
           policyTypes: {{ traffic_type }}
         """
+                )
                 t = Template(network_policy_template)
                 rendered_spec = t.render(
-                    pod_selector=pod_selector, traffic_type=traffic_type
+                    pod_selector=pod_selector,
+                    traffic_type=traffic_type,
+                    match_expressions=match_expressions,
+                    policy_name=policy_name,
                 )
                 yaml_spec = yaml.safe_load(rendered_spec)
                 # Block the traffic by creating network policy
                 logging.info("Creating the network policy")
 
+                self.rollback_handler.set_rollback_callable(
+                    self.rollback_network_policy,
+                    RollbackContent(
+                        namespace=namespace,
+                        resource_identifier=policy_name,
+                    ),
+                )
                 lib_telemetry.get_lib_kubernetes().create_net_policy(
                     yaml_spec, namespace
                 )
@@ -65,7 +107,7 @@ class ApplicationOutageScenarioPlugin(AbstractScenarioPlugin):
                 # unblock the traffic by deleting the network policy
                 logging.info("Deleting the network policy")
                 lib_telemetry.get_lib_kubernetes().delete_net_policy(
-                    "kraken-deny", namespace
+                    policy_name, namespace
                 )
 
                 logging.info(
@@ -84,5 +126,86 @@ class ApplicationOutageScenarioPlugin(AbstractScenarioPlugin):
         else:
             return 0
 
+    @staticmethod
+    def rollback_network_policy(
+        rollback_content: RollbackContent,
+        lib_telemetry: KrknTelemetryOpenshift,
+    ):
+        """Rollback function to delete the network policy created during the scenario.
+
+        :param rollback_content: Rollback content containing namespace and resource_identifier.
+        :param lib_telemetry: Instance of KrknTelemetryOpenshift for Kubernetes operations.
+        """
+        try:
+            namespace = rollback_content.namespace
+            policy_name = rollback_content.resource_identifier
+            logging.info(
+                f"Rolling back network policy: {policy_name} in namespace: {namespace}"
+            )
+            lib_telemetry.get_lib_kubernetes().delete_net_policy(policy_name, namespace)
+            logging.info("Network policy rollback completed successfully.")
+        except Exception as e:
+            logging.error(f"Failed to rollback network policy: {e}")
+
     def get_scenario_types(self) -> list[str]:
         return ["application_outages_scenarios"]
+
+    @staticmethod
+    def _build_exclude_expressions(exclude_label) -> list[dict]:
+        """
+        Build match expressions for NetworkPolicy from exclude_label.
+        
+        Supports multiple formats:
+        - Dict format (preferred, similar to pod_selector): {key1: value1, key2: [value2, value3]}
+          Example: {tier: "gold", env: ["prod", "staging"]}
+        - String format: "key1=value1,key2=value2" or "key1=value1|value2"
+          Example: "tier=gold,env=prod" or "tier=gold|platinum"
+        - List format (list of strings): ["key1=value1", "key2=value2"]
+          Example: ["tier=gold", "env=prod"]
+          Note: List elements must be strings in "key=value" format.
+        
+        :param exclude_label: Can be dict, string, list of strings, or None
+        :return: List of match expression dictionaries
+        """
+        expressions: list[dict] = []
+
+        if not exclude_label:
+            return expressions
+
+        def _append_expr(key: str, values):
+            if not key or values is None:
+                return
+            if not isinstance(values, list):
+                values = [values]
+            cleaned_values = [str(v).strip() for v in values if str(v).strip()]
+            if cleaned_values:
+                expressions.append({"key": key.strip(), "values": cleaned_values})
+
+        if isinstance(exclude_label, dict):
+            for k, v in exclude_label.items():
+                _append_expr(str(k), v)
+            return expressions
+
+        if isinstance(exclude_label, list):
+            selectors = exclude_label
+        else:
+            selectors = [sel.strip() for sel in str(exclude_label).split(",")]
+
+        for selector in selectors:
+            if not selector:
+                continue
+            if "=" not in selector:
+                logging.warning(
+                    "exclude_label entry '%s' is invalid, expected key=value format",
+                    selector,
+                )
+                continue
+            key, value = selector.split("=", 1)
+            value_items = (
+                [item.strip() for item in value.split("|") if item.strip()]
+                if value
+                else []
+            )
+            _append_expr(key, value_items or value)
+
+        return expressions