filled the already checked activities

Signed-off-by: Tullio Sebastiani <tsebasti@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

@@ -1,10 +1,27 @@
+## Type of change
+
+- [ ] Refactor
+- [ ] New feature
+- [ ] Bug fix
+- [ ] Optimization
+
 ## Description  
 <!-- Provide a brief description of the changes made in this PR. -->  
 
+## Related Tickets & Documents
+
+- 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 -->  
+<!-- Add the link to the corresponding documentation PR in the website repository -->  
+
+## Checklist before requesting a review
+
+- [ ] I have performed a self-review of my code.
+- [ ] If it is a core feature, I have added thorough tests.

.github/workflows/release.yml

@@ -16,6 +16,7 @@ jobs:
           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:
@@ -45,3 +46,15 @@ jobs:
           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/tests.yml

@@ -16,14 +16,19 @@ jobs:
         uses: redhat-chaos/actions/kind@main
       - name: Deploy prometheus & Port Forwarding
         uses: redhat-chaos/actions/prometheus@main
-      
       - name: Deploy Elasticsearch
         with:
-          ELASTIC_URL: ${{ vars.ELASTIC_URL }}
-          ELASTIC_PORT: ${{ vars.ELASTIC_PORT }}
-          ELASTIC_USER: ${{ vars.ELASTIC_USER }}
-          ELASTIC_PASSWORD: ${{ vars.ELASTIC_PASSWORD }}
+          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: |
+          ELASTIC_PASSWORD=$(cat elastic_password.txt)
+          echo "ELASTIC_PASSWORD=$ELASTIC_PASSWORD" >> "$GITHUB_ENV"
       - name: Install Python
         uses: actions/setup-python@v4
         with:
@@ -37,8 +42,22 @@ jobs:
 
       - name: Deploy test workloads
         run: |
-          es_pod_name=$(kubectl get pods -l "app.kubernetes.io/instance=elasticsearch" -o name)
+          es_pod_name=$(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 $i: Elasticsearch not ready yet, waiting..."
+            sleep 2
+          done
           kubectl apply -f CI/templates/outage_pod.yaml
           kubectl wait --for=condition=ready pod -l scenario=outage --timeout=300s
           kubectl apply -f CI/templates/container_scenario_pod.yaml
@@ -65,11 +84,14 @@ jobs:
             yq -i '.kraken.performance_monitoring="localhost:9090"' CI/config/common_test_config.yaml
             yq -i '.elastic.elastic_port=9200' CI/config/common_test_config.yaml
             yq -i '.elastic.elastic_url="https://localhost"' CI/config/common_test_config.yaml
-            yq -i '.elastic.enable_elastic=True' CI/config/common_test_config.yaml
+            yq -i '.elastic.enable_elastic=False' CI/config/common_test_config.yaml
+            yq -i '.elastic.password="${{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_service_hijacking" > ./CI/tests/functional_tests
             echo "test_app_outages" >> ./CI/tests/functional_tests
             echo "test_container"      >> ./CI/tests/functional_tests
             echo "test_pod" >> ./CI/tests/functional_tests
+            echo "test_customapp_pod" >> ./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
@@ -78,7 +100,6 @@ jobs:
             echo "test_io_hog" >> ./CI/tests/functional_tests
             echo "test_pod_network_filter" >> ./CI/tests/functional_tests
 
-
       # Push on main only steps + all other functional to collect coverage
       # for the badge
       - name: Configure AWS Credentials
@@ -94,8 +115,11 @@ jobs:
           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 '.elastic.enable_elastic=False' CI/config/common_test_config.yaml
+          yq -i '.elastic.password="${{env.ELASTIC_PASSWORD}}"' CI/config/common_test_config.yaml
           yq -i '.elastic.elastic_port=9200' CI/config/common_test_config.yaml
           yq -i '.elastic.elastic_url="https://localhost"' CI/config/common_test_config.yaml
+          yq -i '.performance_monitoring.prometheus_url="http://localhost:9090"' CI/config/common_test_config.yaml
           yq -i '.telemetry.username="${{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
@@ -103,6 +127,7 @@ jobs:
           echo "test_app_outages" >> ./CI/tests/functional_tests
           echo "test_container"      >> ./CI/tests/functional_tests
           echo "test_pod" >> ./CI/tests/functional_tests
+          echo "test_customapp_pod" >> ./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
@@ -120,36 +145,38 @@ jobs:
           cat ./CI/results.markdown >> $GITHUB_STEP_SUMMARY
           echo >> $GITHUB_STEP_SUMMARY
       - name: Upload CI logs
-        if: ${{ success() || failure() }}
+        if: ${{ always() }}
         uses: actions/upload-artifact@v4
         with:
           name: ci-logs
           path: CI/out
           if-no-files-found: error
       - name: Collect coverage report
-        if: ${{ success() || failure() }}
+        if: ${{ always() }}
         run: |
           python -m coverage html
           python -m coverage json
       - name: Publish coverage report to job summary
-        if: ${{ success() || failure() }}
+        if: ${{ always() }}
         run: |
           pip install html2text
           html2text --ignore-images --ignore-links -b 0 htmlcov/index.html >> $GITHUB_STEP_SUMMARY
       - name: Upload coverage data
-        if: ${{ success() || failure() }}
+        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
+        if: ${{ always() }}
         run: "! grep Fail CI/results.markdown"
 
   badge:

ADOPTERS.md

@@ -6,3 +6,4 @@ This is a list of organizations that have publicly acknowledged usage of Krkn an
 |:-|:-|:-|:-|
 | 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

@@ -2,6 +2,8 @@ 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.
     chaos_scenarios:                                       # List of policies/chaos scenarios to load.
         -   $scenario_type:                                # List of chaos pod scenarios to load.
             - $scenario_file
@@ -15,8 +17,11 @@ 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.
     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.
@@ -27,7 +32,7 @@ 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

CI/legacy/scenarios/volume_scenario.yaml

@@ -51,7 +51,7 @@ spec:
         claimName: kraken-test-pvc
   containers:
     - name: kraken-test-container
-      image: 'quay.io/centos7/httpd-24-centos7:latest'
+      image: 'quay.io/centos7/httpd-24-centos7:centos7'
       volumeMounts:
         - mountPath: "/home/krake-dir/"
           name: kraken-test-pv

CI/tests/test_app_outages.sh

@@ -18,6 +18,8 @@ function functional_test_app_outage {
 
   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_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
+  echo "Pod disruption with node_label_selector test: Success"
+}
+
+functional_test_customapp_pod_node_selector

CI/tests/test_pod.sh

@@ -10,7 +10,7 @@ function functional_test_pod_crash {
   export scenario_file="scenarios/kind/pod_etcd.yml"
   export post_config=""
   envsubst < CI/config/common_test_config.yaml > 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
   echo "Pod disruption scenario test: Success"
 }

CI/tests/test_pod_network_filter.sh

@@ -11,7 +11,7 @@ function functional_pod_network_filter {
   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
@@ -29,7 +29,9 @@ function functional_pod_network_filter {
     [ $COUNTER -eq "100" ] && echo "maximum number of retry reached, test failed" && exit 1
   done
 
-  python3 -m coverage run -a run_kraken.py -c CI/config/pod_network_filter.yaml  > /dev/null 2>&1 &
+  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
@@ -53,6 +55,7 @@ function functional_pod_network_filter {
   done
 
   wait $PID
+
 }
 
 functional_pod_network_filter

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`

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 contributor 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 documents have been borrowed from [Kubernetes governance](https://github.com/kubernetes/community/blob/master/governance.md)

INCUBATION_CHECKLIST.md

@@ -0,0 +1,270 @@
+# Review Project Moving Level Evaluation
+[x] I have reviewed the TOC's [moving level readiness triage guide](https://github.com/cncf/toc/blob/main/operations/dd-toc-guide.md#initial-triageevaluation-prior-to-assignment), ensured the criteria for my project are met before opening this issue, and understand that unmet criteria will result in the project's application being closed.
+
+# Krkn Incubation Application
+v1.6
+This template provides the project with a framework to inform the TOC of their conformance to the Incubation Level Criteria. 
+
+Project Repo(s): https://github.com/krkn-chaos/krkn
+Project Site:  https://www.krkn-chaos.dev 
+Sub-Projects: 
+ - https://github.com/krkn-chaos/krknctl
+ - https://github.com/krkn-chaos/krkn-hub
+Communication: [Slack](https://kubernetes.slack.com/archives/C05SFMHRWK1)
+
+
+Project points of contacts: 
+ - [Naga Ravi Elluri](mailto:nelluri@redhat.com)
+ - [Paige Patton](mailto:ppatton@redhat.com)
+ - [Tullio Sebastiani](mailto:tsebasti@redhat.com)
+
+- [ ] (Post Incubation only) [Book a meeting with CNCF staff](http://project-meetings.cncf.io) to understand project benefits and event resources. 
+
+## Incubation Criteria Summary for Krkn
+
+### Application Level Assertion
+
+- [x] This project is currently Sandbox, accepted on 2023/12/19, and applying to Incubation.
+- [x] This project is applying to join the CNCF at the Incubation level.
+
+### Adoption Assertion
+
+_The project has been adopted by the following organizations in a testing and integration or production capacity:_
+
+| 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.   |
+
+## Application Process Principles
+
+### Suggested
+
+N/A
+
+### Required
+
+- [ ] **Engage with the domain specific TAG(s) to increase awareness through a presentation or completing a General Technical Review.**
+  - This was completed and occurred on DD-MMM-YYYY, and can be discovered at $LINK.
+
+<!-- (Project assertion goes here) --> 
+
+- [x] **All project metadata and resources are [vendor-neutral](https://contribute.cncf.io/maintainers/community/vendor-neutrality/).**
+
+<!-- (Project assertion goes here) --> 
+
+- [ ] **Review and acknowledgement of expectations for [Sandbox](https://sandbox.cncf.io) projects and requirements for moving forward through the CNCF Maturity levels.**		
+- Met during Project's application on DD-MMM-YYYY.
+
+<!-- (Project assertion goes here) --> 
+
+- [ ] **Due Diligence Review.**
+
+Completion of this due diligence document, resolution of concerns raised, and presented for public comment satisfies the Due Diligence Review criteria.
+
+- [ ] **Additional documentation as appropriate for project type, e.g.: installation documentation, end user documentation, reference implementation and/or code samples.**
+
+<!-- (Project assertion goes here) --> 
+
+## Governance and Maintainers
+
+Note: this section may be augmented by the completion of a Governance Review from the Project Reviews subproject.
+
+### Suggested
+
+- [ ] **Governance has continuously been iterated upon by the project as a result of their experience applying it, with the governance history demonstrating evolution of maturity alongside the project's maturity evolution.**
+
+<!-- (Project assertion goes here) --> 
+
+- [ ] **Clear and discoverable project governance documentation.**
+
+<!-- (Project assertion goes here) --> 
+
+- [ ] **Governance is up to date with actual project activities, including any meetings, elections, leadership, or approval processes.**
+
+<!-- (Project assertion goes here) --> 
+
+- [ ] **Governance clearly documents [vendor-neutrality](https://contribute.cncf.io/maintainers/community/vendor-neutrality/) of project direction.**
+
+<!-- (Project assertion goes here) --> 
+
+- [ ] **Document how the project makes decisions on leadership, contribution acceptance, requests to the CNCF, and changes to governance or project goals.**
+
+<!-- (Project assertion goes here) --> 
+
+- [ ] **Document how role, function-based members, or sub-teams are assigned, onboarded, and removed for specific teams (example: Security Response Committee).**
+
+<!-- (Project assertion goes here) --> 
+
+- [ ] **Document a complete maintainer lifecycle process (including roles, onboarding, offboarding, and emeritus status).**
+
+<!-- (Project assertion goes here) --> 
+
+- [ ] **Demonstrate usage of the maintainer lifecycle with outcomes, either through the addition or replacement of maintainers as project events have required.**
+
+<!-- (Project assertion goes here) --> 
+
+- [ ] **If the project has subprojects: subproject leadership, contribution, maturity status documented, including add/remove process.**
+
+<!-- (Project assertion goes here) --> 
+
+### Required
+
+- [x] **Document complete list of current maintainers, including names, contact information, domain of responsibility, and affiliation.**
+
+<!-- (Project assertion goes here) --> 
+
+- [x] **A number of active maintainers which is appropriate to the size and scope of the project.**
+
+<!-- (Project assertion goes here) --> 
+
+- [x] **Code and Doc ownership in Github and elsewhere matches documented governance roles.**
+
+<!-- (Project assertion goes here) --> 
+
+- [x] **Document adoption and adherence to the CNCF Code of Conduct or the project's CoC which is based off the CNCF CoC and not in conflict with it.**
+
+<!-- (Project assertion goes here) --> 
+
+- [x] **CNCF Code of Conduct is cross-linked from other governance documents.**
+
+<!-- (Project assertion goes here) --> 
+
+- [x] **All subprojects, if any, are listed.**
+
+<!-- (Project assertion goes here) --> 
+
+## Contributors and Community
+
+Note: this section may be augmented by the completion of a Governance Review from the Project Reviews subproject.
+
+### Suggested
+
+- [ ] **Contributor ladder with multiple roles for contributors.**
+
+<!-- (Project assertion goes here) --> 
+
+### Required
+
+- [x] **Clearly defined and discoverable process to submit issues or changes.**
+
+<!-- (Project assertion goes here) --> 
+
+- [x] **Project must have, and document, at least one public communications channel for users and/or contributors.**
+
+<!-- (Project assertion goes here) --> 
+
+- [ ] **List and document all project communication channels, including subprojects (mail list/slack/etc.).  List any non-public communications channels and what their special purpose is.**
+
+<!-- (Project assertion goes here) --> 
+
+- [x] **Up-to-date public meeting schedulers and/or integration with CNCF calendar.**
+
+<!-- (Project assertion goes here) --> 
+
+- [ ] **Documentation of how to contribute, with increasing detail as the project matures.**
+
+<!-- (Project assertion goes here) --> 
+
+- [x] **Demonstrate contributor activity and recruitment.**
+
+<!-- (Project assertion goes here) --> 
+
+## Engineering Principles
+
+### Suggested
+
+- [ ] **Roadmap change process is documented.**
+
+<!-- (Project assertion goes here) --> 
+
+- [ ] **History of regular, quality releases.**
+
+<!-- (Project assertion goes here) --> 
+
+### Required 
+
+- [ ] **Document project goals and objectives that illustrate the project’s differentiation in the Cloud Native landscape as well as outlines how this project fulfills an outstanding need and/or solves a problem differently. _This can also be satisfied by completing a General Technical Review._**
+  - _If applicable_ a General Technical Review was completed/updated on DD-MMM-YYYY, and can be discovered at $LINK.
+
+<!-- (Project assertion goes here) --> 
+
+- [ ] **Document what the project does, and why it does it - including viable cloud native use cases. This can also be satisfied by completing a General Technical Review.**
+
+<!-- (Project assertion goes here) --> 
+
+- [ ] **Document and maintain a public roadmap or other forward looking planning document or tracking mechanism.**
+
+<!-- (Project assertion goes here) --> 
+
+- [ ] **Document overview of project architecture and software design that demonstrates viable cloud native use cases, as part of the project's documentation. _This can also be satisfied by completing a General Technical Review and capturing the output in the project's documentation._**
+  - _If applicable_ a General Technical Review was completed/updated on DD-MMM-YYYY, and can be discovered at $LINK.
+
+<!-- (Project assertion goes here) --> 
+
+- [x] **Document the project's release process.**
+
+<!-- (Project assertion goes here) --> 
+
+## Security
+
+### Suggested
+
+N/A
+
+### Required
+
+Note: this section may be augmented by a joint-assessment performed by TAG Security and Compliance.
+
+- [x] **Clearly defined and discoverable process to report security issues.**
+
+<!-- (Project assertion goes here) --> 
+
+- [x] **Enforcing Access Control Rules to secure the code base against attacks (Example: two factor authentication enforcement, and/or use of ACL tools.)**
+
+<!-- (Project assertion goes here) --> 
+
+- [x] **Document assignment of security response roles and how reports are handled.**
+
+<!-- (Project assertion goes here) --> 
+
+- [x] **Document [Security Self-Assessment](https://tag-security.cncf.io/community/assessments/guide/self-assessment/).**
+
+<!-- (Project assertion goes here) --> 
+
+- [ ] **Achieve the Open Source Security Foundation (OpenSSF) Best Practices passing badge.**
+
+<!-- (Project assertion goes here) --> 
+
+## Ecosystem
+
+### Suggested
+
+N/A
+
+### Required
+
+- [ ] **Publicly documented list of adopters, which may indicate their adoption level (dev/trialing, prod, etc.)**
+
+<!-- (Project assertion goes here) --> 
+
+- [ ] **Used in appropriate capacity by at least 3 independent + indirect/direct adopters, (these are not required to be in the publicly documented list of adopters)**
+
+<!-- (Project assertion goes here) --> 
+
+The project provided the TOC with a list of adopters for verification of use of the project at the level expected, i.e. production use for graduation, dev/test for incubation.
+
+- [ ] **TOC verification of adopters.**
+
+<!-- (Project assertion goes here) --> 
+
+Refer to the Adoption portion of this document.
+
+- [ ] **Clearly documented integrations and/or compatibility with other CNCF projects as well as non-CNCF projects.**
+
+<!-- (Project assertion goes here) --> 
+
+## Additional Information
+
+<!-- Provide any additional information you feel is relevant for the TOC in conducting due diligence on this project. -->

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

@@ -22,14 +22,8 @@ Kraken injects deliberate failures into Kubernetes clusters to check if it is re
 Instructions on how to setup, configure and run Kraken can be found in the [documentation](https://krkn-chaos.dev/docs/).
 
 
-### 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
+### Blogs, podcasts and interviews
+Additional resources, including blog posts, podcasts, and community interviews, can be found on the [website](https://krkn-chaos.dev/blog)
 
 
 ### Roadmap

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.
+

config/config.yaml

@@ -1,55 +1,57 @@
 kraken:
     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.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:
+       # 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
+       -  kubevirt_vm_outage:
+              - scenarios/kubevirt/kubevirt-vm-outage.yaml
 
 cerberus:
     cerberus_enabled: False                                # Enable it when cerberus is previously installed
@@ -77,7 +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:
@@ -117,3 +119,13 @@ health_checks:                                              # Utilizing health c
           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

containers/Dockerfile.template

@@ -1,22 +1,35 @@
 # oc build
-FROM golang:1.23.1 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 1.23.1 &&\
-    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&&\
-    go get github.com/go-git/go-git/v5@v5.13.0&&\
-    go get golang.org/x/net@v0.38.0&&\
-    go get github.com/containerd/containerd@v1.7.27&&\
-    go get golang.org/x/oauth2@v0.27.0&&\
-    go get golang.org/x/crypto@v0.35.0&&\
+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
@@ -28,16 +41,20 @@ ENV KUBECONFIG /home/krkn/.kube/config
 
 # 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 python39 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
@@ -48,6 +65,11 @@ RUN if [ -n "$TAG" ]; then git checkout "$TAG";fi
 
 RUN python3.9 -m ensurepip --upgrade --default-pip
 RUN python3.9 -m pip install --upgrade pip setuptools==78.1.1
+
+# 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/python3.9/ensurepip/_bundled
 RUN pip3.9 install -r requirements.txt
 RUN pip3.9 install jsonschema
 
@@ -55,8 +77,14 @@ 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/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",
@@ -425,6 +461,84 @@
     "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",

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

krkn/invoke/command.py

@@ -18,9 +18,8 @@ def invoke(command, timeout=None):
 def invoke_no_exit(command, timeout=None):
     output = ""
     try:
-        output = subprocess.check_output(command, shell=True, universal_newlines=True, timeout=timeout)
+        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/prometheus/client.py

@@ -75,10 +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
@@ -113,7 +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 = (
@@ -136,6 +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)
@@ -149,8 +165,8 @@ def critical_alerts(
 
     if not firing_alerts:
         logging.info("No critical alerts are firing!!")
-
-
+    
+   
 def metrics(
     prom_cli: KrknPrometheus,
     elastic: KrknElastic,
@@ -252,6 +268,14 @@ def metrics(
                         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:

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,
@@ -74,24 +91,39 @@ class AbstractScenarioPlugin(ABC):
                 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(
@@ -118,4 +150,4 @@ class AbstractScenarioPlugin(ABC):
             time.sleep(wait_duration)
         return failed_scenarios, scenario_telemetries
 
-    
+    

krkn/scenario_plugins/application_outage/application_outage_scenario_plugin.py

@@ -7,9 +7,12 @@ 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,
@@ -31,6 +34,21 @@ 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)}"
@@ -40,23 +58,42 @@ class ApplicationOutageScenarioPlugin(AbstractScenarioPlugin):
         apiVersion: networking.k8s.io/v1
         kind: NetworkPolicy
         metadata:
-          name: """
-                    + policy_name
-                    + """
+          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
                 )
@@ -89,5 +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

krkn/scenario_plugins/container/container_scenario_plugin.py

@@ -1,10 +1,10 @@
 import logging
 import random
 import time
-
+from asyncio import Future
 import yaml
 from krkn_lib.k8s import KrknKubernetes
-from krkn_lib.k8s.pods_monitor_pool import PodsMonitorPool
+from krkn_lib.k8s.pod_monitor import select_and_monitor_by_namespace_pattern_and_label
 from krkn_lib.models.telemetry import ScenarioTelemetry
 from krkn_lib.telemetry.ocp import KrknTelemetryOpenshift
 from krkn_lib.utils import get_yaml_item_value
@@ -22,30 +22,26 @@ class ContainerScenarioPlugin(AbstractScenarioPlugin):
         lib_telemetry: KrknTelemetryOpenshift,
         scenario_telemetry: ScenarioTelemetry,
     ) -> int:
-        pool = PodsMonitorPool(lib_telemetry.get_lib_kubernetes())
         try:
             with open(scenario, "r") as f:
                 cont_scenario_config = yaml.full_load(f)
                 
                 for kill_scenario in cont_scenario_config["scenarios"]:
-                    self.start_monitoring(
-                        kill_scenario, pool
+                    future_snapshot = self.start_monitoring(
+                        kill_scenario,
+                        lib_telemetry
                     )
-                    killed_containers = self.container_killing_in_pod(
+                    self.container_killing_in_pod(
                         kill_scenario, lib_telemetry.get_lib_kubernetes()
                     )
-                    result = pool.join()
-                if result.error:
-                    logging.error(
-                        logging.error(
-                            f"ContainerScenarioPlugin pods failed to recovery: {result.error}"
-                        )
-                    )
-                    return 1
-                scenario_telemetry.affected_pods = result
-
-        except (RuntimeError, Exception):
-            logging.error("ContainerScenarioPlugin exiting due to Exception %s")
+                    snapshot = future_snapshot.result()
+                    result = snapshot.get_pods_status()
+                    scenario_telemetry.affected_pods = result
+                    if len(result.unrecovered) > 0:
+                        logging.info("ContainerScenarioPlugin failed with unrecovered containers")
+                        return 1
+        except (RuntimeError, Exception) as e:
+            logging.error("ContainerScenarioPlugin exiting due to Exception %s" % e)
             return 1
         else:
             return 0
@@ -53,17 +49,18 @@ class ContainerScenarioPlugin(AbstractScenarioPlugin):
     def get_scenario_types(self) -> list[str]:
         return ["container_scenarios"]
 
-    def start_monitoring(self, kill_scenario: dict, pool: PodsMonitorPool):
+    def start_monitoring(self, kill_scenario: dict, lib_telemetry: KrknTelemetryOpenshift) -> Future:
         
         namespace_pattern = f"^{kill_scenario['namespace']}$"
         label_selector = kill_scenario["label_selector"]
         recovery_time = kill_scenario["expected_recovery_time"]
-        pool.select_and_monitor_by_namespace_pattern_and_label(
+        future_snapshot = select_and_monitor_by_namespace_pattern_and_label(
             namespace_pattern=namespace_pattern,
             label_selector=label_selector,
             max_timeout=recovery_time,
-            field_selector="status.phase=Running"
+            v1_client=lib_telemetry.get_lib_kubernetes().cli
         )
+        return future_snapshot
 
     def container_killing_in_pod(self, cont_scenario, kubecli: KrknKubernetes):
         scenario_name = get_yaml_item_value(cont_scenario, "name", "")
@@ -73,6 +70,7 @@ class ContainerScenarioPlugin(AbstractScenarioPlugin):
         container_name = get_yaml_item_value(cont_scenario, "container_name", "")
         kill_action = get_yaml_item_value(cont_scenario, "action", 1)
         kill_count = get_yaml_item_value(cont_scenario, "count", 1)
+        exclude_label = get_yaml_item_value(cont_scenario, "exclude_label", "")
         if not isinstance(kill_action, int):
             logging.error(
                 "Please make sure the action parameter defined in the "
@@ -94,7 +92,19 @@ class ContainerScenarioPlugin(AbstractScenarioPlugin):
                 pods = kubecli.get_all_pods(label_selector)
             else:
                 # Only returns pod names
-                pods = kubecli.list_pods(namespace, label_selector)
+                # Use list_pods with exclude_label parameter to exclude pods
+                if exclude_label:
+                    logging.info(
+                        "Using exclude_label '%s' to exclude pods from container scenario %s in namespace %s",
+                        exclude_label,
+                        scenario_name,
+                        namespace,
+                    )
+                pods = kubecli.list_pods(
+                    namespace=namespace,
+                    label_selector=label_selector,
+                    exclude_label=exclude_label if exclude_label else None
+                )
         else:
             if namespace == "*":
                 logging.error(
@@ -105,6 +115,7 @@ class ContainerScenarioPlugin(AbstractScenarioPlugin):
                 # sys.exit(1)
                 raise RuntimeError()
             pods = pod_names
+
         # get container and pod name
         container_pod_list = []
         for pod in pods:

krkn/scenario_plugins/hogs/hogs_scenario_plugin.py

@@ -16,9 +16,13 @@ from krkn_lib.k8s import KrknKubernetes
 from krkn_lib.utils import get_random_string
 
 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 HogsScenarioPlugin(AbstractScenarioPlugin):
+    
+    @set_rollback_context_decorator
     def run(self, run_uuid: str, scenario: str, krkn_config: dict[str, any], lib_telemetry: KrknTelemetryOpenshift,
             scenario_telemetry: ScenarioTelemetry) -> int:
         try:
@@ -79,6 +83,13 @@ class HogsScenarioPlugin(AbstractScenarioPlugin):
             config.node_selector = f"kubernetes.io/hostname={node}"
             pod_name = f"{config.type.value}-hog-{get_random_string(5)}"
             node_resources_start = lib_k8s.get_node_resources_info(node)
+            self.rollback_handler.set_rollback_callable(
+                self.rollback_hog_pod,
+                RollbackContent(
+                    namespace=config.namespace,
+                    resource_identifier=pod_name,
+                ),
+            )
             lib_k8s.deploy_hog(pod_name, config)
             start = time.time()
             # waiting 3 seconds before starting sample collection
@@ -150,3 +161,22 @@ class HogsScenarioPlugin(AbstractScenarioPlugin):
                 raise exception
         except queue.Empty:
             pass
+
+    @staticmethod
+    def rollback_hog_pod(rollback_content: RollbackContent, lib_telemetry: KrknTelemetryOpenshift):
+        """
+        Rollback function to delete hog pod.
+
+        :param rollback_content: Rollback content containing namespace and resource_identifier.
+        :param lib_telemetry: Instance of KrknTelemetryOpenshift for Kubernetes operations
+        """
+        try:
+            namespace = rollback_content.namespace
+            pod_name = rollback_content.resource_identifier
+            logging.info(
+                f"Rolling back hog pod: {pod_name} in namespace: {namespace}"
+            )
+            lib_telemetry.get_lib_kubernetes().delete_pod(pod_name, namespace)
+            logging.info("Rollback of hog pod completed successfully.")
+        except Exception as e:
+            logging.error(f"Failed to rollback hog pod: {e}")

krkn/scenario_plugins/kubevirt_vm_outage/kubevirt_vm_outage_scenario_plugin.py

@@ -20,9 +20,12 @@ class KubevirtVmOutageScenarioPlugin(AbstractScenarioPlugin):
     This plugin simulates a VM crash or outage scenario and supports automated or manual recovery.
     """
 
-    def __init__(self):
+    def __init__(self, scenario_type: str = None):
+        scenario_type = self.get_scenario_types()[0]
+        super().__init__(scenario_type)
         self.k8s_client = None
         self.original_vmi = None
+        self.vmis_list = []
         
     # Scenario type is handled directly in execute_scenario
     def get_scenario_types(self) -> list[str]:
@@ -104,24 +107,24 @@ class KubevirtVmOutageScenarioPlugin(AbstractScenarioPlugin):
         :return: The VMI object if found, None otherwise
         """
         try:
-            vmis = self.custom_object_client.list_namespaced_custom_object(
-                group="kubevirt.io",
-                version="v1",
-                namespace=namespace,
-                plural="virtualmachineinstances",
-            )
+            namespaces = self.k8s_client.list_namespaces_by_regex(namespace)
+            for namespace in namespaces:
+                vmis = self.custom_object_client.list_namespaced_custom_object(
+                    group="kubevirt.io",
+                    version="v1",
+                    namespace=namespace,
+                    plural="virtualmachineinstances",
+                )
 
-            vmi_list = []
-            for vmi in vmis.get("items"):
-                vmi_name = vmi.get("metadata",{}).get("name")
-                match = re.match(regex_name, vmi_name)
-                if match:
-                    vmi_list.append(vmi)
-            return vmi_list
+                for vmi in vmis.get("items"):
+                    vmi_name = vmi.get("metadata",{}).get("name")
+                    match = re.match(regex_name, vmi_name)
+                    if match:
+                        self.vmis_list.append(vmi)
         except ApiException as e:
             if e.status == 404:
                 logging.warning(f"VMI {regex_name} not found in namespace {namespace}")
-                return None
+                return []
             else:
                 logging.error(f"Error getting VMI {regex_name}: {e}")
                 raise
@@ -137,6 +140,7 @@ class KubevirtVmOutageScenarioPlugin(AbstractScenarioPlugin):
         :param scenario_telemetry: The telemetry object for recording metrics
         :return: 0 for success, 1 for failure
         """
+        self.pods_status = PodsStatus()
         try:
             params = config.get("parameters", {})
             vm_name = params.get("vm_name")
@@ -144,55 +148,58 @@ class KubevirtVmOutageScenarioPlugin(AbstractScenarioPlugin):
             timeout = params.get("timeout", 60)
             kill_count = params.get("kill_count", 1)
             disable_auto_restart = params.get("disable_auto_restart", False)
-            self.pods_status = PodsStatus()
+            
             if not vm_name:
                 logging.error("vm_name parameter is required")
                 return 1
-            vmis_list = self.get_vmis(vm_name,namespace)
-            rand_int = random.randint(0, len(vmis_list) - 1)
-            vmi = vmis_list[rand_int]
+            self.pods_status = PodsStatus()
+            self.get_vmis(vm_name,namespace)
+            for _ in range(kill_count):
                 
-            logging.info(f"Starting KubeVirt VM outage scenario for VM: {vm_name} in namespace: {namespace}")
-            vmi_name = vmi.get("metadata").get("name")
-            if not self.validate_environment(vmi_name, namespace):
-                return 1
-                
-            vmi = self.get_vmi(vmi_name, namespace)
-            self.affected_pod = AffectedPod(
-                pod_name=vmi_name,
-                namespace=namespace,
-            )
-            if not vmi:
-                logging.error(f"VMI {vm_name} not found in namespace {namespace}")
-                return 1
-                
-            self.original_vmi = vmi
-            logging.info(f"Captured initial state of VMI: {vm_name}")
-            result = self.delete_vmi(vmi_name, namespace, disable_auto_restart)
-            if result != 0:
-            
-                return self.pods_status
+                rand_int = random.randint(0, len(self.vmis_list) - 1)
+                vmi = self.vmis_list[rand_int]
+                    
+                logging.info(f"Starting KubeVirt VM outage scenario for VM: {vm_name} in namespace: {namespace}")
+                vmi_name = vmi.get("metadata").get("name")
+                vmi_namespace = vmi.get("metadata").get("namespace")
+                if not self.validate_environment(vmi_name, vmi_namespace):
+                    return 1
+                    
+                vmi = self.get_vmi(vmi_name, vmi_namespace)
+                self.affected_pod = AffectedPod(
+                    pod_name=vmi_name,
+                    namespace=vmi_namespace,
+                )
+                if not vmi:
+                    logging.error(f"VMI {vm_name} not found in namespace {namespace}")
+                    return 1
+                    
+                self.original_vmi = vmi
+                logging.info(f"Captured initial state of VMI: {vm_name}")
+                result = self.delete_vmi(vmi_name, vmi_namespace, disable_auto_restart)
+                if result != 0:
+                    self.pods_status.unrecovered.append(self.affected_pod)
+                    continue
 
-            result = self.wait_for_running(vmi_name,namespace, timeout)
-            if result != 0:
-                self.recover(vmi_name, namespace)
-                self.pods_status.unrecovered = self.affected_pod
-                return self.pods_status
-            
-            self.affected_pod.total_recovery_time = (
-                self.affected_pod.pod_readiness_time
-                + self.affected_pod.pod_rescheduling_time
-            )
+                result = self.wait_for_running(vmi_name,vmi_namespace, timeout)
+                if result != 0:
+                    self.pods_status.unrecovered.append(self.affected_pod)
+                    continue
+                
+                self.affected_pod.total_recovery_time = (
+                    self.affected_pod.pod_readiness_time
+                    + self.affected_pod.pod_rescheduling_time
+                )
 
-            self.pods_status.recovered.append(self.affected_pod)
-            logging.info(f"Successfully completed KubeVirt VM outage scenario for VM: {vm_name}")
+                self.pods_status.recovered.append(self.affected_pod)
+                logging.info(f"Successfully completed KubeVirt VM outage scenario for VM: {vm_name}")
             
             return self.pods_status
             
         except Exception as e:
             logging.error(f"Error executing KubeVirt VM outage scenario: {e}")
             log_exception(e)
-            return 1
+            return self.pods_status
 
     def validate_environment(self, vm_name: str, namespace: str) -> bool:
         """
@@ -315,13 +322,13 @@ class KubevirtVmOutageScenarioPlugin(AbstractScenarioPlugin):
                 time.sleep(1)
                 
             logging.error(f"Timed out waiting for VMI {vm_name} to be deleted")
-            self.pods_status.unrecovered = self.affected_pod
+            self.pods_status.unrecovered.append(self.affected_pod)
             return 1
             
         except Exception as e:
             logging.error(f"Error deleting VMI {vm_name}: {e}")
             log_exception(e)
-            self.pods_status.unrecovered = self.affected_pod
+            self.pods_status.unrecovered.append(self.affected_pod)
             return 1
 
     def wait_for_running(self, vm_name: str, namespace: str, timeout: int = 120) -> int: 

krkn/scenario_plugins/native/network/ingress_shaping.py

@@ -5,6 +5,7 @@ import time
 import sys
 import os
 import re
+import random
 from traceback import format_exc
 from jinja2 import Environment, FileSystemLoader
 from . import kubernetes_functions as kube_helper
@@ -168,14 +169,14 @@ def get_default_interface(node: str, pod_template, cli: CoreV1Api, image: str) -
     Returns:
         Default interface (string) belonging to the node
     """
-
-    pod_body = yaml.safe_load(pod_template.render(nodename=node, image=image))
+    pod_name_regex = str(random.randint(0, 10000))
+    pod_body = yaml.safe_load(pod_template.render(regex_name=pod_name_regex,nodename=node, image=image))
     logging.info("Creating pod to query interface on node %s" % node)
     kube_helper.create_pod(cli, pod_body, "default", 300)
-
+    pod_name = f"fedtools-{pod_name_regex}"
     try:
         cmd = ["ip", "r"]
-        output = kube_helper.exec_cmd_in_pod(cli, cmd, "fedtools", "default")
+        output = kube_helper.exec_cmd_in_pod(cli, cmd, pod_name, "default")
 
         if not output:
             logging.error("Exception occurred while executing command in pod")
@@ -191,7 +192,7 @@ def get_default_interface(node: str, pod_template, cli: CoreV1Api, image: str) -
 
     finally:
         logging.info("Deleting pod to query interface on node")
-        kube_helper.delete_pod(cli, "fedtools", "default")
+        kube_helper.delete_pod(cli, pod_name, "default")
 
     return interfaces
 
@@ -220,13 +221,15 @@ def verify_interface(
     Returns:
         The interface list for the node
     """
-    pod_body = yaml.safe_load(pod_template.render(nodename=node, image=image))
+    pod_name_regex = str(random.randint(0, 10000))
+    pod_body = yaml.safe_load(pod_template.render(regex_name=pod_name_regex,nodename=node, image=image))
     logging.info("Creating pod to query interface on node %s" % node)
     kube_helper.create_pod(cli, pod_body, "default", 300)
+    pod_name = f"fedtools-{pod_name_regex}"
     try:
         if input_interface_list == []:
             cmd = ["ip", "r"]
-            output = kube_helper.exec_cmd_in_pod(cli, cmd, "fedtools", "default")
+            output = kube_helper.exec_cmd_in_pod(cli, cmd, pod_name, "default")
 
             if not output:
                 logging.error("Exception occurred while executing command in pod")
@@ -242,7 +245,7 @@ def verify_interface(
 
         else:
             cmd = ["ip", "-br", "addr", "show"]
-            output = kube_helper.exec_cmd_in_pod(cli, cmd, "fedtools", "default")
+            output = kube_helper.exec_cmd_in_pod(cli, cmd, pod_name, "default")
 
             if not output:
                 logging.error("Exception occurred while executing command in pod")
@@ -265,7 +268,7 @@ def verify_interface(
                     )
     finally:
         logging.info("Deleting pod to query interface on node")
-        kube_helper.delete_pod(cli, "fedtools", "default")
+        kube_helper.delete_pod(cli, pod_name, "default")
 
     return input_interface_list
 
@@ -431,16 +434,18 @@ def create_virtual_interfaces(
             - The YAML template used to instantiate a pod to create
               virtual interfaces on the node
     """
-    pod_body = yaml.safe_load(pod_template.render(nodename=node, image=image))
+    pod_name_regex = str(random.randint(0, 10000))
+    pod_body = yaml.safe_load(pod_template.render(regex_name=pod_name_regex,nodename=node, image=image))
     kube_helper.create_pod(cli, pod_body, "default", 300)
     logging.info(
         "Creating {0} virtual interfaces on node {1} using a pod".format(
             len(interface_list), node
         )
     )
-    create_ifb(cli, len(interface_list), "modtools")
+    pod_name = f"modtools-{pod_name_regex}"
+    create_ifb(cli, len(interface_list), pod_name)
     logging.info("Deleting pod used to create virtual interfaces")
-    kube_helper.delete_pod(cli, "modtools", "default")
+    kube_helper.delete_pod(cli, pod_name, "default")
 
 
 def delete_virtual_interfaces(
@@ -467,11 +472,13 @@ def delete_virtual_interfaces(
     """
 
     for node in node_list:
-        pod_body = yaml.safe_load(pod_template.render(nodename=node, image=image))
+        pod_name_regex = str(random.randint(0, 10000))
+        pod_body = yaml.safe_load(pod_template.render(regex_name=pod_name_regex,nodename=node, image=image))
         kube_helper.create_pod(cli, pod_body, "default", 300)
         logging.info("Deleting all virtual interfaces on node {0}".format(node))
-        delete_ifb(cli, "modtools")
-        kube_helper.delete_pod(cli, "modtools", "default")
+        pod_name = f"modtools-{pod_name_regex}"
+        delete_ifb(cli, pod_name)
+        kube_helper.delete_pod(cli, pod_name, "default")
 
 
 def create_ifb(cli: CoreV1Api, number: int, pod_name: str):

krkn/scenario_plugins/native/network/pod_interface.j2

@@ -1,7 +1,7 @@
 apiVersion: v1
 kind: Pod
 metadata:
-  name: fedtools
+  name: fedtools-{{regex_name}}
 spec:
   hostNetwork: true
   nodeName: {{nodename}}

krkn/scenario_plugins/native/network/pod_module.j2

@@ -1,7 +1,7 @@
 apiVersion: v1
 kind: Pod
 metadata:
-  name: modtools
+  name: modtools-{{regex_name}}
 spec:
   nodeName: {{nodename}}
   containers:

krkn/scenario_plugins/native/pod_network_outage/kubernetes_functions.py

@@ -23,8 +23,7 @@ def create_job(batch_cli, body, namespace="default"):
     """
 
     try:
-        api_response = batch_cli.create_namespaced_job(
-            body=body, namespace=namespace)
+        api_response = batch_cli.create_namespaced_job(body=body, namespace=namespace)
         return api_response
     except ApiException as api:
         logging.warning(
@@ -71,7 +70,8 @@ def create_pod(cli, body, namespace, timeout=120):
         end_time = time.time() + timeout
         while True:
             pod_stat = cli.read_namespaced_pod(
-                name=body["metadata"]["name"], namespace=namespace)
+                name=body["metadata"]["name"], namespace=namespace
+            )
             if pod_stat.status.phase == "Running":
                 break
             if time.time() > end_time:
@@ -121,16 +121,18 @@ def exec_cmd_in_pod(cli, command, pod_name, namespace, container=None):
     return ret
 
 
-def list_pods(cli, namespace, label_selector=None):
+def list_pods(cli, namespace, label_selector=None, exclude_label=None):
     """
-    Function used to list pods in a given namespace and having a certain label
+    Function used to list pods in a given namespace and having a certain label and excluding pods with exclude_label
+    and excluding pods with exclude_label
     """
 
     pods = []
     try:
         if label_selector:
             ret = cli.list_namespaced_pod(
-                namespace, pretty=True, label_selector=label_selector)
+                namespace, pretty=True, label_selector=label_selector
+            )
         else:
             ret = cli.list_namespaced_pod(namespace, pretty=True)
     except ApiException as e:
@@ -140,7 +142,16 @@ def list_pods(cli, namespace, label_selector=None):
             % e
         )
         raise e
+
     for pod in ret.items:
+        # Skip pods with the exclude label if specified
+        if exclude_label and pod.metadata.labels:
+            exclude_key, exclude_value = exclude_label.split("=", 1)
+            if (
+                exclude_key in pod.metadata.labels
+                and pod.metadata.labels[exclude_key] == exclude_value
+            ):
+                continue
         pods.append(pod.metadata.name)
 
     return pods
@@ -152,8 +163,7 @@ def get_job_status(batch_cli, name, namespace="default"):
     """
 
     try:
-        return batch_cli.read_namespaced_job_status(
-            name=name, namespace=namespace)
+        return batch_cli.read_namespaced_job_status(name=name, namespace=namespace)
     except Exception as e:
         logging.error(
             "Exception when calling \
@@ -169,7 +179,10 @@ def get_pod_log(cli, name, namespace="default"):
     """
 
     return cli.read_namespaced_pod_log(
-        name=name, namespace=namespace, _return_http_data_only=True, _preload_content=False
+        name=name,
+        namespace=namespace,
+        _return_http_data_only=True,
+        _preload_content=False,
     )
 
 
@@ -191,7 +204,8 @@ def delete_job(batch_cli, name, namespace="default"):
             name=name,
             namespace=namespace,
             body=client.V1DeleteOptions(
-                propagation_policy="Foreground", grace_period_seconds=0),
+                propagation_policy="Foreground", grace_period_seconds=0
+            ),
         )
         logging.debug("Job deleted. status='%s'" % str(api_response.status))
         return api_response
@@ -247,11 +261,8 @@ def get_node(node_name, label_selector, instance_kill_count, cli):
         )
     nodes = list_ready_nodes(cli, label_selector)
     if not nodes:
-        raise Exception(
-            "Ready nodes with the provided label selector do not exist")
-    logging.info(
-        "Ready nodes with the label selector %s: %s" % (label_selector, nodes)
-    )
+        raise Exception("Ready nodes with the provided label selector do not exist")
+    logging.info("Ready nodes with the label selector %s: %s" % (label_selector, nodes))
     number_of_nodes = len(nodes)
     if instance_kill_count == number_of_nodes:
         return nodes

krkn/scenario_plugins/native/pod_network_outage/pod_module.j2

@@ -1,7 +1,7 @@
 apiVersion: v1
 kind: Pod
 metadata:
-  name: modtools
+  name: modtools-{{regex_name}}
 spec:
   nodeName: {{nodename}}
   containers:

krkn/scenario_plugins/native/pod_network_outage/pod_network_outage_plugin.py

@@ -19,7 +19,11 @@ from . import cerberus
 
 
 def get_test_pods(
-    pod_name: str, pod_label: str, namespace: str, kubecli: KrknKubernetes
+    pod_name: str,
+    pod_label: str,
+    namespace: str,
+    kubecli: KrknKubernetes,
+    exclude_label: str = None,
 ) -> typing.List[str]:
     """
     Function that returns a list of pods to apply network policy
@@ -38,11 +42,16 @@ def get_test_pods(
         kubecli (KrknKubernetes)
             - Object to interact with Kubernetes Python client
 
+        exclude_label (string)
+            - pods matching this label will be excluded from the outage
+
     Returns:
         pod names (string) in the namespace
     """
     pods_list = []
-    pods_list = kubecli.list_pods(label_selector=pod_label, namespace=namespace)
+    pods_list = kubecli.list_pods(
+        label_selector=pod_label, namespace=namespace, exclude_label=exclude_label
+    )
     if pod_name and pod_name not in pods_list:
         raise Exception("pod name not found in namespace ")
     elif pod_name and pod_name in pods_list:
@@ -226,6 +235,10 @@ def apply_outage_policy(
 
         image (string)
             - Image of network chaos tool
+            
+        exclude_label (string)
+            - pods matching this label will be excluded from the outage
+
     Returns:
         The name of the job created that executes the commands on a node
         for ingress chaos scenario
@@ -324,6 +337,9 @@ def apply_ingress_policy(
         test_execution (String)
             - The order in which the filters are applied
 
+        exclude_label (string)
+            - pods matching this label will be excluded from the outage
+
     Returns:
         The name of the job created that executes the traffic shaping
         filter
@@ -407,6 +423,9 @@ def apply_net_policy(
         test_execution (String)
             - The order in which the filters are applied
 
+        exclude_label (string)
+            - pods matching this label will be excluded from the outage
+
     Returns:
         The name of the job created that executes the traffic shaping
         filter
@@ -466,6 +485,9 @@ def get_ingress_cmd(
         duration (str):
             - Duration for which the traffic control is to be done
 
+        exclude_label (string)
+            - pods matching this label will be excluded from the outage
+
     Returns:
         str: ingress filter
     """
@@ -517,6 +539,9 @@ def get_egress_cmd(
         duration (str):
             - Duration for which the traffic control is to be done
 
+        exclude_label (string)
+            - pods matching this label will be excluded from the outage
+
     Returns:
         str: egress filter
     """
@@ -537,7 +562,7 @@ def get_egress_cmd(
 
 
 def create_virtual_interfaces(
-    kubecli: KrknKubernetes, nummber: int, node: str, pod_template, image: str, 
+    kubecli: KrknKubernetes, number: int, node: str, pod_template, image: str, 
 ) -> None:
     """
     Function that creates a privileged pod and uses it to create
@@ -561,14 +586,16 @@ def create_virtual_interfaces(
         image (string)
             - Image of network chaos tool
     """
-    pod_body = yaml.safe_load(pod_template.render(nodename=node, image=image))
+    pod_name_regex = str(random.randint(0, 10000))
+    pod_body = yaml.safe_load(pod_template.render(regex_name=pod_name_regex, nodename=node, image=image))
     kubecli.create_pod(pod_body, "default", 300)
+    pod_name = f"modtools-{pod_name_regex}"
     logging.info(
-        "Creating {0} virtual interfaces on node {1} using a pod".format(nummber, node)
+        "Creating {0} virtual interfaces on node {1} using a pod".format(number, node)
     )
-    create_ifb(kubecli, nummber, "modtools")
+    create_ifb(kubecli, number, pod_name)
     logging.info("Deleting pod used to create virtual interfaces")
-    kubecli.delete_pod("modtools", "default")
+    kubecli.delete_pod(pod_name, "default")
 
 
 def delete_virtual_interfaces(
@@ -598,11 +625,12 @@ def delete_virtual_interfaces(
     """
 
     for node in node_list:
-        pod_body = yaml.safe_load(pod_template.render(nodename=node, image=image))
+        pod_name_regex = str(random.randint(0, 10000))
+        pod_body = yaml.safe_load(pod_template.render(regex_name=pod_name_regex, nodename=node, image=image))
         kubecli.create_pod(pod_body, "default", 300)
         logging.info("Deleting all virtual interfaces on node {0}".format(node))
-        delete_ifb(kubecli, "modtools")
-        kubecli.delete_pod("modtools", "default")
+        delete_ifb(kubecli, "modtools-" + pod_name_regex)
+        kubecli.delete_pod("modtools-" + pod_name_regex, "default")
 
 
 def create_ifb(kubecli: KrknKubernetes, number: int, pod_name: str):
@@ -649,18 +677,22 @@ def list_bridges(node: str, pod_template, kubecli: KrknKubernetes, image: str) -
 
         image (string)
             - Image of network chaos tool
+            
+        exclude_label (string)
+            - pods matching this label will be excluded from the outage
+
     Returns:
         List of bridges on the node.
     """
-
-    pod_body = yaml.safe_load(pod_template.render(nodename=node, image=image))
+    pod_name_regex = str(random.randint(0, 10000))
+    pod_body = yaml.safe_load(pod_template.render(regex_name=pod_name_regex, nodename=node, image=image))
     logging.info("Creating pod to query bridge on node %s" % node)
     kubecli.create_pod(pod_body, "default", 300)
-
+    pod_name = f"modtools-{pod_name_regex}"
     try:
         cmd = ["/host", "ovs-vsctl", "list-br"]
         output = kubecli.exec_cmd_in_pod(
-            cmd, "modtools", "default", base_command="chroot"
+            cmd, pod_name, "default", base_command="chroot"
         )
 
         if not output:
@@ -671,7 +703,7 @@ def list_bridges(node: str, pod_template, kubecli: KrknKubernetes, image: str) -
 
     finally:
         logging.info("Deleting pod to query interface on node")
-        kubecli.delete_pod("modtools", "default")
+        kubecli.delete_pod(pod_name, "default")
 
     return bridges
 
@@ -704,11 +736,11 @@ def check_cookie(
     Returns
         Returns the matching flow rules
     """
-
-    pod_body = yaml.safe_load(pod_template.render(nodename=node, image=image))
+    pod_name_regex = str(random.randint(0, 10000))
+    pod_body = yaml.safe_load(pod_template.render(regex_name = pod_name_regex,nodename=node, image=image))
     logging.info("Creating pod to query duplicate rules on node %s" % node)
     kubecli.create_pod(pod_body, "default", 300)
-
+    pod_name = f"modtools-{pod_name_regex}"
     try:
         cmd = [
             "chroot",
@@ -721,7 +753,7 @@ def check_cookie(
             f"cookie={cookie}/-1",
         ]
         output = kubecli.exec_cmd_in_pod(
-            cmd, "modtools", "default", base_command="chroot"
+            cmd, pod_name, "default", base_command="chroot"
         )
 
         if not output:
@@ -732,7 +764,7 @@ def check_cookie(
 
     finally:
         logging.info("Deleting pod to query interface on node")
-        kubecli.delete_pod("modtools", "default")
+        kubecli.delete_pod(pod_name, "default")
 
     return flow_list
 
@@ -763,12 +795,12 @@ def get_pod_interface(
     Returns
         Returns the pod interface name
     """
-
-    pod_body = yaml.safe_load(pod_template.render(nodename=node, image=image))
+    pod_name_regex = str(random.randint(0, 10000))
+    pod_body = yaml.safe_load(pod_template.render(regex_name=pod_name_regex, nodename=node, image=image))
     logging.info("Creating pod to query pod interface on node %s" % node)
     kubecli.create_pod(pod_body, "default", 300)
     inf = ""
-
+    pod_name = f"modtools-{pod_name_regex}"
     try:
         if br_name == "br-int":
             find_ip = f"external-ids:ip_addresses={ip}/23"
@@ -786,12 +818,12 @@ def get_pod_interface(
         ]
 
         output = kubecli.exec_cmd_in_pod(
-            cmd, "modtools", "default", base_command="chroot"
+            cmd, pod_name, "default", base_command="chroot"
         )
         if not output:
             cmd = ["/host", "ip", "addr", "show"]
             output = kubecli.exec_cmd_in_pod(
-                cmd, "modtools", "default", base_command="chroot"
+                cmd, pod_name, "default", base_command="chroot"
             )
             for if_str in output.split("\n"):
                 if re.search(ip, if_str):
@@ -800,7 +832,7 @@ def get_pod_interface(
             inf = output
     finally:
         logging.info("Deleting pod to query interface on node")
-        kubecli.delete_pod("modtools", "default")
+        kubecli.delete_pod(pod_name, "default")
     return inf
 
 
@@ -826,6 +858,9 @@ def check_bridge_interface(
         kubecli (KrknKubernetes)
             - Object to interact with Kubernetes Python client
 
+        exclude_label (string)
+            - pods matching this label will be excluded from the outage
+
     Returns:
         Returns True if the bridge is found in the  node.
     """
@@ -919,6 +954,15 @@ class InputParams:
         },
     )
 
+    exclude_label: typing.Optional[str] = field(
+        default=None,
+        metadata={
+            "name": "Exclude label",
+            "description": "Kubernetes label selector for pods to exclude from the chaos. "
+            "Pods matching this label will be excluded even if they match the label_selector",
+        },
+    )
+
     kraken_config: typing.Dict[str, typing.Any] = field(
         default=None,
         metadata={
@@ -1052,7 +1096,11 @@ def pod_outage(
 
         br_name = get_bridge_name(api_ext, custom_obj)
         pods_list = get_test_pods(
-            test_pod_name, test_label_selector, test_namespace, kubecli
+            test_pod_name,
+            test_label_selector,
+            test_namespace,
+            kubecli,
+            params.exclude_label,
         )
 
         while not len(pods_list) <= params.instance_count:
@@ -1173,6 +1221,15 @@ class EgressParams:
         },
     )
 
+    exclude_label: typing.Optional[str] = field(
+        default=None,
+        metadata={
+            "name": "Exclude label",
+            "description": "Kubernetes label selector for pods to exclude from the chaos. "
+            "Pods matching this label will be excluded even if they match the label_selector",
+        },
+    )
+
     kraken_config: typing.Dict[str, typing.Any] = field(
         default=None,
         metadata={
@@ -1311,7 +1368,11 @@ def pod_egress_shaping(
 
         br_name = get_bridge_name(api_ext, custom_obj)
         pods_list = get_test_pods(
-            test_pod_name, test_label_selector, test_namespace, kubecli
+            test_pod_name,
+            test_label_selector,
+            test_namespace,
+            kubecli,
+            params.exclude_label,
         )
 
         while not len(pods_list) <= params.instance_count:
@@ -1447,6 +1508,15 @@ class IngressParams:
         },
     )
 
+    exclude_label: typing.Optional[str] = field(
+        default=None,
+        metadata={
+            "name": "Exclude label",
+            "description": "Kubernetes label selector for pods to exclude from the chaos. "
+            "Pods matching this label will be excluded even if they match the label_selector",
+        },
+    )
+
     kraken_config: typing.Dict[str, typing.Any] = field(
         default=None,
         metadata={
@@ -1586,7 +1656,11 @@ def pod_ingress_shaping(
 
         br_name = get_bridge_name(api_ext, custom_obj)
         pods_list = get_test_pods(
-            test_pod_name, test_label_selector, test_namespace, kubecli
+            test_pod_name,
+            test_label_selector,
+            test_namespace,
+            kubecli,
+            params.exclude_label,
         )
 
         while not len(pods_list) <= params.instance_count:

krkn/scenario_plugins/network_chaos/network_chaos_scenario_plugin.py

@@ -161,17 +161,19 @@ class NetworkChaosScenarioPlugin(AbstractScenarioPlugin):
         self, test_interface, nodelst, template, kubecli: KrknKubernetes, image: str
     ):
         pod_index = random.randint(0, len(nodelst) - 1)
-        pod_body = yaml.safe_load(template.render(nodename=nodelst[pod_index], image=image))
+        pod_name_regex = str(random.randint(0, 10000))
+        pod_body = yaml.safe_load(template.render(regex_name=pod_name_regex,nodename=nodelst[pod_index], image=image))
         logging.info("Creating pod to query interface on node %s" % nodelst[pod_index])
         kubecli.create_pod(pod_body, "default", 300)
+        pod_name = f"fedtools-{pod_name_regex}"
         try:
             if test_interface == []:
                 cmd = "ip r | grep default | awk '/default/ {print $5}'"
-                output = kubecli.exec_cmd_in_pod(cmd, "fedtools", "default")
+                output = kubecli.exec_cmd_in_pod(cmd, pod_name, "default")
                 test_interface = [output.replace("\n", "")]
             else:
                 cmd = "ip -br addr show|awk -v ORS=',' '{print $1}'"
-                output = kubecli.exec_cmd_in_pod(cmd, "fedtools", "default")
+                output = kubecli.exec_cmd_in_pod(cmd, pod_name, "default")
                 interface_lst = output[:-1].split(",")
                 for interface in test_interface:
                     if interface not in interface_lst:
@@ -183,7 +185,7 @@ class NetworkChaosScenarioPlugin(AbstractScenarioPlugin):
             return test_interface
         finally:
             logging.info("Deleting pod to query interface on node")
-            kubecli.delete_pod("fedtools", "default")
+            kubecli.delete_pod(pod_name, "default")
 
     # krkn_lib
     def get_job_pods(self, api_response, kubecli: KrknKubernetes):

krkn/scenario_plugins/network_chaos/pod.j2

@@ -1,7 +1,7 @@
 apiVersion: v1
 kind: Pod
 metadata:
-  name: fedtools
+  name: fedtools-{{regex_name}}
 spec:
   hostNetwork: true
   nodeName: {{nodename}}

krkn/scenario_plugins/network_chaos_ng/modules/pod_network_filter.py

@@ -1,3 +1,4 @@
+import logging
 import queue
 import time
 
@@ -12,10 +13,9 @@ from krkn.scenario_plugins.network_chaos_ng.models import (
 from krkn.scenario_plugins.network_chaos_ng.modules.abstract_network_chaos_module import (
     AbstractNetworkChaosModule,
 )
-from krkn.scenario_plugins.network_chaos_ng.modules.utils import log_info
+from krkn.scenario_plugins.network_chaos_ng.modules.utils import log_info, log_error
 from krkn.scenario_plugins.network_chaos_ng.modules.utils_network_filter import (
     deploy_network_filter_pod,
-    get_default_interface,
     generate_namespaced_rules,
     apply_network_rules,
     clean_network_rules_namespaced,
@@ -56,23 +56,28 @@ class PodNetworkFilterModule(AbstractNetworkChaosModule):
                 pod_name,
                 self.kubecli.get_lib_kubernetes(),
                 container_name,
+                host_network=False,
             )
 
             if len(self.config.interfaces) == 0:
-                interfaces = [
-                    get_default_interface(
-                        pod_name,
-                        self.config.namespace,
-                        self.kubecli.get_lib_kubernetes(),
+                interfaces = (
+                    self.kubecli.get_lib_kubernetes().list_pod_network_interfaces(
+                        target, self.config.namespace
                     )
-                ]
+                )
 
+                if len(interfaces) == 0:
+                    log_error(
+                        "no network interface found in pod, impossible to execute the network filter scenario",
+                        parallel,
+                        pod_name,
+                    )
+                    return
                 log_info(
-                    f"detected default interface {interfaces[0]}",
+                    f"detected network interfaces: {','.join(interfaces)}",
                     parallel,
                     pod_name,
                 )
-
             else:
                 interfaces = self.config.interfaces
 

krkn/scenario_plugins/network_chaos_ng/modules/utils.py

@@ -11,7 +11,7 @@ def log_info(message: str, parallel: bool = False, node_name: str = ""):
         logging.info(message)
 
 
-def log_error(self, message: str, parallel: bool = False, node_name: str = ""):
+def log_error(message: str, parallel: bool = False, node_name: str = ""):
     """
     log helper method for ERROR severity to be used in the scenarios
     """
@@ -21,7 +21,7 @@ def log_error(self, message: str, parallel: bool = False, node_name: str = ""):
         logging.error(message)
 
 
-def log_warning(self, message: str, parallel: bool = False, node_name: str = ""):
+def log_warning(message: str, parallel: bool = False, node_name: str = ""):
     """
     log helper method for WARNING severity to be used in the scenarios
     """

krkn/scenario_plugins/network_chaos_ng/modules/utils_network_filter.py

@@ -54,6 +54,7 @@ def deploy_network_filter_pod(
     pod_name: str,
     kubecli: KrknKubernetes,
     container_name: str = "fedora",
+    host_network: bool = True,
 ):
     file_loader = FileSystemLoader(os.path.abspath(os.path.dirname(__file__)))
     env = Environment(loader=file_loader, autoescape=True)
@@ -78,17 +79,16 @@ def deploy_network_filter_pod(
             toleration["value"] = value
         tolerations.append(toleration)
 
-
     pod_body = yaml.safe_load(
         pod_template.render(
             pod_name=pod_name,
             namespace=config.namespace,
-            host_network=True,
+            host_network=host_network,
             target=target_node,
             container_name=container_name,
             workload_image=config.image,
             taints=tolerations,
-            service_account=config.service_account
+            service_account=config.service_account,
         )
     )
 

krkn/scenario_plugins/node_actions/abstract_node_scenarios.py

@@ -60,7 +60,7 @@ class abstract_node_scenarios:
         pass
 
     # Node scenario to reboot the node
-    def node_reboot_scenario(self, instance_kill_count, node, timeout):
+    def node_reboot_scenario(self, instance_kill_count, node, timeout, soft_reboot=False):
         pass
 
     # Node scenario to stop the kubelet

krkn/scenario_plugins/node_actions/alibaba_node_scenarios.py

@@ -316,7 +316,7 @@ class alibaba_node_scenarios(abstract_node_scenarios):
             self.affected_nodes_status.affected_nodes.append(affected_node)
 
     # Node scenario to reboot the node
-    def node_reboot_scenario(self, instance_kill_count, node, timeout):
+    def node_reboot_scenario(self, instance_kill_count, node, timeout, soft_reboot=False):
         for _ in range(instance_kill_count):
             affected_node = AffectedNode(node)
             try:

krkn/scenario_plugins/node_actions/aws_node_scenarios.py

@@ -358,7 +358,7 @@ class aws_node_scenarios(abstract_node_scenarios):
             self.affected_nodes_status.affected_nodes.append(affected_node)
 
     # Node scenario to reboot the node
-    def node_reboot_scenario(self, instance_kill_count, node, timeout):
+    def node_reboot_scenario(self, instance_kill_count, node, timeout, soft_reboot=False):
         for _ in range(instance_kill_count):
             affected_node = AffectedNode(node)
             try:

krkn/scenario_plugins/node_actions/az_node_scenarios.py

@@ -308,7 +308,7 @@ class azure_node_scenarios(abstract_node_scenarios):
 
 
     # Node scenario to reboot the node
-    def node_reboot_scenario(self, instance_kill_count, node, timeout):
+    def node_reboot_scenario(self, instance_kill_count, node, timeout, soft_reboot=False):
         for _ in range(instance_kill_count):
             affected_node = AffectedNode(node)
             try:

krkn/scenario_plugins/node_actions/bm_node_scenarios.py

@@ -214,7 +214,7 @@ class bm_node_scenarios(abstract_node_scenarios):
         logging.info("Node termination scenario is not supported on baremetal")
 
     # Node scenario to reboot the node
-    def node_reboot_scenario(self, instance_kill_count, node, timeout):
+    def node_reboot_scenario(self, instance_kill_count, node, timeout, soft_reboot=False):
         for _ in range(instance_kill_count):
             affected_node = AffectedNode(node)
             try:

krkn/scenario_plugins/node_actions/common_node_functions.py

@@ -16,20 +16,22 @@ def get_node_by_name(node_name_list, kubecli: KrknKubernetes):
             )
             return
     return node_name_list
-        
+
 
 # Pick a random node with specified label selector
 def get_node(label_selector, instance_kill_count, kubecli: KrknKubernetes):
 
-    label_selector_list  = label_selector.split(",")
+    label_selector_list = label_selector.split(",")
     nodes = []
-    for label_selector in label_selector_list: 
+    for label_selector in label_selector_list:
         nodes.extend(kubecli.list_killable_nodes(label_selector))
     if not nodes:
         raise Exception("Ready nodes with the provided label selector do not exist")
-    logging.info("Ready nodes with the label selector %s: %s" % (label_selector_list, nodes))
+    logging.info(
+        "Ready nodes with the label selector %s: %s" % (label_selector_list, nodes)
+    )
     number_of_nodes = len(nodes)
-    if instance_kill_count == number_of_nodes:
+    if instance_kill_count == number_of_nodes or instance_kill_count == 0:
         return nodes
     nodes_to_return = []
     for i in range(instance_kill_count):
@@ -38,23 +40,30 @@ def get_node(label_selector, instance_kill_count, kubecli: KrknKubernetes):
         nodes.remove(node_to_add)
     return nodes_to_return
 
+
 # krkn_lib
 # Wait until the node status becomes Ready
-def wait_for_ready_status(node, timeout, kubecli: KrknKubernetes, affected_node: AffectedNode = None):
-    affected_node =  kubecli.watch_node_status(node, "True", timeout, affected_node)
+def wait_for_ready_status(
+    node, timeout, kubecli: KrknKubernetes, affected_node: AffectedNode = None
+):
+    affected_node = kubecli.watch_node_status(node, "True", timeout, affected_node)
     return affected_node
-   
+
 
 # krkn_lib
 # Wait until the node status becomes Not Ready
-def wait_for_not_ready_status(node, timeout, kubecli: KrknKubernetes, affected_node: AffectedNode = None):
+def wait_for_not_ready_status(
+    node, timeout, kubecli: KrknKubernetes, affected_node: AffectedNode = None
+):
     affected_node = kubecli.watch_node_status(node, "False", timeout, affected_node)
     return affected_node
-    
+
 
 # krkn_lib
 # Wait until the node status becomes Unknown
-def wait_for_unknown_status(node, timeout, kubecli: KrknKubernetes, affected_node: AffectedNode = None):
+def wait_for_unknown_status(
+    node, timeout, kubecli: KrknKubernetes, affected_node: AffectedNode = None
+):
     affected_node = kubecli.watch_node_status(node, "Unknown", timeout, affected_node)
     return affected_node
 

krkn/scenario_plugins/node_actions/docker_node_scenarios.py

@@ -120,7 +120,7 @@ class docker_node_scenarios(abstract_node_scenarios):
                 raise e
 
     # Node scenario to reboot the node
-    def node_reboot_scenario(self, instance_kill_count, node, timeout):
+    def node_reboot_scenario(self, instance_kill_count, node, timeout, soft_reboot=False):
         for _ in range(instance_kill_count):
             affected_node = AffectedNode(node)
             try:

krkn/scenario_plugins/node_actions/gcp_node_scenarios.py

@@ -321,7 +321,7 @@ class gcp_node_scenarios(abstract_node_scenarios):
             self.affected_nodes_status.affected_nodes.append(affected_node)
 
     # Node scenario to reboot the node
-    def node_reboot_scenario(self, instance_kill_count, node, timeout):
+    def node_reboot_scenario(self, instance_kill_count, node, timeout, soft_reboot=False):
         for _ in range(instance_kill_count):
             affected_node = AffectedNode(node)
             try:

krkn/scenario_plugins/node_actions/general_cloud_node_scenarios.py

@@ -39,7 +39,7 @@ class general_node_scenarios(abstract_node_scenarios):
         )
 
     # Node scenario to reboot the node
-    def node_reboot_scenario(self, instance_kill_count, node, timeout):
+    def node_reboot_scenario(self, instance_kill_count, node, timeout, soft_reboot=False):
         logging.info(
             "Node reboot is not set up yet for this cloud type,"
             " no action is going to be taken"

krkn/scenario_plugins/node_actions/ibmcloud_node_scenarios.py

@@ -338,7 +338,7 @@ class ibm_node_scenarios(abstract_node_scenarios):
             logging.error("node_stop_scenario injection failed!")
 
 
-    def node_reboot_scenario(self, instance_kill_count, node, timeout):
+    def node_reboot_scenario(self, instance_kill_count, node, timeout, soft_reboot=False):
         try:
             instance_id = self.ibmcloud.get_instance_id(node)
             for _ in range(instance_kill_count):

krkn/scenario_plugins/node_actions/ibmcloud_power_node_scenarios.py

@@ -0,0 +1,403 @@
+#!/usr/bin/env python
+import time
+from os import environ
+from dataclasses import dataclass
+import logging
+
+from krkn_lib.k8s import KrknKubernetes
+import krkn.scenario_plugins.node_actions.common_node_functions as nodeaction
+from krkn.scenario_plugins.node_actions.abstract_node_scenarios import (
+    abstract_node_scenarios,
+)
+import requests
+import sys
+import json
+
+
+#  -o, --operation string   Operation to be done in a PVM server instance. 
+# Valid values are: hard-reboot, immediate-shutdown, soft-reboot, reset-state, start, stop.
+
+from krkn_lib.models.k8s import AffectedNodeStatus, AffectedNode
+
+
+class IbmCloudPower:
+    def __init__(self):
+        """
+        Initialize the ibm cloud client by using the the env variables:
+            'IBMC_APIKEY' 'IBMC_URL'
+        """
+        self.api_key = environ.get("IBMC_APIKEY")
+        self.service_url = environ.get("IBMC_POWER_URL")
+        self.CRN = environ.get("IBMC_POWER_CRN")
+        self.cloud_instance_id = self.CRN.split(":")[-3]
+        print(self.cloud_instance_id)
+        self.headers = None
+        self.token = None
+        if not self.api_key:
+            raise Exception("Environmental variable 'IBMC_APIKEY' is not set")
+        if not self.service_url:
+            raise Exception("Environmental variable 'IBMC_POWER_URL' is not set")
+        if not self.CRN:
+            raise Exception("Environmental variable 'IBMC_POWER_CRN' is not set")
+        try:
+            self.authenticate()
+            
+        except Exception as e:
+            logging.error("error authenticating" + str(e))
+    
+    def authenticate(self):
+        url = "https://iam.cloud.ibm.com/identity/token"
+        iam_auth_headers = {
+            "content-type": "application/x-www-form-urlencoded",
+            "accept": "application/json",
+        }
+        data = {
+            "grant_type": "urn:ibm:params:oauth:grant-type:apikey",
+            "apikey": self.api_key,
+        }
+
+        response = self._make_request("POST", url, data=data, headers=iam_auth_headers)
+        if response.status_code == 200:
+            self.token = response.json()
+            self.headers = {
+                "Authorization": f"Bearer {self.token['access_token']}",
+                "Content-Type": "application/json",
+                "CRN": self.CRN,
+            }
+        else:
+            logging.error(f"Authentication Error: {response.status_code}")
+            return None, None
+            
+
+    def _make_request(self,method, url, data=None, headers=None):
+        try:
+            response = requests.request(method, url, data=data, headers=headers)
+            response.raise_for_status()
+            return response
+        except Exception as e:
+            raise Exception(f"API Error: {e}")
+
+    # Get the instance ID of the node
+    def get_instance_id(self, node_name):
+
+        url = f"{self.service_url}/pcloud/v1/cloud-instances/{self.cloud_instance_id}/pvm-instances/"
+        response = self._make_request("GET", url, headers=self.headers)
+        for node in response.json()["pvmInstances"]:
+            if node_name == node["serverName"]:
+                return node["pvmInstanceID"]
+        logging.error("Couldn't find node with name " + str(node_name) + ", you could try another region")
+        sys.exit(1)
+
+    def delete_instance(self, instance_id):
+        """
+        Deletes the Instance whose name is given by 'instance_id'
+        """
+        try:
+            url = f"{self.service_url}/pcloud/v1/cloud-instances/{self.cloud_instance_id}/pvm-instances/{instance_id}/action"
+            self._make_request("POST", url, headers=self.headers, data=json.dumps({"action": "immediate-shutdown"}))
+            logging.info("Deleted Instance -- '{}'".format(instance_id))
+        except Exception as e:
+            logging.info("Instance '{}' could not be deleted. ".format(instance_id))
+            return False
+
+    def reboot_instances(self, instance_id, soft=False):
+        """
+        Reboots the Instance whose name is given by 'instance_id'. Returns True if successful, or
+        returns False if the Instance is not powered on
+        """
+
+        try:
+            if soft:
+                action = "soft-reboot"
+            else:
+                action = "hard-reboot"
+            url = f"{self.service_url}/pcloud/v1/cloud-instances/{self.cloud_instance_id}/pvm-instances/{instance_id}/action"
+            self._make_request("POST", url, headers=self.headers, data=json.dumps({"action": action}))
+            logging.info("Reset Instance -- '{}'".format(instance_id))
+            return True
+        except Exception as e:
+            logging.info("Instance '{}' could not be rebooted".format(instance_id))
+            return False
+
+    def stop_instances(self, instance_id):
+        """
+        Stops the Instance whose name is given by 'instance_id'. Returns True if successful, or
+        returns False if the Instance is already stopped
+        """
+
+        try:
+            url = f"{self.service_url}/pcloud/v1/cloud-instances/{self.cloud_instance_id}/pvm-instances/{instance_id}/action"
+            self._make_request("POST", url, headers=self.headers, data=json.dumps({"action": "stop"}))
+            logging.info("Stopped Instance -- '{}'".format(instance_id))
+            return True
+        except Exception as e:
+            logging.info("Instance '{}' could not be stopped".format(instance_id))
+            logging.info("error" + str(e))
+            return False
+
+    def start_instances(self, instance_id):
+        """
+        Stops the Instance whose name is given by 'instance_id'. Returns True if successful, or
+        returns False if the Instance is already running
+        """
+
+        try:
+            url = f"{self.service_url}/pcloud/v1/cloud-instances/{self.cloud_instance_id}/pvm-instances/{instance_id}/action"
+            self._make_request("POST", url, headers=self.headers, data=json.dumps({"action": "start"}))
+            logging.info("Started Instance -- '{}'".format(instance_id))
+            return True
+        except Exception as e:
+            logging.info("Instance '{}' could not start running".format(instance_id))
+            return False
+
+    def list_instances(self):
+        """
+        Returns a list of Instances present in the datacenter
+        """
+        instance_names = []
+        try:
+            url = f"{self.service_url}/pcloud/v1/cloud-instances/{self.cloud_instance_id}/pvm-instances/"
+            response = self._make_request("GET", url, headers=self.headers)
+            for pvm in response.json()["pvmInstances"]:
+                instance_names.append({"serverName": pvm.serverName, "pvmInstanceID": pvm.pvmInstanceID})
+        except Exception as e:
+            logging.error("Error listing out instances: " + str(e))
+            sys.exit(1)
+        return instance_names
+
+    def find_id_in_list(self, name, vpc_list):
+        for vpc in vpc_list:
+            if vpc["vpc_name"] == name:
+                return vpc["vpc_id"]
+
+    def get_instance_status(self, instance_id):
+        """
+        Returns the status of the Instance whose name is given by 'instance_id'
+        """
+
+        try:
+            url = f"{self.service_url}/pcloud/v1/cloud-instances/{self.cloud_instance_id}/pvm-instances/{instance_id}"
+            response = self._make_request("GET", url, headers=self.headers)
+            state = response.json()["status"]
+            return state
+        except Exception as e:
+            logging.error(
+                "Failed to get node instance status %s. Encountered following "
+                "exception: %s." % (instance_id, e)
+            )
+            return None
+
+    def wait_until_deleted(self, instance_id, timeout, affected_node=None):
+        """
+        Waits until the instance is deleted or until the timeout. Returns True if
+        the instance is successfully deleted, else returns False
+        """
+        start_time = time.time()
+        time_counter = 0
+        vpc = self.get_instance_status(instance_id)
+        while vpc is not None:
+            vpc = self.get_instance_status(instance_id)
+            logging.info(
+                "Instance %s is still being deleted, sleeping for 5 seconds"
+                % instance_id
+            )
+            time.sleep(5)
+            time_counter += 5
+            if time_counter >= timeout:
+                logging.info(
+                    "Instance %s is still not deleted in allotted time" % instance_id
+                )
+                return False
+        end_time = time.time()
+        if affected_node:
+            affected_node.set_affected_node_status("terminated", end_time - start_time)
+        return True
+
+    def wait_until_running(self, instance_id, timeout, affected_node=None):
+        """
+        Waits until the Instance switches to running state or until the timeout.
+        Returns True if the Instance switches to running, else returns False
+        """
+        start_time = time.time()
+        time_counter = 0
+        status = self.get_instance_status(instance_id)
+        while status != "ACTIVE":
+            status = self.get_instance_status(instance_id)
+            logging.info(
+                "Instance %s is still not running, sleeping for 5 seconds" % instance_id
+            )
+            time.sleep(5)
+            time_counter += 5
+            if time_counter >= timeout:
+                logging.info(
+                    "Instance %s is still not ready in allotted time" % instance_id
+                )
+                return False
+        end_time = time.time()
+        if affected_node:
+            affected_node.set_affected_node_status("running", end_time - start_time)
+        return True
+
+    def wait_until_stopped(self, instance_id, timeout, affected_node):
+        """
+        Waits until the Instance switches to stopped state or until the timeout.
+        Returns True if the Instance switches to stopped, else returns False
+        """
+        start_time = time.time()
+        time_counter = 0
+        status = self.get_instance_status(instance_id)
+        while status != "STOPPED":
+            status = self.get_instance_status(instance_id)
+            logging.info(
+                "Instance %s is still not stopped, sleeping for 5 seconds" % instance_id
+            )
+            time.sleep(5)
+            time_counter += 5
+            if time_counter >= timeout:
+                logging.info(
+                    "Instance %s is still not stopped in allotted time" % instance_id
+                )
+                return False
+        end_time = time.time()
+        print('affected_node' + str(affected_node))
+        if affected_node:
+            affected_node.set_affected_node_status("stopped", end_time - start_time)
+        return True
+
+
+    def wait_until_rebooted(self, instance_id, timeout, affected_node):
+        """
+        Waits until the Instance switches to restarting state and then running state or until the timeout.
+        Returns True if the Instance switches back to running, else returns False
+        """
+
+        time_counter = 0
+        status = self.get_instance_status(instance_id)
+        while status == "HARD_REBOOT" or status == "SOFT_REBOOT":
+            status = self.get_instance_status(instance_id)
+            logging.info(
+                "Instance %s is still restarting, sleeping for 5 seconds" % instance_id
+            )
+            time.sleep(5)
+            time_counter += 5
+            if time_counter >= timeout:
+                logging.info(
+                    "Instance %s is still restarting after allotted time" % instance_id
+                )
+                return False
+        self.wait_until_running(instance_id, timeout, affected_node)
+        print('affected_node' + str(affected_node))
+        return True
+
+
+@dataclass
+class ibmcloud_power_node_scenarios(abstract_node_scenarios):
+    def __init__(self, kubecli: KrknKubernetes, node_action_kube_check: bool, affected_nodes_status: AffectedNodeStatus, disable_ssl_verification: bool):
+        super().__init__(kubecli, node_action_kube_check, affected_nodes_status)
+        self.ibmcloud_power = IbmCloudPower()
+        
+        self.node_action_kube_check = node_action_kube_check
+
+    def node_start_scenario(self, instance_kill_count, node, timeout):
+        try:
+            instance_id = self.ibmcloud_power.get_instance_id( node)
+            affected_node = AffectedNode(node, node_id=instance_id)
+            for _ in range(instance_kill_count):
+                logging.info("Starting node_start_scenario injection")
+                logging.info("Starting the node %s " % (node))
+                
+                if instance_id:
+                    vm_started = self.ibmcloud_power.start_instances(instance_id)
+                    if vm_started:
+                        self.ibmcloud_power.wait_until_running(instance_id, timeout, affected_node)
+                        if self.node_action_kube_check: 
+                            nodeaction.wait_for_ready_status(
+                                node, timeout, self.kubecli, affected_node
+                            )
+                    logging.info(
+                        "Node with instance ID: %s is in running state" % node
+                    )
+                    logging.info(
+                        "node_start_scenario has been successfully injected!"
+                    )
+                else:
+                    logging.error(
+                        "Failed to find node that matched instances on ibm cloud in region"
+                    )
+
+        except Exception as e:
+            logging.error("Failed to start node instance. Test Failed")
+            logging.error("node_start_scenario injection failed!")
+        self.affected_nodes_status.affected_nodes.append(affected_node)
+
+
+    def node_stop_scenario(self, instance_kill_count, node, timeout):
+        try:
+            instance_id = self.ibmcloud_power.get_instance_id(node)
+            for _ in range(instance_kill_count):
+                affected_node = AffectedNode(node, instance_id)
+                logging.info("Starting node_stop_scenario injection")
+                logging.info("Stopping the node %s " % (node))
+                vm_stopped = self.ibmcloud_power.stop_instances(instance_id)
+                if vm_stopped:
+                    self.ibmcloud_power.wait_until_stopped(instance_id, timeout, affected_node)
+                logging.info(
+                    "Node with instance ID: %s is in stopped state" % node
+                )
+                logging.info(
+                    "node_stop_scenario has been successfully injected!"
+                )
+        except Exception as e:
+            logging.error("Failed to stop node instance. Test Failed")
+            logging.error("node_stop_scenario injection failed!")
+
+
+    def node_reboot_scenario(self, instance_kill_count, node, timeout, soft_reboot=False):
+        try:
+            instance_id = self.ibmcloud_power.get_instance_id(node)
+            for _ in range(instance_kill_count):
+                affected_node = AffectedNode(node, node_id=instance_id)
+                logging.info("Starting node_reboot_scenario injection")
+                logging.info("Rebooting the node %s " % (node))
+                self.ibmcloud_power.reboot_instances(instance_id, soft_reboot)
+                self.ibmcloud_power.wait_until_rebooted(instance_id, timeout, affected_node)
+                if self.node_action_kube_check:
+                    nodeaction.wait_for_unknown_status(
+                        node, timeout, affected_node
+                    )
+                    nodeaction.wait_for_ready_status(
+                        node, timeout, affected_node
+                    )
+                logging.info(
+                    "Node with instance ID: %s has rebooted successfully" % node
+                )
+                logging.info(
+                    "node_reboot_scenario has been successfully injected!"
+                )
+
+        except Exception as e:
+            logging.error("Failed to reboot node instance. Test Failed")
+            logging.error("node_reboot_scenario injection failed!")
+
+
+    def node_terminate_scenario(self, instance_kill_count, node, timeout):
+        try:
+            instance_id = self.ibmcloud_power.get_instance_id(node)
+            for _ in range(instance_kill_count):
+                affected_node = AffectedNode(node, node_id=instance_id)
+                logging.info(
+                    "Starting node_termination_scenario injection by first stopping the node"
+                )
+                logging.info("Deleting the node with instance ID: %s " % (node))
+                self.ibmcloud_power.delete_instance(instance_id)
+                self.ibmcloud_power.wait_until_deleted(node, timeout, affected_node)
+                logging.info(
+                    "Node with instance ID: %s has been released" % node
+                )
+                logging.info(
+                    "node_terminate_scenario has been successfully injected!"
+                )
+        except Exception as e:
+            logging.error("Failed to terminate node instance. Test Failed")
+            logging.error("node_terminate_scenario injection failed!")
+

krkn/scenario_plugins/node_actions/node_actions_scenario_plugin.py

@@ -22,8 +22,16 @@ from krkn.scenario_plugins.node_actions.gcp_node_scenarios import gcp_node_scena
 from krkn.scenario_plugins.node_actions.general_cloud_node_scenarios import (
     general_node_scenarios,
 )
-from krkn.scenario_plugins.node_actions.vmware_node_scenarios import vmware_node_scenarios
-from krkn.scenario_plugins.node_actions.ibmcloud_node_scenarios import ibm_node_scenarios
+from krkn.scenario_plugins.node_actions.vmware_node_scenarios import (
+    vmware_node_scenarios,
+)
+from krkn.scenario_plugins.node_actions.ibmcloud_node_scenarios import (
+    ibm_node_scenarios,
+)
+
+from krkn.scenario_plugins.node_actions.ibmcloud_power_node_scenarios import (
+     ibmcloud_power_node_scenarios,
+)
 node_general = False
 
 
@@ -63,29 +71,39 @@ class NodeActionsScenarioPlugin(AbstractScenarioPlugin):
     def get_node_scenario_object(self, node_scenario, kubecli: KrknKubernetes):
         affected_nodes_status = AffectedNodeStatus()
 
-        node_action_kube_check = get_yaml_item_value(node_scenario,"kube_check",True)
+        node_action_kube_check = get_yaml_item_value(node_scenario, "kube_check", True)
         if (
             "cloud_type" not in node_scenario.keys()
             or node_scenario["cloud_type"] == "generic"
         ):
             global node_general
             node_general = True
-            return general_node_scenarios(kubecli, node_action_kube_check, affected_nodes_status)
+            return general_node_scenarios(
+                kubecli, node_action_kube_check, affected_nodes_status
+            )
         if node_scenario["cloud_type"].lower() == "aws":
-            return aws_node_scenarios(kubecli, node_action_kube_check, affected_nodes_status)
+            return aws_node_scenarios(
+                kubecli, node_action_kube_check, affected_nodes_status
+            )
         elif node_scenario["cloud_type"].lower() == "gcp":
-            return gcp_node_scenarios(kubecli, node_action_kube_check, affected_nodes_status)
+            return gcp_node_scenarios(
+                kubecli, node_action_kube_check, affected_nodes_status
+            )
         elif node_scenario["cloud_type"].lower() == "openstack":
             from krkn.scenario_plugins.node_actions.openstack_node_scenarios import (
                 openstack_node_scenarios,
             )
 
-            return openstack_node_scenarios(kubecli, node_action_kube_check, affected_nodes_status)
+            return openstack_node_scenarios(
+                kubecli, node_action_kube_check, affected_nodes_status
+            )
         elif (
             node_scenario["cloud_type"].lower() == "azure"
             or node_scenario["cloud_type"].lower() == "az"
         ):
-            return azure_node_scenarios(kubecli, node_action_kube_check, affected_nodes_status)
+            return azure_node_scenarios(
+                kubecli, node_action_kube_check, affected_nodes_status
+            )
         elif (
             node_scenario["cloud_type"].lower() == "alibaba"
             or node_scenario["cloud_type"].lower() == "alicloud"
@@ -94,7 +112,9 @@ class NodeActionsScenarioPlugin(AbstractScenarioPlugin):
                 alibaba_node_scenarios,
             )
 
-            return alibaba_node_scenarios(kubecli, node_action_kube_check, affected_nodes_status)
+            return alibaba_node_scenarios(
+                kubecli, node_action_kube_check, affected_nodes_status
+            )
         elif node_scenario["cloud_type"].lower() == "bm":
             from krkn.scenario_plugins.node_actions.bm_node_scenarios import (
                 bm_node_scenarios,
@@ -106,22 +126,31 @@ class NodeActionsScenarioPlugin(AbstractScenarioPlugin):
                 node_scenario.get("bmc_password", None),
                 kubecli,
                 node_action_kube_check,
-                affected_nodes_status
+                affected_nodes_status,
             )
         elif node_scenario["cloud_type"].lower() == "docker":
-            return docker_node_scenarios(kubecli,node_action_kube_check,
-                affected_nodes_status)
+            return docker_node_scenarios(
+                kubecli, node_action_kube_check, affected_nodes_status
+            )
         elif (
             node_scenario["cloud_type"].lower() == "vsphere"
             or node_scenario["cloud_type"].lower() == "vmware"
         ):
-            return vmware_node_scenarios(kubecli, node_action_kube_check,affected_nodes_status)
+            return vmware_node_scenarios(
+                kubecli, node_action_kube_check, affected_nodes_status
+            )
         elif (
             node_scenario["cloud_type"].lower() == "ibm"
             or node_scenario["cloud_type"].lower() == "ibmcloud"
         ):
             disable_ssl_verification = get_yaml_item_value(node_scenario, "disable_ssl_verification", True)
             return ibm_node_scenarios(kubecli, node_action_kube_check, affected_nodes_status, disable_ssl_verification)
+        elif (
+            node_scenario["cloud_type"].lower() == "ibmpower"
+            or node_scenario["cloud_type"].lower() == "ibmcloudpower"
+        ):
+            disable_ssl_verification = get_yaml_item_value(node_scenario, "disable_ssl_verification", True)
+            return ibmcloud_power_node_scenarios(kubecli, node_action_kube_check, affected_nodes_status, disable_ssl_verification)
         else:
             logging.error(
                 "Cloud type "
@@ -139,16 +168,22 @@ class NodeActionsScenarioPlugin(AbstractScenarioPlugin):
             )
 
     def inject_node_scenario(
-        self, action, node_scenario, node_scenario_object, kubecli: KrknKubernetes, scenario_telemetry: ScenarioTelemetry
+        self,
+        action,
+        node_scenario,
+        node_scenario_object,
+        kubecli: KrknKubernetes,
+        scenario_telemetry: ScenarioTelemetry,
     ):
-        
+
         # Get the node scenario configurations for setting nodes
-       
+
         instance_kill_count = get_yaml_item_value(node_scenario, "instance_count", 1)
         node_name = get_yaml_item_value(node_scenario, "node_name", "")
         label_selector = get_yaml_item_value(node_scenario, "label_selector", "")
+        exclude_label = get_yaml_item_value(node_scenario, "exclude_label", "")
         parallel_nodes = get_yaml_item_value(node_scenario, "parallel", False)
-        
+
         # Get the node to apply the scenario
         if node_name:
             node_name_list = node_name.split(",")
@@ -157,11 +192,22 @@ class NodeActionsScenarioPlugin(AbstractScenarioPlugin):
             nodes = common_node_functions.get_node(
                 label_selector, instance_kill_count, kubecli
             )
-        
-        # GCP api doesn't support multiprocessing calls, will only actually run 1 
+            if exclude_label:
+                exclude_nodes = common_node_functions.get_node(
+                    exclude_label, 0, kubecli
+                )
+
+                for node in nodes:
+                    if node in exclude_nodes:
+                        logging.info(
+                            f"excluding node {node} with exclude label {exclude_nodes}"
+                        )
+                        nodes.remove(node)
+
+        # GCP api doesn't support multiprocessing calls, will only actually run 1
         if parallel_nodes:
             self.multiprocess_nodes(nodes, node_scenario_object, action, node_scenario)
-        else: 
+        else:
             for single_node in nodes:
                 self.run_node(single_node, node_scenario_object, action, node_scenario)
         affected_nodes_status = node_scenario_object.affected_nodes_status
@@ -171,14 +217,21 @@ class NodeActionsScenarioPlugin(AbstractScenarioPlugin):
         try:
             # pool object with number of element
             pool = ThreadPool(processes=len(nodes))
-    
-            pool.starmap(self.run_node,zip(nodes, repeat(node_scenario_object), repeat(action), repeat(node_scenario)))
+
+            pool.starmap(
+                self.run_node,
+                zip(
+                    nodes,
+                    repeat(node_scenario_object),
+                    repeat(action),
+                    repeat(node_scenario),
+                ),
+            )
 
             pool.close()
         except Exception as e:
             logging.info("Error on pool multiprocessing: " + str(e))
 
-
     def run_node(self, single_node, node_scenario_object, action, node_scenario):
         # Get the scenario specifics for running action nodes
         run_kill_count = get_yaml_item_value(node_scenario, "runs", 1)
@@ -186,6 +239,7 @@ class NodeActionsScenarioPlugin(AbstractScenarioPlugin):
 
         timeout = get_yaml_item_value(node_scenario, "timeout", 120)
         service = get_yaml_item_value(node_scenario, "service", "")
+        soft_reboot = get_yaml_item_value(node_scenario, "soft_reboot", False)
         ssh_private_key = get_yaml_item_value(
             node_scenario, "ssh_private_key", "~/.ssh/id_rsa"
         )
@@ -216,11 +270,12 @@ class NodeActionsScenarioPlugin(AbstractScenarioPlugin):
                 )
             elif action == "node_reboot_scenario":
                 node_scenario_object.node_reboot_scenario(
-                    run_kill_count, single_node, timeout
+                    run_kill_count, single_node, timeout, soft_reboot
                 )
             elif action == "node_disk_detach_attach_scenario":
                 node_scenario_object.node_disk_detach_attach_scenario(
-                    run_kill_count, single_node, timeout, duration)
+                    run_kill_count, single_node, timeout, duration
+                )
             elif action == "stop_start_kubelet_scenario":
                 node_scenario_object.stop_start_kubelet_scenario(
                     run_kill_count, single_node, timeout
@@ -248,9 +303,7 @@ class NodeActionsScenarioPlugin(AbstractScenarioPlugin):
                 else:
                     if not node_scenario["helper_node_ip"]:
                         logging.error("Helper node IP address is not provided")
-                        raise Exception(
-                            "Helper node IP address is not provided"
-                        )
+                        raise Exception("Helper node IP address is not provided")
                     node_scenario_object.helper_node_stop_start_scenario(
                         run_kill_count, node_scenario["helper_node_ip"], timeout
                     )
@@ -270,6 +323,5 @@ class NodeActionsScenarioPlugin(AbstractScenarioPlugin):
                     % action
                 )
 
-
     def get_scenario_types(self) -> list[str]:
         return ["node_scenarios"]

krkn/scenario_plugins/node_actions/openstack_node_scenarios.py

@@ -171,7 +171,7 @@ class openstack_node_scenarios(abstract_node_scenarios):
             self.affected_nodes_status.affected_nodes.append(affected_node)
 
     # Node scenario to reboot the node
-    def node_reboot_scenario(self, instance_kill_count, node, timeout):
+    def node_reboot_scenario(self, instance_kill_count, node, timeout, soft_reboot=False):
         for _ in range(instance_kill_count):
             affected_node = AffectedNode(node)
             try:

krkn/scenario_plugins/node_actions/vmware_node_scenarios.py

@@ -73,7 +73,7 @@ class vSphere:
         vms = self.client.vcenter.VM.list(VM.FilterSpec(names=names))
 
         if len(vms) == 0:
-            logging.info("VM with name ({}) not found", instance_id)
+            logging.info("VM with name ({}) not found".format(instance_id))
             return None
         vm = vms[0].vm
 
@@ -97,7 +97,7 @@ class vSphere:
             self.client.vcenter.vm.Power.start(vm)
             self.client.vcenter.vm.Power.stop(vm)
         self.client.vcenter.VM.delete(vm)
-        logging.info("Deleted VM -- '{}-({})'", instance_id, vm)
+        logging.info("Deleted VM -- '{}-({})'".format(instance_id, vm))
 
     def reboot_instances(self, instance_id):
         """
@@ -108,11 +108,11 @@ class vSphere:
         vm = self.get_vm(instance_id)
         try:
             self.client.vcenter.vm.Power.reset(vm)
-            logging.info("Reset VM -- '{}-({})'", instance_id, vm)
+            logging.info("Reset VM -- '{}-({})'".format(instance_id, vm))
             return True
         except NotAllowedInCurrentState:
             logging.info(
-                "VM '{}'-'({})' is not Powered On. Cannot reset it", instance_id, vm
+                "VM '{}'-'({})' is not Powered On. Cannot reset it".format(instance_id, vm)
             )
             return False
 
@@ -158,7 +158,7 @@ class vSphere:
         try:
             datacenter_id = datacenter_summaries[0].datacenter
         except IndexError:
-            logging.error("Datacenter '{}' doesn't exist", datacenter)
+            logging.error("Datacenter '{}' doesn't exist".format(datacenter))
             sys.exit(1)
 
         vm_filter = self.client.vcenter.VM.FilterSpec(datacenters={datacenter_id})
@@ -432,7 +432,7 @@ class vmware_node_scenarios(abstract_node_scenarios):
             )
                 
 
-    def node_reboot_scenario(self, instance_kill_count, node, timeout):
+    def node_reboot_scenario(self, instance_kill_count, node, timeout, soft_reboot=False):
         try:
             for _ in range(instance_kill_count):
                 affected_node = AffectedNode(node)

krkn/scenario_plugins/pod_disruption/models/models.py

@@ -11,6 +11,9 @@ class InputParams:
             self.label_selector = config["label_selector"] if "label_selector" in config else ""
             self.namespace_pattern = config["namespace_pattern"] if "namespace_pattern" in config else ""
             self.name_pattern = config["name_pattern"] if "name_pattern" in config else ""
+            self.node_label_selector = config["node_label_selector"] if "node_label_selector" in config else ""
+            self.node_names = config["node_names"] if "node_names" in config else []
+            self.exclude_label = config["exclude_label"] if "exclude_label" in config else ""
 
     namespace_pattern: str
     krkn_pod_recovery_time: int
@@ -18,4 +21,7 @@ class InputParams:
     duration: int
     kill: int
     label_selector: str
-    name_pattern: str
+    name_pattern: str
+    node_label_selector: str
+    node_names: list
+    exclude_label: str

krkn/scenario_plugins/pod_disruption/pod_disruption_scenario_plugin.py

@@ -1,14 +1,16 @@
 import logging
 import random
 import time
+from asyncio import Future
 
 import yaml
 from krkn_lib.k8s import KrknKubernetes
-from krkn_lib.k8s.pods_monitor_pool import PodsMonitorPool
+from krkn_lib.k8s.pod_monitor import select_and_monitor_by_namespace_pattern_and_label, \
+    select_and_monitor_by_name_pattern_and_namespace_pattern
+
 from krkn.scenario_plugins.pod_disruption.models.models import InputParams
 from krkn_lib.models.telemetry import ScenarioTelemetry
 from krkn_lib.telemetry.ocp import KrknTelemetryOpenshift
-from krkn_lib.utils import get_yaml_item_value
 from datetime import datetime
 from dataclasses import dataclass
 
@@ -29,31 +31,25 @@ class PodDisruptionScenarioPlugin(AbstractScenarioPlugin):
         lib_telemetry: KrknTelemetryOpenshift,
         scenario_telemetry: ScenarioTelemetry,
     ) -> int:
-        pool = PodsMonitorPool(lib_telemetry.get_lib_kubernetes())
         try:
             with open(scenario, "r") as f:
                 cont_scenario_config = yaml.full_load(f)
                 for kill_scenario in cont_scenario_config:
                     kill_scenario_config = InputParams(kill_scenario["config"])
-                    self.start_monitoring(
-                        kill_scenario_config, pool
+                    future_snapshot=self.start_monitoring(
+                        kill_scenario_config,
+                        lib_telemetry
                     )
-                    return_status = self.killing_pods(
+                    self.killing_pods(
                         kill_scenario_config, lib_telemetry.get_lib_kubernetes()
                     )
-                    if return_status != 0: 
-                        result = pool.cancel()
-                    else:
-                        result = pool.join()
-                if result.error:
-                    logging.error(
-                        logging.error(
-                            f"PodDisruptionScenariosPlugin pods failed to recovery: {result.error}"
-                        )
-                    )
-                    return 1
-                
-                scenario_telemetry.affected_pods = result
+
+                    snapshot = future_snapshot.result()
+                    result = snapshot.get_pods_status()
+                    scenario_telemetry.affected_pods = result
+                    if len(result.unrecovered) > 0:
+                        logging.info("PodDisruptionScenarioPlugin failed with unrecovered pods")
+                        return 1
 
         except (RuntimeError, Exception) as e:
             logging.error("PodDisruptionScenariosPlugin exiting due to Exception %s" % e)
@@ -64,7 +60,7 @@ class PodDisruptionScenarioPlugin(AbstractScenarioPlugin):
     def get_scenario_types(self) -> list[str]:
         return ["pod_disruption_scenarios"]
 
-    def start_monitoring(self, kill_scenario: InputParams, pool: PodsMonitorPool):
+    def start_monitoring(self, kill_scenario: InputParams, lib_telemetry: KrknTelemetryOpenshift) -> Future:
 
         recovery_time = kill_scenario.krkn_pod_recovery_time
         if (
@@ -73,16 +69,17 @@ class PodDisruptionScenarioPlugin(AbstractScenarioPlugin):
         ):
             namespace_pattern = kill_scenario.namespace_pattern
             label_selector = kill_scenario.label_selector
-            pool.select_and_monitor_by_namespace_pattern_and_label(
+            future_snapshot = select_and_monitor_by_namespace_pattern_and_label(
                 namespace_pattern=namespace_pattern,
                 label_selector=label_selector,
                 max_timeout=recovery_time,
-                field_selector="status.phase=Running"
+                v1_client=lib_telemetry.get_lib_kubernetes().cli
             )
             logging.info(
                 f"waiting up to {recovery_time} seconds for pod recovery, "
                 f"pod label pattern: {label_selector} namespace pattern: {namespace_pattern}"
             )
+            return future_snapshot
 
         elif (
             kill_scenario.namespace_pattern
@@ -90,32 +87,101 @@ class PodDisruptionScenarioPlugin(AbstractScenarioPlugin):
         ):
             namespace_pattern = kill_scenario.namespace_pattern
             name_pattern = kill_scenario.name_pattern
-            pool.select_and_monitor_by_name_pattern_and_namespace_pattern(
+            future_snapshot = select_and_monitor_by_name_pattern_and_namespace_pattern(
                 pod_name_pattern=name_pattern,
                 namespace_pattern=namespace_pattern,
                 max_timeout=recovery_time,
-                field_selector="status.phase=Running"
+                v1_client=lib_telemetry.get_lib_kubernetes().cli
             )
             logging.info(
                 f"waiting up to {recovery_time} seconds for pod recovery, "
                 f"pod name pattern: {name_pattern} namespace pattern: {namespace_pattern}"
             )
+            return future_snapshot
         else:
             raise Exception(
                 f"impossible to determine monitor parameters, check {kill_scenario} configuration"
             )
+    
+    def _select_pods_with_field_selector(self, name_pattern, label_selector, namespace, kubecli: KrknKubernetes, field_selector: str, node_name: str = None):
+        """Helper function to select pods using either label_selector or name_pattern with field_selector, optionally filtered by node"""
+        # Combine field selectors if node targeting is specified
+        if node_name:
+            node_field_selector = f"spec.nodeName={node_name}"
+            if field_selector:
+                combined_field_selector = f"{field_selector},{node_field_selector}"
+            else:
+                combined_field_selector = node_field_selector
+        else:
+            combined_field_selector = field_selector
         
+        if label_selector:
+            return kubecli.select_pods_by_namespace_pattern_and_label(
+                label_selector=label_selector, 
+                namespace_pattern=namespace, 
+                field_selector=combined_field_selector
+            )
+        else:  # name_pattern
+            return kubecli.select_pods_by_name_pattern_and_namespace_pattern(
+                pod_name_pattern=name_pattern, 
+                namespace_pattern=namespace, 
+                field_selector=combined_field_selector
+            )
 
-    def get_pods(self, name_pattern, label_selector,namespace, kubecli: KrknKubernetes, field_selector: str =None): 
+    def get_pods(self, name_pattern, label_selector, namespace, kubecli: KrknKubernetes, field_selector: str = None, node_label_selector: str = None, node_names: list = None, quiet: bool = False): 
         if label_selector and name_pattern: 
             logging.error('Only, one of name pattern or label pattern can be specified')
-        elif label_selector:
-            pods = kubecli.select_pods_by_namespace_pattern_and_label(label_selector=label_selector,namespace_pattern=namespace, field_selector=field_selector)
-        elif name_pattern:
-            pods = kubecli.select_pods_by_name_pattern_and_namespace_pattern(pod_name_pattern=name_pattern, namespace_pattern=namespace, field_selector=field_selector)
-        else: 
+            return []
+        
+        if not label_selector and not name_pattern:
             logging.error('Name pattern or label pattern must be specified ')
-        return pods
+            return []
+        
+        # If specific node names are provided, make multiple calls with field selector
+        if node_names:
+            if not quiet:
+                logging.info(f"Targeting pods on {len(node_names)} specific nodes")
+            all_pods = []
+            for node_name in node_names:
+                pods = self._select_pods_with_field_selector(
+                    name_pattern, label_selector, namespace, kubecli, field_selector, node_name
+                )
+                
+                if pods:
+                    all_pods.extend(pods)
+            
+            if not quiet:
+                logging.info(f"Found {len(all_pods)} target pods across {len(node_names)} nodes")
+            return all_pods
+        
+        #  Node label selector approach - use field selectors
+        if node_label_selector:
+            # Get nodes matching the label selector first
+            nodes_with_label = kubecli.list_nodes(label_selector=node_label_selector)
+            if not nodes_with_label:
+                logging.info(f"No nodes found with label selector: {node_label_selector}")
+                return []
+            
+            if not quiet:
+                logging.info(f"Targeting pods on {len(nodes_with_label)} nodes with label: {node_label_selector}")
+            # Use field selector for each node
+            all_pods = []
+            for node_name in nodes_with_label:
+                pods = self._select_pods_with_field_selector(
+                    name_pattern, label_selector, namespace, kubecli, field_selector, node_name
+                )
+                
+                if pods:
+                    all_pods.extend(pods)
+            
+            if not quiet:
+                logging.info(f"Found {len(all_pods)} target pods across {len(nodes_with_label)} nodes")
+            return all_pods
+        
+        # Standard pod selection (no node targeting)
+        return self._select_pods_with_field_selector(
+            name_pattern, label_selector, namespace, kubecli, field_selector
+        )
     
     def killing_pods(self, config: InputParams, kubecli: KrknKubernetes):
         # region Select target pods
@@ -124,7 +190,14 @@ class PodDisruptionScenarioPlugin(AbstractScenarioPlugin):
         if not namespace: 
             logging.error('Namespace pattern must be specified')
 
-        pods = self.get_pods(config.name_pattern,config.label_selector,config.namespace_pattern, kubecli, field_selector="status.phase=Running")
+        pods = self.get_pods(config.name_pattern,config.label_selector,config.namespace_pattern, kubecli, field_selector="status.phase=Running", node_label_selector=config.node_label_selector, node_names=config.node_names)
+        exclude_pods = set()
+        if config.exclude_label:
+            _exclude_pods = self.get_pods("",config.exclude_label,config.namespace_pattern, kubecli, field_selector="status.phase=Running", node_label_selector=config.node_label_selector, node_names=config.node_names)
+            for pod in _exclude_pods:
+                exclude_pods.add(pod[0])
+
+
         pods_count = len(pods)
         if len(pods) < config.kill:
             logging.error("Not enough pods match the criteria, expected {} but found only {} pods".format(
@@ -133,23 +206,25 @@ class PodDisruptionScenarioPlugin(AbstractScenarioPlugin):
         
         random.shuffle(pods)
         for i in range(config.kill):
-
             pod = pods[i]
             logging.info(pod)
-            logging.info(f'Deleting pod {pod[0]}')
-            kubecli.delete_pod(pod[0], pod[1])
+            if pod[0] in exclude_pods:
+                logging.info(f"Excluding {pod[0]} from chaos")
+            else:
+                logging.info(f'Deleting pod {pod[0]}')
+                kubecli.delete_pod(pod[0], pod[1])
         
-        self.wait_for_pods(config.label_selector,config.name_pattern,config.namespace_pattern, pods_count, config.duration, config.timeout, kubecli)
+        self.wait_for_pods(config.label_selector,config.name_pattern,config.namespace_pattern, pods_count, config.duration, config.timeout, kubecli, config.node_label_selector, config.node_names)
         return 0
 
     def wait_for_pods(
-        self, label_selector, pod_name, namespace, pod_count, duration, wait_timeout, kubecli: KrknKubernetes
+        self, label_selector, pod_name, namespace, pod_count, duration, wait_timeout, kubecli: KrknKubernetes, node_label_selector, node_names
     ):
         timeout = False
         start_time = datetime.now()
 
         while not timeout:
-            pods = self.get_pods(name_pattern=pod_name, label_selector=label_selector,namespace=namespace, field_selector="status.phase=Running", kubecli=kubecli)
+            pods = self.get_pods(name_pattern=pod_name, label_selector=label_selector,namespace=namespace, field_selector="status.phase=Running", kubecli=kubecli, node_label_selector=node_label_selector, node_names=node_names, quiet=True)
             if pod_count == len(pods):
                 return
                

krkn/scenario_plugins/pvc/pvc_scenario_plugin.py

@@ -1,3 +1,5 @@
+import base64
+import json
 import logging
 import random
 import re
@@ -11,9 +13,12 @@ from krkn_lib.utils import get_yaml_item_value, log_exception
 
 from krkn import cerberus, utils
 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 PvcScenarioPlugin(AbstractScenarioPlugin):
+    @set_rollback_context_decorator
     def run(
         self,
         run_uuid: str,
@@ -229,6 +234,24 @@ class PvcScenarioPlugin(AbstractScenarioPlugin):
                 logging.info("\n" + str(response))
                 if str(file_name).lower() in str(response).lower():
                     logging.info("%s file successfully created" % (str(full_path)))
+                    
+                    # Set rollback callable to ensure temp file cleanup on failure or interruption
+                    rollback_data = {
+                        "pod_name": pod_name,
+                        "container_name": container_name,
+                        "mount_path": mount_path,
+                        "file_name": file_name,
+                        "full_path": full_path,
+                    }
+                    json_str = json.dumps(rollback_data)
+                    encoded_data = base64.b64encode(json_str.encode('utf-8')).decode('utf-8')
+                    self.rollback_handler.set_rollback_callable(
+                        self.rollback_temp_file,
+                        RollbackContent(
+                            namespace=namespace,
+                            resource_identifier=encoded_data,
+                        ),
+                    )
                 else:
                     logging.error(
                         "PvcScenarioPlugin Failed to create tmp file with %s size"
@@ -313,5 +336,57 @@ class PvcScenarioPlugin(AbstractScenarioPlugin):
         res = int(value[:-2]) * (base**exp)
         return res
 
+    @staticmethod
+    def rollback_temp_file(
+        rollback_content: RollbackContent,
+        lib_telemetry: KrknTelemetryOpenshift,
+    ):
+        """Rollback function to remove temporary file created during the PVC scenario.
+
+        :param rollback_content: Rollback content containing namespace and encoded rollback data in resource_identifier.
+        :param lib_telemetry: Instance of KrknTelemetryOpenshift for Kubernetes operations.
+        """
+        try:
+            namespace = rollback_content.namespace
+            import base64 # noqa
+            import json # noqa
+            decoded_data = base64.b64decode(rollback_content.resource_identifier.encode('utf-8')).decode('utf-8')
+            rollback_data = json.loads(decoded_data)
+            pod_name = rollback_data["pod_name"]
+            container_name = rollback_data["container_name"]
+            full_path = rollback_data["full_path"]
+            file_name = rollback_data["file_name"]
+            mount_path = rollback_data["mount_path"]
+            
+            logging.info(
+                f"Rolling back PVC scenario: removing temp file {full_path} from pod {pod_name} in namespace {namespace}"
+            )
+            
+            # Remove the temp file
+            command = "rm -f %s" % (str(full_path))
+            logging.info("Remove temp file from the PVC command:\n %s" % command)
+            response = lib_telemetry.get_lib_kubernetes().exec_cmd_in_pod(
+                [command], pod_name, namespace, container_name
+            )
+            logging.info("\n" + str(response))
+            # Verify removal
+            command = "ls -lh %s" % (str(mount_path))
+            logging.info("Check temp file is removed command:\n %s" % command)
+            response = lib_telemetry.get_lib_kubernetes().exec_cmd_in_pod(
+                [command], pod_name, namespace, container_name
+            )
+            logging.info("\n" + str(response))
+            
+            if not (str(file_name).lower() in str(response).lower()):
+                logging.info("Temp file successfully removed during rollback")
+            else:
+                logging.warning(
+                    f"Temp file {file_name} may still exist after rollback attempt"
+                )
+            
+            logging.info("PVC scenario rollback completed successfully.")
+        except Exception as e:
+            logging.error(f"Failed to rollback PVC scenario temp file: {e}")
+
     def get_scenario_types(self) -> list[str]:
         return ["pvc_scenarios"]

krkn/scenario_plugins/scenario_plugin_factory.py

@@ -33,7 +33,7 @@ class ScenarioPluginFactory:
             inherits from the AbstractScenarioPlugin abstract class
         """
         if scenario_type in self.loaded_plugins:
-            return self.loaded_plugins[scenario_type]()
+            return self.loaded_plugins[scenario_type](scenario_type)
         else:
             raise ScenarioPluginNotFound(
                 f"Failed to load the {scenario_type} scenario plugin. "
@@ -61,7 +61,10 @@ class ScenarioPluginFactory:
                             continue
 
                         cls = getattr(module, name)
-                        instance = cls()
+                        # The AbstractScenarioPlugin constructor requires a scenario_type.
+                        # However, since we only need to call `get_scenario_types()` here,
+                        # it is acceptable to use a placeholder value.
+                        instance = cls("placeholder_scenario_type")
                         get_scenario_type = getattr(instance, "get_scenario_types")
                         scenario_types = get_scenario_type()
                         has_duplicates = False

krkn/scenario_plugins/service_hijacking/service_hijacking_scenario_plugin.py

@@ -1,13 +1,17 @@
+import json
 import logging
 import time
-
+import base64
 import yaml
 from krkn_lib.models.telemetry import ScenarioTelemetry
 from krkn_lib.telemetry.ocp import KrknTelemetryOpenshift
 from krkn.scenario_plugins.abstract_scenario_plugin import AbstractScenarioPlugin
-
+from krkn_lib.utils import get_yaml_item_value
+from krkn.rollback.config import RollbackContent
+from krkn.rollback.handler import set_rollback_context_decorator
 
 class ServiceHijackingScenarioPlugin(AbstractScenarioPlugin):
+    @set_rollback_context_decorator
     def run(
         self,
         run_uuid: str,
@@ -25,6 +29,8 @@ class ServiceHijackingScenarioPlugin(AbstractScenarioPlugin):
         image = scenario_config["image"]
         target_port = scenario_config["service_target_port"]
         chaos_duration = scenario_config["chaos_duration"]
+        privileged = get_yaml_item_value(scenario_config,"privileged", True)
+
 
         logging.info(
             f"checking service {service_name} in namespace: {service_namespace}"
@@ -46,14 +52,14 @@ class ServiceHijackingScenarioPlugin(AbstractScenarioPlugin):
                 logging.info(f"webservice will listen on port {target_port}")
                 webservice = (
                     lib_telemetry.get_lib_kubernetes().deploy_service_hijacking(
-                        service_namespace, plan, image, port_number=target_port
+                        service_namespace, plan, image, port_number=target_port, privileged=privileged
                     )
                 )
             else:
                 logging.info(f"traffic will be redirected to named port: {target_port}")
                 webservice = (
                     lib_telemetry.get_lib_kubernetes().deploy_service_hijacking(
-                        service_namespace, plan, image, port_name=target_port
+                        service_namespace, plan, image, port_name=target_port, privileged=privileged
                     )
                 )
             logging.info(
@@ -76,6 +82,24 @@ class ServiceHijackingScenarioPlugin(AbstractScenarioPlugin):
 
             logging.info(f"service: {service_name} successfully patched!")
             logging.info(f"original service manifest:\n\n{yaml.dump(original_service)}")
+            
+            # Set rollback callable to ensure service restoration and pod cleanup on failure or interruption
+            rollback_data = {
+                "service_name": service_name,
+                "service_namespace": service_namespace,
+                "original_selectors": original_service["spec"]["selector"],
+                "webservice_pod_name": webservice.pod_name,
+            }
+            json_str = json.dumps(rollback_data)
+            encoded_data = base64.b64encode(json_str.encode("utf-8")).decode("utf-8")
+            self.rollback_handler.set_rollback_callable(
+                self.rollback_service_hijacking,
+                RollbackContent(
+                    namespace=service_namespace,
+                    resource_identifier=encoded_data,
+                ),
+            )
+            
             logging.info(f"waiting {chaos_duration} before restoring the service")
             time.sleep(chaos_duration)
             selectors = [
@@ -104,5 +128,63 @@ class ServiceHijackingScenarioPlugin(AbstractScenarioPlugin):
             )
             return 1
 
+    @staticmethod
+    def rollback_service_hijacking(
+        rollback_content: RollbackContent,
+        lib_telemetry: KrknTelemetryOpenshift,
+    ):
+        """Rollback function to restore original service selectors and cleanup hijacker pod.
+
+        :param rollback_content: Rollback content containing namespace and encoded rollback data in resource_identifier.
+        :param lib_telemetry: Instance of KrknTelemetryOpenshift for Kubernetes operations.
+        """
+        try:
+            namespace = rollback_content.namespace
+            import json # noqa
+            import base64 # noqa
+            # Decode rollback data from resource_identifier
+            decoded_data = base64.b64decode(rollback_content.resource_identifier.encode("utf-8")).decode("utf-8")
+            rollback_data = json.loads(decoded_data)
+            service_name = rollback_data["service_name"]
+            service_namespace = rollback_data["service_namespace"]
+            original_selectors = rollback_data["original_selectors"]
+            webservice_pod_name = rollback_data["webservice_pod_name"]
+            
+            logging.info(
+                f"Rolling back service hijacking: restoring service {service_name} in namespace {service_namespace}"
+            )
+            
+            # Restore original service selectors
+            selectors = [
+                "=".join([key, original_selectors[key]])
+                for key in original_selectors.keys()
+            ]
+            logging.info(f"Restoring original service selectors: {selectors}")
+            
+            restored_service = lib_telemetry.get_lib_kubernetes().replace_service_selector(
+                selectors, service_name, service_namespace
+            )
+            
+            if restored_service is None:
+                logging.warning(
+                    f"Failed to restore service {service_name} in namespace {service_namespace}"
+                )
+            else:
+                logging.info(f"Successfully restored service {service_name}")
+            
+            # Delete the hijacker pod
+            logging.info(f"Deleting hijacker pod: {webservice_pod_name}")
+            try:
+                lib_telemetry.get_lib_kubernetes().delete_pod(
+                    webservice_pod_name, service_namespace
+                )
+                logging.info(f"Successfully deleted hijacker pod: {webservice_pod_name}")
+            except Exception as e:
+                logging.warning(f"Failed to delete hijacker pod {webservice_pod_name}: {e}")
+            
+            logging.info("Service hijacking rollback completed successfully.")
+        except Exception as e:
+            logging.error(f"Failed to rollback service hijacking: {e}")
+
     def get_scenario_types(self) -> list[str]:
         return ["service_hijacking_scenarios"]

krkn/scenario_plugins/syn_flood/syn_flood_scenario_plugin.py

@@ -1,3 +1,5 @@
+import base64
+import json
 import logging
 import os
 import time
@@ -7,9 +9,12 @@ from krkn_lib import utils as krkn_lib_utils
 from krkn_lib.models.telemetry import ScenarioTelemetry
 from krkn_lib.telemetry.ocp import KrknTelemetryOpenshift
 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 SynFloodScenarioPlugin(AbstractScenarioPlugin):
+    @set_rollback_context_decorator
     def run(
         self,
         run_uuid: str,
@@ -50,6 +55,16 @@ class SynFloodScenarioPlugin(AbstractScenarioPlugin):
                         config["attacker-nodes"],
                     )
                     pod_names.append(pod_name)
+                
+                # Set rollback callable to ensure pod cleanup on failure or interruption
+                rollback_data = base64.b64encode(json.dumps(pod_names).encode('utf-8')).decode('utf-8')
+                self.rollback_handler.set_rollback_callable(
+                    self.rollback_syn_flood_pods,
+                    RollbackContent(
+                        namespace=config["namespace"],
+                        resource_identifier=rollback_data,
+                    ),
+                )
 
             logging.info("waiting all the attackers to finish:")
             did_finish = False
@@ -137,3 +152,23 @@ class SynFloodScenarioPlugin(AbstractScenarioPlugin):
 
     def get_scenario_types(self) -> list[str]:
         return ["syn_flood_scenarios"]
+
+    @staticmethod
+    def rollback_syn_flood_pods(rollback_content: RollbackContent, lib_telemetry: KrknTelemetryOpenshift):
+        """
+        Rollback function to delete syn flood pods.
+
+        :param rollback_content: Rollback content containing namespace and resource_identifier.
+        :param lib_telemetry: Instance of KrknTelemetryOpenshift for Kubernetes operations
+        """
+        try:
+            namespace = rollback_content.namespace
+            import base64 # noqa
+            import json # noqa
+            pod_names = json.loads(base64.b64decode(rollback_content.resource_identifier.encode('utf-8')).decode('utf-8'))
+            logging.info(f"Rolling back syn flood pods: {pod_names} in namespace: {namespace}")
+            for pod_name in pod_names:
+                lib_telemetry.get_lib_kubernetes().delete_pod(pod_name, namespace)
+            logging.info("Rollback of syn flood pods completed successfully.")
+        except Exception as e:
+            logging.error(f"Failed to rollback syn flood pods: {e}")

krkn/scenario_plugins/time_actions/time_actions_scenario_plugin.py

@@ -144,6 +144,10 @@ class TimeActionsScenarioPlugin(AbstractScenarioPlugin):
                 node_names = scenario["object_name"]
             elif "label_selector" in scenario.keys() and scenario["label_selector"]:
                 node_names = kubecli.list_nodes(scenario["label_selector"])
+                # going to filter out nodes with the exclude_label if it is provided
+                if "exclude_label" in scenario.keys() and scenario["exclude_label"]:
+                    excluded_nodes = kubecli.list_nodes(scenario["exclude_label"])
+                    node_names = [node for node in node_names if node not in excluded_nodes]
             for node in node_names:
                 self.skew_node(node, scenario["action"], kubecli)
                 logging.info("Reset date/time on node " + str(node))
@@ -189,6 +193,10 @@ class TimeActionsScenarioPlugin(AbstractScenarioPlugin):
                     counter += 1
             elif "label_selector" in scenario.keys() and scenario["label_selector"]:
                 pod_names = kubecli.get_all_pods(scenario["label_selector"])
+                # and here filter out the pods with exclude_label if it is provided
+                if "exclude_label" in scenario.keys() and scenario["exclude_label"]:
+                    excluded_pods = kubecli.get_all_pods(scenario["exclude_label"])
+                    pod_names = [pod for pod in pod_names if pod not in excluded_pods]
 
             if len(pod_names) == 0:
                 logging.info(

krkn/utils/VirtChecker.py

@@ -0,0 +1,262 @@
+
+import time
+import logging
+import math
+import queue
+from datetime import datetime
+from krkn_lib.models.telemetry.models import VirtCheck
+from krkn.invoke.command import invoke_no_exit
+from krkn.scenario_plugins.kubevirt_vm_outage.kubevirt_vm_outage_scenario_plugin import KubevirtVmOutageScenarioPlugin
+from krkn_lib.k8s import KrknKubernetes
+import threading
+from krkn_lib.utils.functions import get_yaml_item_value
+
+
+class VirtChecker:
+    current_iterations: int = 0
+    ret_value = 0
+    def __init__(self, kubevirt_check_config, iterations, krkn_lib: KrknKubernetes, threads_limit=20):
+        self.iterations = iterations
+        self.namespace = get_yaml_item_value(kubevirt_check_config, "namespace", "")
+        self.vm_list = []
+        self.threads = []
+        self.threads_limit = threads_limit
+        # setting to 0 in case no variables are set, so no threads later get made
+        self.batch_size = 0
+        self.ret_value = 0
+        vmi_name_match = get_yaml_item_value(kubevirt_check_config, "name", ".*")
+        self.krkn_lib = krkn_lib
+        self.disconnected =  get_yaml_item_value(kubevirt_check_config, "disconnected", False)
+        self.only_failures =  get_yaml_item_value(kubevirt_check_config, "only_failures", False)
+        self.interval = get_yaml_item_value(kubevirt_check_config, "interval", 2)
+        self.ssh_node = get_yaml_item_value(kubevirt_check_config, "ssh_node", "")
+        self.node_names = get_yaml_item_value(kubevirt_check_config, "node_names", "")
+        self.exit_on_failure = get_yaml_item_value(kubevirt_check_config, "exit_on_failure", False)
+        if self.namespace == "":
+            logging.info("kube virt checks config is not defined, skipping them")
+            return
+        try:
+            self.kube_vm_plugin = KubevirtVmOutageScenarioPlugin()
+            self.kube_vm_plugin.init_clients(k8s_client=krkn_lib)
+
+            self.kube_vm_plugin.get_vmis(vmi_name_match,self.namespace)
+        except Exception as e:
+            logging.error('Virt Check init exception: ' + str(e))
+            return
+        # See if multiple node names exist
+        node_name_list = [node_name for node_name in self.node_names.split(',') if node_name]
+        for vmi in self.kube_vm_plugin.vmis_list:
+            node_name = vmi.get("status",{}).get("nodeName")
+            vmi_name = vmi.get("metadata",{}).get("name")
+            ip_address = vmi.get("status",{}).get("interfaces",[])[0].get("ipAddress")
+            namespace = vmi.get("metadata",{}).get("namespace")
+            # If node_name_list exists, only add if node name is in list
+
+            if len(node_name_list) > 0 and node_name in node_name_list:
+                self.vm_list.append(VirtCheck({'vm_name':vmi_name, 'ip_address': ip_address, 'namespace':namespace, 'node_name':node_name, "new_ip_address":""}))
+            elif len(node_name_list) == 0:
+                # If node_name_list is blank, add all vms
+                self.vm_list.append(VirtCheck({'vm_name':vmi_name, 'ip_address': ip_address, 'namespace':namespace, 'node_name':node_name, "new_ip_address":""}))
+
+        self.batch_size = math.ceil(len(self.vm_list)/self.threads_limit)
+
+    def check_disconnected_access(self, ip_address: str, worker_name:str = '', vmi_name: str = ''):
+        
+        virtctl_vm_cmd = f"ssh core@{worker_name} -o ConnectTimeout=5 'ssh -o BatchMode=yes -o ConnectTimeout=5 -o StrictHostKeyChecking=no root@{ip_address}'"
+        
+        all_out = invoke_no_exit(virtctl_vm_cmd)
+        logging.debug(f"Checking disconnected access for {ip_address} on {worker_name} output: {all_out}")
+        virtctl_vm_cmd = f"ssh core@{worker_name} -o ConnectTimeout=5 'ssh -o BatchMode=yes -o ConnectTimeout=5 -o StrictHostKeyChecking=no root@{ip_address} 2>&1 | grep Permission' && echo 'True' || echo 'False'"
+        output = invoke_no_exit(virtctl_vm_cmd)
+        if 'True' in output:
+            logging.debug(f"Disconnected access for {ip_address} on {worker_name} is successful: {output}")
+            return True, None, None
+        else:
+            logging.debug(f"Disconnected access for {ip_address} on {worker_name} is failed: {output}")
+            vmi = self.kube_vm_plugin.get_vmi(vmi_name,self.namespace)
+            new_ip_address = vmi.get("status",{}).get("interfaces",[])[0].get("ipAddress")
+            new_node_name = vmi.get("status",{}).get("nodeName")
+            # if vm gets deleted, it'll start up with a new ip address
+            if new_ip_address != ip_address:
+                virtctl_vm_cmd = f"ssh core@{worker_name} -o ConnectTimeout=5 'ssh -o BatchMode=yes -o ConnectTimeout=5 -o StrictHostKeyChecking=no root@{new_ip_address} 2>&1 | grep Permission' && echo 'True' || echo 'False'"
+                new_output = invoke_no_exit(virtctl_vm_cmd)
+                logging.debug(f"Disconnected access for {ip_address} on {worker_name}: {new_output}")
+                if 'True' in new_output:
+                    return True, new_ip_address, None
+            # if node gets stopped, vmis will start up with a new node (and with new ip)
+            if new_node_name != worker_name:
+                virtctl_vm_cmd = f"ssh core@{new_node_name} -o ConnectTimeout=5 'ssh -o BatchMode=yes -o ConnectTimeout=5 -o StrictHostKeyChecking=no root@{new_ip_address} 2>&1 | grep Permission' && echo 'True' || echo 'False'"
+                new_output = invoke_no_exit(virtctl_vm_cmd)
+                logging.debug(f"Disconnected access for {ip_address} on {new_node_name}: {new_output}")
+                if 'True' in new_output:
+                    return True, new_ip_address, new_node_name
+            # try to connect with a common "up" node as last resort
+            if self.ssh_node:
+                # using new_ip_address here since if it hasn't changed it'll match ip_address
+                virtctl_vm_cmd = f"ssh core@{self.ssh_node} -o ConnectTimeout=5 'ssh -o BatchMode=yes -o ConnectTimeout=5 -o StrictHostKeyChecking=no root@{new_ip_address} 2>&1 | grep Permission' && echo 'True' || echo 'False'"
+                new_output = invoke_no_exit(virtctl_vm_cmd)
+                logging.debug(f"Disconnected access for {new_ip_address} on {self.ssh_node}: {new_output}")
+                if 'True' in new_output:
+                    return True, new_ip_address, None
+        return False, None, None
+
+    def get_vm_access(self, vm_name: str = '', namespace: str = ''):
+        """
+        This method returns True when the VM is access and an error message when it is not, using virtctl protocol
+        :param vm_name:
+        :param namespace:
+        :return: virtctl_status 'True' if successful, or an error message if it fails.
+        """
+        virtctl_vm_cmd = f"virtctl ssh --local-ssh-opts='-o BatchMode=yes' --local-ssh-opts='-o PasswordAuthentication=no' --local-ssh-opts='-o ConnectTimeout=5' root@vmi/{vm_name} -n {namespace} 2>&1 |egrep 'denied|verification failed'  && echo 'True' || echo 'False'"
+        check_virtctl_vm_cmd = f"virtctl ssh --local-ssh-opts='-o BatchMode=yes' --local-ssh-opts='-o PasswordAuthentication=no' --local-ssh-opts='-o ConnectTimeout=5' root@{vm_name} -n {namespace} 2>&1 |egrep 'denied|verification failed'  && echo 'True' || echo 'False'"
+        if 'True' in invoke_no_exit(check_virtctl_vm_cmd):
+            return True
+        else:
+            second_invoke = invoke_no_exit(virtctl_vm_cmd)
+            if 'True' in second_invoke:
+                return True
+            return False
+    
+    def thread_join(self):
+        for thread in self.threads:
+            thread.join()
+
+    def batch_list(self, queue: queue.Queue = None):
+        logging.info("batch size" + str(self.batch_size))
+        if self.batch_size > 0:
+            # Provided prints to easily visualize how the threads are processed.    
+            for i in range (0, len(self.vm_list),self.batch_size):
+                if i+self.batch_size > len(self.vm_list):
+                    sub_list = self.vm_list[i:]
+                else:
+                    sub_list = self.vm_list[i: i+self.batch_size]
+                index = i
+                t = threading.Thread(target=self.run_virt_check,name=str(index), args=(sub_list,queue))
+                self.threads.append(t)
+                t.start()
+
+    
+    def run_virt_check(self, vm_list_batch, virt_check_telemetry_queue: queue.Queue):
+        
+        virt_check_telemetry = []
+        virt_check_tracker = {}
+        while self.current_iterations < self.iterations:
+            for vm in vm_list_batch:
+                try: 
+                    if not self.disconnected: 
+                        vm_status = self.get_vm_access(vm.vm_name, vm.namespace)
+                    else:
+                        # if new ip address exists use it 
+                        if vm.new_ip_address: 
+                            vm_status, new_ip_address, new_node_name = self.check_disconnected_access(vm.new_ip_address, vm.node_name, vm.vm_name)
+                            # since we already set the new ip address, we don't want to reset to none each time
+                        else: 
+                            vm_status, new_ip_address, new_node_name = self.check_disconnected_access(vm.ip_address, vm.node_name, vm.vm_name)
+                            if new_ip_address and vm.ip_address != new_ip_address:
+                                vm.new_ip_address = new_ip_address
+                            if new_node_name and vm.node_name != new_node_name:
+                                vm.node_name = new_node_name
+                except Exception:
+                    vm_status = False
+                
+                if vm.vm_name not in virt_check_tracker:
+                    start_timestamp = datetime.now()
+                    virt_check_tracker[vm.vm_name] = {
+                        "vm_name": vm.vm_name,
+                        "ip_address": vm.ip_address,
+                        "namespace": vm.namespace,
+                        "node_name": vm.node_name,
+                        "status": vm_status,
+                        "start_timestamp": start_timestamp,
+                        "new_ip_address": vm.new_ip_address
+                    }
+                else:
+                    if vm_status != virt_check_tracker[vm.vm_name]["status"]:
+                        end_timestamp = datetime.now()
+                        start_timestamp = virt_check_tracker[vm.vm_name]["start_timestamp"]
+                        duration = (end_timestamp - start_timestamp).total_seconds()
+                        virt_check_tracker[vm.vm_name]["end_timestamp"] = end_timestamp.isoformat()
+                        virt_check_tracker[vm.vm_name]["duration"] = duration
+                        virt_check_tracker[vm.vm_name]["start_timestamp"] = start_timestamp.isoformat()
+                        if vm.new_ip_address:
+                            virt_check_tracker[vm.vm_name]["new_ip_address"] = vm.new_ip_address
+                        if self.only_failures: 
+                            if not virt_check_tracker[vm.vm_name]["status"]:
+                                virt_check_telemetry.append(VirtCheck(virt_check_tracker[vm.vm_name]))
+                        else:
+                            virt_check_telemetry.append(VirtCheck(virt_check_tracker[vm.vm_name]))
+                        del virt_check_tracker[vm.vm_name]
+            time.sleep(self.interval)
+        virt_check_end_time_stamp = datetime.now()
+        for vm in virt_check_tracker.keys():
+            final_start_timestamp = virt_check_tracker[vm]["start_timestamp"]
+            final_duration = (virt_check_end_time_stamp - final_start_timestamp).total_seconds()
+            virt_check_tracker[vm]["end_timestamp"] = virt_check_end_time_stamp.isoformat()
+            virt_check_tracker[vm]["duration"] = final_duration
+            virt_check_tracker[vm]["start_timestamp"] = final_start_timestamp.isoformat()
+            if self.only_failures:
+                if not virt_check_tracker[vm]["status"]:
+                    virt_check_telemetry.append(VirtCheck(virt_check_tracker[vm]))
+            else:
+                virt_check_telemetry.append(VirtCheck(virt_check_tracker[vm]))
+        virt_check_telemetry_queue.put(virt_check_telemetry)
+    
+    def run_post_virt_check(self, vm_list_batch, virt_check_telemetry, post_virt_check_queue: queue.Queue):
+        
+        virt_check_telemetry = []
+        virt_check_tracker = {}
+        start_timestamp = datetime.now()
+        for vm in vm_list_batch:
+            
+            try: 
+                if not self.disconnected: 
+                    vm_status = self.get_vm_access(vm.vm_name, vm.namespace)
+                else:
+                    vm_status, new_ip_address, new_node_name = self.check_disconnected_access(vm.ip_address, vm.node_name, vm.vm_name)
+                    if new_ip_address and vm.ip_address != new_ip_address:
+                        vm.new_ip_address = new_ip_address
+                    if new_node_name and vm.node_name != new_node_name:
+                        vm.node_name = new_node_name
+            except Exception:
+                vm_status = False
+            
+            if not vm_status:
+
+                virt_check_tracker= {
+                    "vm_name": vm.vm_name,
+                    "ip_address": vm.ip_address,
+                    "namespace": vm.namespace,
+                    "node_name": vm.node_name,
+                    "status": vm_status,
+                    "start_timestamp": start_timestamp.isoformat(),
+                    "new_ip_address": vm.new_ip_address,
+                    "duration": 0,
+                    "end_timestamp": start_timestamp.isoformat()
+                }
+                
+                virt_check_telemetry.append(VirtCheck(virt_check_tracker))
+        post_virt_check_queue.put(virt_check_telemetry)
+    
+
+    def gather_post_virt_checks(self, kubevirt_check_telem):
+
+        post_kubevirt_check_queue = queue.Queue()
+        post_threads = []
+
+        if self.batch_size > 0:
+            for i in range (0, len(self.vm_list),self.batch_size):
+                sub_list = self.vm_list[i: i+self.batch_size]
+                index = i
+                t = threading.Thread(target=self.run_post_virt_check,name=str(index), args=(sub_list,kubevirt_check_telem, post_kubevirt_check_queue))
+                post_threads.append(t)
+                t.start()
+
+            kubevirt_check_telem = []
+            for thread in post_threads:
+                thread.join()
+                if not post_kubevirt_check_queue.empty():
+                    kubevirt_check_telem.extend(post_kubevirt_check_queue.get_nowait())
+        
+        if self.exit_on_failure and len(kubevirt_check_telem) > 0:
+            self.ret_value = 2
+        return kubevirt_check_telem

requirements.txt

@@ -16,9 +16,9 @@ google-cloud-compute==1.22.0
 ibm_cloud_sdk_core==3.18.0
 ibm_vpc==0.20.0
 jinja2==3.1.6
-krkn-lib==5.1.0
+krkn-lib==5.1.12
 lxml==5.1.0
-kubernetes==28.1.0
+kubernetes==34.1.0
 numpy==1.26.4
 pandas==2.2.0
 openshift-client==1.0.21

run_kraken.py

@@ -11,6 +11,7 @@ import uuid
 import time
 import queue
 import threading
+from typing import Optional
 
 from krkn_lib.elastic.krkn_elastic import KrknElastic
 from krkn_lib.models.elastic import ElasticChaosRunTelemetry
@@ -28,10 +29,16 @@ from krkn_lib.utils.functions import get_yaml_item_value, get_junit_test_case
 
 from krkn.utils import TeeLogHandler
 from krkn.utils.HealthChecker import HealthChecker
+from krkn.utils.VirtChecker import VirtChecker
 from krkn.scenario_plugins.scenario_plugin_factory import (
     ScenarioPluginFactory,
     ScenarioPluginNotFound,
 )
+from krkn.rollback.config import RollbackConfig
+from krkn.rollback.command import (
+    list_rollback as list_rollback_command,
+    execute_rollback as execute_rollback_command,
+)
 
 # removes TripleDES warning
 import warnings
@@ -39,13 +46,13 @@ warnings.filterwarnings(action='ignore', module='.*paramiko.*')
 
 report_file = ""
 
-
 # Main function
-def main(cfg) -> int:
+def main(options, command: Optional[str]) -> int:
     # Start kraken
     print(pyfiglet.figlet_format("kraken"))
     logging.info("Starting kraken")
 
+    cfg = options.cfg
     # Parse and read the config
     if os.path.isfile(cfg):
         with open(cfg, "r") as f:
@@ -61,6 +68,18 @@ def main(cfg) -> int:
             config["kraken"], "publish_kraken_status", False
         )
         port = get_yaml_item_value(config["kraken"], "port", 8081)
+        RollbackConfig.register(
+            auto=get_yaml_item_value(
+                config["kraken"],
+                "auto_rollback",
+                False
+            ),
+            versions_directory=get_yaml_item_value(
+                config["kraken"],
+                "rollback_versions_directory",
+                "/tmp/kraken-rollback"
+            ),
+        )
         signal_address = get_yaml_item_value(
             config["kraken"], "signal_address", "0.0.0.0"
         )
@@ -112,8 +131,9 @@ def main(cfg) -> int:
             config["performance_monitoring"], "check_critical_alerts", False
         )
         telemetry_api_url = config["telemetry"].get("api_url")
-        health_check_config = config["health_checks"]
-
+        health_check_config = get_yaml_item_value(config, "health_checks",{})
+        kubevirt_check_config = get_yaml_item_value(config, "kubevirt_checks", {})
+        
         # Initialize clients
         if not os.path.isfile(kubeconfig_path) and not os.path.isfile(
                 "/var/run/secrets/kubernetes.io/serviceaccount/token"
@@ -231,6 +251,19 @@ def main(cfg) -> int:
 
         logging.info("Server URL: %s" % kubecli.get_host())
 
+        if command == "list-rollback":
+            sys.exit(
+                list_rollback_command(
+                    options.run_uuid, options.scenario_type
+                )
+            )
+        elif command == "execute-rollback":
+            sys.exit(
+                execute_rollback_command(
+                    telemetry_ocp, options.run_uuid, options.scenario_type
+                )
+            )
+
         # Initialize the start iteration to 0
         iteration = 0
 
@@ -293,6 +326,10 @@ def main(cfg) -> int:
                                                args=(health_check_config, health_check_telemetry_queue))
         health_check_worker.start()
 
+        kubevirt_check_telemetry_queue = queue.Queue()
+        kubevirt_checker = VirtChecker(kubevirt_check_config, iterations=iterations, krkn_lib=kubecli)
+        kubevirt_checker.batch_list(kubevirt_check_telemetry_queue)
+
         # Loop to run the chaos starts here
         while int(iteration) < iterations and run_signal != "STOP":
             # Inject chaos scenarios specified in the config
@@ -338,10 +375,12 @@ def main(cfg) -> int:
                             prometheus_plugin.critical_alerts(
                                 prometheus,
                                 summary,
+                                elastic_search,
                                 run_uuid,
                                 scenario_type,
                                 start_time,
                                 datetime.datetime.now(),
+                                elastic_alerts_index
                             )
 
                             chaos_output.critical_alerts = summary
@@ -354,6 +393,7 @@ def main(cfg) -> int:
 
             iteration += 1
             health_checker.current_iterations += 1
+            kubevirt_checker.current_iterations += 1
 
         # telemetry
         # in order to print decoded telemetry data even if telemetry collection
@@ -365,7 +405,14 @@ def main(cfg) -> int:
             chaos_telemetry.health_checks = health_check_telemetry_queue.get_nowait()
         except queue.Empty:
             chaos_telemetry.health_checks = None
-
+        
+        kubevirt_checker.thread_join()
+        kubevirt_check_telem = []
+        while not kubevirt_check_telemetry_queue.empty():
+            kubevirt_check_telem.extend(kubevirt_check_telemetry_queue.get_nowait())
+        chaos_telemetry.virt_checks = kubevirt_check_telem
+        post_kubevirt_check = kubevirt_checker.gather_post_virt_checks(kubevirt_check_telem)
+        chaos_telemetry.post_virt_checks = post_kubevirt_check
         # if platform is openshift will be collected
         # Cloud platform and network plugins metadata
         # through OCP specific APIs
@@ -505,6 +552,10 @@ def main(cfg) -> int:
             logging.error("Health check failed for the applications, Please check; exiting")
             return health_checker.ret_value
 
+        if kubevirt_checker.ret_value != 0:
+            logging.error("Kubevirt check still had failed VMIs at end of run, Please check; exiting")
+            return kubevirt_checker.ret_value
+
         logging.info(
             "Successfully finished running Kraken. UUID for the run: "
             "%s. Report generated at %s. Exiting" % (run_uuid, report_file)
@@ -519,7 +570,13 @@ def main(cfg) -> int:
 
 if __name__ == "__main__":
     # Initialize the parser to read the config
-    parser = optparse.OptionParser()
+    parser = optparse.OptionParser(
+        usage="%prog [options] [command]\n\n"
+              "Commands:\n"
+              "  list-rollback     List rollback version files in a tree-like format\n"
+              "  execute-rollback  Execute rollback version files and cleanup if successful\n\n"
+              "If no command is specified, kraken will run chaos scenarios.",
+    )
     parser.add_option(
         "-c",
         "--config",
@@ -556,7 +613,34 @@ if __name__ == "__main__":
         default=None,
     )
 
+    # Add rollback command options
+    parser.add_option(
+        "-r",
+        "--run_uuid",
+        dest="run_uuid",
+        help="run UUID to filter rollback operations",
+        default=None,
+    )
+
+    parser.add_option(
+        "-s",
+        "--scenario_type",
+        dest="scenario_type",
+        help="scenario type to filter rollback operations",
+        default=None,
+    )
+
+    parser.add_option(
+        "-d",
+        "--debug",
+        dest="debug",
+        help="enable debug logging",
+        default=False,
+    )
+
     (options, args) = parser.parse_args()
+    
+    # If no command or regular execution, continue with existing logic
     report_file = options.output
     tee_handler = TeeLogHandler()
     handlers = [
@@ -566,7 +650,7 @@ if __name__ == "__main__":
     ]
 
     logging.basicConfig(
-        level=logging.INFO,
+        level=logging.DEBUG if options.debug else logging.INFO,
         format="%(asctime)s [%(levelname)s] %(message)s",
         handlers=handlers,
     )
@@ -625,7 +709,9 @@ if __name__ == "__main__":
     if option_error:
         retval = 1
     else:
-        retval = main(options.cfg)
+        # Check if command is provided as positional argument
+        command = args[0] if args else None
+        retval = main(options, command)
 
     junit_endtime = time.time()
 

scenarios/kube/container_dns.yml

@@ -6,3 +6,4 @@ scenarios:
   action: 1
   count: 1
   retry_wait: 60
+  exclude_label: ""

scenarios/kube/service_hijacking.yaml

@@ -5,6 +5,7 @@ service_name: nginx-service # name of the service to 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.
+privileged: True # True or false if need privileged securityContext to run
 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.

scenarios/openshift/app_outage.yaml

@@ -3,3 +3,4 @@ application_outage:                                  # Scenario to create an out
   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
+  exclude_label: ""                                  # Optional label selector to exclude pods. Supports dict, string, or list format

scenarios/openshift/container_etcd.yml

@@ -6,3 +6,4 @@ scenarios:
   action: 1
   count: 1
   expected_recovery_time: 120
+  exclude_label: ""

scenarios/openshift/customapp_pod.yaml

@@ -1,6 +1,15 @@
 # yaml-language-server: $schema=../plugin.schema.json
 - id: kill-pods
   config:
-    namespace_pattern: ^acme-air$
+    namespace_pattern: "kube-system"
     name_pattern: .*
-    krkn_pod_recovery_time: 120
+    krkn_pod_recovery_time: 60
+    kill: 1     # num of pods to kill
+    #Not needed by default, but can be used if you want to target pods on specific nodes
+    # Option 1: Target pods on nodes with specific labels [master/worker nodes]
+    node_label_selector: node-role.kubernetes.io/control-plane=      # Target control-plane nodes (works on both k8s and openshift) 
+    # Option 2: Target pods of specific nodes (testing mixed node types)
+    # node_names: 
+    #   - ip-10-0-31-8.us-east-2.compute.internal      # Worker node 1
+    #   - ip-10-0-48-188.us-east-2.compute.internal    # Worker node 2  
+    #   - ip-10-0-14-59.us-east-2.compute.internal     # Master node 1

scenarios/openshift/egress_ip_ovn.yml

@@ -0,0 +1,20 @@
+# EgressIP failovr scenario - blocks OVN healthcheck port 9107 for EgressIP to move to another node
+
+- id: node_network_filter
+  image: "quay.io/krkn-chaos/krkn-network-chaos:latest"
+  wait_duration: 60
+  test_duration: 30
+  label_selector: "k8s.ovn.org/egress-assignable="
+  service_account: ""
+  taints: []
+  namespace: 'default'
+  instance_count: 1
+  execution: serial
+  ingress: true
+  egress: false
+  target: ''
+  interfaces: []
+  ports:
+    - 9107
+  protocols:
+    - tcp

scenarios/openshift/etcd.yml

@@ -4,3 +4,4 @@
     namespace_pattern: ^openshift-etcd$
     label_selector: k8s-app=etcd
     krkn_pod_recovery_time: 120
+    exclude_label: "" # excludes pods marked with this label from chaos

scenarios/openshift/openshift-apiserver.yml

@@ -4,4 +4,5 @@
     namespace_pattern: ^openshift-apiserver$
     label_selector: app=openshift-apiserver-a
     krkn_pod_recovery_time: 120
+    exclude_label: "" # excludes pods marked with this label from chaos
 

scenarios/openshift/openshift-kube-apiserver.yml

@@ -4,4 +4,5 @@
     namespace_pattern: ^openshift-kube-apiserver$
     label_selector: app=openshift-kube-apiserver
     krkn_pod_recovery_time: 120
+    exclude_label: "" # excludes pods marked with this label from chaos
 

scenarios/openshift/prom_kill.yml

@@ -2,4 +2,5 @@
   config:
     namespace_pattern: ^openshift-monitoring$
     label_selector: statefulset.kubernetes.io/pod-name=prometheus-k8s-0
-    krkn_pod_recovery_time: 120
+    krkn_pod_recovery_time: 120
+    exclude_label: "" # excludes pods marked with this label from chaos

scenarios/openshift/regex_openshift_pod_kill.yml

@@ -5,3 +5,4 @@
     name_pattern: .*
     kill: 3
     krkn_pod_recovery_time: 120
+    exclude_label: "" # excludes pods marked with this label from chaos

scenarios/plugin.schema.README.md

@@ -1,5 +0,0 @@
-This file is generated by running the "plugins" module in the kraken project:
-
-```
-python -m kraken.plugins >scenarios/plugin.schema.json
-```

scenarios/plugin.schema.json

@@ -1,584 +0,0 @@
-{
-	"$id": "https://github.com/redhat-chaos/krkn/",
-	"$schema": "https://json-schema.org/draft/2020-12/schema",
-	"title": "Kraken Arcaflow scenarios",
-	"description": "Serial execution of Arcaflow Python plugins. See https://github.com/arcaflow for details.",
-	"type": "array",
-	"minContains": 1,
-	"items": {
-		"oneOf": [
-			{
-				"type": "object",
-				"properties": {
-					"id": {
-						"type": "string",
-						"const": "run_python"
-					},
-					"config": {
-						"$defs": {
-							"RunPythonFileInput": {
-								"type": "object",
-								"properties": {
-									"filename": {
-										"type": "string"
-									}
-								},
-								"required": [
-									"filename"
-								],
-								"additionalProperties": false,
-								"dependentRequired": {}
-							}
-						},
-						"type": "object",
-						"properties": {
-							"filename": {
-								"type": "string"
-							}
-						},
-						"required": [
-							"filename"
-						],
-						"additionalProperties": false,
-						"dependentRequired": {}
-					}
-				},
-				"required": [
-					"id",
-					"config"
-				]
-			},
-			{
-				"type": "object",
-				"title": "pod_network_outage Arcaflow scenarios",
-				"properties": {
-					"id": {
-						"type": "string",
-						"const": "pod_network_outage"
-					},
-					"config": {
-						"$defs": {
-							"InputParams": {
-								"type": "object",
-								"properties": {
-									"namespace": {
-										"type": "string",
-										"minLength": 1,
-										"title": "Namespace",
-										"description": "Namespace of the pod to which filter need to be appliedfor details."
-									},
-									"image": {
-										"type": "string",
-										"minLength": 1,
-										"title": "Image",
-										"default": "image: quay.io/krkn-chaos/krkn:tools",
-										"description": "Image of the krkn tools to run network outage."
-									},
-									"direction": {
-										"type": "array",
-										"items": {
-											"type": "string"
-										},
-										"default": [
-											"ingress",
-											"egress"
-										],
-										"title": "Direction",
-										"description": "List of directions to apply filtersDefault both egress and ingress."
-									},
-									"ingress_ports": {
-										"type": "array",
-										"items": {
-											"type": "integer"
-										},
-										"default": [],
-										"title": "Ingress ports",
-										"description": "List of ports to block traffic onDefault [], i.e. all ports"
-									},
-									"egress_ports": {
-										"type": "array",
-										"items": {
-											"type": "integer"
-										},
-										"default": [],
-										"title": "Egress ports",
-										"description": "List of ports to block traffic onDefault [], i.e. all ports"
-									},
-									"kubeconfig_path": {
-										"type": "string",
-										"title": "Kubeconfig path",
-										"description": "Kubeconfig file as string\nSee https://kubernetes.io/docs/concepts/configuration/organize-cluster-access-kubeconfig/ for details."
-									},
-									"pod_name": {
-										"type": "string",
-										"title": "Pod name",
-										"description": "When label_selector is not specified, pod matching the name will beselected for the chaos scenario"
-									},
-									"label_selector": {
-										"type": "string",
-										"title": "Label selector",
-										"description": "Kubernetes label selector for the target pod. When pod_name is not specified, pod with matching label_selector is selected for chaos scenario"
-									},
-									"kraken_config": {
-										"type": "string",
-										"title": "Kraken Config",
-										"description": "Path to the config file of Kraken. Set this field if you wish to publish status onto Cerberus"
-									},
-									"test_duration": {
-										"type": "integer",
-										"minimum": 1,
-										"default": 120,
-										"title": "Test duration",
-										"description": "Duration for which each step of the ingress chaos testing is to be performed."
-									},
-									"wait_duration": {
-										"type": "integer",
-										"minimum": 1,
-										"default": 300,
-										"title": "Wait Duration",
-										"description": "Wait duration for finishing a test and its cleanup.Ensure that it is significantly greater than wait_duration"
-									},
-									"instance_count": {
-										"type": "integer",
-										"minimum": 1,
-										"default": 1,
-										"title": "Instance Count",
-										"description": "Number of pods to perform action/select that match the label selector."
-									}
-								},
-								"required": [
-									"namespace"
-								],
-								"additionalProperties": false,
-								"dependentRequired": {}
-							}
-						},
-						"type": "object",
-						"properties": {
-							"namespace": {
-								"type": "string",
-								"minLength": 1,
-								"title": "Namespace",
-								"description": "Namespace of the pod to which filter need to be appliedfor details."
-							},
-							"direction": {
-								"type": "array",
-								"items": {
-									"type": "string"
-								},
-								"default": [
-									"ingress",
-									"egress"
-								],
-								"title": "Direction",
-								"description": "List of directions to apply filtersDefault both egress and ingress."
-							},
-							"ingress_ports": {
-								"type": "array",
-								"items": {
-									"type": "integer"
-								},
-								"default": [],
-								"title": "Ingress ports",
-								"description": "List of ports to block traffic onDefault [], i.e. all ports"
-							},
-							"egress_ports": {
-								"type": "array",
-								"items": {
-									"type": "integer"
-								},
-								"default": [],
-								"title": "Egress ports",
-								"description": "List of ports to block traffic onDefault [], i.e. all ports"
-							},
-							"kubeconfig_path": {
-								"type": "string",
-								"title": "Kubeconfig path",
-								"description": "Kubeconfig file as string\nSee https://kubernetes.io/docs/concepts/configuration/organize-cluster-access-kubeconfig/ for details."
-							},
-							"pod_name": {
-								"type": "string",
-								"title": "Pod name",
-								"description": "When label_selector is not specified, pod matching the name will beselected for the chaos scenario"
-							},
-							"label_selector": {
-								"type": "string",
-								"title": "Label selector",
-								"description": "Kubernetes label selector for the target pod. When pod_name is not specified, pod with matching label_selector is selected for chaos scenario"
-							},
-							"kraken_config": {
-								"type": "string",
-								"title": "Kraken Config",
-								"description": "Path to the config file of Kraken. Set this field if you wish to publish status onto Cerberus"
-							},
-							"test_duration": {
-								"type": "integer",
-								"minimum": 1,
-								"default": 120,
-								"title": "Test duration",
-								"description": "Duration for which each step of the ingress chaos testing is to be performed."
-							},
-							"wait_duration": {
-								"type": "integer",
-								"minimum": 1,
-								"default": 300,
-								"title": "Wait Duration",
-								"description": "Wait duration for finishing a test and its cleanup.Ensure that it is significantly greater than wait_duration"
-							},
-							"instance_count": {
-								"type": "integer",
-								"minimum": 1,
-								"default": 1,
-								"title": "Instance Count",
-								"description": "Number of pods to perform action/select that match the label selector."
-							}
-						},
-						"required": [
-							"namespace"
-						],
-						"additionalProperties": false,
-						"dependentRequired": {}
-					}
-				},
-				"required": [
-					"id",
-					"config"
-				]
-			},
-			{
-				"type": "object",
-				"title": "pod_egress_shaping Arcaflow scenarios",
-				"properties": {
-					"id": {
-						"type": "string",
-						"const": "pod_egress_shaping"
-					},
-					"config": {
-						"$defs": {
-							"EgressParams": {
-								"type": "object",
-								"properties": {
-									"namespace": {
-										"type": "string",
-										"minLength": 1,
-										"title": "Namespace",
-										"description": "Namespace of the pod to which filter need to be appliedfor details."
-									},
-									"image": {
-										"type": "string",
-										"minLength": 1,
-										"title": "Image",
-										"default": "image: quay.io/krkn-chaos/krkn:tools",
-										"description": "Image of the krkn tools to run network outage."
-									},
-									"kubeconfig_path": {
-										"type": "string",
-										"title": "Kubeconfig path",
-										"description": "Kubeconfig file as string\nSee https://kubernetes.io/docs/concepts/configuration/organize-cluster-access-kubeconfig/ for details."
-									},
-									"pod_name": {
-										"type": "string",
-										"title": "Pod name",
-										"description": "When label_selector is not specified, pod matching the name will beselected for the chaos scenario"
-									},
-									"label_selector": {
-										"type": "string",
-										"title": "Label selector",
-										"description": "Kubernetes label selector for the target pod. When pod_name is not specified, pod with matching label_selector is selected for chaos scenario"
-									},
-									"kraken_config": {
-										"type": "string",
-										"title": "Kraken Config",
-										"description": "Path to the config file of Kraken. Set this field if you wish to publish status onto Cerberus"
-									},
-									"test_duration": {
-										"type": "integer",
-										"minimum": 1,
-										"default": 90,
-										"title": "Test duration",
-										"description": "Duration for which each step of the ingress chaos testing is to be performed."
-									},
-									"wait_duration": {
-										"type": "integer",
-										"minimum": 1,
-										"default": 300,
-										"title": "Wait Duration",
-										"description": "Wait duration for finishing a test and its cleanup.Ensure that it is significantly greater than wait_duration"
-									},
-									"instance_count": {
-										"type": "integer",
-										"minimum": 1,
-										"default": 1,
-										"title": "Instance Count",
-										"description": "Number of pods to perform action/select that match the label selector."
-									},
-									"execution_type": {
-										"type": "string",
-										"default": "parallel",
-										"title": "Execution Type",
-										"description": "The order in which the ingress filters are applied. Execution type can be 'serial' or 'parallel'"
-									},
-									"network_params": {
-										"type": "object",
-										"propertyNames": {},
-										"additionalProperties": {
-											"type": "string"
-										},
-										"title": "Network Parameters",
-										"description": "The network filters that are applied on the interface. The currently supported filters are latency, loss and bandwidth"
-									}
-								},
-								"required": [
-									"namespace"
-								],
-								"additionalProperties": false,
-								"dependentRequired": {}
-							}
-						},
-						"type": "object",
-						"properties": {
-							"namespace": {
-								"type": "string",
-								"minLength": 1,
-								"title": "Namespace",
-								"description": "Namespace of the pod to which filter need to be appliedfor details."
-							},
-							"kubeconfig_path": {
-								"type": "string",
-								"title": "Kubeconfig path",
-								"description": "Kubeconfig file as string\nSee https://kubernetes.io/docs/concepts/configuration/organize-cluster-access-kubeconfig/ for details."
-							},
-							"pod_name": {
-								"type": "string",
-								"title": "Pod name",
-								"description": "When label_selector is not specified, pod matching the name will beselected for the chaos scenario"
-							},
-							"label_selector": {
-								"type": "string",
-								"title": "Label selector",
-								"description": "Kubernetes label selector for the target pod. When pod_name is not specified, pod with matching label_selector is selected for chaos scenario"
-							},
-							"kraken_config": {
-								"type": "string",
-								"title": "Kraken Config",
-								"description": "Path to the config file of Kraken. Set this field if you wish to publish status onto Cerberus"
-							},
-							"test_duration": {
-								"type": "integer",
-								"minimum": 1,
-								"default": 90,
-								"title": "Test duration",
-								"description": "Duration for which each step of the ingress chaos testing is to be performed."
-							},
-							"wait_duration": {
-								"type": "integer",
-								"minimum": 1,
-								"default": 300,
-								"title": "Wait Duration",
-								"description": "Wait duration for finishing a test and its cleanup.Ensure that it is significantly greater than wait_duration"
-							},
-							"instance_count": {
-								"type": "integer",
-								"minimum": 1,
-								"default": 1,
-								"title": "Instance Count",
-								"description": "Number of pods to perform action/select that match the label selector."
-							},
-							"execution_type": {
-								"type": "string",
-								"default": "parallel",
-								"title": "Execution Type",
-								"description": "The order in which the ingress filters are applied. Execution type can be 'serial' or 'parallel'"
-							},
-							"network_params": {
-								"type": "object",
-								"propertyNames": {},
-								"additionalProperties": {
-									"type": "string"
-								},
-								"title": "Network Parameters",
-								"description": "The network filters that are applied on the interface. The currently supported filters are latency, loss and bandwidth"
-							}
-						},
-						"required": [
-							"namespace"
-						],
-						"additionalProperties": false,
-						"dependentRequired": {}
-					}
-				},
-				"required": [
-					"id",
-					"config"
-				]
-			},
-			{
-				"type": "object",
-				"title": "pod_ingress_shaping Arcaflow scenarios",
-				"properties": {
-					"id": {
-						"type": "string",
-						"const": "pod_ingress_shaping"
-					},
-					"config": {
-						"$defs": {
-							"IngressParams": {
-								"type": "object",
-								"properties": {
-									"namespace": {
-										"type": "string",
-										"minLength": 1,
-										"title": "Namespace",
-										"description": "Namespace of the pod to which filter need to be appliedfor details."
-									},
-									"image": {
-										"type": "string",
-										"minLength": 1,
-										"title": "Image",
-										"default": "image: quay.io/krkn-chaos/krkn:tools",
-										"description": "Image of the krkn tools to run network outage."
-									},
-									"network_params": {
-										"type": "object",
-										"propertyNames": {},
-										"additionalProperties": {
-											"type": "string"
-										},
-										"title": "Network Parameters",
-										"description": "The network filters that are applied on the interface. The currently supported filters are latency, loss and bandwidth"
-									},
-									"kubeconfig_path": {
-										"type": "string",
-										"title": "Kubeconfig path",
-										"description": "Kubeconfig file as string\nSee https://kubernetes.io/docs/concepts/configuration/organize-cluster-access-kubeconfig/ for details."
-									},
-									"pod_name": {
-										"type": "string",
-										"title": "Pod name",
-										"description": "When label_selector is not specified, pod matching the name will beselected for the chaos scenario"
-									},
-									"label_selector": {
-										"type": "string",
-										"title": "Label selector",
-										"description": "Kubernetes label selector for the target pod. When pod_name is not specified, pod with matching label_selector is selected for chaos scenario"
-									},
-									"kraken_config": {
-										"type": "string",
-										"title": "Kraken Config",
-										"description": "Path to the config file of Kraken. Set this field if you wish to publish status onto Cerberus"
-									},
-									"test_duration": {
-										"type": "integer",
-										"minimum": 1,
-										"default": 90,
-										"title": "Test duration",
-										"description": "Duration for which each step of the ingress chaos testing is to be performed."
-									},
-									"wait_duration": {
-										"type": "integer",
-										"minimum": 1,
-										"default": 300,
-										"title": "Wait Duration",
-										"description": "Wait duration for finishing a test and its cleanup.Ensure that it is significantly greater than wait_duration"
-									},
-									"instance_count": {
-										"type": "integer",
-										"minimum": 1,
-										"default": 1,
-										"title": "Instance Count",
-										"description": "Number of pods to perform action/select that match the label selector."
-									},
-									"execution_type": {
-										"type": "string",
-										"default": "parallel",
-										"title": "Execution Type",
-										"description": "The order in which the ingress filters are applied. Execution type can be 'serial' or 'parallel'"
-									}
-								},
-								"required": [
-									"namespace"
-								],
-								"additionalProperties": false,
-								"dependentRequired": {}
-							}
-						},
-						"type": "object",
-						"properties": {
-							"namespace": {
-								"type": "string",
-								"minLength": 1,
-								"title": "Namespace",
-								"description": "Namespace of the pod to which filter need to be appliedfor details."
-							},
-							"network_params": {
-								"type": "object",
-								"propertyNames": {},
-								"additionalProperties": {
-									"type": "string"
-								},
-								"title": "Network Parameters",
-								"description": "The network filters that are applied on the interface. The currently supported filters are latency, loss and bandwidth"
-							},
-							"kubeconfig_path": {
-								"type": "string",
-								"title": "Kubeconfig path",
-								"description": "Kubeconfig file as string\nSee https://kubernetes.io/docs/concepts/configuration/organize-cluster-access-kubeconfig/ for details."
-							},
-							"pod_name": {
-								"type": "string",
-								"title": "Pod name",
-								"description": "When label_selector is not specified, pod matching the name will beselected for the chaos scenario"
-							},
-							"label_selector": {
-								"type": "string",
-								"title": "Label selector",
-								"description": "Kubernetes label selector for the target pod. When pod_name is not specified, pod with matching label_selector is selected for chaos scenario"
-							},
-							"kraken_config": {
-								"type": "string",
-								"title": "Kraken Config",
-								"description": "Path to the config file of Kraken. Set this field if you wish to publish status onto Cerberus"
-							},
-							"test_duration": {
-								"type": "integer",
-								"minimum": 1,
-								"default": 90,
-								"title": "Test duration",
-								"description": "Duration for which each step of the ingress chaos testing is to be performed."
-							},
-							"wait_duration": {
-								"type": "integer",
-								"minimum": 1,
-								"default": 300,
-								"title": "Wait Duration",
-								"description": "Wait duration for finishing a test and its cleanup.Ensure that it is significantly greater than wait_duration"
-							},
-							"instance_count": {
-								"type": "integer",
-								"minimum": 1,
-								"default": 1,
-								"title": "Instance Count",
-								"description": "Number of pods to perform action/select that match the label selector."
-							},
-							"execution_type": {
-								"type": "string",
-								"default": "parallel",
-								"title": "Execution Type",
-								"description": "The order in which the ingress filters are applied. Execution type can be 'serial' or 'parallel'"
-							}
-						},
-						"required": [
-							"namespace"
-						],
-						"additionalProperties": false,
-						"dependentRequired": {}
-					}
-				},
-				"required": [
-					"id",
-					"config"
-				]
-			}
-		]
-	}
-}

tests/rollback_scenario_plugins/simple.py

@@ -0,0 +1,63 @@
+import logging
+
+from krkn_lib.telemetry.ocp import KrknTelemetryOpenshift
+from krkn_lib.models.telemetry import ScenarioTelemetry
+
+from krkn.scenario_plugins.abstract_scenario_plugin import AbstractScenarioPlugin
+from krkn.rollback.config import RollbackContent
+from krkn.rollback.handler import set_rollback_context_decorator
+
+logger = logging.getLogger(__name__)
+logger.setLevel(logging.DEBUG)
+logger.addHandler(logging.StreamHandler())
+
+
+class SimpleRollbackScenarioPlugin(AbstractScenarioPlugin):
+    """
+    Mock implementation of RollbackScenarioPlugin for testing purposes.
+    This plugin does not perform any actual rollback operations.
+    """
+
+    @set_rollback_context_decorator
+    def run(
+        self,
+        run_uuid: str,
+        scenario: str,
+        krkn_config: dict[str, any],
+        lib_telemetry: KrknTelemetryOpenshift,
+        scenario_telemetry: ScenarioTelemetry,
+    ) -> int:
+        logger.info(
+            f"Setting rollback callable for run {run_uuid} with scenario {scenario}."
+        )
+        logger.debug(f"Krkn config: {krkn_config}")
+        self.rollback_handler.set_rollback_callable(
+            self.rollback_callable,
+            RollbackContent(
+                resource_identifier=run_uuid,
+            ),
+        )
+        logger.info("Rollback callable set successfully.")
+        print("Rollback callable has been set for the scenario.")
+        return 0
+
+    def get_scenario_types(self) -> list[str]:
+        """
+        Returns the scenario types that this plugin supports.
+        :return: a list of scenario types
+        """
+        return ["simple_rollback_scenario"]
+
+    @staticmethod
+    def rollback_callable(
+        rollback_context: RollbackContent, lib_telemetry: KrknTelemetryOpenshift
+    ):
+        """
+        Simple rollback callable that simulates a rollback operation.
+        """
+        run_uuid = rollback_context.resource_identifier
+
+        print(f"Rollback called for run {run_uuid}.")
+        # Simulate a rollback operation
+        # In a real scenario, this would contain logic to revert changes made during the scenario execution.
+        print("Rollback operation completed successfully.")

tests/run_python_plugin.py

@@ -0,0 +1,37 @@
+import tempfile
+import unittest
+
+from krkn.scenario_plugins.native.run_python_plugin import (
+    RunPythonFileInput,
+    run_python_file,
+)
+
+
+class RunPythonPluginTest(unittest.TestCase):
+    def test_success_execution(self):
+        tmp_file = tempfile.NamedTemporaryFile()
+        tmp_file.write(bytes("print('Hello world!')", "utf-8"))
+        tmp_file.flush()
+        output_id, output_data = run_python_file(
+            params=RunPythonFileInput(tmp_file.name),
+            run_id="test-python-plugin-success",
+        )
+        self.assertEqual("success", output_id)
+        self.assertEqual("Hello world!\n", output_data.stdout)
+
+    def test_error_execution(self):
+        tmp_file = tempfile.NamedTemporaryFile()
+        tmp_file.write(
+            bytes("import sys\nprint('Hello world!')\nsys.exit(42)\n", "utf-8")
+        )
+        tmp_file.flush()
+        output_id, output_data = run_python_file(
+            params=RunPythonFileInput(tmp_file.name), run_id="test-python-plugin-error"
+        )
+        self.assertEqual("error", output_id)
+        self.assertEqual(42, output_data.exit_code)
+        self.assertEqual("Hello world!\n", output_data.stdout)
+
+
+if __name__ == "__main__":
+    unittest.main()

tests/test_application_outage_scenario_plugin.py

@@ -0,0 +1,40 @@
+#!/usr/bin/env python3
+
+"""
+Test suite for ApplicationOutageScenarioPlugin class
+
+Usage:
+    python -m coverage run -a -m unittest tests/test_application_outage_scenario_plugin.py -v
+
+Assisted By: Claude Code
+"""
+
+import unittest
+from unittest.mock import MagicMock
+
+from krkn_lib.k8s import KrknKubernetes
+from krkn_lib.telemetry.ocp import KrknTelemetryOpenshift
+
+from krkn.scenario_plugins.application_outage.application_outage_scenario_plugin import ApplicationOutageScenarioPlugin
+
+
+class TestApplicationOutageScenarioPlugin(unittest.TestCase):
+
+    def setUp(self):
+        """
+        Set up test fixtures for ApplicationOutageScenarioPlugin
+        """
+        self.plugin = ApplicationOutageScenarioPlugin()
+
+    def test_get_scenario_types(self):
+        """
+        Test get_scenario_types returns correct scenario type
+        """
+        result = self.plugin.get_scenario_types()
+
+        self.assertEqual(result, ["application_outages_scenarios"])
+        self.assertEqual(len(result), 1)
+
+
+if __name__ == "__main__":
+    unittest.main()

tests/test_container_scenario_plugin.py

@@ -0,0 +1,40 @@
+#!/usr/bin/env python3
+
+"""
+Test suite for ContainerScenarioPlugin class
+
+Usage:
+    python -m coverage run -a -m unittest tests/test_container_scenario_plugin.py -v
+
+Assisted By: Claude Code
+"""
+
+import unittest
+from unittest.mock import MagicMock
+
+from krkn_lib.k8s import KrknKubernetes
+from krkn_lib.telemetry.ocp import KrknTelemetryOpenshift
+
+from krkn.scenario_plugins.container.container_scenario_plugin import ContainerScenarioPlugin
+
+
+class TestContainerScenarioPlugin(unittest.TestCase):
+
+    def setUp(self):
+        """
+        Set up test fixtures for ContainerScenarioPlugin
+        """
+        self.plugin = ContainerScenarioPlugin()
+
+    def test_get_scenario_types(self):
+        """
+        Test get_scenario_types returns correct scenario type
+        """
+        result = self.plugin.get_scenario_types()
+
+        self.assertEqual(result, ["container_scenarios"])
+        self.assertEqual(len(result), 1)
+
+
+if __name__ == "__main__":
+    unittest.main()

tests/test_health_checker.py

@@ -0,0 +1,503 @@
+#!/usr/bin/env python3
+
+"""
+Test suite for HealthChecker class
+
+This test file provides comprehensive coverage for the main functionality of HealthChecker:
+- HTTP request making with various authentication methods
+- Health check monitoring with status tracking
+- Failure detection and recovery tracking
+- Exit on failure behavior
+- Telemetry collection
+
+Usage:
+    python -m coverage run -a -m unittest tests/test_health_checker.py -v
+
+Assisted By: Claude Code
+"""
+
+import queue
+import unittest
+from datetime import datetime
+from unittest.mock import MagicMock, patch
+
+from krkn_lib.models.telemetry.models import HealthCheck
+
+from krkn.utils.HealthChecker import HealthChecker
+
+
+class TestHealthChecker(unittest.TestCase):
+
+    def setUp(self):
+        """
+        Set up test fixtures for HealthChecker
+        """
+        self.checker = HealthChecker(iterations=5)
+        self.health_check_queue = queue.Queue()
+
+    def tearDown(self):
+        """
+        Clean up after each test
+        """
+        self.checker.current_iterations = 0
+        self.checker.ret_value = 0
+
+    def make_increment_side_effect(self, response_data):
+        """
+        Helper to create a side effect that increments current_iterations
+        """
+        def side_effect(*args, **kwargs):
+            self.checker.current_iterations += 1
+            return response_data
+        return side_effect
+
+    @patch('requests.get')
+    def test_make_request_success(self, mock_get):
+        """
+        Test make_request returns success for 200 status code
+        """
+        mock_response = MagicMock()
+        mock_response.status_code = 200
+        mock_get.return_value = mock_response
+
+        result = self.checker.make_request("http://example.com")
+
+        self.assertEqual(result["url"], "http://example.com")
+        self.assertEqual(result["status"], True)
+        self.assertEqual(result["status_code"], 200)
+        mock_get.assert_called_once_with(
+            "http://example.com",
+            auth=None,
+            headers=None,
+            verify=True,
+            timeout=3
+        )
+
+    @patch('requests.get')
+    def test_make_request_with_auth(self, mock_get):
+        """
+        Test make_request with basic authentication
+        """
+        mock_response = MagicMock()
+        mock_response.status_code = 200
+        mock_get.return_value = mock_response
+
+        auth = ("user", "pass")
+        result = self.checker.make_request("http://example.com", auth=auth)
+
+        self.assertEqual(result["status"], True)
+        mock_get.assert_called_once_with(
+            "http://example.com",
+            auth=auth,
+            headers=None,
+            verify=True,
+            timeout=3
+        )
+
+    @patch('requests.get')
+    def test_make_request_with_bearer_token(self, mock_get):
+        """
+        Test make_request with bearer token authentication
+        """
+        mock_response = MagicMock()
+        mock_response.status_code = 200
+        mock_get.return_value = mock_response
+
+        headers = {"Authorization": "Bearer token123"}
+        result = self.checker.make_request("http://example.com", headers=headers)
+
+        self.assertEqual(result["status"], True)
+        mock_get.assert_called_once_with(
+            "http://example.com",
+            auth=None,
+            headers=headers,
+            verify=True,
+            timeout=3
+        )
+
+    @patch('requests.get')
+    def test_make_request_failure(self, mock_get):
+        """
+        Test make_request returns failure for non-200 status code
+        """
+        mock_response = MagicMock()
+        mock_response.status_code = 500
+        mock_get.return_value = mock_response
+
+        result = self.checker.make_request("http://example.com")
+
+        self.assertEqual(result["status"], False)
+        self.assertEqual(result["status_code"], 500)
+
+    @patch('requests.get')
+    def test_make_request_with_verify_false(self, mock_get):
+        """
+        Test make_request with SSL verification disabled
+        """
+        mock_response = MagicMock()
+        mock_response.status_code = 200
+        mock_get.return_value = mock_response
+
+        result = self.checker.make_request("https://example.com", verify=False)
+
+        self.assertEqual(result["status"], True)
+        mock_get.assert_called_once_with(
+            "https://example.com",
+            auth=None,
+            headers=None,
+            verify=False,
+            timeout=3
+        )
+
+    @patch('krkn.utils.HealthChecker.HealthChecker.make_request')
+    @patch('time.sleep')
+    def test_run_health_check_empty_config(self, mock_sleep, mock_make_request):
+        """
+        Test run_health_check with empty config skips checks
+        """
+        config = {
+            "config": [],
+            "interval": 2
+        }
+
+        self.checker.run_health_check(config, self.health_check_queue)
+
+        mock_make_request.assert_not_called()
+        self.assertTrue(self.health_check_queue.empty())
+
+    @patch('krkn.utils.HealthChecker.HealthChecker.make_request')
+    @patch('time.sleep')
+    def test_run_health_check_successful_requests(self, mock_sleep, mock_make_request):
+        """
+        Test run_health_check with all successful requests
+        """
+        mock_make_request.side_effect = self.make_increment_side_effect({
+            "url": "http://example.com",
+            "status": True,
+            "status_code": 200
+        })
+
+        config = {
+            "config": [
+                {
+                    "url": "http://example.com",
+                    "bearer_token": None,
+                    "auth": None,
+                    "exit_on_failure": False
+                }
+            ],
+            "interval": 0.01
+        }
+
+        self.checker.iterations = 2
+        self.checker.run_health_check(config, self.health_check_queue)
+
+        # Should have telemetry
+        self.assertFalse(self.health_check_queue.empty())
+        telemetry = self.health_check_queue.get()
+        self.assertEqual(len(telemetry), 1)
+        self.assertEqual(telemetry[0].status, True)
+
+    @patch('krkn.utils.HealthChecker.HealthChecker.make_request')
+    @patch('time.sleep')
+    def test_run_health_check_failure_then_recovery(self, mock_sleep, mock_make_request):
+        """
+        Test run_health_check detects failure and recovery
+        """
+        # Create side effects that increment and return different values
+        call_count = [0]
+        def side_effect(*args, **kwargs):
+            self.checker.current_iterations += 1
+            call_count[0] += 1
+            if call_count[0] == 1:
+                return {"url": "http://example.com", "status": False, "status_code": 500}
+            else:
+                return {"url": "http://example.com", "status": True, "status_code": 200}
+
+        mock_make_request.side_effect = side_effect
+
+        config = {
+            "config": [
+                {
+                    "url": "http://example.com",
+                    "bearer_token": None,
+                    "auth": None,
+                    "exit_on_failure": False
+                }
+            ],
+            "interval": 0.01
+        }
+
+        self.checker.iterations = 3
+        self.checker.run_health_check(config, self.health_check_queue)
+
+        # Should have telemetry showing failure period
+        self.assertFalse(self.health_check_queue.empty())
+        telemetry = self.health_check_queue.get()
+
+        # Should have at least 2 entries: one for failure period, one for success period
+        self.assertGreaterEqual(len(telemetry), 1)
+
+    @patch('krkn.utils.HealthChecker.HealthChecker.make_request')
+    @patch('time.sleep')
+    def test_run_health_check_with_bearer_token(self, mock_sleep, mock_make_request):
+        """
+        Test run_health_check correctly handles bearer token
+        """
+        mock_make_request.side_effect = self.make_increment_side_effect({
+            "url": "http://example.com",
+            "status": True,
+            "status_code": 200
+        })
+
+        config = {
+            "config": [
+                {
+                    "url": "http://example.com",
+                    "bearer_token": "test-token-123",
+                    "auth": None,
+                    "exit_on_failure": False
+                }
+            ],
+            "interval": 0.01
+        }
+
+        self.checker.iterations = 1
+        self.checker.run_health_check(config, self.health_check_queue)
+
+        # Verify bearer token was added to headers
+        # make_request is called as: make_request(url, auth, headers, verify_url)
+        call_args = mock_make_request.call_args
+        self.assertEqual(call_args[0][2]['Authorization'], "Bearer test-token-123")
+
+    @patch('krkn.utils.HealthChecker.HealthChecker.make_request')
+    @patch('time.sleep')
+    def test_run_health_check_with_auth(self, mock_sleep, mock_make_request):
+        """
+        Test run_health_check correctly handles basic auth
+        """
+        mock_make_request.side_effect = self.make_increment_side_effect({
+            "url": "http://example.com",
+            "status": True,
+            "status_code": 200
+        })
+
+        config = {
+            "config": [
+                {
+                    "url": "http://example.com",
+                    "bearer_token": None,
+                    "auth": "user,pass",
+                    "exit_on_failure": False
+                }
+            ],
+            "interval": 0.01
+        }
+
+        self.checker.iterations = 1
+        self.checker.run_health_check(config, self.health_check_queue)
+
+        # Verify auth tuple was created correctly
+        # make_request is called as: make_request(url, auth, headers, verify_url)
+        call_args = mock_make_request.call_args
+        self.assertEqual(call_args[0][1], ("user", "pass"))
+
+    @patch('krkn.utils.HealthChecker.HealthChecker.make_request')
+    @patch('time.sleep')
+    def test_run_health_check_exit_on_failure(self, mock_sleep, mock_make_request):
+        """
+        Test run_health_check sets ret_value=2 when exit_on_failure is True
+        """
+        mock_make_request.side_effect = self.make_increment_side_effect({
+            "url": "http://example.com",
+            "status": False,
+            "status_code": 500
+        })
+
+        config = {
+            "config": [
+                {
+                    "url": "http://example.com",
+                    "bearer_token": None,
+                    "auth": None,
+                    "exit_on_failure": True
+                }
+            ],
+            "interval": 0.01
+        }
+
+        self.checker.iterations = 1
+        self.checker.run_health_check(config, self.health_check_queue)
+
+        # ret_value should be set to 2 on failure
+        self.assertEqual(self.checker.ret_value, 2)
+
+    @patch('krkn.utils.HealthChecker.HealthChecker.make_request')
+    @patch('time.sleep')
+    def test_run_health_check_exit_on_failure_not_set_on_success(self, mock_sleep, mock_make_request):
+        """
+        Test run_health_check does not set ret_value when request succeeds
+        """
+        mock_make_request.side_effect = self.make_increment_side_effect({
+            "url": "http://example.com",
+            "status": True,
+            "status_code": 200
+        })
+
+        config = {
+            "config": [
+                {
+                    "url": "http://example.com",
+                    "bearer_token": None,
+                    "auth": None,
+                    "exit_on_failure": True
+                }
+            ],
+            "interval": 0.01
+        }
+
+        self.checker.iterations = 1
+        self.checker.run_health_check(config, self.health_check_queue)
+
+        # ret_value should remain 0 on success
+        self.assertEqual(self.checker.ret_value, 0)
+
+    @patch('krkn.utils.HealthChecker.HealthChecker.make_request')
+    @patch('time.sleep')
+    def test_run_health_check_with_verify_url_false(self, mock_sleep, mock_make_request):
+        """
+        Test run_health_check respects verify_url setting
+        """
+        mock_make_request.side_effect = self.make_increment_side_effect({
+            "url": "https://example.com",
+            "status": True,
+            "status_code": 200
+        })
+
+        config = {
+            "config": [
+                {
+                    "url": "https://example.com",
+                    "bearer_token": None,
+                    "auth": None,
+                    "exit_on_failure": False,
+                    "verify_url": False
+                }
+            ],
+            "interval": 0.01
+        }
+
+        self.checker.iterations = 1
+        self.checker.run_health_check(config, self.health_check_queue)
+
+        # Verify that verify parameter was set to False
+        # make_request is called as: make_request(url, auth, headers, verify_url)
+        call_args = mock_make_request.call_args
+        self.assertEqual(call_args[0][3], False)
+
+    @patch('krkn.utils.HealthChecker.HealthChecker.make_request')
+    @patch('time.sleep')
+    def test_run_health_check_exception_handling(self, mock_sleep, mock_make_request):
+        """
+        Test run_health_check handles exceptions during requests
+        """
+        # Simulate exception during request but also increment to avoid infinite loop
+        def side_effect(*args, **kwargs):
+            self.checker.current_iterations += 1
+            raise Exception("Connection error")
+
+        mock_make_request.side_effect = side_effect
+
+        config = {
+            "config": [
+                {
+                    "url": "http://example.com",
+                    "bearer_token": None,
+                    "auth": None,
+                    "exit_on_failure": False
+                }
+            ],
+            "interval": 0.01
+        }
+
+        self.checker.iterations = 1
+
+        # Should not raise exception
+        self.checker.run_health_check(config, self.health_check_queue)
+
+    @patch('krkn.utils.HealthChecker.HealthChecker.make_request')
+    @patch('time.sleep')
+    def test_run_health_check_multiple_urls(self, mock_sleep, mock_make_request):
+        """
+        Test run_health_check with multiple URLs
+        """
+        call_count = [0]
+        def side_effect(*args, **kwargs):
+            call_count[0] += 1
+            # Increment only after both URLs are called (one iteration)
+            if call_count[0] % 2 == 0:
+                self.checker.current_iterations += 1
+            return {
+                "status": True,
+                "status_code": 200
+            }
+
+        mock_make_request.side_effect = side_effect
+
+        config = {
+            "config": [
+                {
+                    "url": "http://example1.com",
+                    "bearer_token": None,
+                    "auth": None,
+                    "exit_on_failure": False
+                },
+                {
+                    "url": "http://example2.com",
+                    "bearer_token": None,
+                    "auth": None,
+                    "exit_on_failure": False
+                }
+            ],
+            "interval": 0.01
+        }
+
+        self.checker.iterations = 1
+        self.checker.run_health_check(config, self.health_check_queue)
+
+        # Should have called make_request for both URLs
+        self.assertEqual(mock_make_request.call_count, 2)
+
+    @patch('krkn.utils.HealthChecker.HealthChecker.make_request')
+    @patch('time.sleep')
+    def test_run_health_check_custom_interval(self, mock_sleep, mock_make_request):
+        """
+        Test run_health_check uses custom interval
+        """
+        mock_make_request.side_effect = self.make_increment_side_effect({
+            "url": "http://example.com",
+            "status": True,
+            "status_code": 200
+        })
+
+        config = {
+            "config": [
+                {
+                    "url": "http://example.com",
+                    "bearer_token": None,
+                    "auth": None,
+                    "exit_on_failure": False
+                }
+            ],
+            "interval": 5
+        }
+
+        self.checker.iterations = 2
+        self.checker.run_health_check(config, self.health_check_queue)
+
+        # Verify sleep was called with custom interval
+        mock_sleep.assert_called_with(5)
+
+
+if __name__ == "__main__":
+    unittest.main()

tests/test_hogs_scenario_plugin.py

@@ -0,0 +1,40 @@
+#!/usr/bin/env python3
+
+"""
+Test suite for HogsScenarioPlugin class
+
+Usage:
+    python -m coverage run -a -m unittest tests/test_hogs_scenario_plugin.py -v
+
+Assisted By: Claude Code
+"""
+
+import unittest
+from unittest.mock import MagicMock
+
+from krkn_lib.k8s import KrknKubernetes
+from krkn_lib.telemetry.ocp import KrknTelemetryOpenshift
+
+from krkn.scenario_plugins.hogs.hogs_scenario_plugin import HogsScenarioPlugin
+
+
+class TestHogsScenarioPlugin(unittest.TestCase):
+
+    def setUp(self):
+        """
+        Set up test fixtures for HogsScenarioPlugin
+        """
+        self.plugin = HogsScenarioPlugin()
+
+    def test_get_scenario_types(self):
+        """
+        Test get_scenario_types returns correct scenario type
+        """
+        result = self.plugin.get_scenario_types()
+
+        self.assertEqual(result, ["hog_scenarios"])
+        self.assertEqual(len(result), 1)
+
+
+if __name__ == "__main__":
+    unittest.main()

tests/test_kubevirt_vm_outage.py

@@ -0,0 +1,696 @@
+#!/usr/bin/env python3
+
+"""
+Test suite for KubeVirt VM Outage Scenario Plugin class
+
+Note: This test file uses mocks extensively to avoid needing actual Kubernetes/KubeVirt infrastructure.
+
+Usage:
+    python -m coverage run -a -m unittest tests/test_kubevirt_vm_outage.py -v
+
+Assisted By: Claude Code
+"""
+
+import copy
+import itertools
+import os
+import tempfile
+import unittest
+from unittest.mock import MagicMock, patch
+
+import yaml
+from krkn_lib.k8s import KrknKubernetes
+from krkn_lib.models.k8s import AffectedPod, PodsStatus
+from krkn_lib.models.telemetry import ScenarioTelemetry
+from krkn_lib.telemetry.ocp import KrknTelemetryOpenshift
+from kubernetes.client.rest import ApiException
+
+from krkn.scenario_plugins.kubevirt_vm_outage.kubevirt_vm_outage_scenario_plugin import KubevirtVmOutageScenarioPlugin
+
+class TestKubevirtVmOutageScenarioPlugin(unittest.TestCase):
+    
+    def setUp(self):
+        """
+        Set up test fixtures for KubevirtVmOutageScenarioPlugin
+        """
+        self.plugin = KubevirtVmOutageScenarioPlugin()
+
+        # Create mock k8s client
+        self.k8s_client = MagicMock()
+        self.custom_object_client = MagicMock()
+        self.k8s_client.custom_object_client = self.custom_object_client
+        self.plugin.k8s_client = self.k8s_client
+        self.plugin.custom_object_client = self.custom_object_client
+
+        # Mock methods needed for KubeVirt operations
+        self.k8s_client.list_custom_resource_definition = MagicMock()
+
+        # Mock custom resource definition list with KubeVirt CRDs
+        crd_list = MagicMock()
+        crd_item = MagicMock()
+        crd_item.spec = MagicMock()
+        crd_item.spec.group = "kubevirt.io"
+        crd_list.items = [crd_item]
+        self.k8s_client.list_custom_resource_definition.return_value = crd_list
+        
+        # Mock VMI data
+        self.mock_vmi = {
+            "metadata": {
+                "name": "test-vm",
+                "namespace": "default"
+            },
+            "status": {
+                "phase": "Running"
+            }
+        }
+        
+        # Create test config
+        self.config = {
+            "scenarios": [
+                {
+                    "name": "kubevirt outage test",
+                    "scenario": "kubevirt_vm_outage",
+                    "parameters": {
+                        "vm_name": "test-vm",
+                        "namespace": "default",
+                        "duration": 0  
+                    }
+                }
+            ]
+        }
+        
+        # Create a temporary config file
+        temp_dir = tempfile.gettempdir()
+        self.scenario_file = os.path.join(temp_dir, "test_kubevirt_scenario.yaml")
+        with open(self.scenario_file, "w") as f:
+            yaml.dump(self.config, f)
+            
+        # Mock dependencies
+        self.telemetry = MagicMock(spec=KrknTelemetryOpenshift)
+        self.scenario_telemetry = MagicMock(spec=ScenarioTelemetry)
+        self.telemetry.get_lib_kubernetes.return_value = self.k8s_client
+
+        # Initialize counters for reusable mock functions
+        self.delete_count = 0
+        self.wait_count = 0
+
+    def mock_delete(self, *args, **kwargs):
+        self.delete_count += 1
+        self.plugin.affected_pod = AffectedPod(pod_name=f"test-vm-{self.delete_count}", namespace="default")
+        self.plugin.affected_pod.pod_rescheduling_time = 5.0
+        return 0
+
+    def mock_wait(self, *args, **kwargs):
+        self.wait_count += 1
+        self.plugin.affected_pod.pod_readiness_time = 3.0
+        return 0
+    
+    def test_successful_injection_and_recovery(self):
+        """
+        Test successful deletion and recovery of a VMI
+        """
+        # Populate vmis_list to avoid randrange error
+        self.plugin.vmis_list = [self.mock_vmi]
+
+        # Mock get_vmis to not clear the list
+        with patch.object(self.plugin, 'get_vmis'):
+            # Mock get_vmi to return our mock VMI
+            with patch.object(self.plugin, 'get_vmi', return_value=self.mock_vmi):
+                # Mock validate_environment to return True
+                with patch.object(self.plugin, 'validate_environment', return_value=True):
+                    # Mock delete_vmi and wait_for_running to simulate success
+                    with patch.object(self.plugin, 'delete_vmi', side_effect=self.mock_delete) as mock_delete:
+                        with patch.object(self.plugin, 'wait_for_running', side_effect=self.mock_wait) as mock_wait:
+                            with patch("builtins.open", unittest.mock.mock_open(read_data=yaml.dump(self.config))):
+                                result = self.plugin.run("test-uuid", self.scenario_file, {}, self.telemetry, self.scenario_telemetry)
+
+        self.assertEqual(result, 0)
+        mock_delete.assert_called_once_with("test-vm", "default", False)
+        mock_wait.assert_called_once_with("test-vm", "default", 60)
+        
+    def test_injection_failure(self):
+        """
+        Test failure during VMI deletion
+        """
+        # Populate vmis_list to avoid randrange error
+        self.plugin.vmis_list = [self.mock_vmi]
+
+        # Mock get_vmis to not clear the list
+        with patch.object(self.plugin, 'get_vmis'):
+            # Mock get_vmi to return our mock VMI
+            with patch.object(self.plugin, 'get_vmi', return_value=self.mock_vmi):
+                # Mock validate_environment to return True
+                with patch.object(self.plugin, 'validate_environment', return_value=True):
+                    # Mock delete_vmi to simulate failure
+                    with patch.object(self.plugin, 'delete_vmi', return_value=1) as mock_delete:
+                        with patch.object(self.plugin, 'wait_for_running', return_value=0) as mock_wait:
+                            with patch("builtins.open", unittest.mock.mock_open(read_data=yaml.dump(self.config))):
+                                result = self.plugin.run("test-uuid", self.scenario_file, {}, self.telemetry, self.scenario_telemetry)
+
+        self.assertEqual(result, 0)
+        mock_delete.assert_called_once_with("test-vm", "default", False)
+        mock_wait.assert_not_called()
+        
+    def test_disable_auto_restart(self):
+        """
+        Test VM auto-restart can be disabled
+        """
+        # Configure test with disable_auto_restart=True
+        self.config["scenarios"][0]["parameters"]["disable_auto_restart"] = True
+
+        # Populate vmis_list to avoid randrange error
+        self.plugin.vmis_list = [self.mock_vmi]
+
+        # Mock get_vmis to not clear the list
+        with patch.object(self.plugin, 'get_vmis'):
+            # Mock get_vmi to return our mock VMI
+            with patch.object(self.plugin, 'get_vmi', return_value=self.mock_vmi):
+                # Mock validate_environment to return True
+                with patch.object(self.plugin, 'validate_environment', return_value=True):
+                    # Mock delete_vmi and wait_for_running
+                    with patch.object(self.plugin, 'delete_vmi', side_effect=self.mock_delete) as mock_delete:
+                        with patch.object(self.plugin, 'wait_for_running', side_effect=self.mock_wait) as mock_wait:
+                            with patch("builtins.open", unittest.mock.mock_open(read_data=yaml.dump(self.config))):
+                                result = self.plugin.run("test-uuid", self.scenario_file, {}, self.telemetry, self.scenario_telemetry)
+
+        self.assertEqual(result, 0)
+        # delete_vmi should be called with disable_auto_restart=True
+        mock_delete.assert_called_once_with("test-vm", "default", True)
+        mock_wait.assert_called_once_with("test-vm", "default", 60)
+        
+    def test_recovery_when_vmi_does_not_exist(self):
+        """
+        Test recovery logic when VMI does not exist after deletion
+        """
+        # Initialize the plugin's custom_object_client
+        self.plugin.custom_object_client = self.custom_object_client
+
+        # Store the original VMI in the plugin for recovery
+        self.plugin.original_vmi = self.mock_vmi.copy()
+
+        # Create a cleaned vmi_dict as the plugin would
+        vmi_dict = self.mock_vmi.copy()
+
+        # Set up running VMI data for after recovery
+        running_vmi = {
+            "metadata": {"name": "test-vm", "namespace": "default"},
+            "status": {"phase": "Running"}
+        }
+
+        # Set up time.time to immediately exceed the timeout for auto-recovery
+        with patch('time.time', side_effect=[0, 301, 301, 301, 301, 310, 320]):
+            # Mock get_vmi to always return None (not auto-recovered)
+            with patch.object(self.plugin, 'get_vmi', side_effect=[None, None, running_vmi]):
+                # Mock the custom object API to return success
+                self.custom_object_client.create_namespaced_custom_object = MagicMock(return_value=running_vmi)
+
+                # Run recovery with mocked time.sleep
+                with patch('time.sleep'):
+                    result = self.plugin.recover("test-vm", "default", False)
+
+        self.assertEqual(result, 0)
+        # Verify create was called with the right arguments for our API version and kind
+        self.custom_object_client.create_namespaced_custom_object.assert_called_once_with(
+            group="kubevirt.io",
+            version="v1",
+            namespace="default",
+            plural="virtualmachineinstances",
+            body=vmi_dict
+        )
+    
+    def test_validation_failure(self):
+        """
+        Test validation failure when KubeVirt is not installed
+        """
+        # Populate vmis_list to avoid randrange error
+        self.plugin.vmis_list = [self.mock_vmi]
+
+        # Mock get_vmis to not clear the list
+        with patch.object(self.plugin, 'get_vmis'):
+            # Mock get_vmi to return our mock VMI
+            with patch.object(self.plugin, 'get_vmi', return_value=self.mock_vmi):
+                # Mock validate_environment to return False (KubeVirt not installed)
+                with patch.object(self.plugin, 'validate_environment', return_value=False):
+                    with patch("builtins.open", unittest.mock.mock_open(read_data=yaml.dump(self.config))):
+                        result = self.plugin.run("test-uuid", self.scenario_file, {}, self.telemetry, self.scenario_telemetry)
+
+        # When validation fails, run() returns 1 due to exception handling
+        self.assertEqual(result, 1)
+        
+    def test_delete_vmi_timeout(self):
+        """
+        Test timeout during VMI deletion
+        """
+        # Initialize the plugin's custom_object_client and required attributes
+        self.plugin.custom_object_client = self.custom_object_client
+
+        # Initialize original_vmi which is required by delete_vmi
+        self.plugin.original_vmi = self.mock_vmi.copy()
+        self.plugin.original_vmi['metadata']['creationTimestamp'] = '2023-01-01T00:00:00Z'
+
+        # Initialize pods_status which delete_vmi needs
+        from krkn_lib.models.k8s import PodsStatus, AffectedPod
+        self.plugin.pods_status = PodsStatus()
+        self.plugin.affected_pod = AffectedPod(pod_name="test-vm", namespace="default")
+
+        # Mock successful delete operation
+        self.custom_object_client.delete_namespaced_custom_object = MagicMock(return_value={})
+
+        # Mock that get_vmi always returns VMI with same creationTimestamp (never gets recreated)
+        mock_vmi_with_time = self.mock_vmi.copy()
+        mock_vmi_with_time['metadata']['creationTimestamp'] = '2023-01-01T00:00:00Z'
+
+        with patch.object(self.plugin, 'get_vmi', return_value=mock_vmi_with_time):
+            # Simulate timeout by making time.time return values that exceed the timeout
+            with patch('time.sleep'), patch('time.time', side_effect=[0, 10, 20, 130, 130, 130, 130, 140]):
+                result = self.plugin.delete_vmi("test-vm", "default", False)
+
+        self.assertEqual(result, 1)
+        self.custom_object_client.delete_namespaced_custom_object.assert_called_once_with(
+            group="kubevirt.io",
+            version="v1",
+            namespace="default",
+            plural="virtualmachineinstances",
+            name="test-vm"
+        )
+
+
+    def test_get_vmi_api_exception_non_404(self):
+        """
+        Test get_vmi raises ApiException for non-404 errors
+        """
+
+        # Mock API exception with non-404 status
+        api_error = ApiException(status=500, reason="Internal Server Error")
+        self.custom_object_client.get_namespaced_custom_object = MagicMock(side_effect=api_error)
+
+        with self.assertRaises(ApiException):
+            self.plugin.get_vmi("test-vm", "default")
+
+    def test_get_vmi_general_exception(self):
+        """
+        Test get_vmi raises general exceptions
+        """
+        # Mock general exception
+        self.custom_object_client.get_namespaced_custom_object = MagicMock(
+            side_effect=Exception("Connection error")
+        )
+
+        with self.assertRaises(Exception):
+            self.plugin.get_vmi("test-vm", "default")
+
+    def test_get_vmis_with_regex_matching(self):
+        """
+        Test get_vmis successfully filters VMIs by regex pattern
+        """
+        # Mock namespace list
+        self.k8s_client.list_namespaces_by_regex = MagicMock(return_value=["default", "test-ns"])
+
+        # Mock VMI list with multiple VMIs
+        vmi_list = {
+            "items": [
+                {"metadata": {"name": "test-vm-1"}, "status": {"phase": "Running"}},
+                {"metadata": {"name": "test-vm-2"}, "status": {"phase": "Running"}},
+                {"metadata": {"name": "other-vm"}, "status": {"phase": "Running"}},
+            ]
+        }
+        self.custom_object_client.list_namespaced_custom_object = MagicMock(return_value=vmi_list)
+
+        # Test with regex pattern that matches test-vm-*
+        self.plugin.get_vmis("test-vm-.*", "default")
+
+        # Should have 4 VMs (2 per namespace * 2 namespaces)
+        self.assertEqual(len(self.plugin.vmis_list), 4)
+        # Verify only test-vm-* were added
+        for vmi in self.plugin.vmis_list:
+            self.assertTrue(vmi["metadata"]["name"].startswith("test-vm-"))
+
+    def test_get_vmis_api_exception_404(self):
+        """
+        Test get_vmis handles 404 ApiException gracefully
+        """
+
+        self.k8s_client.list_namespaces_by_regex = MagicMock(return_value=["default"])
+        api_error = ApiException(status=404, reason="Not Found")
+        self.custom_object_client.list_namespaced_custom_object = MagicMock(side_effect=api_error)
+
+        # Should not raise, returns empty list
+        result = self.plugin.get_vmis("test-vm", "default")
+        self.assertEqual(result, [])
+
+    def test_get_vmis_api_exception_non_404(self):
+        """
+        Test get_vmis raises ApiException for non-404 errors
+        """
+
+        self.k8s_client.list_namespaces_by_regex = MagicMock(return_value=["default"])
+        api_error = ApiException(status=500, reason="Internal Server Error")
+        self.custom_object_client.list_namespaced_custom_object = MagicMock(side_effect=api_error)
+
+        with self.assertRaises(ApiException):
+            self.plugin.get_vmis("test-vm", "default")
+
+    def test_patch_vm_spec_success(self):
+        """
+        Test patch_vm_spec successfully patches VM
+        """
+        mock_vm = {
+            "metadata": {"name": "test-vm", "namespace": "default"},
+            "spec": {"running": True}
+        }
+
+        self.custom_object_client.get_namespaced_custom_object = MagicMock(return_value=mock_vm)
+        self.custom_object_client.patch_namespaced_custom_object = MagicMock(return_value=mock_vm)
+
+        result = self.plugin.patch_vm_spec("test-vm", "default", False)
+
+        self.assertTrue(result)
+        self.custom_object_client.patch_namespaced_custom_object.assert_called_once()
+
+    def test_patch_vm_spec_api_exception(self):
+        """
+        Test patch_vm_spec handles ApiException
+        """
+
+        api_error = ApiException(status=404, reason="Not Found")
+        self.custom_object_client.get_namespaced_custom_object = MagicMock(side_effect=api_error)
+
+        result = self.plugin.patch_vm_spec("test-vm", "default", False)
+
+        self.assertFalse(result)
+
+    def test_patch_vm_spec_general_exception(self):
+        """
+        Test patch_vm_spec handles general exceptions
+        """
+        self.custom_object_client.get_namespaced_custom_object = MagicMock(
+            side_effect=Exception("Connection error")
+        )
+
+        result = self.plugin.patch_vm_spec("test-vm", "default", False)
+
+        self.assertFalse(result)
+
+    def test_delete_vmi_api_exception_404(self):
+        """
+        Test delete_vmi handles 404 ApiException during deletion
+        """
+
+        # Initialize required attributes
+        self.plugin.original_vmi = self.mock_vmi.copy()
+        self.plugin.original_vmi['metadata']['creationTimestamp'] = '2023-01-01T00:00:00Z'
+        self.plugin.pods_status = PodsStatus()
+        self.plugin.affected_pod = AffectedPod(pod_name="test-vm", namespace="default")
+
+        api_error = ApiException(status=404, reason="Not Found")
+        self.custom_object_client.delete_namespaced_custom_object = MagicMock(side_effect=api_error)
+
+        result = self.plugin.delete_vmi("test-vm", "default", False)
+
+        self.assertEqual(result, 1)
+
+    def test_delete_vmi_api_exception_non_404(self):
+        """
+        Test delete_vmi handles non-404 ApiException during deletion
+        """
+        # Initialize required attributes
+        self.plugin.original_vmi = self.mock_vmi.copy()
+        self.plugin.original_vmi['metadata']['creationTimestamp'] = '2023-01-01T00:00:00Z'
+        self.plugin.pods_status = PodsStatus()
+        self.plugin.affected_pod = AffectedPod(pod_name="test-vm", namespace="default")
+
+        api_error = ApiException(status=500, reason="Internal Server Error")
+        self.custom_object_client.delete_namespaced_custom_object = MagicMock(side_effect=api_error)
+
+        result = self.plugin.delete_vmi("test-vm", "default", False)
+
+        self.assertEqual(result, 1)
+
+    def test_delete_vmi_successful_recreation(self):
+        """
+        Test delete_vmi succeeds when VMI is recreated with new creationTimestamp
+        """
+        # Initialize required attributes - use deepcopy to avoid shared references
+        self.plugin.original_vmi = copy.deepcopy(self.mock_vmi)
+        self.plugin.original_vmi['metadata']['creationTimestamp'] = '2023-01-01T00:00:00Z'
+        self.plugin.pods_status = PodsStatus()
+        self.plugin.affected_pod = AffectedPod(pod_name="test-vm", namespace="default")
+
+        self.custom_object_client.delete_namespaced_custom_object = MagicMock(return_value={})
+
+        # Mock get_vmi to return VMI with new creationTimestamp - use deepcopy
+        new_vmi = copy.deepcopy(self.mock_vmi)
+        new_vmi['metadata']['creationTimestamp'] = '2023-01-01T00:05:00Z'
+
+        # Use itertools to create an infinite iterator for time values
+        time_iter = itertools.count(0, 0.001)
+
+        with patch.object(self.plugin, 'get_vmi', return_value=new_vmi):
+            with patch('time.sleep'):
+                with patch('time.time', side_effect=lambda: next(time_iter)):
+                    result = self.plugin.delete_vmi("test-vm", "default", False)
+
+        self.assertEqual(result, 0)
+        self.assertIsNotNone(self.plugin.affected_pod.pod_rescheduling_time)
+
+    def test_delete_vmi_with_disable_auto_restart_failure(self):
+        """
+        Test delete_vmi continues when patch_vm_spec fails and VMI stays deleted
+        """
+        # Initialize required attributes
+        self.plugin.original_vmi = self.mock_vmi.copy()
+        self.plugin.original_vmi['metadata']['creationTimestamp'] = '2023-01-01T00:00:00Z'
+        self.plugin.pods_status = PodsStatus()
+        self.plugin.affected_pod = AffectedPod(pod_name="test-vm", namespace="default")
+
+        # Mock patch_vm_spec to fail
+        with patch.object(self.plugin, 'patch_vm_spec', return_value=False):
+            self.custom_object_client.delete_namespaced_custom_object = MagicMock(return_value={})
+
+            # Mock VMI deleted (returns None) - it will timeout waiting for recreation
+            with patch.object(self.plugin, 'get_vmi', return_value=None):
+                with patch('time.sleep'):
+                    # Use itertools to create infinite time sequence
+                    # Use 1.0 increment to quickly reach timeout (120 seconds)
+                    time_iter = itertools.count(0, 1.0)
+                    with patch('time.time', side_effect=lambda: next(time_iter)):
+                        result = self.plugin.delete_vmi("test-vm", "default", True)
+
+        # When VMI stays deleted (None), delete_vmi waits for recreation and times out
+        self.assertEqual(result, 1)
+
+    def test_wait_for_running_timeout(self):
+        """
+        Test wait_for_running times out when VMI doesn't reach Running state
+        """
+        self.plugin.affected_pod = AffectedPod(pod_name="test-vm", namespace="default")
+
+        # Mock VMI in Pending state
+        pending_vmi = self.mock_vmi.copy()
+        pending_vmi['status']['phase'] = 'Pending'
+
+        with patch.object(self.plugin, 'get_vmi', return_value=pending_vmi):
+            with patch('time.sleep'):
+                with patch('time.time', side_effect=[0, 10, 20, 30, 40, 50, 60, 70, 80, 90, 100, 110, 121]):
+                    result = self.plugin.wait_for_running("test-vm", "default", 120)
+
+        self.assertEqual(result, 1)
+
+    def test_wait_for_running_vmi_not_exists(self):
+        """
+        Test wait_for_running when VMI doesn't exist yet
+        """
+        self.plugin.affected_pod = AffectedPod(pod_name="test-vm", namespace="default")
+
+        # First return None (not exists), then return running VMI
+        running_vmi = self.mock_vmi.copy()
+        running_vmi['status']['phase'] = 'Running'
+
+        with patch.object(self.plugin, 'get_vmi', side_effect=[None, None, running_vmi]):
+            with patch('time.sleep'):
+                # time.time() called: start_time (0), while loop iteration 1 (1), iteration 2 (2), iteration 3 (3), end_time (3)
+                with patch('time.time', side_effect=[0, 1, 2, 3, 3]):
+                    result = self.plugin.wait_for_running("test-vm", "default", 120)
+
+        self.assertEqual(result, 0)
+        self.assertIsNotNone(self.plugin.affected_pod.pod_readiness_time)
+
+    def test_recover_no_original_vmi(self):
+        """
+        Test recover fails when no original VMI is captured
+        """
+        self.plugin.original_vmi = None
+
+        result = self.plugin.recover("test-vm", "default", False)
+
+        self.assertEqual(result, 1)
+
+    def test_recover_exception_during_creation(self):
+        """
+        Test recover handles exception during VMI creation
+        """
+        self.plugin.original_vmi = self.mock_vmi.copy()
+
+        self.custom_object_client.create_namespaced_custom_object = MagicMock(
+            side_effect=Exception("Creation failed")
+        )
+
+        with patch.object(self.plugin, 'get_vmi', return_value=None):
+            with patch('time.sleep'):
+                with patch('time.time', side_effect=[0, 301]):
+                    result = self.plugin.recover("test-vm", "default", False)
+
+        self.assertEqual(result, 1)
+
+    def test_execute_scenario_missing_vm_name(self):
+        """
+        Test execute_scenario fails when vm_name is missing
+        """
+        config = {
+            "parameters": {
+                "namespace": "default"
+            }
+        }
+
+        result = self.plugin.execute_scenario(config, self.scenario_telemetry)
+
+        self.assertEqual(result, 1)
+
+    def test_execute_scenario_vmi_not_found(self):
+        """
+        Test execute_scenario when VMI is not found after get_vmi
+        """
+        self.plugin.vmis_list = [self.mock_vmi]
+
+        config = {
+            "parameters": {
+                "vm_name": "test-vm",
+                "namespace": "default"
+            }
+        }
+
+        with patch.object(self.plugin, 'get_vmis'):
+            with patch.object(self.plugin, 'validate_environment', return_value=True):
+                # First get_vmi returns VMI, second returns None
+                with patch.object(self.plugin, 'get_vmi', side_effect=[self.mock_vmi, None]):
+                    result = self.plugin.execute_scenario(config, self.scenario_telemetry)
+
+        # Should be PodsStatus with unrecovered pod
+        self.assertIsInstance(result, type(self.plugin.pods_status))
+
+    def test_execute_scenario_with_kill_count(self):
+        """
+        Test execute_scenario with kill_count > 1
+        """
+        # Create multiple VMIs
+        vmi_1 = self.mock_vmi.copy()
+        vmi_1["metadata"]["name"] = "test-vm-1"
+        vmi_2 = self.mock_vmi.copy()
+        vmi_2["metadata"]["name"] = "test-vm-2"
+
+        self.plugin.vmis_list = [vmi_1, vmi_2]
+
+        config = {
+            "parameters": {
+                "vm_name": "test-vm",
+                "namespace": "default",
+                "kill_count": 2
+            }
+        }
+
+        # Reset counters
+        self.delete_count = 0
+        self.wait_count = 0
+
+        with patch.object(self.plugin, 'get_vmis'):
+            with patch.object(self.plugin, 'validate_environment', return_value=True):
+                with patch.object(self.plugin, 'get_vmi', side_effect=[vmi_1, vmi_2]):
+                    with patch.object(self.plugin, 'delete_vmi', side_effect=self.mock_delete) as mock_del:
+                        with patch.object(self.plugin, 'wait_for_running', side_effect=self.mock_wait) as mock_wt:
+                            result = self.plugin.execute_scenario(config, self.scenario_telemetry)
+
+        # Should call delete_vmi and wait_for_running twice
+        self.assertEqual(mock_del.call_count, 2)
+        self.assertEqual(mock_wt.call_count, 2)
+
+    def test_execute_scenario_wait_for_running_failure(self):
+        """
+        Test execute_scenario when wait_for_running fails
+        """
+        self.plugin.vmis_list = [self.mock_vmi]
+
+        config = {
+            "parameters": {
+                "vm_name": "test-vm",
+                "namespace": "default"
+            }
+        }
+
+        def mock_delete(*args, **kwargs):
+            self.plugin.affected_pod = AffectedPod(pod_name="test-vm", namespace="default")
+            self.plugin.affected_pod.pod_rescheduling_time = 5.0
+            return 0
+
+        with patch.object(self.plugin, 'get_vmis'):
+            with patch.object(self.plugin, 'validate_environment', return_value=True):
+                with patch.object(self.plugin, 'get_vmi', return_value=self.mock_vmi):
+                    with patch.object(self.plugin, 'delete_vmi', side_effect=mock_delete):
+                        with patch.object(self.plugin, 'wait_for_running', return_value=1):
+                            result = self.plugin.execute_scenario(config, self.scenario_telemetry)
+
+        # Should have unrecovered pod
+        self.assertEqual(len(result.unrecovered), 1)
+
+    def test_validate_environment_exception(self):
+        """
+        Test validate_environment handles exceptions
+        """
+        self.custom_object_client.list_namespaced_custom_object = MagicMock(
+            side_effect=Exception("Connection error")
+        )
+
+        result = self.plugin.validate_environment("test-vm", "default")
+
+        self.assertFalse(result)
+
+    def test_validate_environment_vmi_not_found(self):
+        """
+        Test validate_environment when VMI doesn't exist
+        """
+        # Mock CRDs exist
+        mock_crd_list = MagicMock()
+        mock_crd_list.items = MagicMock(return_value=["item1"])
+        self.custom_object_client.list_namespaced_custom_object = MagicMock(return_value=mock_crd_list)
+
+        # Mock VMI not found
+        with patch.object(self.plugin, 'get_vmi', return_value=None):
+            result = self.plugin.validate_environment("test-vm", "default")
+
+        self.assertFalse(result)
+
+    def test_init_clients(self):
+        """
+        Test init_clients initializes k8s client correctly
+        """
+        
+        mock_k8s = MagicMock(spec=KrknKubernetes)
+        mock_custom_client = MagicMock()
+        mock_k8s.custom_object_client = mock_custom_client
+
+        self.plugin.init_clients(mock_k8s)
+
+        self.assertEqual(self.plugin.k8s_client, mock_k8s)
+        self.assertEqual(self.plugin.custom_object_client, mock_custom_client)
+
+    def test_get_scenario_types(self):
+        """
+        Test get_scenario_types returns correct scenario type
+        """
+        result = self.plugin.get_scenario_types()
+
+        self.assertEqual(result, ["kubevirt_vm_outage"])
+        self.assertEqual(len(result), 1)
+
+
+if __name__ == "__main__":
+    unittest.main()

tests/test_managed_cluster_scenario_plugin.py

@@ -0,0 +1,40 @@
+#!/usr/bin/env python3
+
+"""
+Test suite for ManagedClusterScenarioPlugin class
+
+Usage:
+    python -m coverage run -a -m unittest tests/test_managed_cluster_scenario_plugin.py -v
+
+Assisted By: Claude Code
+"""
+
+import unittest
+from unittest.mock import MagicMock
+
+from krkn_lib.k8s import KrknKubernetes
+from krkn_lib.telemetry.ocp import KrknTelemetryOpenshift
+
+from krkn.scenario_plugins.managed_cluster.managed_cluster_scenario_plugin import ManagedClusterScenarioPlugin
+
+
+class TestManagedClusterScenarioPlugin(unittest.TestCase):
+
+    def setUp(self):
+        """
+        Set up test fixtures for ManagedClusterScenarioPlugin
+        """
+        self.plugin = ManagedClusterScenarioPlugin()
+
+    def test_get_scenario_types(self):
+        """
+        Test get_scenario_types returns correct scenario type
+        """
+        result = self.plugin.get_scenario_types()
+
+        self.assertEqual(result, ["managedcluster_scenarios"])
+        self.assertEqual(len(result), 1)
+
+
+if __name__ == "__main__":
+    unittest.main()

tests/test_native_scenario_plugin.py

@@ -0,0 +1,40 @@
+#!/usr/bin/env python3
+
+"""
+Test suite for NativeScenarioPlugin class
+
+Usage:
+    python -m coverage run -a -m unittest tests/test_native_scenario_plugin.py -v
+
+Assisted By: Claude Code
+"""
+
+import unittest
+from unittest.mock import MagicMock
+
+from krkn_lib.k8s import KrknKubernetes
+from krkn_lib.telemetry.ocp import KrknTelemetryOpenshift
+
+from krkn.scenario_plugins.native.native_scenario_plugin import NativeScenarioPlugin
+
+
+class TestNativeScenarioPlugin(unittest.TestCase):
+
+    def setUp(self):
+        """
+        Set up test fixtures for NativeScenarioPlugin
+        """
+        self.plugin = NativeScenarioPlugin()
+
+    def test_get_scenario_types(self):
+        """
+        Test get_scenario_types returns correct scenario types
+        """
+        result = self.plugin.get_scenario_types()
+
+        self.assertEqual(result, ["pod_network_scenarios", "ingress_node_scenarios"])
+        self.assertEqual(len(result), 2)
+
+
+if __name__ == "__main__":
+    unittest.main()

tests/test_network_chaos_ng_scenario_plugin.py

@@ -0,0 +1,40 @@
+#!/usr/bin/env python3
+
+"""
+Test suite for NetworkChaosNgScenarioPlugin class
+
+Usage:
+    python -m coverage run -a -m unittest tests/test_network_chaos_ng_scenario_plugin.py -v
+
+Assisted By: Claude Code
+"""
+
+import unittest
+from unittest.mock import MagicMock
+
+from krkn_lib.k8s import KrknKubernetes
+from krkn_lib.telemetry.ocp import KrknTelemetryOpenshift
+
+from krkn.scenario_plugins.network_chaos_ng.network_chaos_ng_scenario_plugin import NetworkChaosNgScenarioPlugin
+
+
+class TestNetworkChaosNgScenarioPlugin(unittest.TestCase):
+
+    def setUp(self):
+        """
+        Set up test fixtures for NetworkChaosNgScenarioPlugin
+        """
+        self.plugin = NetworkChaosNgScenarioPlugin()
+
+    def test_get_scenario_types(self):
+        """
+        Test get_scenario_types returns correct scenario type
+        """
+        result = self.plugin.get_scenario_types()
+
+        self.assertEqual(result, ["network_chaos_ng_scenarios"])
+        self.assertEqual(len(result), 1)
+
+
+if __name__ == "__main__":
+    unittest.main()