adding affected nodes to affectednodestatus (#884 )

Signed-off-by: Paige Patton <prubenda@redhat.com>
adding setting own image for network chaos (#883 )
2026-02-19 20:40:33 +00:00 · 2025-08-13 20:54:13 -04:00 · 2025-08-13 17:49:47 -04:00 · 2025-08-05 11:27:41 -04:00 · 2025-08-01 13:23:23 -04:00 · 2025-07-31 10:41:31 -04:00
53 changed files with 1037 additions and 2222 deletions
--- a/.github/workflows/tests.yml
+++ b/.github/workflows/tests.yml
@@ -14,34 +14,16 @@ jobs:
        uses: actions/checkout@v3
      - name: Create multi-node KinD cluster
        uses: redhat-chaos/actions/kind@main
-      - name: Install Helm & add repos
-        run: |
-          curl https://raw.githubusercontent.com/helm/helm/main/scripts/get-helm-3 | bash
-          helm repo add prometheus-community https://prometheus-community.github.io/helm-charts
-          helm repo add stable https://charts.helm.sh/stable
-          helm repo update
      - name: Deploy prometheus & Port Forwarding
-        run: |
-          kubectl create namespace prometheus-k8s
-          helm install \
-          --wait --timeout 360s \
-          kind-prometheus \
-          prometheus-community/kube-prometheus-stack \
-          --namespace prometheus-k8s \
-          --set prometheus.service.nodePort=30000 \
-          --set prometheus.service.type=NodePort \
-          --set grafana.service.nodePort=31000 \
-          --set grafana.service.type=NodePort \
-          --set alertmanager.service.nodePort=32000 \
-          --set alertmanager.service.type=NodePort \
-          --set prometheus-node-exporter.service.nodePort=32001 \
-          --set prometheus-node-exporter.service.type=NodePort \
-          --set prometheus.prometheusSpec.maximumStartupDurationSeconds=300
-
-          SELECTOR=`kubectl -n prometheus-k8s get service kind-prometheus-kube-prome-prometheus -o wide --no-headers=true | awk '{ print $7 }'`
-          POD_NAME=`kubectl -n prometheus-k8s get pods --selector="$SELECTOR" --no-headers=true | awk '{ print $1 }'`
-          kubectl -n prometheus-k8s port-forward $POD_NAME 9090:9090 &
-          sleep 5
+        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 }}
+        uses: redhat-chaos/actions/elastic@main
      - name: Install Python
        uses: actions/setup-python@v4
        with:
@@ -55,6 +37,8 @@ jobs:

      - name: Deploy test workloads
        run: |
+          es_pod_name=$(kubectl get pods -l "app.kubernetes.io/instance=elasticsearch" -o name)
+          kubectl --namespace default port-forward $es_pod_name 9200 &
          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
@@ -79,6 +63,9 @@ 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.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
            echo "test_service_hijacking" > ./CI/tests/functional_tests
            echo "test_app_outages" >> ./CI/tests/functional_tests
            echo "test_container"      >> ./CI/tests/functional_tests
@@ -89,6 +76,7 @@ jobs:
            echo "test_cpu_hog" >> ./CI/tests/functional_tests
            echo "test_memory_hog" >> ./CI/tests/functional_tests
            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
@@ -106,6 +94,8 @@ 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.elastic_port=9200' CI/config/common_test_config.yaml
+          yq -i '.elastic.elastic_url="https://localhost"' 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
@@ -119,6 +109,7 @@ jobs:
          echo "test_cpu_hog" >> ./CI/tests/functional_tests
          echo "test_memory_hog" >> ./CI/tests/functional_tests
          echo "test_io_hog" >> ./CI/tests/functional_tests
+          echo "test_pod_network_filter" >> ./CI/tests/functional_tests

      # Final common steps
      - name: Run Functional tests
@@ -129,20 +120,24 @@ jobs:
          cat ./CI/results.markdown >> $GITHUB_STEP_SUMMARY
          echo >> $GITHUB_STEP_SUMMARY
      - name: Upload CI logs
+        if: ${{ success() || failure() }}
        uses: actions/upload-artifact@v4
        with:
          name: ci-logs
          path: CI/out
          if-no-files-found: error
      - name: Collect coverage report
+        if: ${{ success() || failure() }}
        run: |
          python -m coverage html
          python -m coverage json
      - name: Publish coverage report to job summary
+        if: ${{ success() || failure() }}
        run: |
          pip install html2text
          html2text --ignore-images --ignore-links -b 0 htmlcov/index.html >> $GITHUB_STEP_SUMMARY
      - name: Upload coverage data
+        if: ${{ success() || failure() }}
        uses: actions/upload-artifact@v4
        with:
          name: coverage
--- a/CI/config/common_test_config.yaml
+++ b/CI/config/common_test_config.yaml
@@ -10,8 +10,6 @@ cerberus:
    cerberus_url:                                          # When cerberus_enabled is set to True, provide the url where cerberus publishes go/no-go signal.

 performance_monitoring:
-    deploy_dashboards: False                               # Install a mutable grafana and load the performance dashboards. Enable this only when running on OpenShift.
-    repo: "https://github.com/cloud-bulldozer/performance-dashboards.git"
    capture_metrics: False
    metrics_profile_path: config/metrics-aggregated.yaml
    prometheus_url:                                        # The prometheus url/route is automatically obtained in case of OpenShift, please set it when the distribution is Kubernetes.
--- a/CI/templates/outage_pod.yaml
+++ b/CI/templates/outage_pod.yaml
@@ -8,9 +8,9 @@ spec:
  hostNetwork: true
  containers:
  - name: fedtools
-    image: docker.io/fedora/tools
+    image: quay.io/krkn-chaos/krkn:tools
    command:
    - /bin/sh
    - -c
    - |
-      sleep infinity
+      sleep infinity
--- a/CI/templates/pod_network_filter.yaml
+++ b/CI/templates/pod_network_filter.yaml
@@ -0,0 +1,29 @@
+apiVersion: v1
+kind: Pod
+metadata:
+  name: pod-network-filter-test
+  labels:
+    app.kubernetes.io/name: pod-network-filter
+spec:
+  containers:
+  - name: nginx
+    image: quay.io/krkn-chaos/krkn-funtests:pod-network-filter
+    ports:
+      - containerPort: 5000
+        name: pod-network-prt
+
+---
+apiVersion: v1
+kind: Service
+metadata:
+  name: pod-network-filter-service
+spec:
+  selector:
+    app.kubernetes.io/name: pod-network-filter
+  type: NodePort
+  ports:
+  - name: pod-network-filter-svc
+    protocol: TCP
+    port: 80
+    targetPort: pod-network-prt
+    nodePort: 30037
--- a/CI/templates/time_pod.yaml
+++ b/CI/templates/time_pod.yaml
@@ -8,9 +8,9 @@ spec:
  hostNetwork: true
  containers:
  - name: fedtools
-    image: docker.io/fedora/tools
+    image: quay.io/krkn-chaos/krkn:tools
    command:
    - /bin/sh
    - -c
    - |
-      sleep infinity
+      sleep infinity
--- a/CI/tests/test_app_outages.sh
+++ b/CI/tests/test_app_outages.sh
@@ -13,6 +13,10 @@ function functional_test_app_outage {
  export scenario_type="application_outages_scenarios"
  export scenario_file="scenarios/openshift/app_outage.yaml"
  export post_config=""
+
+  kubectl get services -A 
+
+  kubectl get pods 
  envsubst < CI/config/common_test_config.yaml > CI/config/app_outage.yaml
  python3 -m coverage run -a run_kraken.py -c CI/config/app_outage.yaml
  echo "App outage scenario test: Success"
--- a/CI/tests/test_cpu_hog.sh
+++ b/CI/tests/test_cpu_hog.sh
@@ -7,7 +7,7 @@ trap finish EXIT


 function functional_test_cpu_hog {
-  yq -i '.node_selector="kubernetes.io/hostname=kind-worker2"' scenarios/kube/cpu-hog.yml
+  yq -i '."node-selector"="kubernetes.io/hostname=kind-worker2"' scenarios/kube/cpu-hog.yml

  export scenario_type="hog_scenarios"
  export scenario_file="scenarios/kube/cpu-hog.yml"
--- a/CI/tests/test_io_hog.sh
+++ b/CI/tests/test_io_hog.sh
@@ -5,12 +5,13 @@ source CI/tests/common.sh
 trap error ERR
 trap finish EXIT

-
 function functional_test_io_hog {
-  yq -i '.node_selector="kubernetes.io/hostname=kind-worker2"' scenarios/kube/io-hog.yml
+  yq -i '."node-selector"="kubernetes.io/hostname=kind-worker2"' scenarios/kube/io-hog.yml
  export scenario_type="hog_scenarios"
  export scenario_file="scenarios/kube/io-hog.yml"
  export post_config=""
+
+  cat $scenario_file
  envsubst < CI/config/common_test_config.yaml > CI/config/io_hog.yaml
  python3 -m coverage run -a run_kraken.py -c CI/config/io_hog.yaml
  echo "IO Hog: Success"
--- a/CI/tests/test_memory_hog.sh
+++ b/CI/tests/test_memory_hog.sh
@@ -7,7 +7,7 @@ trap finish EXIT


 function functional_test_memory_hog {
-  yq -i '.node_selector="kubernetes.io/hostname=kind-worker2"' scenarios/kube/memory-hog.yml
+  yq -i '."node-selector"="kubernetes.io/hostname=kind-worker2"' scenarios/kube/memory-hog.yml
  export scenario_type="hog_scenarios"
  export scenario_file="scenarios/kube/memory-hog.yml"
  export post_config=""
--- a/CI/tests/test_pod_network_filter.sh
+++ b/CI/tests/test_pod_network_filter.sh
@@ -0,0 +1,59 @@
+function functional_pod_network_filter {
+  export SERVICE_URL="http://localhost:8889"
+  export scenario_type="network_chaos_ng_scenarios"
+  export scenario_file="scenarios/kube/pod-network-filter.yml"
+  export post_config=""
+  envsubst < CI/config/common_test_config.yaml > CI/config/pod_network_filter.yaml
+  yq -i '.[0].test_duration=10' scenarios/kube/pod-network-filter.yml
+  yq -i '.[0].label_selector=""' scenarios/kube/pod-network-filter.yml
+  yq -i '.[0].ingress=false' scenarios/kube/pod-network-filter.yml
+  yq -i '.[0].egress=true' scenarios/kube/pod-network-filter.yml
+  yq -i '.[0].target="pod-network-filter-test"' scenarios/kube/pod-network-filter.yml
+  yq -i '.[0].protocols=["tcp"]' scenarios/kube/pod-network-filter.yml
+  yq -i '.[0].ports=[443]' scenarios/kube/pod-network-filter.yml
+
+
+  ## Test webservice deployment
+  kubectl apply -f ./CI/templates/pod_network_filter.yaml
+  COUNTER=0
+  while true
+   do
+    curl $SERVICE_URL
+    EXITSTATUS=$?
+    if [ "$EXITSTATUS" -eq "0" ]
+      then
+        break
+    fi
+    sleep 1
+    COUNTER=$((COUNTER+1))
+    [ $COUNTER -eq "100" ] && echo "maximum number of retry reached, test failed" && exit 1
+  done
+
+  python3 -m coverage run -a run_kraken.py -c CI/config/pod_network_filter.yaml  > /dev/null 2>&1 &
+  PID=$!
+
+  # wait until the dns resolution starts failing and the service returns 400
+  DNS_FAILURE_STATUS=0
+  while true
+   do
+    OUT_STATUS_CODE=$(curl -X GET -s -o /dev/null -I -w "%{http_code}" $SERVICE_URL)
+    if [ "$OUT_STATUS_CODE" -eq "404" ]
+      then
+        DNS_FAILURE_STATUS=404
+    fi
+
+    if [ "$DNS_FAILURE_STATUS" -eq "404" ] && [ "$OUT_STATUS_CODE" -eq "200" ]
+      then
+        echo "service restored"
+        break
+    fi
+    COUNTER=$((COUNTER+1))
+    [ $COUNTER -eq "100" ] && echo "maximum number of retry reached, test failed" && exit 1
+    sleep 2
+  done
+
+  wait $PID
+}
+
+functional_pod_network_filter
+
--- a/ROADMAP.md
+++ b/ROADMAP.md
@@ -2,11 +2,11 @@

 Following are a list of enhancements that we are planning to work on adding support in Krkn. Of course any help/contributions are greatly appreciated.

- [ ] [Ability to run multiple chaos scenarios in parallel under load to mimic real world outages](https://github.com/krkn-chaos/krkn/issues/424)
+- [x] [Ability to run multiple chaos scenarios in parallel under load to mimic real world outages](https://github.com/krkn-chaos/krkn/issues/424)
 - [x] [Centralized storage for chaos experiments artifacts](https://github.com/krkn-chaos/krkn/issues/423)
- [ ] [Support for causing DNS outages](https://github.com/krkn-chaos/krkn/issues/394)
+- [x] [Support for causing DNS outages](https://github.com/krkn-chaos/krkn/issues/394)
 - [x] [Chaos recommender](https://github.com/krkn-chaos/krkn/tree/main/utils/chaos-recommender) to suggest scenarios having probability of impacting the service under test using profiling results 
- [] Chaos AI integration to improve test coverage while reducing fault space to save costs and execution time
+- [x] Chaos AI integration to improve test coverage while reducing fault space to save costs and execution time [krkn-chaos-ai](https://github.com/krkn-chaos/krkn-chaos-ai)
 - [x] [Support for pod level network traffic shaping](https://github.com/krkn-chaos/krkn/issues/393)
 - [ ] [Ability to visualize the metrics that are being captured by Kraken and stored in Elasticsearch](https://github.com/krkn-chaos/krkn/issues/124)
 - [x] Support for running all the scenarios of Kraken on Kubernetes distribution - see https://github.com/krkn-chaos/krkn/issues/185, https://github.com/redhat-chaos/krkn/issues/186
@@ -14,3 +14,7 @@ Following are a list of enhancements that we are planning to work on adding supp
 - [x] [Switch documentation references to Kubernetes](https://github.com/krkn-chaos/krkn/issues/495)
 - [x] [OCP and Kubernetes functionalities segregation](https://github.com/krkn-chaos/krkn/issues/497)
 - [x] [Krknctl - client for running Krkn scenarios with ease](https://github.com/krkn-chaos/krknctl)
+- [x] [AI Chat bot to help get started with Krkn and commands](https://github.com/krkn-chaos/krkn-lightspeed)
+- [ ] [Ability to roll back cluster to original state if chaos fails](https://github.com/krkn-chaos/krkn/issues/804)
+- [ ] Add recovery time metrics to each scenario for each better regression analysis
+- [ ] [Add resiliency scoring to chaos scenarios ran on cluster](https://github.com/krkn-chaos/krkn/issues/125)
--- a/config/config.yaml
+++ b/config/config.yaml
@@ -46,7 +46,10 @@ kraken:
        - syn_flood_scenarios:
              - scenarios/kube/syn_flood.yaml
        -  network_chaos_ng_scenarios:
-               - scenarios/kube/network-filter.yml
+               - scenarios/kube/pod-network-filter.yml
+               - scenarios/kube/node-network-filter.yml
+        -  kubevirt_vm_outage:
+               - scenarios/kubevirt/kubevirt-vm-outage.yaml

 cerberus:
    cerberus_enabled: False                                # Enable it when cerberus is previously installed
@@ -54,9 +57,7 @@ cerberus:
    check_applicaton_routes: False                         # When enabled will look for application unavailability using the routes specified in the cerberus config and fails the run

 performance_monitoring:
-    deploy_dashboards: False                              # Install a mutable grafana and load the performance dashboards. Enable this only when running on OpenShift
-    repo: "https://github.com/cloud-bulldozer/performance-dashboards.git"
-    prometheus_url: ''                                      # The prometheus url/route is automatically obtained in case of OpenShift, please set it when the distribution is Kubernetes.
+    prometheus_url: ''                                    # The prometheus url/route is automatically obtained in case of OpenShift, please set it when the distribution is Kubernetes.
    prometheus_bearer_token:                              # The bearer token is automatically obtained in case of OpenShift, please set it when the distribution is Kubernetes. This is needed to authenticate with prometheus.
    uuid:                                                 # uuid for the run is generated by default if not set
    enable_alerts: False                                  # Runs the queries specified in the alert profile and displays the info or exits 1 when severity=error
--- a/config/config_kind.yaml
+++ b/config/config_kind.yaml
@@ -7,10 +7,8 @@ kraken:
    signal_state: RUN                                      # Will wait for the RUN signal when set to PAUSE before running the scenarios, refer docs/signal.md for more details
    signal_address: 0.0.0.0                                # Signal listening address
    chaos_scenarios:                                       # List of policies/chaos scenarios to load
-        - plugin_scenarios:
-            - scenarios/kind/scheduler.yml
-        - node_scenarios:
-            - scenarios/kind/node_scenarios_example.yml        
+        - pod_disruption_scenarios:
+            - scenarios/kube/pod.yml

 cerberus:
    cerberus_enabled: False                                # Enable it when cerberus is previously installed
@@ -18,15 +16,24 @@ cerberus:
    check_applicaton_routes: False                         # When enabled will look for application unavailability using the routes specified in the cerberus config and fails the run

 performance_monitoring:
-    deploy_dashboards: False                              # Install a mutable grafana and load the performance dashboards. Enable this only when running on OpenShift
-    repo: "https://github.com/cloud-bulldozer/performance-dashboards.git"
    prometheus_url:                                       # The prometheus url/route is automatically obtained in case of OpenShift, please set it when the distribution is Kubernetes.
    prometheus_bearer_token:                              # The bearer token is automatically obtained in case of OpenShift, please set it when the distribution is Kubernetes. This is needed to authenticate with prometheus.
    uuid:                                                 # uuid for the run is generated by default if not set
    enable_alerts: False                                  # Runs the queries specified in the alert profile and displays the info or exits 1 when severity=error
    alert_profile: config/alerts.yaml                          # Path to alert profile with the prometheus queries

+elastic:
+    enable_elastic: False
+
 tunings:
    wait_duration: 60                                      # Duration to wait between each chaos scenario
    iterations: 1                                          # Number of times to execute the scenarios
    daemon_mode: False                                     # Iterations are set to infinity which means that the kraken will cause chaos forever
+
+telemetry:
+    enabled: False                                         # enable/disables the telemetry collection feature
+    archive_path: /tmp                                     # local path where the archive files will be temporarly stored
+    events_backup: False                                   # enables/disables cluster events collection
+    logs_backup: False
+
+health_checks:                                             # Utilizing health check endpoints to observe application behavior during chaos injection.
--- a/config/config_kubernetes.yaml
+++ b/config/config_kubernetes.yaml
@@ -17,8 +17,6 @@ cerberus:
    check_applicaton_routes: False                         # When enabled will look for application unavailability using the routes specified in the cerberus config and fails the run

 performance_monitoring:
-    deploy_dashboards: False                              # Install a mutable grafana and load the performance dashboards. Enable this only when running on OpenShift
-    repo: "https://github.com/cloud-bulldozer/performance-dashboards.git"
    prometheus_url:                                       # The prometheus url/route is automatically obtained in case of OpenShift, please set it when the distribution is Kubernetes.
    prometheus_bearer_token:                              # The bearer token is automatically obtained in case of OpenShift, please set it when the distribution is Kubernetes. This is needed to authenticate with prometheus.
    uuid:                                                 # uuid for the run is generated by default if not set
--- a/containers/Dockerfile.template
+++ b/containers/Dockerfile.template
@@ -10,7 +10,7 @@ RUN go mod edit -go 1.23.1 &&\
    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@v0.36.0&&\
+    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&&\
@@ -47,7 +47,7 @@ RUN if [ -n "$PR_NUMBER" ]; then git fetch origin pull/${PR_NUMBER}/head:pr-${PR
 RUN if [ -n "$TAG" ]; then git checkout "$TAG";fi

 RUN python3.9 -m ensurepip --upgrade --default-pip
-RUN python3.9 -m pip install --upgrade pip setuptools==70.0.0
+RUN python3.9 -m pip install --upgrade pip setuptools==78.1.1
 RUN pip3.9 install -r requirements.txt
 RUN pip3.9 install jsonschema

--- a/kind-config.yml
+++ b/kind-config.yml
@@ -5,6 +5,8 @@ nodes:
    extraPortMappings:
      - containerPort: 30036
        hostPort: 8888
+      - containerPort: 30037
+        hostPort: 8889
  - role: control-plane
  - role: control-plane
  - role: worker
--- a/krkn/invoke/command.py
+++ b/krkn/invoke/command.py
@@ -19,7 +19,6 @@ def invoke_no_exit(command, timeout=None):
    output = ""
    try:
        output = subprocess.check_output(command, shell=True, universal_newlines=True, timeout=timeout)
-        logging.info("output " + str(output))
    except Exception as e:
        logging.error("Failed to run %s, error: %s" % (command, e))
        return str(e)
--- a/krkn/performance_dashboards/init.py
+++ b/krkn/performance_dashboards/init.py
--- a/krkn/performance_dashboards/setup.py
+++ b/krkn/performance_dashboards/setup.py
@@ -1,28 +0,0 @@
-import subprocess
-import logging
-import git
-import sys
-
-
-# Installs a mutable grafana on the Kubernetes/OpenShift cluster and loads the performance dashboards
-def setup(repo, distribution):
-    if distribution == "kubernetes":
-        command = "cd performance-dashboards/dittybopper && ./k8s-deploy.sh"
-    elif distribution == "openshift":
-        command = "cd performance-dashboards/dittybopper && ./deploy.sh"
-    else:
-        logging.error("Provided distribution: %s is not supported" % (distribution))
-        sys.exit(1)
-    delete_repo = "rm -rf performance-dashboards || exit 0"
-    logging.info(
-        "Cloning, installing mutable grafana on the cluster and loading the dashboards"
-    )
-    try:
-        # delete repo to clone the latest copy if exists
-        subprocess.run(delete_repo, shell=True, universal_newlines=True, timeout=45)
-        # clone the repo
-        git.Repo.clone_from(repo, "performance-dashboards")
-        # deploy performance dashboards
-        subprocess.run(command, shell=True, universal_newlines=True)
-    except Exception as e:
-        logging.error("Failed to install performance-dashboards, error: %s" % (e))
--- a/krkn/prometheus/client.py
+++ b/krkn/prometheus/client.py
@@ -9,6 +9,7 @@ import logging
 import urllib3
 import sys
 import json
+import tempfile

 import yaml
 from krkn_lib.elastic.krkn_elastic import KrknElastic
@@ -251,11 +252,29 @@ def metrics(
                        metric[k] = v
                        metric['timestamp'] = str(datetime.datetime.now())
                    metrics_list.append(metric.copy())
-        if elastic:
+
+        save_metrics = False
+        if elastic is not None and elastic_metrics_index is not None:
            result = elastic.upload_metrics_to_elasticsearch(
                run_uuid=run_uuid, index=elastic_metrics_index, raw_data=metrics_list
            )
            if result == -1:
                logging.error("failed to save metrics on ElasticSearch")
+                save_metrics = True
+        else:
+            save_metrics = True
+        if save_metrics:
+            local_dir = os.path.join(tempfile.gettempdir(), "krkn_metrics")
+            os.makedirs(local_dir, exist_ok=True)
+            local_file = os.path.join(local_dir, f"{elastic_metrics_index}_{run_uuid}.json")

+            try:
+                with open(local_file, "w") as f:
+                    json.dump({
+                        "run_uuid": run_uuid,
+                        "metrics": metrics_list
+                }, f, indent=2)
+                logging.info(f"Metrics saved to {local_file}")
+            except Exception as e:
+                logging.error(f"Failed to save metrics to {local_file}: {e}")
    return metrics_list
--- a/krkn/scenario_plugins/hogs/hogs_scenario_plugin.py
+++ b/krkn/scenario_plugins/hogs/hogs_scenario_plugin.py
@@ -25,6 +25,10 @@ class HogsScenarioPlugin(AbstractScenarioPlugin):
            with open(scenario, "r") as f:
                scenario = yaml.full_load(f)
            scenario_config = HogConfig.from_yaml_dict(scenario)
+            
+            # Get node-name if provided
+            node_name = scenario.get('node-name')
+            
            has_selector = True
            if not scenario_config.node_selector or not re.match("^.+=.*$", scenario_config.node_selector):
                if scenario_config.node_selector:
@@ -33,13 +37,19 @@ class HogsScenarioPlugin(AbstractScenarioPlugin):
            else:
                node_selector = scenario_config.node_selector

-            available_nodes = lib_telemetry.get_lib_kubernetes().list_nodes(node_selector)
-            if len(available_nodes) == 0:
-                raise Exception("no available nodes to schedule workload")
+            if node_name:
+                logging.info(f"Using specific node: {node_name}")
+                all_nodes = lib_telemetry.get_lib_kubernetes().list_nodes("")
+                if node_name not in all_nodes:
+                    raise Exception(f"Specified node {node_name} not found or not available")
+                available_nodes = [node_name]
+            else:
+                available_nodes = lib_telemetry.get_lib_kubernetes().list_nodes(node_selector)
+                if len(available_nodes) == 0:
+                    raise Exception("no available nodes to schedule workload")

-            if not has_selector:
-                # if selector not specified picks a random node between the available
-                available_nodes = [available_nodes[random.randint(0, len(available_nodes))]]
+                if not has_selector:
+                    available_nodes = [available_nodes[random.randint(0, len(available_nodes))]]

            if scenario_config.number_of_nodes and len(available_nodes) > scenario_config.number_of_nodes:
                available_nodes = random.sample(available_nodes, scenario_config.number_of_nodes)
--- a/krkn/scenario_plugins/kubevirt_vm_outage/init.py
+++ b/krkn/scenario_plugins/kubevirt_vm_outage/init.py
--- a/krkn/scenario_plugins/kubevirt_vm_outage/kubevirt_vm_outage_scenario_plugin.py
+++ b/krkn/scenario_plugins/kubevirt_vm_outage/kubevirt_vm_outage_scenario_plugin.py
@@ -0,0 +1,399 @@
+import logging
+import time
+from typing import Dict, Any, Optional
+import random
+import re
+import yaml
+from kubernetes.client.rest import ApiException
+from krkn_lib.k8s import KrknKubernetes
+from krkn_lib.models.telemetry import ScenarioTelemetry
+from krkn_lib.telemetry.ocp import KrknTelemetryOpenshift
+from krkn_lib.utils import log_exception
+from krkn_lib.models.k8s import AffectedPod, PodsStatus
+
+from krkn.scenario_plugins.abstract_scenario_plugin import AbstractScenarioPlugin
+
+
+class KubevirtVmOutageScenarioPlugin(AbstractScenarioPlugin):
+    """
+    A scenario plugin that injects chaos by deleting a KubeVirt Virtual Machine Instance (VMI).
+    This plugin simulates a VM crash or outage scenario and supports automated or manual recovery.
+    """
+
+    def __init__(self):
+        self.k8s_client = None
+        self.original_vmi = None
+        
+    # Scenario type is handled directly in execute_scenario
+    def get_scenario_types(self) -> list[str]:
+        return ["kubevirt_vm_outage"]
+
+    def run(
+        self,
+        run_uuid: str,
+        scenario: str,
+        krkn_config: dict[str, any],
+        lib_telemetry: KrknTelemetryOpenshift,
+        scenario_telemetry: ScenarioTelemetry,
+    ) -> int:
+        """
+        Main entry point for the plugin.
+        Parses the scenario configuration and executes the chaos scenario.
+        """
+        try:
+            with open(scenario, "r") as f:
+                scenario_config = yaml.full_load(f)
+                
+            self.init_clients(lib_telemetry.get_lib_kubernetes())
+            pods_status = PodsStatus()
+            for config in scenario_config["scenarios"]:
+                if config.get("scenario") == "kubevirt_vm_outage":
+                    single_pods_status = self.execute_scenario(config, scenario_telemetry)
+                    pods_status.merge(single_pods_status)
+            
+            scenario_telemetry.affected_pods = pods_status
+                        
+            return 0
+        except Exception as e:
+            logging.error(f"KubeVirt VM Outage scenario failed: {e}")
+            log_exception(e)
+            return 1
+
+    def init_clients(self, k8s_client: KrknKubernetes):
+        """
+        Initialize Kubernetes client for KubeVirt operations.
+        """
+        self.k8s_client = k8s_client
+        self.custom_object_client = k8s_client.custom_object_client
+        logging.info("Successfully initialized Kubernetes client for KubeVirt operations")
+
+    def get_vmi(self, name: str, namespace: str) -> Optional[Dict]:
+        """
+        Get a Virtual Machine Instance by name and namespace.
+        
+        :param name: Name of the VMI to retrieve
+        :param namespace: Namespace of the VMI
+        :return: The VMI object if found, None otherwise
+        """
+        try:
+            vmi = self.custom_object_client.get_namespaced_custom_object(
+                group="kubevirt.io",
+                version="v1",
+                namespace=namespace,
+                plural="virtualmachineinstances",
+                name=name
+            )
+            return vmi
+        except ApiException as e:
+            if e.status == 404:
+                logging.warning(f"VMI {name} not found in namespace {namespace}")
+                return None
+            else:
+                logging.error(f"Error getting VMI {name}: {e}")
+                raise
+        except Exception as e:
+            logging.error(f"Unexpected error getting VMI {name}: {e}")
+            raise
+            
+    def get_vmis(self, regex_name: str, namespace: str) -> Optional[Dict]:
+        """
+        Get a Virtual Machine Instance by name and namespace.
+        
+        :param name: Name of the VMI to retrieve
+        :param namespace: Namespace of the VMI
+        :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",
+            )
+
+            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
+        except ApiException as e:
+            if e.status == 404:
+                logging.warning(f"VMI {regex_name} not found in namespace {namespace}")
+                return None
+            else:
+                logging.error(f"Error getting VMI {regex_name}: {e}")
+                raise
+        except Exception as e:
+            logging.error(f"Unexpected error getting VMI {regex_name}: {e}")
+            raise
+    
+    def execute_scenario(self, config: Dict[str, Any], scenario_telemetry: ScenarioTelemetry) -> int:
+        """
+        Execute a KubeVirt VM outage scenario based on the provided configuration.
+        
+        :param config: The scenario configuration
+        :param scenario_telemetry: The telemetry object for recording metrics
+        :return: 0 for success, 1 for failure
+        """
+        try:
+            params = config.get("parameters", {})
+            vm_name = params.get("vm_name")
+            namespace = params.get("namespace", "default")
+            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]
+                
+            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
+
+            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
+            )
+
+            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
+
+    def validate_environment(self, vm_name: str, namespace: str) -> bool:
+        """
+        Validate that KubeVirt is installed and the specified VM exists.
+        
+        :param vm_name: Name of the VM to validate
+        :param namespace: Namespace of the VM
+        :return: True if environment is valid, False otherwise
+        """
+        try:
+            # Check if KubeVirt CRDs exist
+            crd_list = self.custom_object_client.list_namespaced_custom_object("kubevirt.io","v1",namespace,"virtualmachines")
+            kubevirt_crds = [crd for crd in crd_list.items() ]
+            
+            if not kubevirt_crds:
+                logging.error("KubeVirt CRDs not found. Ensure KubeVirt/CNV is installed in the cluster")
+                return False
+                
+            # Check if VMI exists
+            vmi = self.get_vmi(vm_name, namespace)
+            if not vmi:
+                logging.error(f"VMI {vm_name} not found in namespace {namespace}")
+                return False
+                
+            logging.info(f"Validated environment: KubeVirt is installed and VMI {vm_name} exists")
+            return True
+            
+        except Exception as e:
+            logging.error(f"Error validating environment: {e}")
+            return False
+
+    def patch_vm_spec(self, vm_name: str, namespace: str, running: bool) -> bool:
+        """
+        Patch the VM spec to enable/disable auto-restart.
+        
+        :param vm_name: Name of the VM to patch
+        :param namespace: Namespace of the VM
+        :param running: Whether the VM should be set to running state
+        :return: True if patch was successful, False otherwise
+        """
+        try:
+            # Get the VM object first to get its current spec
+            vm = self.custom_object_client.get_namespaced_custom_object(
+                group="kubevirt.io",
+                version="v1",
+                namespace=namespace,
+                plural="virtualmachines",
+                name=vm_name
+            )
+            
+            # Update the running state
+            if 'spec' not in vm:
+                vm['spec'] = {}
+            vm['spec']['running'] = running
+            
+            # Apply the patch
+            self.custom_object_client.patch_namespaced_custom_object(
+                group="kubevirt.io",
+                version="v1",
+                namespace=namespace,
+                plural="virtualmachines",
+                name=vm_name,
+                body=vm
+            )
+            return True
+            
+        except ApiException as e:
+            logging.error(f"Failed to patch VM {vm_name}: {e}")
+            return False
+        except Exception as e:
+            logging.error(f"Unexpected error patching VM {vm_name}: {e}")
+            return False
+            
+    def delete_vmi(self, vm_name: str, namespace: str, disable_auto_restart: bool = False, timeout: int = 120) -> int:
+        """
+        Delete a Virtual Machine Instance to simulate a VM outage.
+        
+        :param vm_name: Name of the VMI to delete
+        :param namespace: Namespace of the VMI
+        :return: 0 for success, 1 for failure
+        """
+        try:
+            logging.info(f"Injecting chaos: Deleting VMI {vm_name} in namespace {namespace}")
+            
+            # If auto-restart should be disabled, patch the VM spec first
+            if disable_auto_restart:
+                logging.info(f"Disabling auto-restart for VM {vm_name} by setting spec.running=False")
+                if not self.patch_vm_spec(vm_name, namespace, running=False):
+                    logging.error("Failed to disable auto-restart for VM"
+                               " - proceeding with deletion but VM may auto-restart")
+            start_creation_time =  self.original_vmi.get('metadata', {}).get('creationTimestamp')
+            start_time = time.time()
+            try:
+                self.custom_object_client.delete_namespaced_custom_object(
+                    group="kubevirt.io",
+                    version="v1",
+                    namespace=namespace,
+                    plural="virtualmachineinstances",
+                    name=vm_name
+                )
+            except ApiException as e:
+                if e.status == 404:
+                    logging.warning(f"VMI {vm_name} not found during deletion")
+                    return 1
+                else:
+                    logging.error(f"API error during VMI deletion: {e}")
+                    return 1
+            
+            # Wait for the VMI to be deleted
+            
+            while time.time() - start_time < timeout:
+                deleted_vmi = self.get_vmi(vm_name, namespace)
+                if deleted_vmi:
+                    if start_creation_time != deleted_vmi.get('metadata', {}).get('creationTimestamp'):
+                        logging.info(f"VMI {vm_name} successfully recreated")
+                        self.affected_pod.pod_rescheduling_time = time.time() - start_time
+                        return 0
+                else: 
+                    logging.info(f"VMI {vm_name} successfully deleted")
+                time.sleep(1)
+                
+            logging.error(f"Timed out waiting for VMI {vm_name} to be deleted")
+            self.pods_status.unrecovered = 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
+            return 1
+
+    def wait_for_running(self, vm_name: str, namespace: str, timeout: int = 120) -> int: 
+        start_time = time.time()
+        while time.time() - start_time < timeout: 
+
+            # Check current state once since we've already waited for the duration
+            vmi = self.get_vmi(vm_name, namespace)
+            
+            if vmi:
+                if vmi.get('status', {}).get('phase') == "Running":
+                    end_time = time.time()
+                    self.affected_pod.pod_readiness_time = end_time - start_time
+
+                    logging.info(f"VMI {vm_name} is already running")
+                    return 0
+                logging.info(f"VMI {vm_name} exists but is not in Running state. Current state: {vmi.get('status', {}).get('phase')}")
+            else:
+                logging.info(f"VMI {vm_name} not yet recreated")
+            time.sleep(1)
+        return 1
+    
+
+    def recover(self, vm_name: str, namespace: str, disable_auto_restart: bool = False) -> int:
+        """
+        Recover a deleted VMI, either by waiting for auto-recovery or manually recreating it.
+        
+        :param vm_name: Name of the VMI to recover
+        :param namespace: Namespace of the VMI
+        :param disable_auto_restart: Whether auto-restart was disabled during injection
+        :return: 0 for success, 1 for failure
+        """
+        try:
+            logging.info(f"Attempting to recover VMI {vm_name} in namespace {namespace}")
+            
+            if self.original_vmi:
+                logging.info(f"Auto-recovery didn't occur for VMI {vm_name}. Attempting manual recreation")
+                
+                try:
+                    # Clean up server-generated fields
+                    vmi_dict = self.original_vmi.copy()
+                    if 'metadata' in vmi_dict:
+                        metadata = vmi_dict['metadata']
+                        for field in ['resourceVersion', 'uid', 'creationTimestamp', 'generation']:
+                            if field in metadata:
+                                del metadata[field]
+                    
+                    # Create the VMI
+                    self.custom_object_client.create_namespaced_custom_object(
+                        group="kubevirt.io",
+                        version="v1",
+                        namespace=namespace,
+                        plural="virtualmachineinstances",
+                        body=vmi_dict
+                    )
+                    logging.info(f"Successfully recreated VMI {vm_name}")
+                    
+                    # Wait for VMI to start running
+                    self.wait_for_running(vm_name,namespace)
+                    
+                    logging.warning(f"VMI {vm_name} was recreated but didn't reach Running state in time")
+                    return 0  # Still consider it a success as the VMI was recreated
+                    
+                except Exception as e:
+                    logging.error(f"Error recreating VMI {vm_name}: {e}")
+                    log_exception(e)
+                    return 1
+            else:
+                logging.error(f"Failed to recover VMI {vm_name}: No original state captured and auto-recovery did not occur")
+                return 1
+                
+        except Exception as e:
+            logging.error(f"Unexpected error recovering VMI {vm_name}: {e}")
+            log_exception(e)
+            return 1
--- a/krkn/scenario_plugins/native/native_scenario_plugin.py
+++ b/krkn/scenario_plugins/native/native_scenario_plugin.py
@@ -1,6 +1,5 @@
 from krkn.scenario_plugins.abstract_scenario_plugin import AbstractScenarioPlugin
 from krkn.scenario_plugins.native.plugins import PLUGINS
-from krkn_lib.k8s.pods_monitor_pool import PodsMonitorPool
 from krkn_lib.models.telemetry import ScenarioTelemetry
 from krkn_lib.telemetry.ocp import KrknTelemetryOpenshift
 from typing import Any
@@ -28,7 +27,6 @@ class NativeScenarioPlugin(AbstractScenarioPlugin):

        except Exception as e:
            logging.error("NativeScenarioPlugin exiting due to Exception %s" % e)
-            pool.cancel()
            return 1
        else:
            return 0
--- a/krkn/scenario_plugins/native/network/ingress_shaping.py
+++ b/krkn/scenario_plugins/native/network/ingress_shaping.py
@@ -28,6 +28,14 @@ class NetworkScenarioConfig:
        },
    )

+    image: typing.Annotated[str, validation.min(1)]= field(
+        default="quay.io/krkn-chaos/krkn:tools",
+        metadata={
+            "name": "Image",
+            "description": "Image of krkn tools to run"
+        }
+    )
+
    label_selector: typing.Annotated[
        typing.Optional[str], validation.required_if_not("node_interface_name")
    ] = field(
@@ -142,7 +150,7 @@ class NetworkScenarioErrorOutput:
    )


-def get_default_interface(node: str, pod_template, cli: CoreV1Api) -> str:
+def get_default_interface(node: str, pod_template, cli: CoreV1Api, image: str) -> str:
    """
    Function that returns a random interface from a node

@@ -161,7 +169,7 @@ def get_default_interface(node: str, pod_template, cli: CoreV1Api) -> str:
        Default interface (string) belonging to the node
    """

-    pod_body = yaml.safe_load(pod_template.render(nodename=node))
+    pod_body = yaml.safe_load(pod_template.render(nodename=node, image=image))
    logging.info("Creating pod to query interface on node %s" % node)
    kube_helper.create_pod(cli, pod_body, "default", 300)

@@ -189,7 +197,7 @@ def get_default_interface(node: str, pod_template, cli: CoreV1Api) -> str:


 def verify_interface(
-    input_interface_list: typing.List[str], node: str, pod_template, cli: CoreV1Api
+    input_interface_list: typing.List[str], node: str, pod_template, cli: CoreV1Api, image: str
 ) -> typing.List[str]:
    """
    Function that verifies whether a list of interfaces is present in the node.
@@ -212,7 +220,7 @@ def verify_interface(
    Returns:
        The interface list for the node
    """
-    pod_body = yaml.safe_load(pod_template.render(nodename=node))
+    pod_body = yaml.safe_load(pod_template.render(nodename=node, image=image))
    logging.info("Creating pod to query interface on node %s" % node)
    kube_helper.create_pod(cli, pod_body, "default", 300)
    try:
@@ -268,6 +276,7 @@ def get_node_interfaces(
    instance_count: int,
    pod_template,
    cli: CoreV1Api,
+    image: str
 ) -> typing.Dict[str, typing.List[str]]:
    """
    Function that is used to process the input dictionary with the nodes and
@@ -309,7 +318,7 @@ def get_node_interfaces(
        nodes = kube_helper.get_node(None, label_selector, instance_count, cli)
        node_interface_dict = {}
        for node in nodes:
-            node_interface_dict[node] = get_default_interface(node, pod_template, cli)
+            node_interface_dict[node] = get_default_interface(node, pod_template, cli, image)
    else:
        node_name_list = node_interface_dict.keys()
        filtered_node_list = []
@@ -321,7 +330,7 @@ def get_node_interfaces(

        for node in filtered_node_list:
            node_interface_dict[node] = verify_interface(
-                node_interface_dict[node], node, pod_template, cli
+                node_interface_dict[node], node, pod_template, cli, image
            )

    return node_interface_dict
@@ -337,6 +346,7 @@ def apply_ingress_filter(
    cli: CoreV1Api,
    create_interfaces: bool = True,
    param_selector: str = "all",
+    image:str = "quay.io/krkn-chaos/krkn:tools",
 ) -> str:
    """
    Function that applies the filters to shape incoming traffic to
@@ -382,14 +392,14 @@ def apply_ingress_filter(
        network_params = {param_selector: cfg.network_params[param_selector]}

    if create_interfaces:
-        create_virtual_interfaces(cli, interface_list, node, pod_template)
+        create_virtual_interfaces(cli, interface_list, node, pod_template, image)

    exec_cmd = get_ingress_cmd(
        interface_list, network_params, duration=cfg.test_duration
    )
    logging.info("Executing %s on node %s" % (exec_cmd, node))
    job_body = yaml.safe_load(
-        job_template.render(jobname=str(hash(node))[:5], nodename=node, cmd=exec_cmd)
+        job_template.render(jobname=str(hash(node))[:5], nodename=node, image=image, cmd=exec_cmd)
    )
    api_response = kube_helper.create_job(batch_cli, job_body)

@@ -400,7 +410,7 @@ def apply_ingress_filter(


 def create_virtual_interfaces(
-    cli: CoreV1Api, interface_list: typing.List[str], node: str, pod_template
+    cli: CoreV1Api, interface_list: typing.List[str], node: str, pod_template, image: str
 ) -> None:
    """
    Function that creates a privileged pod and uses it to create
@@ -421,7 +431,7 @@ 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))
+    pod_body = yaml.safe_load(pod_template.render(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(
@@ -434,7 +444,7 @@ def create_virtual_interfaces(


 def delete_virtual_interfaces(
-    cli: CoreV1Api, node_list: typing.List[str], pod_template
+    cli: CoreV1Api, node_list: typing.List[str], pod_template, image: str
 ):
    """
    Function that creates a privileged pod and uses it to delete all
@@ -457,7 +467,7 @@ def delete_virtual_interfaces(
    """

    for node in node_list:
-        pod_body = yaml.safe_load(pod_template.render(nodename=node))
+        pod_body = yaml.safe_load(pod_template.render(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")
@@ -700,7 +710,7 @@ def network_chaos(
    pod_interface_template = env.get_template("pod_interface.j2")
    pod_module_template = env.get_template("pod_module.j2")
    cli, batch_cli = kube_helper.setup_kubernetes(cfg.kubeconfig_path)
-
+    test_image = cfg.image
    logging.info("Starting Ingress Network Chaos")
    try:
        node_interface_dict = get_node_interfaces(
@@ -709,6 +719,7 @@ def network_chaos(
            cfg.instance_count,
            pod_interface_template,
            cli,
+            test_image
        )
    except Exception:
        return "error", NetworkScenarioErrorOutput(format_exc())
@@ -726,6 +737,7 @@ def network_chaos(
                        job_template,
                        batch_cli,
                        cli,
+                        test_image
                    )
                )
            logging.info("Waiting for parallel job to finish")
@@ -746,6 +758,7 @@ def network_chaos(
                            cli,
                            create_interfaces=create_interfaces,
                            param_selector=param,
+                            image=test_image
                        )
                    )
                logging.info("Waiting for serial job to finish")
@@ -772,6 +785,6 @@ def network_chaos(
        logging.error("Ingress Network Chaos exiting due to Exception - %s" % e)
        return "error", NetworkScenarioErrorOutput(format_exc())
    finally:
-        delete_virtual_interfaces(cli, node_interface_dict.keys(), pod_module_template)
+        delete_virtual_interfaces(cli, node_interface_dict.keys(), pod_module_template, test_image)
        logging.info("Deleting jobs(if any)")
        delete_jobs(cli, batch_cli, job_list[:])
--- a/krkn/scenario_plugins/native/network/job.j2
+++ b/krkn/scenario_plugins/native/network/job.j2
@@ -9,7 +9,7 @@ spec:
      hostNetwork: true
      containers:
      - name: networkchaos
-        image: docker.io/fedora/tools
+        image: {{image}}
        command: ["/bin/sh",  "-c", "{{cmd}}"]
        securityContext:
          privileged: true
@@ -22,4 +22,4 @@ spec:
          hostPath:
            path: /lib/modules
      restartPolicy: Never
-  backoffLimit: 0
+  backoffLimit: 0
--- a/krkn/scenario_plugins/native/network/pod_interface.j2
+++ b/krkn/scenario_plugins/native/network/pod_interface.j2
@@ -7,7 +7,7 @@ spec:
  nodeName: {{nodename}}
  containers:
  - name: fedtools
-    image: docker.io/fedora/tools
+    image: {{image}}
    command:
    - /bin/sh
    - -c
--- a/krkn/scenario_plugins/native/network/pod_module.j2
+++ b/krkn/scenario_plugins/native/network/pod_module.j2
@@ -6,7 +6,7 @@ spec:
  nodeName: {{nodename}}
  containers:
  - name: modtools
-    image: docker.io/fedora/tools
+    image: {{image}}
    imagePullPolicy: IfNotPresent
    command:
    - /bin/sh
@@ -27,4 +27,4 @@ spec:
  hostNetwork: true
  hostIPC: true
  hostPID: true
-  restartPolicy: Never
+  restartPolicy: Never
--- a/krkn/scenario_plugins/native/pod_network_outage/job.j2
+++ b/krkn/scenario_plugins/native/pod_network_outage/job.j2
@@ -9,7 +9,7 @@ spec:
      hostNetwork: true
      containers:
      - name: networkchaos
-        image: docker.io/fedora/tools
+        image: {{image}}
        command: ["chroot", "/host", "/bin/sh",  "-c", "{{cmd}}"]
        securityContext:
          privileged: true
--- a/krkn/scenario_plugins/native/pod_network_outage/pod_module.j2
+++ b/krkn/scenario_plugins/native/pod_network_outage/pod_module.j2
@@ -6,7 +6,7 @@ spec:
  nodeName: {{nodename}}
  containers:
  - name: modtools
-    image: docker.io/fedora/tools
+    image: {{image}}
    imagePullPolicy: IfNotPresent
    command:
    - /bin/sh
@@ -27,4 +27,4 @@ spec:
  hostNetwork: true
  hostIPC: true
  hostPID: true
-  restartPolicy: Never
+  restartPolicy: Never
--- a/krkn/scenario_plugins/native/pod_network_outage/pod_network_outage_plugin.py
+++ b/krkn/scenario_plugins/native/pod_network_outage/pod_network_outage_plugin.py
@@ -192,6 +192,7 @@ def apply_outage_policy(
    duration: str,
    bridge_name: str,
    kubecli: KrknKubernetes,
+    image: str
 ) -> typing.List[str]:
    """
    Function that applies filters(ingress or egress) to block traffic.
@@ -223,6 +224,8 @@ def apply_outage_policy(
        batch_cli (BatchV1Api)
            - Object to interact with Kubernetes Python client's BatchV1Api API

+        image (string)
+            - Image of network chaos tool
    Returns:
        The name of the job created that executes the commands on a node
        for ingress chaos scenario
@@ -239,7 +242,7 @@ def apply_outage_policy(
        br = "br-int"
        table = 8
    for node, ips in node_dict.items():
-        while len(check_cookie(node, pod_template, br, cookie, kubecli)) > 2 or cookie in cookie_list:
+        while len(check_cookie(node, pod_template, br, cookie, kubecli, image)) > 2 or cookie in cookie_list:
            cookie = random.randint(100, 10000)
        exec_cmd = ""
        for ip in ips:
@@ -257,6 +260,7 @@ def apply_outage_policy(
            job_template.render(
                jobname=str(hash(node))[:5] + str(random.randint(0, 10000)),
                nodename=node,
+                image=image,
                cmd=exec_cmd,
            )
        )
@@ -281,6 +285,7 @@ def apply_ingress_policy(
    bridge_name: str,
    kubecli: KrknKubernetes,
    test_execution: str,
+    image: str,
 ) -> typing.List[str]:
    """
    Function that applies ingress traffic shaping to pod interface.
@@ -327,22 +332,23 @@ def apply_ingress_policy(
    job_list = []
    yml_list = []

-    create_virtual_interfaces(kubecli, len(ips), node, pod_template)
+    create_virtual_interfaces(kubecli, len(ips), node, pod_template, image)

    for count, pod_ip in enumerate(set(ips)):
-        pod_inf = get_pod_interface(node, pod_ip, pod_template, bridge_name, kubecli)
+        pod_inf = get_pod_interface(node, pod_ip, pod_template, bridge_name, kubecli, image)
        exec_cmd = get_ingress_cmd(
            test_execution, pod_inf, mod, count, network_params, duration
        )
        logging.info("Executing %s on pod %s in node %s" % (exec_cmd, pod_ip, node))
        job_body = yaml.safe_load(
-            job_template.render(jobname=mod + str(pod_ip), nodename=node, cmd=exec_cmd)
+            job_template.render(jobname=mod + str(pod_ip), nodename=node, image=image, cmd=exec_cmd)
        )
        yml_list.append(job_body)
        if pod_ip == node:
            break

    for job_body in yml_list:
+        print('jbo body' + str(job_body))
        api_response = kubecli.create_job(job_body)
        if api_response is None:
            raise Exception("Error creating job")
@@ -362,6 +368,7 @@ def apply_net_policy(
    bridge_name: str,
    kubecli: KrknKubernetes,
    test_execution: str,
+    image: str, 
 ) -> typing.List[str]:
    """
    Function that applies egress traffic shaping to pod interface.
@@ -415,7 +422,7 @@ def apply_net_policy(
        )
        logging.info("Executing %s on pod %s in node %s" % (exec_cmd, pod_ip, node))
        job_body = yaml.safe_load(
-            job_template.render(jobname=mod + str(pod_ip), nodename=node, cmd=exec_cmd)
+            job_template.render(jobname=mod + str(pod_ip), nodename=node, image=image, cmd=exec_cmd)
        )
        yml_list.append(job_body)

@@ -530,7 +537,7 @@ def get_egress_cmd(


 def create_virtual_interfaces(
-    kubecli: KrknKubernetes, nummber: int, node: str, pod_template
+    kubecli: KrknKubernetes, nummber: int, node: str, pod_template, image: str, 
 ) -> None:
    """
    Function that creates a privileged pod and uses it to create
@@ -550,8 +557,11 @@ def create_virtual_interfaces(
        pod_template (jinja2.environment.Template))
            - The YAML template used to instantiate a pod to create
              virtual interfaces on the node
+
+        image (string)
+            - Image of network chaos tool
    """
-    pod_body = yaml.safe_load(pod_template.render(nodename=node))
+    pod_body = yaml.safe_load(pod_template.render(nodename=node, image=image))
    kubecli.create_pod(pod_body, "default", 300)
    logging.info(
        "Creating {0} virtual interfaces on node {1} using a pod".format(nummber, node)
@@ -562,7 +572,7 @@ def create_virtual_interfaces(


 def delete_virtual_interfaces(
-    kubecli: KrknKubernetes, node_list: typing.List[str], pod_template
+    kubecli: KrknKubernetes, node_list: typing.List[str], pod_template, image: str, 
 ):
    """
    Function that creates a privileged pod and uses it to delete all
@@ -582,10 +592,13 @@ def delete_virtual_interfaces(
        pod_template (jinja2.environment.Template))
            - The YAML template used to instantiate a pod to delete
              virtual interfaces on the node
+        
+        image (string)
+            - Image of network chaos tool
    """

    for node in node_list:
-        pod_body = yaml.safe_load(pod_template.render(nodename=node))
+        pod_body = yaml.safe_load(pod_template.render(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")
@@ -619,7 +632,7 @@ def delete_ifb(kubecli: KrknKubernetes, pod_name: str):
    kubecli.exec_cmd_in_pod(exec_command, pod_name, "default", base_command="chroot")


-def list_bridges(node: str, pod_template, kubecli: KrknKubernetes) -> typing.List[str]:
+def list_bridges(node: str, pod_template, kubecli: KrknKubernetes, image: str) -> typing.List[str]:
    """
    Function that returns a list of bridges on the node

@@ -634,11 +647,13 @@ def list_bridges(node: str, pod_template, kubecli: KrknKubernetes) -> typing.Lis
        kubecli (KrknKubernetes)
            - Object to interact with Kubernetes Python client

+        image (string)
+            - Image of network chaos tool
    Returns:
        List of bridges on the node.
    """

-    pod_body = yaml.safe_load(pod_template.render(nodename=node))
+    pod_body = yaml.safe_load(pod_template.render(nodename=node, image=image))
    logging.info("Creating pod to query bridge on node %s" % node)
    kubecli.create_pod(pod_body, "default", 300)

@@ -662,7 +677,7 @@ def list_bridges(node: str, pod_template, kubecli: KrknKubernetes) -> typing.Lis


 def check_cookie(
-    node: str, pod_template, br_name, cookie, kubecli: KrknKubernetes
+    node: str, pod_template, br_name, cookie, kubecli: KrknKubernetes, image: str
 ) -> str:
    """
    Function to check for matching flow rules
@@ -684,11 +699,13 @@ def check_cookie(
        cli (CoreV1Api)
            - Object to interact with Kubernetes Python client's CoreV1 API

+        image (string)
+            - Image of network chaos tool
    Returns
        Returns the matching flow rules
    """

-    pod_body = yaml.safe_load(pod_template.render(nodename=node))
+    pod_body = yaml.safe_load(pod_template.render(nodename=node, image=image))
    logging.info("Creating pod to query duplicate rules on node %s" % node)
    kubecli.create_pod(pod_body, "default", 300)

@@ -721,7 +738,7 @@ def check_cookie(


 def get_pod_interface(
-    node: str, ip: str, pod_template, br_name, kubecli: KrknKubernetes
+    node: str, ip: str, pod_template, br_name, kubecli: KrknKubernetes, image: str = "quay.io/krkn-chaos/krkn:tools"
 ) -> str:
    """
    Function to query the pod interface on a node
@@ -747,7 +764,7 @@ def get_pod_interface(
        Returns the pod interface name
    """

-    pod_body = yaml.safe_load(pod_template.render(nodename=node))
+    pod_body = yaml.safe_load(pod_template.render(nodename=node, image=image))
    logging.info("Creating pod to query pod interface on node %s" % node)
    kubecli.create_pod(pod_body, "default", 300)
    inf = ""
@@ -788,7 +805,8 @@ def get_pod_interface(


 def check_bridge_interface(
-    node_name: str, pod_template, bridge_name: str, kubecli: KrknKubernetes
+    node_name: str, pod_template, bridge_name: str, kubecli: KrknKubernetes,
+    image: str = "quay.io/krkn-chaos/krkn:tools"
 ) -> bool:
    """
    Function  is used to check if the required OVS or OVN bridge is found in
@@ -814,7 +832,7 @@ def check_bridge_interface(
    nodes = kubecli.get_node(node_name, None, 1)
    node_bridge = []
    for node in nodes:
-        node_bridge = list_bridges(node, pod_template, kubecli)
+        node_bridge = list_bridges(node, pod_template, kubecli, image=image)
    if bridge_name not in node_bridge:
        raise Exception(f"OVS bridge {bridge_name} not found on the node ")

@@ -835,6 +853,14 @@ class InputParams:
        }
    )

+    image: typing.Annotated[str, validation.min(1)]= field(
+        default="quay.io/krkn-chaos/krkn:tools",
+        metadata={
+            "name": "Image",
+            "description": "Image of krkn tools to run"
+        }
+    )
+
    direction: typing.List[str] = field(
        default_factory=lambda: ["ingress", "egress"],
        metadata={
@@ -1004,6 +1030,7 @@ def pod_outage(
    test_namespace = params.namespace
    test_label_selector = params.label_selector
    test_pod_name = params.pod_name
+    test_image = params.image
    filter_dict = {}
    job_list = []
    publish = False
@@ -1040,7 +1067,7 @@ def pod_outage(
                label_set.add("%s=%s" % (key, value))

        check_bridge_interface(
-            list(node_dict.keys())[0], pod_module_template, br_name, kubecli
+            list(node_dict.keys())[0], pod_module_template, br_name, kubecli, test_image
        )

        for direction, ports in filter_dict.items():
@@ -1055,6 +1082,7 @@ def pod_outage(
                    params.test_duration,
                    br_name,
                    kubecli,
+                    test_image
                )
            )

@@ -1095,7 +1123,16 @@ class EgressParams:
        }
    )

+    image: typing.Annotated[str, validation.min(1)]= field(
+        default="quay.io/krkn-chaos/krkn:tools",
+        metadata={
+            "name": "Image",
+            "description": "Image of krkn tools to run"
+        }
+    )
+
    network_params: typing.Dict[str, str] = field(
+        default=None,
        metadata={
            "name": "Network Parameters",
            "description": "The network filters that are applied on the interface. "
@@ -1254,6 +1291,7 @@ def pod_egress_shaping(
    test_namespace = params.namespace
    test_label_selector = params.label_selector
    test_pod_name = params.pod_name
+    test_image = params.image
    job_list = []
    publish = False

@@ -1287,7 +1325,7 @@ def pod_egress_shaping(
                label_set.add("%s=%s" % (key, value))

        check_bridge_interface(
-            list(node_dict.keys())[0], pod_module_template, br_name, kubecli
+            list(node_dict.keys())[0], pod_module_template, br_name, kubecli, test_image
        )

        for mod in mod_lst:
@@ -1304,6 +1342,7 @@ def pod_egress_shaping(
                        br_name,
                        kubecli,
                        params.execution_type,
+                        test_image
                    )
                )
            if params.execution_type == "serial":
@@ -1357,8 +1396,17 @@ class IngressParams:
            "for details.",
        }
    )
+    
+    image: typing.Annotated[str, validation.min(1)] = field(
+        default="quay.io/krkn-chaos/krkn:tools",
+        metadata={
+            "name": "Image",
+            "description": "Image to use for injecting network chaos",
+        }
+    )

    network_params: typing.Dict[str, str] = field(
+        default=None,
        metadata={
            "name": "Network Parameters",
            "description": "The network filters that are applied on the interface. "
@@ -1518,6 +1566,7 @@ def pod_ingress_shaping(
    test_namespace = params.namespace
    test_label_selector = params.label_selector
    test_pod_name = params.pod_name
+    test_image = params.image
    job_list = []
    publish = False

@@ -1551,7 +1600,7 @@ def pod_ingress_shaping(
                label_set.add("%s=%s" % (key, value))

        check_bridge_interface(
-            list(node_dict.keys())[0], pod_module_template, br_name, kubecli
+            list(node_dict.keys())[0], pod_module_template, br_name, kubecli, test_image
        )

        for mod in mod_lst:
@@ -1568,6 +1617,7 @@ def pod_ingress_shaping(
                        br_name,
                        kubecli,
                        params.execution_type,
+                        image=test_image
                    )
                )
            if params.execution_type == "serial":
@@ -1604,6 +1654,6 @@ def pod_ingress_shaping(
        logging.error("Pod network Shaping scenario exiting due to Exception - %s" % e)
        return "error", PodIngressNetShapingErrorOutput(format_exc())
    finally:
-        delete_virtual_interfaces(kubecli, node_dict.keys(), pod_module_template)
+        delete_virtual_interfaces(kubecli, node_dict.keys(), pod_module_template, test_image)
        logging.info("Deleting jobs(if any)")
        delete_jobs(kubecli, job_list[:])
--- a/krkn/scenario_plugins/network_chaos/job.j2
+++ b/krkn/scenario_plugins/network_chaos/job.j2
@@ -9,7 +9,7 @@ spec:
      hostNetwork: true
      containers:
      - name: networkchaos
-        image: docker.io/fedora/tools
+        image: {{image}}
        command: ["/bin/sh",  "-c", "{{cmd}}"]
        securityContext:
          privileged: true
--- a/krkn/scenario_plugins/network_chaos/network_chaos_scenario_plugin.py
+++ b/krkn/scenario_plugins/network_chaos/network_chaos_scenario_plugin.py
@@ -42,7 +42,9 @@ class NetworkChaosScenarioPlugin(AbstractScenarioPlugin):
                test_egress = get_yaml_item_value(
                    test_dict, "egress", {"bandwidth": "100mbit"}
                )
-
+                test_image = get_yaml_item_value(
+                    test_dict, "image", "quay.io/krkn-chaos/krkn:tools"
+                )
                if test_node:
                    node_name_list = test_node.split(",")
                    nodelst = common_node_functions.get_node_by_name(node_name_list, lib_telemetry.get_lib_kubernetes())
@@ -60,6 +62,7 @@ class NetworkChaosScenarioPlugin(AbstractScenarioPlugin):
                    nodelst,
                    pod_template,
                    lib_telemetry.get_lib_kubernetes(),
+                    image=test_image
                )
                joblst = []
                egress_lst = [i for i in param_lst if i in test_egress]
@@ -71,6 +74,7 @@ class NetworkChaosScenarioPlugin(AbstractScenarioPlugin):
                        "execution": test_execution,
                        "instance_count": test_instance_count,
                        "egress": test_egress,
+                        "image": test_image
                    }
                }
                logging.info(
@@ -94,6 +98,7 @@ class NetworkChaosScenarioPlugin(AbstractScenarioPlugin):
                                    jobname=i + str(hash(node))[:5],
                                    nodename=node,
                                    cmd=exec_cmd,
+                                    image=test_image
                                )
                            )
                            joblst.append(job_body["metadata"]["name"])
@@ -153,10 +158,10 @@ class NetworkChaosScenarioPlugin(AbstractScenarioPlugin):
            return 0

    def verify_interface(
-        self, test_interface, nodelst, template, kubecli: KrknKubernetes
+        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]))
+        pod_body = yaml.safe_load(template.render(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)
        try:
@@ -177,7 +182,7 @@ class NetworkChaosScenarioPlugin(AbstractScenarioPlugin):
                        raise RuntimeError()
            return test_interface
        finally:
-            logging.info("Deleteing pod to query interface on node")
+            logging.info("Deleting pod to query interface on node")
            kubecli.delete_pod("fedtools", "default")

    # krkn_lib
--- a/krkn/scenario_plugins/network_chaos/pod.j2
+++ b/krkn/scenario_plugins/network_chaos/pod.j2
@@ -7,7 +7,7 @@ spec:
  nodeName: {{nodename}}
  containers:
  - name: fedtools
-    image: docker.io/fedora/tools
+    image: {{image}}
    command:
    - /bin/sh
    - -c
--- a/krkn/scenario_plugins/network_chaos_ng/models.py
+++ b/krkn/scenario_plugins/network_chaos_ng/models.py
@@ -14,9 +14,11 @@ class BaseNetworkChaosConfig:
    wait_duration: int
    test_duration: int
    label_selector: str
+    service_account: str
    instance_count: int
    execution: str
    namespace: str
+    taints: list[str]

    def validate(self) -> list[str]:
        errors = []
--- a/krkn/scenario_plugins/network_chaos_ng/modules/templates/network-chaos.j2
+++ b/krkn/scenario_plugins/network_chaos_ng/modules/templates/network-chaos.j2
@@ -4,16 +4,26 @@ metadata:
  name: {{pod_name}}
  namespace: {{namespace}}
 spec:
+  {% if service_account %}
+  serviceAccountName: {{ service_account }}
+  {%endif%}
  {% if host_network %}
  hostNetwork: true
  {%endif%}
+  {% if taints %}
+  tolerations:
+  {% for toleration in taints %}
+  - key: "{{ toleration.key }}"
+    operator: "{{ toleration.operator }}"
+    {% if toleration.value %}
+    value: "{{ toleration.value }}"
+    {% endif %}
+    effect: "{{ toleration.effect }}"
+  {% endfor %}
+  {% endif %}
  hostPID: true
  nodeSelector:
    kubernetes.io/hostname: {{target}}
-  tolerations:
-  - key: "node-role.kubernetes.io/master"
-    operator: "Exists"
-    effect: "NoSchedule"
  containers:
  - name: {{container_name}}
    imagePullPolicy: Always
--- a/krkn/scenario_plugins/network_chaos_ng/modules/utils_network_filter.py
+++ b/krkn/scenario_plugins/network_chaos_ng/modules/utils_network_filter.py
@@ -58,6 +58,27 @@ def deploy_network_filter_pod(
    file_loader = FileSystemLoader(os.path.abspath(os.path.dirname(__file__)))
    env = Environment(loader=file_loader, autoescape=True)
    pod_template = env.get_template("templates/network-chaos.j2")
+    tolerations = []
+
+    for taint in config.taints:
+        key_value_part, effect = taint.split(":", 1)
+        if "=" in key_value_part:
+            key, value = key_value_part.split("=", 1)
+            operator = "Equal"
+        else:
+            key = key_value_part
+            value = None
+            operator = "Exists"
+        toleration = {
+            "key": key,
+            "operator": operator,
+            "effect": effect,
+        }
+        if value is not None:
+            toleration["value"] = value
+        tolerations.append(toleration)
+
+
    pod_body = yaml.safe_load(
        pod_template.render(
            pod_name=pod_name,
@@ -66,6 +87,8 @@ def deploy_network_filter_pod(
            target=target_node,
            container_name=container_name,
            workload_image=config.image,
+            taints=tolerations,
+            service_account=config.service_account
        )
    )

--- a/krkn/scenario_plugins/node_actions/abstract_node_scenarios.py
+++ b/krkn/scenario_plugins/node_actions/abstract_node_scenarios.py
@@ -84,7 +84,7 @@ class abstract_node_scenarios:
                )
                logging.error("stop_kubelet_scenario injection failed!")
                raise e
-            self.add_affected_node(affected_node)
+            self.affected_nodes_status.affected_nodes.append(affected_node)

    # Node scenario to stop and start the kubelet
    def stop_start_kubelet_scenario(self, instance_kill_count, node, timeout):
@@ -106,7 +106,6 @@ class abstract_node_scenarios:
                    + node
                    + " -- chroot /host systemctl restart kubelet &"
                )
-                nodeaction.wait_for_not_ready_status(node, timeout, self.kubecli, affected_node)
                nodeaction.wait_for_ready_status(node, timeout, self.kubecli,affected_node)
                logging.info("The kubelet of the node %s has been restarted" % (node))
                logging.info("restart_kubelet_scenario has been successfuly injected!")
@@ -117,7 +116,7 @@ class abstract_node_scenarios:
                )
                logging.error("restart_kubelet_scenario injection failed!")
                raise e
-            self.add_affected_node(affected_node)
+            self.affected_nodes_status.affected_nodes.append(affected_node)

    # Node scenario to crash the node
    def node_crash_scenario(self, instance_kill_count, node, timeout):
@@ -125,7 +124,7 @@ class abstract_node_scenarios:
            try:
                logging.info("Starting node_crash_scenario injection")
                logging.info("Crashing the node %s" % (node))
-                runcommand.invoke(
+                runcommand.run(
                    "oc debug node/" + node + " -- chroot /host "
                    "dd if=/dev/urandom of=/proc/sysrq-trigger"
                )
@@ -136,7 +135,7 @@ class abstract_node_scenarios:
                    "Test Failed" % (e)
                )
                logging.error("node_crash_scenario injection failed!")
-                raise e
+                return 1

    # Node scenario to check service status on helper node
    def node_service_status(self, node, service, ssh_private_key, timeout):
--- a/krkn/scenario_plugins/node_actions/bm_node_scenarios.py
+++ b/krkn/scenario_plugins/node_actions/bm_node_scenarios.py
@@ -274,7 +274,7 @@ done'''
                logging.info("Disk response: %s" % (disk_response))
                node_disks = [disk for disk in disk_response.split("\n") if disk]
                logging.info("Node disks: %s" % (node_disks))
-                offline_disks = [disk for disk in node_disks if disk not in user_disks]
+                offline_disks = [disk for disk in user_disks if disk in node_disks]
                return offline_disks if offline_disks else node_disks
            except Exception as e:
                logging.error(
--- a/krkn/scenario_plugins/node_actions/common_node_functions.py
+++ b/krkn/scenario_plugins/node_actions/common_node_functions.py
@@ -1,16 +1,10 @@
-import datetime
 import time
 import random
 import logging
 import paramiko
-from krkn_lib.models.k8s import AffectedNode
-import krkn.invoke.command as runcommand
 from krkn_lib.k8s import KrknKubernetes
-from krkn_lib.models.k8s import AffectedNode, AffectedNodeStatus
 from krkn_lib.models.k8s import AffectedNode

-node_general = False
-

 def get_node_by_name(node_name_list, kubecli: KrknKubernetes):
    killable_nodes = kubecli.list_killable_nodes()
@@ -65,14 +59,6 @@ def wait_for_unknown_status(node, timeout, kubecli: KrknKubernetes, affected_nod
    return affected_node


-# Get the ip of the cluster node
-def get_node_ip(node):
-    return runcommand.invoke(
-        "kubectl get node %s -o "
-        "jsonpath='{.status.addresses[?(@.type==\"InternalIP\")].address}'" % (node)
-    )
-
-
 def check_service_status(node, service, ssh_private_key, timeout):
    ssh = paramiko.SSHClient()
    ssh.set_missing_host_key_policy(paramiko.AutoAddPolicy())
--- a/krkn/scenario_plugins/node_actions/ibmcloud_node_scenarios.py
+++ b/krkn/scenario_plugins/node_actions/ibmcloud_node_scenarios.py
@@ -36,10 +36,25 @@ class IbmCloud:
            self.service = VpcV1(authenticator=authenticator)

            self.service.set_service_url(service_url)
+            
        except Exception as e:
            logging.error("error authenticating" + str(e))

-
+    def configure_ssl_verification(self, disable_ssl_verification):
+        """
+        Configure SSL verification for IBM Cloud VPC service.
+        
+        Args:
+            disable_ssl_verification: If True, disables SSL verification.
+        """
+        logging.info(f"Configuring SSL verification: disable_ssl_verification={disable_ssl_verification}")
+        if disable_ssl_verification:
+            self.service.set_disable_ssl_verification(True)
+            logging.info("SSL verification disabled for IBM Cloud VPC service")
+        else:
+            self.service.set_disable_ssl_verification(False)
+            logging.info("SSL verification enabled for IBM Cloud VPC service")
+            
    # Get the instance ID of the node
    def get_instance_id(self, node_name):
        node_list = self.list_instances()
@@ -260,9 +275,13 @@ class IbmCloud:

@dataclass
 class ibm_node_scenarios(abstract_node_scenarios):
-    def __init__(self, kubecli: KrknKubernetes, node_action_kube_check: bool, affected_nodes_status: AffectedNodeStatus):
+    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 = IbmCloud()
+        
+        # Configure SSL verification
+        self.ibmcloud.configure_ssl_verification(disable_ssl_verification)
+        
        self.node_action_kube_check = node_action_kube_check

    def node_start_scenario(self, instance_kill_count, node, timeout):
@@ -327,7 +346,7 @@ class ibm_node_scenarios(abstract_node_scenarios):
                logging.info("Starting node_reboot_scenario injection")
                logging.info("Rebooting the node %s " % (node))
                self.ibmcloud.reboot_instances(instance_id)
-                self.ibmcloud.wait_until_rebooted(instance_id, timeout)
+                self.ibmcloud.wait_until_rebooted(instance_id, timeout, affected_node)
                if self.node_action_kube_check:
                    nodeaction.wait_for_unknown_status(
                        node, timeout, affected_node
--- a/krkn/scenario_plugins/node_actions/node_actions_scenario_plugin.py
+++ b/krkn/scenario_plugins/node_actions/node_actions_scenario_plugin.py
@@ -120,7 +120,8 @@ class NodeActionsScenarioPlugin(AbstractScenarioPlugin):
            node_scenario["cloud_type"].lower() == "ibm"
            or node_scenario["cloud_type"].lower() == "ibmcloud"
        ):
-            return ibm_node_scenarios(kubecli, node_action_kube_check, affected_nodes_status)
+            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)
        else:
            logging.error(
                "Cloud type "
--- a/requirements.txt
+++ b/requirements.txt
@@ -38,3 +38,4 @@ zope.interface==5.4.0

 git+https://github.com/vmware/vsphere-automation-sdk-python.git@v8.0.0.0
 cryptography>=42.0.4 # not directly required, pinned by Snyk to avoid a vulnerability
+protobuf>=4.25.8 # not directly required, pinned by Snyk to avoid a vulnerability
--- a/run_kraken.py
+++ b/run_kraken.py
@@ -16,7 +16,6 @@ from krkn_lib.elastic.krkn_elastic import KrknElastic
 from krkn_lib.models.elastic import ElasticChaosRunTelemetry
 from krkn_lib.models.krkn import ChaosRunOutput, ChaosRunAlertSummary
 from krkn_lib.prometheus.krkn_prometheus import KrknPrometheus
-import krkn.performance_dashboards.setup as performance_dashboards
 import krkn.prometheus as prometheus_plugin
 import server as server
 from krkn_lib.k8s import KrknKubernetes
@@ -69,14 +68,6 @@ def main(cfg) -> int:
        wait_duration = get_yaml_item_value(config["tunings"], "wait_duration", 60)
        iterations = get_yaml_item_value(config["tunings"], "iterations", 1)
        daemon_mode = get_yaml_item_value(config["tunings"], "daemon_mode", False)
-        deploy_performance_dashboards = get_yaml_item_value(
-            config["performance_monitoring"], "deploy_dashboards", False
-        )
-        dashboard_repo = get_yaml_item_value(
-            config["performance_monitoring"],
-            "repo",
-            "https://github.com/cloud-bulldozer/performance-dashboards.git",
-        )

        prometheus_url = config["performance_monitoring"].get("prometheus_url")
        prometheus_bearer_token = config["performance_monitoring"].get(
@@ -240,10 +231,6 @@ def main(cfg) -> int:

        logging.info("Server URL: %s" % kubecli.get_host())

-        # Deploy performance dashboards
-        if deploy_performance_dashboards:
-            performance_dashboards.setup(dashboard_repo, distribution)
-
        # Initialize the start iteration to 0
        iteration = 0

--- a/scenarios/kube/cpu-hog.yml
+++ b/scenarios/kube/cpu-hog.yml
@@ -5,6 +5,7 @@ image: quay.io/krkn-chaos/krkn-hog
 namespace: default
 cpu-load-percentage: 90
 cpu-method: all
+# node-name: "worker-0" # Uncomment to target a specific node by name
 node-selector: "node-role.kubernetes.io/worker="
 number-of-nodes: 2
 taints: [] #example ["node-role.kubernetes.io/master:NoSchedule"]
--- a/scenarios/kube/io-hog.yml
+++ b/scenarios/kube/io-hog.yml
@@ -6,10 +6,11 @@ namespace: default
 io-block-size: 1m
 io-write-bytes: 1g
 io-target-pod-folder: /hog-data
+# node-name: "worker-0" # Uncomment to target a specific node by name
 io-target-pod-volume:
  name: node-volume
  hostPath:
    path: /root # a path writable by kubelet in the root filesystem of the node
 node-selector: "node-role.kubernetes.io/worker="
 number-of-nodes: ''
-taints: [] #example ["node-role.kubernetes.io/master:NoSchedule"]
+taints: [] #example ["node-role.kubernetes.io/master:NoSchedule"]    
--- a/scenarios/kube/memory-hog.yml
+++ b/scenarios/kube/memory-hog.yml
@@ -4,6 +4,7 @@ hog-type: memory
 image: quay.io/krkn-chaos/krkn-hog
 namespace: default
 memory-vm-bytes: 90%
+# node-name: "worker-0" # Uncomment to target a specific node by name
 node-selector: "node-role.kubernetes.io/worker="
 number-of-nodes: ''
 taints: [] #example ["node-role.kubernetes.io/master:NoSchedule"]
--- a/scenarios/kube/node-network-filter.yml
+++ b/scenarios/kube/node-network-filter.yml
@@ -1,14 +1,18 @@
 - id: node_network_filter
  image: "quay.io/krkn-chaos/krkn-network-chaos:latest"
-  wait_duration: 300
-  test_duration: 100
-  label_selector: "kubernetes.io/hostname=minikube"
+  wait_duration: 1
+  test_duration: 10
+  label_selector: "<node_selector>"
+  service_account: ""
+  taints: [] # example ["node-role.kubernetes.io/master:NoSchedule"]
  namespace: 'default'
  instance_count: 1
  execution: parallel
  ingress: false
  egress: true
-  target: ''
+  target: '<node_name>'
  interfaces: []
  ports:
-    - 53
+    - 2309
+  protocols:
+    - tcp
--- a/scenarios/kube/pod-network-filter.yml
+++ b/scenarios/kube/pod-network-filter.yml
@@ -2,13 +2,15 @@
  image: "quay.io/krkn-chaos/krkn-network-chaos:latest"
  wait_duration: 1
  test_duration: 60
-  label_selector: "app=network-attacked"
+  label_selector: "<pod_selector>"
+  service_account: ""
+  taints: [] # example ["node-role.kubernetes.io/master:NoSchedule"]
  namespace: 'default'
  instance_count: 1
  execution: parallel
  ingress: false
  egress: true
-  target: ""
+  target: "<pod_name>"
  interfaces: []
  protocols:
    - tcp
--- a/scenarios/kubevirt/kubevirt-vm-outage.yaml
+++ b/scenarios/kubevirt/kubevirt-vm-outage.yaml
@@ -0,0 +1,7 @@
+scenarios:
+  - name: "kubevirt outage test"
+    scenario: kubevirt_vm_outage
+    parameters:
+      vm_name: <vm-name>  
+      namespace: <namespace>  
+      timeout: 60
--- a/scenarios/openshift/ibmcloud_node_scenarios.yml
+++ b/scenarios/openshift/ibmcloud_node_scenarios.yml
@@ -7,10 +7,12 @@ node_scenarios:
    timeout: 360
    duration: 120
    cloud_type: ibm
+    disable_ssl_verification: true  # Set to true for CI environments with certificate issues
  - actions:
    - node_reboot_scenario
    node_name:
    label_selector: node-role.kubernetes.io/worker
    instance_count: 1
    timeout: 120
-    cloud_type: ibm
+    cloud_type: ibm
+    disable_ssl_verification: true  # Set to true for CI environments with certificate issues
--- a/scenarios/plugin.schema.json
+++ b/scenarios/plugin.schema.json
--- a/tests/kubevirt_vm_outage/test_kubevirt_vm_outage.py
+++ b/tests/kubevirt_vm_outage/test_kubevirt_vm_outage.py
@@ -0,0 +1,215 @@
+import unittest
+import time
+from unittest.mock import MagicMock, patch
+
+import yaml
+from krkn_lib.k8s import KrknKubernetes
+from krkn_lib.models.telemetry import ScenarioTelemetry
+from krkn_lib.telemetry.ocp import KrknTelemetryOpenshift
+
+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
+        
+        # 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
+        import tempfile, os
+        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
+        
+    def test_successful_injection_and_recovery(self):
+        """
+        Test successful deletion and recovery of a VMI
+        """
+        # Mock get_vmi to return our mock VMI
+        with patch.object(self.plugin, 'get_vmi', return_value=self.mock_vmi):
+            # Mock inject and recover to simulate success
+            with patch.object(self.plugin, 'inject', return_value=0) as mock_inject:
+                with patch.object(self.plugin, 'recover', return_value=0) as mock_recover:
+                    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_inject.assert_called_once_with("test-vm", "default", False)
+        mock_recover.assert_called_once_with("test-vm", "default", False)
+        
+    def test_injection_failure(self):
+        """
+        Test failure during VMI deletion
+        """
+        # Mock get_vmi to return our mock VMI
+        with patch.object(self.plugin, 'get_vmi', return_value=self.mock_vmi):
+            # Mock inject to simulate failure
+            with patch.object(self.plugin, 'inject', return_value=1) as mock_inject:
+                with patch.object(self.plugin, 'recover', return_value=0) as mock_recover:
+                    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, 1)
+        mock_inject.assert_called_once_with("test-vm", "default", False)
+        mock_recover.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
+        
+        # Mock VM object for patching
+        mock_vm = {
+            "metadata": {"name": "test-vm", "namespace": "default"},
+            "spec": {}
+        }
+        
+        # Mock get_vmi to return our mock VMI
+        with patch.object(self.plugin, 'get_vmi', return_value=self.mock_vmi):
+            # Mock VM patch operation
+            with patch.object(self.plugin, 'patch_vm_spec') as mock_patch_vm:
+                mock_patch_vm.return_value = True
+                # Mock inject and recover
+                with patch.object(self.plugin, 'inject', return_value=0) as mock_inject:
+                    with patch.object(self.plugin, 'recover', return_value=0) as mock_recover:
+                        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)
+        # Should call patch_vm_spec to disable auto-restart
+        mock_patch_vm.assert_any_call("test-vm", "default", False)
+        # Should call patch_vm_spec to re-enable auto-restart during recovery
+        mock_patch_vm.assert_any_call("test-vm", "default", True)
+        mock_inject.assert_called_once_with("test-vm", "default", True)
+        mock_recover.assert_called_once_with("test-vm", "default", True)
+        
+    def test_recovery_when_vmi_does_not_exist(self):
+        """
+        Test recovery logic when VMI does not exist after deletion
+        """
+        # 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
+        """
+        # Mock empty CRD list (no KubeVirt CRDs)
+        empty_crd_list = MagicMock()
+        empty_crd_list.items = []
+        self.k8s_client.list_custom_resource_definition.return_value = empty_crd_list
+        
+        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, 1)
+        
+    def test_delete_vmi_timeout(self):
+        """
+        Test timeout during VMI deletion
+        """
+        # Mock successful delete operation
+        self.custom_object_client.delete_namespaced_custom_object = MagicMock(return_value={})
+        
+        # Mock that get_vmi always returns VMI (never gets deleted)
+        with patch.object(self.plugin, 'get_vmi', return_value=self.mock_vmi):
+            # 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.inject("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"
+        )
+
+
+if __name__ == "__main__":
+    unittest.main()
Author	SHA1	Message	Date
Paige Patton	4f250c9601	adding affected nodes to affectednodestatus (#884 ) Some checks failed Functional & Unit Tests / Functional & Unit Tests (push) Failing after 4m20s Functional & Unit Tests / Generate Coverage Badge (push) Has been skipped Signed-off-by: Paige Patton <prubenda@redhat.com>	2025-08-13 20:54:13 -04:00
Paige Patton	6480adc00a	adding setting own image for network chaos (#883 ) Some checks failed Functional & Unit Tests / Functional & Unit Tests (push) Failing after 10m5s Functional & Unit Tests / Generate Coverage Badge (push) Has been skipped Signed-off-by: Paige Patton <prubenda@redhat.com>	2025-08-13 17:49:47 -04:00
Paige Patton	5002f210ae	removing dashboard installation Some checks failed Functional & Unit Tests / Functional & Unit Tests (push) Failing after 9m9s Functional & Unit Tests / Generate Coverage Badge (push) Has been skipped Signed-off-by: Paige Patton <prubenda@redhat.com>	2025-08-05 11:27:41 -04:00
Paige Patton	62c5afa9a2	updated done items in roadmap Some checks failed Functional & Unit Tests / Functional & Unit Tests (push) Failing after 9m52s Functional & Unit Tests / Generate Coverage Badge (push) Has been skipped Signed-off-by: Paige Patton <prubenda@redhat.com>	2025-08-01 13:23:23 -04:00
Paige Patton	c109fc0b17	adding elastic installation into krkn tests Some checks failed Functional & Unit Tests / Functional & Unit Tests (push) Failing after 6m36s Functional & Unit Tests / Generate Coverage Badge (push) Has been skipped Signed-off-by: Paige Patton <prubenda@redhat.com>	2025-07-31 10:41:31 -04:00
Tullio Sebastiani	fff675f3dd	added service account to Network Chaos NG workload (#870 ) Some checks failed Functional & Unit Tests / Functional & Unit Tests (push) Failing after 8m56s Functional & Unit Tests / Generate Coverage Badge (push) Has been skipped Signed-off-by: Tullio Sebastiani <tsebasti@redhat.com>	2025-07-23 10:17:50 +02:00
Naga Ravi Chaitanya Elluri	c125e5acf7	Update network scenario image Some checks failed Functional & Unit Tests / Functional & Unit Tests (push) Failing after 9m34s Functional & Unit Tests / Generate Coverage Badge (push) Has been skipped This commit updates fedora tools image reference used by the network scenarios to the one hosted in the krkn-chaos quay org. This also fixes the issues with RHACS flagging runs when using latest tag by using tools tag instead. Signed-off-by: Naga Ravi Chaitanya Elluri <nelluri@redhat.com>	2025-07-22 14:29:00 -04:00
Naga Ravi Chaitanya Elluri	ca6995a1a1	[Snyk] Fix for 3 vulnerabilities (#859 ) * fix: requirements.txt to reduce vulnerabilities The following vulnerabilities are fixed by pinning transitive dependencies: - https://snyk.io/vuln/SNYK-PYTHON-PROTOBUF-10364902 - https://snyk.io/vuln/SNYK-PYTHON-URLLIB3-10390193 - https://snyk.io/vuln/SNYK-PYTHON-URLLIB3-10390194 * partial vulnerability fix Signed-off-by: Tullio Sebastiani <tsebasti@redhat.com> --------- Signed-off-by: Tullio Sebastiani <tsebasti@redhat.com> Co-authored-by: snyk-bot <snyk-bot@snyk.io> Co-authored-by: Tullio Sebastiani <tsebasti@redhat.com>	2025-07-22 16:50:31 +02:00
Sahil Shah	50cf91ac9e	Disable SSL verification for IBM node scenarios and fix node reboot s… (#861 ) Some checks failed Functional & Unit Tests / Functional & Unit Tests (push) Failing after 9m9s Functional & Unit Tests / Generate Coverage Badge (push) Has been skipped * Disable SSL verification for IBM node scenarios and fix node reboot scenario Signed-off-by: Sahil Shah <sahshah@redhat.com> * adding disable ssl as a scenario parameter for ibmcloud Signed-off-by: Sahil Shah <sahshah@redhat.com> --------- Signed-off-by: Sahil Shah <sahshah@redhat.com>	2025-07-16 12:48:45 -04:00
Tullio Sebastiani	11069c6982	added tolerations to node network filter pod deployment (#867 )	2025-07-16 17:11:46 +02:00
Charles Uneze	106d9bf1ae	A working kind config (#866 ) Some checks failed Functional & Unit Tests / Functional & Unit Tests (push) Failing after 5m13s Functional & Unit Tests / Generate Coverage Badge (push) Has been skipped Signed-off-by: Charles Uneze <charlesniklaus@gmail.com>	2025-07-15 10:25:01 -04:00
Abhinav Sharma	17f832637c	feat: add optional node-name field to hog scenarios with precedence over node-selector (#831 ) Some checks failed Functional & Unit Tests / Functional & Unit Tests (push) Failing after 8m31s Functional & Unit Tests / Generate Coverage Badge (push) Has been skipped Signed-off-by: Abhinav Sharma <abhinavs1920bpl@gmail.com> Co-authored-by: Paige Patton <64206430+paigerube14@users.noreply.github.com>	2025-07-11 14:10:16 -04:00
Paige Patton	0e5c8c55a4	adding details of node for hog failure Some checks failed Functional & Unit Tests / Functional & Unit Tests (push) Failing after 8m23s Functional & Unit Tests / Generate Coverage Badge (push) Has been skipped Signed-off-by: Paige Patton <prubenda@redhat.com>	2025-07-10 16:49:28 -04:00
Tullio Sebastiani	9d9a6f9b80	added missing parameters to node-network-filter + added default values Signed-off-by: Tullio Sebastiani <tsebasti@redhat.com>	2025-07-10 13:22:50 -04:00
Anshuman Panda	f8fe2ae5b7	Refactor: to use krkn-lib for getting and remove invoke funct. usage node IP Signed-off-by: Anshuman Panda <ichuk0078@gmail.com> Signed-off-by: Paige Patton <prubenda@redhat.com>	2025-07-10 13:21:10 -04:00
Paige Patton	77b1dd32c7	adding kubevirt with pod timing Signed-off-by: Paige Patton <prubenda@redhat.com>	2025-07-10 13:19:37 -04:00
Anshuman Panda	9df727ccf5	Ensure metrics are always saved with improved local fallback Signed-off-by: Anshuman Panda <ichuk0078@gmail.com> Signed-off-by: Paige Patton <prubenda@redhat.com>	2025-07-10 13:19:07 -04:00
Tullio Sebastiani	70c8fec705	added pod-network-filter funtest (#863 ) Some checks failed Functional & Unit Tests / Functional & Unit Tests (push) Failing after 9m37s Functional & Unit Tests / Generate Coverage Badge (push) Has been skipped * added pod-network-filter funtest Signed-off-by: Tullio Sebastiani <tsebasti@redhat.com> * updated kind settings Signed-off-by: Tullio Sebastiani <tsebasti@redhat.com> --------- Signed-off-by: Tullio Sebastiani <tsebasti@redhat.com>	2025-07-10 09:35:59 +02:00
Abhinav Sharma	0731144a6b	Add support for triggering kubevirt VM outages (#816 ) Some checks failed Functional & Unit Tests / Functional & Unit Tests (push) Failing after 10m2s Functional & Unit Tests / Generate Coverage Badge (push) Has been skipped * add requirement for kubevirt_vm_outage Signed-off-by: Abhinav Sharma <abhinavs1920bpl@gmail.com> Signed-off-by: Paige Patton <prubenda@redhat.com> * add initial init and kubevirt_plugin files Signed-off-by: Abhinav Sharma <abhinavs1920bpl@gmail.com> Signed-off-by: Paige Patton <prubenda@redhat.com> * add scenario in kubevirt-vm-outage.yaml Signed-off-by: Abhinav Sharma <abhinavs1920bpl@gmail.com> Signed-off-by: Paige Patton <prubenda@redhat.com> * implement init, get_scenario_types, run and placeholder for inject and recover functions Signed-off-by: Abhinav Sharma <abhinavs1920bpl@gmail.com> Signed-off-by: Paige Patton <prubenda@redhat.com> * implement init client, execute_scenario, validate environment, inject and get_VMinstance fucntions Signed-off-by: Abhinav Sharma <abhinavs1920bpl@gmail.com> Signed-off-by: Paige Patton <prubenda@redhat.com> * implement recover function Signed-off-by: Abhinav Sharma <abhinavs1920bpl@gmail.com> Signed-off-by: Paige Patton <prubenda@redhat.com> * implement recover function Signed-off-by: Abhinav Sharma <abhinavs1920bpl@gmail.com> Signed-off-by: Paige Patton <prubenda@redhat.com> * add test for kubevirt_vm_outage feature Signed-off-by: Abhinav Sharma <abhinavs1920bpl@gmail.com> Signed-off-by: Paige Patton <prubenda@redhat.com> * improve KubeVirt recovery logic and update dependencies, for kubevirt Signed-off-by: Paige Patton <prubenda@redhat.com> * refactor(kubevirt): use KrknKubernetes client for KubeVirt operations Signed-off-by: Abhinav Sharma <abhinavs1920bpl@gmail.com> Signed-off-by: Paige Patton <prubenda@redhat.com> * chore: Add auto-restart disable option and simplify code Signed-off-by: Abhinav Sharma <abhinavs1920bpl@gmail.com> Signed-off-by: Paige Patton <prubenda@redhat.com> * chore: remove kubevirt external package used. Signed-off-by: Abhinav Sharma <abhinavs1920bpl@gmail.com> Signed-off-by: Paige Patton <prubenda@redhat.com> * adding few changes and scenario in config file Signed-off-by: Paige Patton <prubenda@redhat.com> * removing docs Signed-off-by: Paige Patton <prubenda@redhat.com> * no affected pods Signed-off-by: Paige Patton <prubenda@redhat.com> --------- Signed-off-by: Abhinav Sharma <abhinavs1920bpl@gmail.com> Signed-off-by: Paige Patton <prubenda@redhat.com> Co-authored-by: Paige Patton <prubenda@redhat.com>	2025-07-08 14:04:57 -04:00
yogananth subramanian	9337052e7b	Fix bm_node_scenarios.py Some checks failed Functional & Unit Tests / Functional & Unit Tests (push) Failing after 10m29s Functional & Unit Tests / Generate Coverage Badge (push) Has been skipped Fix the logic in disk disruption scenario, which was returning the right set of disks to be off-lined. Signed-off-by: Yogananth Subramanian <ysubrama@redhat.com>	2025-07-07 13:49:33 -04:00