updated krkn-lib to 2.1.0 (#588)

Signed-off-by: Tullio Sebastiani <tsebasti@redhat.com>

.github/workflows/build.yml

@@ -1,70 +0,0 @@
-name: Build Krkn
-on:
-  push:
-    branches:
-      - main
-  pull_request:
-
-jobs:
-  build:
-    runs-on: ubuntu-latest
-    steps:
-      - name: Check out code
-        uses: actions/checkout@v3
-      - name: Create multi-node KinD cluster
-        uses: redhat-chaos/actions/kind@main
-      - name: Install Python
-        uses: actions/setup-python@v4
-        with:
-          python-version: '3.9'
-          architecture: 'x64'
-      - name: Install environment
-        run: |
-          sudo apt-get install build-essential python3-dev
-          pip install --upgrade pip
-          pip install -r requirements.txt
-      - name: Run unit tests
-        run: python -m coverage run -a -m unittest discover -s tests -v
-      - name: Run CI
-        run: |
-          ./CI/run.sh
-          cat ./CI/results.markdown >> $GITHUB_STEP_SUMMARY
-          echo >> $GITHUB_STEP_SUMMARY
-      - name: Upload CI logs
-        uses: actions/upload-artifact@v3
-        with:
-          name: ci-logs
-          path: CI/out
-          if-no-files-found: error
-      - name: Collect coverage report
-        run: |
-          python -m coverage html
-      - name: Publish coverage report to job summary
-        run: |
-          pip install html2text
-          html2text --ignore-images --ignore-links -b 0 htmlcov/index.html >> $GITHUB_STEP_SUMMARY
-      - name: Upload coverage data
-        uses: actions/upload-artifact@v3
-        with:
-          name: coverage
-          path: htmlcov
-          if-no-files-found: error
-      - name: Check CI results
-        run: grep Fail CI/results.markdown && false || true
-      - name: Build the Docker images
-        run: docker build --no-cache -t quay.io/chaos-kubox/krkn containers/
-      - name: Login in quay
-        if: github.ref == 'refs/heads/main' && github.event_name == 'push'
-        run: docker login quay.io -u ${QUAY_USER} -p ${QUAY_TOKEN}
-        env:
-          QUAY_USER: ${{ secrets.QUAY_USER_1 }}
-          QUAY_TOKEN: ${{ secrets.QUAY_TOKEN_1 }}
-      - name: Push the Docker images
-        if: github.ref == 'refs/heads/main' && github.event_name == 'push'
-        run: docker push quay.io/chaos-kubox/krkn
-      - name: Rebuild krkn-hub
-        if: github.ref == 'refs/heads/main' && github.event_name == 'push'
-        uses: redhat-chaos/actions/krkn-hub@main
-        with:
-          QUAY_USER: ${{ secrets.QUAY_USER_1 }}
-          QUAY_TOKEN: ${{ secrets.QUAY_TOKEN_1 }}

.github/workflows/docker-image.yml

@@ -0,0 +1,41 @@
+name: Docker Image CI
+on:
+  push:
+    branches:
+      - main
+  pull_request:
+
+jobs:
+  build:
+    runs-on: ubuntu-latest
+    steps:
+    - name: Check out code
+      uses: actions/checkout@v3
+    - name: Build the Docker images
+      run:  |
+        docker build --no-cache -t quay.io/krkn-chaos/krkn containers/
+        docker tag quay.io/krkn-chaos/krkn quay.io/redhat-chaos/krkn
+    - name: Login in quay
+      if: github.ref == 'refs/heads/main' && github.event_name == 'push'
+      run: docker login quay.io -u ${QUAY_USER} -p ${QUAY_TOKEN}
+      env:
+        QUAY_USER: ${{ secrets.QUAY_USERNAME }}
+        QUAY_TOKEN: ${{ secrets.QUAY_PASSWORD }}
+    - name: Push the KrknChaos Docker images
+      if: github.ref == 'refs/heads/main' && github.event_name == 'push'
+      run: docker push quay.io/krkn-chaos/krkn
+    - name: Login in to redhat-chaos quay
+      if: github.ref == 'refs/heads/main' && github.event_name == 'push'
+      run: docker login quay.io -u ${QUAY_USER} -p ${QUAY_TOKEN}
+      env:
+        QUAY_USER: ${{ secrets.QUAY_USER_1 }}
+        QUAY_TOKEN: ${{ secrets.QUAY_TOKEN_1 }}
+    - name: Push the RedHat Chaos Docker images
+      if: github.ref == 'refs/heads/main' && github.event_name == 'push'
+      run: docker push quay.io/redhat-chaos/krkn
+    - name: Rebuild krkn-hub
+      if: github.ref == 'refs/heads/main' && github.event_name == 'push'
+      uses: redhat-chaos/actions/krkn-hub@main
+      with:
+        QUAY_USER: ${{ secrets.QUAY_USERNAME }}
+        QUAY_TOKEN: ${{ secrets.QUAY_PASSWORD }}

.github/workflows/tests.yml

@@ -0,0 +1,134 @@
+name: Functional & Unit Tests
+on:
+  pull_request:
+  push:
+    branches:
+      - main
+jobs:
+  tests:
+    # Common steps
+    name: Functional & Unit Tests
+    runs-on: ubuntu-latest
+    steps:
+      - name: Check out code
+        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
+
+          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
+      - name: Install Python
+        uses: actions/setup-python@v4
+        with:
+          python-version: '3.9'
+          architecture: 'x64'
+      - name: Install environment
+        run: |
+          sudo apt-get install build-essential python3-dev
+          pip install --upgrade pip
+          pip install -r requirements.txt
+
+      - name: Deploy test workloads
+        run: |
+          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
+          kubectl wait --for=condition=ready pod -l scenario=container --timeout=300s
+          kubectl create namespace namespace-scenario
+          kubectl apply -f CI/templates/time_pod.yaml
+          kubectl wait --for=condition=ready pod -l scenario=time-skew --timeout=300s
+      - name: Get Kind nodes
+        run: |
+          kubectl get nodes --show-labels=true
+      # Pull request only steps
+      - name: Run unit tests
+        if: github.event_name == 'pull_request'
+        run: python -m coverage run -a -m unittest discover -s tests -v
+
+      - name: Setup Pull Request Functional Tests
+        if: github.event_name == 'pull_request'
+        run: |
+            yq -i '.kraken.port="8081"' CI/config/common_test_config.yaml
+            yq -i '.kraken.signal_address="0.0.0.0"' CI/config/common_test_config.yaml
+            yq -i '.kraken.performance_monitoring="localhost:9090"' CI/config/common_test_config.yaml
+            echo "test_app_outages" > ./CI/tests/functional_tests
+            echo "test_container"      >> ./CI/tests/functional_tests
+            echo "test_namespace"      >> ./CI/tests/functional_tests
+            echo "test_net_chaos"      >> ./CI/tests/functional_tests
+            echo "test_time"           >> ./CI/tests/functional_tests
+            echo "test_arca_cpu_hog" >> ./CI/tests/functional_tests
+            echo "test_arca_memory_hog" >> ./CI/tests/functional_tests
+            echo "test_arca_io_hog" >> ./CI/tests/functional_tests
+
+      # Push on main only steps
+      - name: Configure AWS Credentials
+        if: github.ref == 'refs/heads/main' && github.event_name == 'push'
+        uses: aws-actions/configure-aws-credentials@v4
+        with:
+          aws-access-key-id: ${{ secrets.AWS_ACCESS_KEY_ID }}
+          aws-secret-access-key: ${{ secrets.AWS_SECRET_ACCESS_KEY }}
+          aws-region : ${{ secrets.AWS_REGION }}
+      - name: Setup Post Merge Request Functional Tests
+        if: github.ref == 'refs/heads/main' && github.event_name == 'push'
+        run: |
+          yq -i '.kraken.port="8081"' CI/config/common_test_config.yaml
+          yq -i '.kraken.signal_address="0.0.0.0"' CI/config/common_test_config.yaml
+          yq -i '.kraken.performance_monitoring="localhost:9090"' CI/config/common_test_config.yaml
+          yq -i '.telemetry.username="${{secrets.TELEMETRY_USERNAME}}"' CI/config/common_test_config.yaml
+          yq -i '.telemetry.password="${{secrets.TELEMETRY_PASSWORD}}"' CI/config/common_test_config.yaml
+          echo "test_telemetry" > ./CI/tests/functional_tests
+
+      # Final common steps
+      - name: Run Functional tests
+        env:
+          AWS_BUCKET: ${{ secrets.AWS_BUCKET }}
+        run: |
+          ./CI/run.sh
+          cat ./CI/results.markdown >> $GITHUB_STEP_SUMMARY
+          echo >> $GITHUB_STEP_SUMMARY
+      - name: Upload CI logs
+        uses: actions/upload-artifact@v3
+        with:
+          name: ci-logs
+          path: CI/out
+          if-no-files-found: error
+      - name: Collect coverage report
+        run: |
+          python -m coverage html
+      - name: Publish coverage report to job summary
+        run: |
+          pip install html2text
+          html2text --ignore-images --ignore-links -b 0 htmlcov/index.html >> $GITHUB_STEP_SUMMARY
+      - name: Upload coverage data
+        uses: actions/upload-artifact@v3
+        with:
+          name: coverage
+          path: htmlcov
+          if-no-files-found: error
+      - name: Check CI results
+        run: grep Fail CI/results.markdown && false || true
+      

.gitignore

@@ -16,6 +16,7 @@ __pycache__/*
 *.out
 kube-burner*
 kube_burner*
+recommender_*.json
 
 # Project files
 .ropeproject
@@ -61,7 +62,7 @@ inspect.local.*
 !CI/config/common_test_config.yaml
 CI/out/*
 CI/ci_results
-CI/scenarios/*node.yaml
+CI/legacy/*node.yaml
 CI/results.markdown
 
 #env

.gitleaks.toml

@@ -0,0 +1,6 @@
+[allowlist]
+  description = "Global Allowlist"
+
+  paths = [
+        '''kraken/arcaflow_plugin/fixtures/*'''
+  ]

CI/README.md

@@ -1,7 +1,7 @@
 ## CI Tests
 
 ### First steps
-Edit [my_tests](tests/my_tests) with tests you want to run
+Edit [functional_tests](tests/functional_tests) with tests you want to run
 
 ### How to run
 ```./CI/run.sh```
@@ -11,7 +11,7 @@ This will run kraken using python, make sure python3 is set up and configured pr
 
 ### Adding a test case
 
-1. Add in simple scenario yaml file to execute under [../CI/scenarios/](scenarios)
+1. Add in simple scenario yaml file to execute under [../CI/scenarios/](legacy)
 
 2. Copy [test_application_outages.sh](tests/test_app_outages.sh) for example on how to get started
 
@@ -27,7 +27,7 @@ This will run kraken using python, make sure python3 is set up and configured pr
 
     e. 15: Make sure name of config in line 14 matches what you pass on this line
 
-4. Add test name to [my_tests](../CI/tests/my_tests) file
+4. Add test name to [functional_tests](../CI/tests/functional_tests) file
 
     a. This will be the name of the file without ".sh"
 

CI/config/common_test_config.yaml

@@ -1,5 +1,5 @@
 kraken:
-    distribution: openshift                                # Distribution can be kubernetes or openshift.
+    distribution: kubernetes                                # Distribution can be kubernetes or openshift.
     kubeconfig_path: ~/.kube/config                        # Path to kubeconfig.
     exit_on_failure: False                                 # Exit when a post action scenario fails.
     litmus_version: v1.13.6                                # Litmus version to install.
@@ -15,17 +15,38 @@ cerberus:
 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"
-    kube_burner_binary_url: "https://github.com/cloud-bulldozer/kube-burner/releases/download/v0.9.1/kube-burner-0.9.1-Linux-x86_64.tar.gz"
     capture_metrics: False
-    config_path: config/kube_burner.yaml                   # Define the Elasticsearch url and index name in this config.
     metrics_profile_path: config/metrics-aggregated.yaml
     prometheus_url:                                        # The prometheus url/route is automatically obtained in case of OpenShift, please set it when the distribution is Kubernetes.
     prometheus_bearer_token:                               # The bearer token is automatically obtained in case of OpenShift, please set it when the distribution is Kubernetes. This is needed to authenticate with prometheus.
     uuid:                                                  # uuid for the run is generated by default if not set.
     enable_alerts: False                                   # Runs the queries specified in the alert profile and displays the info or exits 1 when severity=error.
-    alert_profile: config/alerts                           # Path to alert profile with the prometheus queries.
+    alert_profile: config/alerts.yaml                           # Path to alert profile with the prometheus queries.
 
 tunings:
     wait_duration: 6                                       # 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
+    api_url: https://yvnn4rfoi7.execute-api.us-west-2.amazonaws.com/test #telemetry service endpoint
+    username: $TELEMETRY_USERNAME                                      # telemetry service username
+    password: $TELEMETRY_PASSWORD                                      # telemetry service password
+    prometheus_namespace: 'prometheus-k8s'                                # prometheus namespace
+    prometheus_pod_name: 'prometheus-kind-prometheus-kube-prome-prometheus-0'                                 # prometheus pod_name
+    prometheus_container_name: 'prometheus'
+    prometheus_backup: True                                 # enables/disables prometheus data collection
+    full_prometheus_backup: False                           # if is set to False only the /prometheus/wal folder will be downloaded.
+    backup_threads: 5                                       # number of telemetry download/upload threads
+    archive_path: /tmp                                      # local path where the archive files will be temporarly stored
+    max_retries: 0                                          # maximum number of upload retries (if 0 will retry forever)
+    run_tag: ''                                             # if set, this will be appended to the run folder in the bucket (useful to group the runs)
+    archive_size: 10000                                     # the size of the prometheus data archive size in KB. The lower the size of archive is
+    logs_backup: True
+    logs_filter_patterns:
+        - "(\\w{3}\\s\\d{1,2}\\s\\d{2}:\\d{2}:\\d{2}\\.\\d+).+"         # Sep 9 11:20:36.123425532
+        - "kinit (\\d+/\\d+/\\d+\\s\\d{2}:\\d{2}:\\d{2})\\s+"          # kinit 2023/09/15 11:20:36 log
+        - "(\\d{4}-\\d{2}-\\d{2}T\\d{2}:\\d{2}:\\d{2}\\.\\d+Z).+"      # 2023-09-15T11:20:36.123425532Z log
+    oc_cli_path: /usr/bin/oc                                # optional, if not specified will be search in $PATH
+    events_backup: True                                     # enables/disables cluster events collection
+    telemetry_group: "funtests"

CI/legacy/scenarios/volume_scenario.yaml

@@ -1,7 +1,20 @@
 apiVersion: v1
+kind: Namespace
+metadata:
+  labels:
+    kubernetes.io/metadata.name: kraken
+    pod-security.kubernetes.io/audit: privileged
+    pod-security.kubernetes.io/enforce: privileged
+    pod-security.kubernetes.io/enforce-version: v1.24
+    pod-security.kubernetes.io/warn: privileged
+    security.openshift.io/scc.podSecurityLabelSync: "false"
+  name: kraken
+---
+apiVersion: v1
 kind: PersistentVolume
 metadata:
   name: kraken-test-pv
+  namespace: kraken
   labels:
     type: local
 spec:
@@ -17,6 +30,7 @@ apiVersion: v1
 kind: PersistentVolumeClaim
 metadata:
   name: kraken-test-pvc
+  namespace: kraken
 spec:
   storageClassName: manual
   accessModes:
@@ -29,6 +43,7 @@ apiVersion: v1
 kind: Pod
 metadata:
   name: kraken-test-pod
+  namespace: kraken
 spec:
   volumes:
     - name: kraken-test-pv
@@ -36,7 +51,7 @@ spec:
         claimName: kraken-test-pvc
   containers:
     - name: kraken-test-container
-      image: 'image-registry.openshift-image-registry.svc:5000/openshift/httpd:latest'
+      image: 'quay.io/centos7/httpd-24-centos7:latest'
       volumeMounts:
         - mountPath: "/home/krake-dir/"
           name: kraken-test-pv

CI/run.sh

@@ -1,9 +1,25 @@
 #!/bin/bash
-set -x
+MAX_RETRIES=60
 
-ci_tests_loc="CI/tests/my_tests"
+KUBECTL=`which kubectl 2>/dev/null`
+[[ $? != 0 ]] && echo "[ERROR]: kubectl missing, please install it and try again" && exit 1
 
-echo "running test suit consisting of ${ci_tests}"
+wait_cluster_become_ready() {
+  COUNT=1
+  until `$KUBECTL get namespace > /dev/null 2>&1`
+  do
+    echo "[INF] waiting Kubernetes to become ready, after $COUNT check"
+    sleep 3
+    [[ $COUNT == $MAX_RETRIES ]] && echo "[ERR] max retries exceeded, failing" && exit 1
+    ((COUNT++))
+  done 
+}
+
+
+
+ci_tests_loc="CI/tests/functional_tests"
+
+echo -e "********* Running Functional Tests Suite *********\n\n"
 
 rm -rf CI/out
 
@@ -20,7 +36,32 @@ echo 'Test                   | Result | Duration' >> $results
 echo '-----------------------|--------|---------' >> $results
 
 # Run each test
-for test_name in `cat CI/tests/my_tests`
+failed_tests=()
+for test_name in `cat CI/tests/functional_tests`
 do
-  ./CI/run_test.sh $test_name $results
+  #wait_cluster_become_ready
+  return_value=`./CI/run_test.sh $test_name $results`
+  if [[ $return_value == 1 ]]
+  then
+    echo "Failed"
+    failed_tests+=("$test_name")
+  fi
+  wait_cluster_become_ready
 done
+
+
+if (( ${#failed_tests[@]}>0 ))
+then
+  echo -e "\n\n======================================================================"
+  echo -e "\n     FUNCTIONAL TESTS FAILED  ${failed_tests[*]} ABORTING"
+  echo -e "\n======================================================================\n\n"
+
+  for test in "${failed_tests[@]}"
+  do
+    echo -e "\n********** $test KRKN RUN OUTPUT **********\n"
+    cat "CI/out/$test.out"
+    echo -e "\n********************************************\n\n\n\n"
+  done
+
+  exit 1
+fi

CI/run_test.sh

@@ -1,5 +1,4 @@
 #!/bin/bash
-set -x
 readonly SECONDS_PER_HOUR=3600
 readonly SECONDS_PER_MINUTE=60
 function get_time_format() {
@@ -14,9 +13,7 @@ ci_test=`echo $1`
 
 results_file=$2
 
-echo -e "\n======================================================================"
-echo -e "     CI test for ${ci_test}                    "
-echo -e "======================================================================\n"
+echo -e "test: ${ci_test}" >&2
 
 ci_results="CI/out/$ci_test.out"
 # Test ci
@@ -28,13 +25,16 @@ then
   # if the test passes update the results and complete
   duration=$SECONDS
   duration=$(get_time_format $duration)
-  echo "$ci_test: Successful"
+  echo -e  "> $ci_test: Successful\n" >&2
   echo "$ci_test | Pass | $duration" >> $results_file
   count=$retries
+  # return value for run.sh
+  echo 0
 else
   duration=$SECONDS
   duration=$(get_time_format $duration)
-  echo "$ci_test: Failed"
+  echo -e "> $ci_test: Failed\n" >&2
   echo "$ci_test | Fail | $duration" >> $results_file
-  echo "Logs for "$ci_test
+  # return value for run.sh
+  echo 1
 fi

CI/scenarios/app_outage.yaml

@@ -1,5 +0,0 @@
-application_outage:                                  # Scenario to create an outage of an application by blocking traffic
-  duration: 10                                      # Duration in seconds after which the routes will be accessible
-  namespace: openshift-monitoring            # Namespace to target - all application routes will go inaccessible if pod selector is empty
-  pod_selector: {}                            # Pods to target
-  block: [Ingress, Egress]                           # It can be Ingress or Egress or Ingress, Egress

CI/scenarios/container_scenario.yml

@@ -1,8 +0,0 @@
-scenarios:
-- name: "kill machine config container"
-  namespace: "openshift-machine-config-operator"
-  label_selector: "k8s-app=machine-config-server"
-  container_name: "hello-openshift"
-  action: "kill 1"
-  count: 1
-  retry_wait: 60

CI/scenarios/hello_pod.yaml

@@ -1,31 +0,0 @@
----
-kind: Pod
-apiVersion: v1
-metadata:
-  name: hello-pod
-  creationTimestamp:
-  labels:
-    name: hello-openshift
-spec:
-  containers:
-  - name: hello-openshift
-    image: openshift/hello-openshift
-    ports:
-    - containerPort: 5050
-      protocol: TCP
-    resources: {}
-    volumeMounts:
-    - name: tmp
-      mountPath: "/tmp"
-    terminationMessagePath: "/dev/termination-log"
-    imagePullPolicy: IfNotPresent
-    securityContext:
-      capabilities: {}
-      privileged: false
-  volumes:
-  - name: tmp
-    emptyDir: {}
-  restartPolicy: Always
-  dnsPolicy: ClusterFirst
-  serviceAccount: ''
-status: {}

CI/scenarios/hello_pod_killing.yml

@@ -1,6 +0,0 @@
-# yaml-language-server: $schema=../../scenarios/plugin.schema.json
-- id: kill-pods
-  config:
-    label_selector: name=hello-openshift
-    namespace_pattern: ^default$
-    kill: 1

CI/scenarios/ingress_namespace.yaml

@@ -1,7 +0,0 @@
-scenarios:
-- action: delete
-  namespace: "^.*ingress.*$"
-  label_selector:
-  runs: 1
-  sleep: 15
-  wait_time: 30

CI/scenarios/network_chaos.yaml

@@ -1,6 +0,0 @@
-network_chaos:                   # Scenario to create an outage by simulating random variations in the network.
-  duration: 10                   # seconds
-  instance_count: 1
-  execution: serial
-  egress:
-    bandwidth: 100mbit

CI/scenarios/node_cpu_hog_engine.yaml

@@ -1,34 +0,0 @@
-apiVersion: litmuschaos.io/v1alpha1
-kind: ChaosEngine
-metadata:
-  name: nginx-chaos
-  namespace: litmus
-spec:
-  # It can be true/false
-  annotationCheck: 'false'
-  # It can be active/stop
-  engineState: 'active'
-  chaosServiceAccount: litmus-sa
-  monitoring: false
-  # It can be delete/retain
-  jobCleanUpPolicy: 'delete'
-  experiments:
-    - name: node-cpu-hog
-      spec:
-        components:
-          env:
-            # set chaos duration (in sec) as desired
-            - name: TOTAL_CHAOS_DURATION
-              value: '10'
-
-            # Number of cores of node CPU to be consumed
-            - name: NODE_CPU_CORE
-              value: '1'
-
-            # percentage of total nodes to target
-            - name: NODES_AFFECTED_PERC
-              value: '30'
-
-            # ENTER THE COMMA SEPARATED TARGET NODES NAME
-            - name: TARGET_NODES
-              value: $WORKER_NODE

CI/scenarios/node_cpu_hog_engine_node.yaml

@@ -1,34 +0,0 @@
-apiVersion: litmuschaos.io/v1alpha1
-kind: ChaosEngine
-metadata:
-  name: nginx-chaos
-  namespace: litmus
-spec:
-  # It can be true/false
-  annotationCheck: 'false'
-  # It can be active/stop
-  engineState: 'active'
-  chaosServiceAccount: litmus-sa
-  monitoring: false
-  # It can be delete/retain
-  jobCleanUpPolicy: 'delete'
-  experiments:
-    - name: node-cpu-hog
-      spec:
-        components:
-          env:
-            # set chaos duration (in sec) as desired
-            - name: TOTAL_CHAOS_DURATION
-              value: '10'
-
-            # Number of cores of node CPU to be consumed
-            - name: NODE_CPU_CORE
-              value: '1'
-
-            # percentage of total nodes to target
-            - name: NODES_AFFECTED_PERC
-              value: '30'
-
-            # ENTER THE COMMA SEPARATED TARGET NODES NAME
-            - name: TARGET_NODES
-              value:

CI/scenarios/node_io_engine.yaml

@@ -1,35 +0,0 @@
-apiVersion: litmuschaos.io/v1alpha1
-kind: ChaosEngine
-metadata:
-  name: nginx-chaos
-  namespace: litmus
-spec:
-  # It can be delete/retain
-  jobCleanUpPolicy: 'retain'
-  # It can be active/stop
-  engineState: 'active'
-  chaosServiceAccount: litmus-sa
-  experiments:
-    - name: node-io-stress
-      spec:
-        components:
-          env:
-            # set chaos duration (in sec) as desired
-            - name: TOTAL_CHAOS_DURATION
-              value: '10'
-
-            ## specify the size as percentage of free space on the file system
-            - name: FILESYSTEM_UTILIZATION_PERCENTAGE
-              value: '100'
-
-            ## Number of core of CPU
-            - name: CPU
-              value: '1'
-
-            ## Total number of workers default value is 4
-            - name: NUMBER_OF_WORKERS
-              value: '3'
-
-             ## enter the comma separated target nodes name
-            - name: TARGET_NODES
-              value: $WORKER_NODE

CI/scenarios/node_io_engine_node.yaml

@@ -1,35 +0,0 @@
-apiVersion: litmuschaos.io/v1alpha1
-kind: ChaosEngine
-metadata:
-  name: nginx-chaos
-  namespace: litmus
-spec:
-  # It can be delete/retain
-  jobCleanUpPolicy: 'retain'
-  # It can be active/stop
-  engineState: 'active'
-  chaosServiceAccount: litmus-sa
-  experiments:
-    - name: node-io-stress
-      spec:
-        components:
-          env:
-            # set chaos duration (in sec) as desired
-            - name: TOTAL_CHAOS_DURATION
-              value: '10'
-
-            ## specify the size as percentage of free space on the file system
-            - name: FILESYSTEM_UTILIZATION_PERCENTAGE
-              value: '100'
-
-            ## Number of core of CPU
-            - name: CPU
-              value: '1'
-
-            ## Total number of workers default value is 4
-            - name: NUMBER_OF_WORKERS
-              value: '3'
-
-             ## enter the comma separated target nodes name
-            - name: TARGET_NODES
-              value:

CI/scenarios/node_mem_engine.yaml

@@ -1,28 +0,0 @@
-apiVersion: litmuschaos.io/v1alpha1
-kind: ChaosEngine
-metadata:
-  name: nginx-chaos
-  namespace: litmus
-spec:
-  # It can be delete/retain
-  jobCleanUpPolicy: 'retain'
-  # It can be active/stop
-  engineState: 'active'
-  chaosServiceAccount: litmus-sa
-  experiments:
-    - name: node-memory-hog
-      spec:
-        components:
-          env:
-            # set chaos duration (in sec) as desired
-            - name: TOTAL_CHAOS_DURATION
-              value: '10'
-
-            ## Specify the size as percent of total node capacity Ex: '30'
-            ## Note: For consuming memory in mebibytes change the variable to MEMORY_CONSUMPTION_MEBIBYTES
-            - name: MEMORY_CONSUMPTION_PERCENTAGE
-              value: '30'
-
-            # ENTER THE COMMA SEPARATED TARGET NODES NAME
-            - name: TARGET_NODES
-              value: $WORKER_NODE

CI/scenarios/node_mem_engine_node.yaml

@@ -1,28 +0,0 @@
-apiVersion: litmuschaos.io/v1alpha1
-kind: ChaosEngine
-metadata:
-  name: nginx-chaos
-  namespace: litmus
-spec:
-  # It can be delete/retain
-  jobCleanUpPolicy: 'retain'
-  # It can be active/stop
-  engineState: 'active'
-  chaosServiceAccount: litmus-sa
-  experiments:
-    - name: node-memory-hog
-      spec:
-        components:
-          env:
-            # set chaos duration (in sec) as desired
-            - name: TOTAL_CHAOS_DURATION
-              value: '10'
-
-            ## Specify the size as percent of total node capacity Ex: '30'
-            ## Note: For consuming memory in mebibytes change the variable to MEMORY_CONSUMPTION_MEBIBYTES
-            - name: MEMORY_CONSUMPTION_PERCENTAGE
-              value: '30'
-
-            # ENTER THE COMMA SEPARATED TARGET NODES NAME
-            - name: TARGET_NODES
-              value:

CI/scenarios/time_scenarios.yml

@@ -1,5 +0,0 @@
-time_scenarios:
-- action: skew_time
-  object_type: pod
-  label_selector: k8s-app=etcd
-  container_name: ""

CI/templates/container_scenario_pod.yaml

@@ -0,0 +1,16 @@
+apiVersion: v1
+kind: Pod
+metadata:
+  name: container
+  labels:
+    scenario: container
+spec:
+  hostNetwork: true
+  containers:
+  - name: fedtools
+    image: docker.io/fedora/tools
+    command:
+    - /bin/sh
+    - -c
+    - |
+      sleep infinity

CI/templates/outage_pod.yaml

@@ -0,0 +1,16 @@
+apiVersion: v1
+kind: Pod
+metadata:
+  name: outage
+  labels:
+    scenario: outage
+spec:
+  hostNetwork: true
+  containers:
+  - name: fedtools
+    image: docker.io/fedora/tools
+    command:
+    - /bin/sh
+    - -c
+    - |
+      sleep infinity

CI/templates/time_pod.yaml

@@ -0,0 +1,16 @@
+apiVersion: v1
+kind: Pod
+metadata:
+  name: time-skew
+  labels:
+    scenario: time-skew
+spec:
+  hostNetwork: true
+  containers:
+  - name: fedtools
+    image: docker.io/fedora/tools
+    command:
+    - /bin/sh
+    - -c
+    - |
+      sleep infinity

CI/tests/common.sh

@@ -13,6 +13,6 @@ function error {
 }
 
 function get_node {
-  worker_node=$(oc get nodes --no-headers | grep worker | head -n 1)
+  worker_node=$(kubectl get nodes --no-headers | grep worker | head -n 1)
   export WORKER_NODE=$worker_node
 }

CI/tests/functional_tests

@@ -0,0 +1 @@
+

CI/tests/my_tests

@@ -1 +0,0 @@
-test_net_chaos

CI/tests/test_app_outages.sh

@@ -7,9 +7,11 @@ trap finish EXIT
 
 
 function functional_test_app_outage {
-
+  yq -i '.application_outage.duration=10' scenarios/openshift/app_outage.yaml
+  yq -i '.application_outage.pod_selector={"scenario":"outage"}' scenarios/openshift/app_outage.yaml
+  yq -i '.application_outage.namespace="default"' scenarios/openshift/app_outage.yaml
   export scenario_type="application_outages"
-  export scenario_file="CI/scenarios/app_outage.yaml"
+  export scenario_file="scenarios/openshift/app_outage.yaml"
   export post_config=""
   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

CI/tests/test_arca_cpu_hog.sh

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

CI/tests/test_arca_io_hog.sh

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

CI/tests/test_arca_memory_hog.sh

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

CI/tests/test_container.sh

@@ -8,9 +8,11 @@ trap finish EXIT
 pod_file="CI/scenarios/hello_pod.yaml"
 
 function functional_test_container_crash {
-
+  yq -i '.scenarios[0].namespace="default"' scenarios/openshift/app_outage.yaml
+  yq -i '.scenarios[0].label_selector="scenario=container"' scenarios/openshift/app_outage.yaml
+  yq -i '.scenarios[0].container_name="fedtools"' scenarios/openshift/app_outage.yaml
   export scenario_type="container_scenarios"
-  export scenario_file="- CI/scenarios/container_scenario.yml"
+  export scenario_file="- scenarios/openshift/app_outage.yaml"
   export post_config=""
   envsubst < CI/config/common_test_config.yaml > CI/config/container_config.yaml
 

CI/tests/test_cpu_hog.sh

@@ -1,20 +0,0 @@
-set -xeEo pipefail
-
-source CI/tests/common.sh
-
-trap error ERR
-trap finish EXIT
-
-
-function functional_test_litmus_cpu {
-
-  export scenario_type="litmus_scenarios"
-  export scenario_file="- scenarios/templates/litmus-rbac.yaml"
-  export post_config="- CI/scenarios/node_cpu_hog_engine_node.yaml"
-  envsubst < CI/config/common_test_config.yaml > CI/config/litmus_config.yaml
-  envsubst < CI/scenarios/node_cpu_hog_engine.yaml > CI/scenarios/node_cpu_hog_engine_node.yaml
-  python3 -m coverage run -a run_kraken.py -c CI/config/litmus_config.yaml
-  echo "Litmus scenario test: Success"
-}
-
-functional_test_litmus_cpu

CI/tests/test_io_hog.sh

@@ -1,20 +0,0 @@
-set -xeEo pipefail
-
-source CI/tests/common.sh
-
-trap error ERR
-trap finish EXIT
-
-
-function functional_test_litmus_io {
-
-  export scenario_type="litmus_scenarios"
-  export scenario_file="- scenarios/templates/litmus-rbac.yaml"
-  export post_config="- CI/scenarios/node_io_engine_node.yaml"
-  envsubst < CI/config/common_test_config.yaml > CI/config/litmus_config.yaml
-  envsubst < CI/scenarios/node_io_engine.yaml > CI/scenarios/node_io_engine_node.yaml
-  python3 -m coverage run -a run_kraken.py -c CI/config/litmus_config.yaml
-  echo "Litmus scenario test: Success"
-}
-
-functional_test_litmus_io

CI/tests/test_mem_hog.sh

@@ -1,20 +0,0 @@
-set -xeEo pipefail
-
-source CI/tests/common.sh
-
-trap error ERR
-trap finish EXIT
-
-
-function functional_test_litmus_mem {
-
-  export scenario_type="litmus_scenarios"
-  export scenario_file="- scenarios/templates/litmus-rbac.yaml"
-  export post_config="- CI/scenarios/node_mem_engine_node.yaml"
-  envsubst < CI/config/common_test_config.yaml > CI/config/litmus_config.yaml
-  envsubst < CI/scenarios/node_mem_engine.yaml > CI/scenarios/node_mem_engine_node.yaml
-  python3 -m coverage run -a run_kraken.py -c CI/config/litmus_config.yaml
-  echo "Litmus scenario $1 test: Success"
-}
-
-functional_test_litmus_mem "- CI/scenarios/node_mem_engine.yaml"

CI/tests/test_namespace.sh

@@ -7,12 +7,13 @@ trap finish EXIT
 
 function funtional_test_namespace_deletion {
   export scenario_type="namespace_scenarios"
-  export scenario_file="-  CI/scenarios/ingress_namespace.yaml"
+  export scenario_file="-  scenarios/openshift/ingress_namespace.yaml"
   export post_config=""
+  yq '.scenarios[0].namespace="^namespace-scenario$"' -i scenarios/openshift/ingress_namespace.yaml
+  yq '.scenarios[0].wait_time=30' -i scenarios/openshift/ingress_namespace.yaml
+  yq '.scenarios[0].action="delete"' -i scenarios/openshift/ingress_namespace.yaml
   envsubst < CI/config/common_test_config.yaml > CI/config/namespace_config.yaml
-
   python3 -m coverage run -a run_kraken.py -c CI/config/namespace_config.yaml
-  echo $?
   echo "Namespace scenario test: Success"
 }
 

CI/tests/test_net_chaos.sh

@@ -7,9 +7,16 @@ trap finish EXIT
 
 
 function functional_test_network_chaos {
+  yq -i '.network_chaos.duration=10' scenarios/openshift/network_chaos.yaml
+  yq -i '.network_chaos.node_name="kind-worker2"' scenarios/openshift/network_chaos.yaml
+  yq -i '.network_chaos.egress.bandwidth="100mbit"' scenarios/openshift/network_chaos.yaml
+  yq -i 'del(.network_chaos.interfaces)' scenarios/openshift/network_chaos.yaml
+  yq -i 'del(.network_chaos.label_selector)' scenarios/openshift/network_chaos.yaml
+  yq -i 'del(.network_chaos.egress.latency)' scenarios/openshift/network_chaos.yaml
+  yq -i 'del(.network_chaos.egress.loss)' scenarios/openshift/network_chaos.yaml
 
   export scenario_type="network_chaos"
-  export scenario_file="CI/scenarios/network_chaos.yaml"
+  export scenario_file="scenarios/openshift/network_chaos.yaml"
   export post_config=""
   envsubst < CI/config/common_test_config.yaml > CI/config/network_chaos.yaml
   python3 -m coverage run -a run_kraken.py -c CI/config/network_chaos.yaml

CI/tests/test_pods.sh

@@ -1,19 +0,0 @@
-set -xeEo pipefail
-
-source CI/tests/common.sh
-
-trap error ERR
-trap finish EXIT
-
-function funtional_test_pod_deletion {
-  export scenario_type="pod_scenarios"
-  export scenario_file="-  CI/scenarios/hello_pod_killing.yml"
-  export post_config=""
-  envsubst < CI/config/common_test_config.yaml > CI/config/pod_config.yaml
-
-  python3 -m coverage run -a run_kraken.py -c CI/config/pod_config.yaml
-  echo $?
-  echo "Pod scenario test: Success"
-}
-
-funtional_test_pod_deletion

CI/tests/test_telemetry.sh

@@ -0,0 +1,37 @@
+set -xeEo pipefail
+
+source CI/tests/common.sh
+
+trap error ERR
+trap finish EXIT
+
+
+function functional_test_telemetry {
+  AWS_CLI=`which aws`
+  [ -z "$AWS_CLI" ]&& echo "AWS cli not found in path" && exit 1
+  [ -z "$AWS_BUCKET" ] && echo "AWS bucket not set in environment" && exit 1
+
+  export RUN_TAG="funtest-telemetry"
+  yq -i '.telemetry.enabled=True' CI/config/common_test_config.yaml
+  yq -i '.telemetry.full_prometheus_backup=True' CI/config/common_test_config.yaml
+  yq -i '.performance_monitoring.check_critical_alerts=True' CI/config/common_test_config.yaml
+  yq -i '.performance_monitoring.prometheus_url="http://localhost:9090"' CI/config/common_test_config.yaml
+  yq -i '.telemetry.run_tag=env(RUN_TAG)' CI/config/common_test_config.yaml
+
+  export scenario_type="arcaflow_scenarios"
+  export scenario_file="scenarios/arcaflow/cpu-hog/input.yaml"
+  export post_config=""
+  envsubst < CI/config/common_test_config.yaml > CI/config/telemetry.yaml
+  python3 -m coverage run -a run_kraken.py -c CI/config/telemetry.yaml
+  RUN_FOLDER=`cat CI/out/test_telemetry.out | grep amazonaws.com | sed -rn "s#.*https:\/\/.*\/files/(.*)#\1#p"`
+  $AWS_CLI s3 ls "s3://$AWS_BUCKET/$RUN_FOLDER/" | awk '{ print $4 }' > s3_remote_files
+  echo "checking if telemetry files are uploaded on s3"
+  cat s3_remote_files | grep events-00.json || ( echo "FAILED: events-00.json not uploaded" && exit 1 )
+  cat s3_remote_files | grep critical-alerts-00.json || ( echo "FAILED: critical-alerts-00.json not uploaded" && exit 1 )
+  cat s3_remote_files | grep prometheus-00.tar || ( echo "FAILED: prometheus backup not uploaded" && exit 1 )
+  cat s3_remote_files | grep telemetry.json || ( echo "FAILED: telemetry.json not uploaded" && exit 1 )
+  echo "all files uploaded!"
+  echo "Telemetry Collection: Success"
+}
+
+functional_test_telemetry

CI/tests/test_time.sh

@@ -7,8 +7,12 @@ trap finish EXIT
 
 
 function functional_test_time_scenario {
+  yq -i '.time_scenarios[0].label_selector="scenario=time-skew"' scenarios/openshift/time_scenarios_example.yml
+  yq -i '.time_scenarios[0].container_name=""' scenarios/openshift/time_scenarios_example.yml
+  yq -i '.time_scenarios[0].namespace="default"' scenarios/openshift/time_scenarios_example.yml
+  yq -i '.time_scenarios[1].label_selector="kubernetes.io/hostname=kind-worker2"' scenarios/openshift/time_scenarios_example.yml
   export scenario_type="time_scenarios"
-  export scenario_file="CI/scenarios/time_scenarios.yml"
+  export scenario_file="scenarios/openshift/time_scenarios_example.yml"
   export post_config=""
   envsubst < CI/config/common_test_config.yaml > CI/config/time_config.yaml
 

CODE_OF_CONDUCT.md

@@ -0,0 +1,104 @@
+## CNCF Community Code of Conduct v1.3
+
+Other languages available:
+- [Arabic/العربية](code-of-conduct-languages/ar.md)
+- [Bulgarian/Български](code-of-conduct-languages/bg.md)
+- [Chinese/中文](code-of-conduct-languages/zh.md)
+- [Czech/Česky](code-of-conduct-languages/cs.md)
+- [Farsi/فارسی](code-of-conduct-languages/fa.md)
+- [French/Français](code-of-conduct-languages/fr.md)
+- [German/Deutsch](code-of-conduct-languages/de.md)
+- [Hindi/हिन्दी](code-of-conduct-languages/hi.md)
+- [Indonesian/Bahasa Indonesia](code-of-conduct-languages/id.md)
+- [Italian/Italiano](code-of-conduct-languages/it.md)
+- [Japanese/日本語](code-of-conduct-languages/jp.md)
+- [Korean/한국어](code-of-conduct-languages/ko.md)
+- [Polish/Polski](code-of-conduct-languages/pl.md)
+- [Portuguese/Português](code-of-conduct-languages/pt.md)
+- [Russian/Русский](code-of-conduct-languages/ru.md)
+- [Spanish/Español](code-of-conduct-languages/es.md)
+- [Turkish/Türkçe](code-of-conduct-languages/tr.md)
+- [Ukrainian/Українська](code-of-conduct-languages/uk.md)
+- [Vietnamese/Tiếng Việt](code-of-conduct-languages/vi.md)
+
+### Community Code of Conduct
+
+As contributors, maintainers, and participants in the CNCF community, and in the interest of fostering
+an open and welcoming community, we pledge to respect all people who participate or contribute
+through reporting issues, posting feature requests, updating documentation,
+submitting pull requests or patches, attending conferences or events, or engaging in other community or project activities.
+
+We are committed to making participation in the CNCF community a harassment-free experience for everyone, regardless of age, body size, caste, disability, ethnicity, level of experience, family status, gender, gender identity and expression, marital status, military or veteran status, nationality, personal appearance, race, religion, sexual orientation, socioeconomic status, tribe, or any other dimension of diversity.
+
+## Scope
+
+This code of conduct applies:
+* within project and community spaces,
+* in other spaces when an individual CNCF community participant's words or actions are directed at or are about a CNCF project, the CNCF community, or another CNCF community participant.
+
+### CNCF Events
+
+CNCF events that are produced by the Linux Foundation with professional events staff are governed by the Linux Foundation [Events Code of Conduct](https://events.linuxfoundation.org/code-of-conduct/) available on the event page. This is designed to be used in conjunction with the CNCF Code of Conduct.
+
+## Our Standards
+
+The CNCF Community is open, inclusive and respectful. Every member of our community has the right to have their identity respected.
+
+Examples of behavior that contributes to a positive environment include but are not limited to:
+
+* Demonstrating empathy and kindness toward other people
+* Being respectful of differing opinions, viewpoints, and experiences
+* Giving and gracefully accepting constructive feedback
+* Accepting responsibility and apologizing to those affected by our mistakes,
+  and learning from the experience
+* Focusing on what is best not just for us as individuals, but for the
+  overall community
+* Using welcoming and inclusive language
+
+
+Examples of unacceptable behavior include but are not limited to:
+
+* The use of sexualized language or imagery
+* Trolling, insulting or derogatory comments, and personal or political attacks
+* Public or private harassment in any form
+* Publishing others' private information, such as a physical or email
+  address, without their explicit permission
+* Violence, threatening violence, or encouraging others to engage in violent behavior
+* Stalking or following someone without their consent
+* Unwelcome physical contact
+* Unwelcome sexual or romantic attention or advances
+* Other conduct which could reasonably be considered inappropriate in a
+  professional setting
+
+The following behaviors are also prohibited:
+* Providing knowingly false or misleading information in connection with a Code of Conduct investigation or otherwise intentionally tampering with an investigation.
+* Retaliating against a person because they reported an incident or provided information about an incident as a witness.
+
+Project maintainers have the right and responsibility to remove, edit, or reject comments, commits, code, wiki edits, issues, and other contributions that are not aligned to this Code of Conduct.
+By adopting this Code of Conduct, project maintainers commit themselves to fairly and consistently applying these principles to every aspect
+of managing a CNCF project.
+Project maintainers who do not follow or enforce the Code of Conduct may be temporarily or permanently removed from the project team.
+
+## Reporting
+
+For incidents occurring in the Kubernetes community, contact the [Kubernetes Code of Conduct Committee](https://git.k8s.io/community/committee-code-of-conduct) via <conduct@kubernetes.io>. You can expect a response within three business days.
+
+For other projects, or for incidents that are project-agnostic or impact multiple CNCF projects, please contact the [CNCF Code of Conduct Committee](https://www.cncf.io/conduct/committee/) via <conduct@cncf.io>.  Alternatively, you can contact any of the individual members of the [CNCF Code of Conduct Committee](https://www.cncf.io/conduct/committee/) to submit your report. For more detailed instructions on how to submit a report, including how to submit a report anonymously, please see our [Incident Resolution Procedures](https://github.com/cncf/foundation/blob/main/code-of-conduct/coc-incident-resolution-procedures.md). You can expect a response within three business days.
+
+For incidents occurring at CNCF event that is produced by the Linux Foundation, please contact <eventconduct@cncf.io>.
+
+## Enforcement
+
+Upon review and investigation of a reported incident, the CoC response team that has jurisdiction will determine what action is appropriate based on this Code of Conduct and its related documentation.
+
+For information about which Code of Conduct incidents are handled by project leadership, which incidents are handled by the CNCF Code of Conduct Committee, and which incidents are handled by the Linux Foundation (including its events team), see our [Jurisdiction Policy](https://github.com/cncf/foundation/blob/main/code-of-conduct/coc-committee-jurisdiction-policy.md).
+
+## Amendments
+
+Consistent with the CNCF Charter, any substantive changes to this Code of Conduct must be approved by the Technical Oversight Committee.
+
+## Acknowledgements
+
+This Code of Conduct is adapted from the Contributor Covenant
+(http://contributor-covenant.org), version 2.0 available at
+http://contributor-covenant.org/version/2/0/code_of_conduct/

MAINTAINERS.md

@@ -0,0 +1,12 @@
+## Overview
+
+This document contains a list of maintainers in this repo.
+
+## Current Maintainers
+
+| Maintainer          | GitHub ID                                                 | Email                   |
+|---------------------| --------------------------------------------------------- | ----------------------- |
+| Ravi Elluri         | [chaitanyaenr](https://github.com/chaitanyaenr)           | nelluri@redhat.com      |
+| Pradeep Surisetty   | [psuriset](https://github.com/psuriset)                   | psuriset@redhat.com     |
+| Paige Rubendall     | [paigerube14](https://github.com/paigerube14)             | prubenda@redhat.com     |
+| Tullio Sebastiani   | [tsebastiani](https://github.com/tsebastiani)             | tsebasti@redhat.com     |

README.md

@@ -1,10 +1,11 @@
 # Krkn aka Kraken
-[![Docker Repository on Quay](https://quay.io/repository/chaos-kubox/krkn/status "Docker Repository on Quay")](https://quay.io/repository/chaos-kubox/krkn?tab=tags&tag=latest)
+[![Docker Repository on Quay](https://quay.io/repository/krkn-chaos/krkn/status "Docker Repository on Quay")](https://quay.io/repository/krkn-chaos/krkn?tab=tags&tag=latest)
+![Workflow-Status](https://github.com/krkn-chaos/krkn/actions/workflows/docker-image.yml/badge.svg)
 
 ![Krkn logo](media/logo.png)
 
-Chaos and resiliency testing tool for Kubernetes and OpenShift.
-Kraken injects deliberate failures into Kubernetes/OpenShift clusters to check if it is resilient to turbulent conditions.
+Chaos and resiliency testing tool for Kubernetes.
+Kraken injects deliberate failures into Kubernetes clusters to check if it is resilient to turbulent conditions.
 
 
 ### Workflow
@@ -17,28 +18,30 @@ Kraken injects deliberate failures into Kubernetes/OpenShift clusters to check i
 ### Chaos Testing Guide
 [Guide](docs/index.md) encapsulates:
 - Test methodology that needs to be embraced.
-- Best practices that an OpenShift cluster, platform and applications running on top of it should take into account for best user experience, performance, resilience and reliability.
+- Best practices that an Kubernetes cluster, platform and applications running on top of it should take into account for best user experience, performance, resilience and reliability.
 - Tooling.
 - Scenarios supported.
 - Test environment recommendations as to how and where to run chaos tests.
 - Chaos testing in practice.
 
-The guide is hosted at https://redhat-chaos.github.io/krkn.
+The guide is hosted at https://krkn-chaos.github.io/krkn.
 
 
 ### How to Get Started
 Instructions on how to setup, configure and run Kraken can be found at [Installation](docs/installation.md).
 
+You may consider utilizing the chaos recommendation tool prior to initiating the chaos runs to profile the application service(s) under test. This tool discovers a list of Krkn scenarios with a high probability of causing failures or disruptions to your application service(s). The tool can be accessed at [Chaos-Recommender](utils/chaos_recommender/README.md).
+
 See the [getting started doc](docs/getting_started.md) on support on how to get started with your own custom scenario or editing current scenarios for your specific usage.
 
 After installation, refer back to the below sections for supported scenarios and how to tweak the kraken config to load them on your cluster.
 
 
 #### Running Kraken with minimal configuration tweaks
-For cases where you want to run Kraken with minimal configuration changes, refer to [Kraken-hub](https://github.com/redhat-chaos/krkn-hub). One use case is CI integration where you do not want to carry around different configuration files for the scenarios.
+For cases where you want to run Kraken with minimal configuration changes, refer to [krkn-hub](https://github.com/krkn-chaos/krkn-hub). One use case is CI integration where you do not want to carry around different configuration files for the scenarios.
 
 ### Setting up infrastructure dependencies
-Kraken indexes the metrics specified in the profile into Elasticsearch in addition to leveraging Cerberus for understanding the health of the Kubernetes/OpenShift cluster under test. More information on the features is documented below. The infrastructure pieces can be easily installed and uninstalled by running:
+Kraken indexes the metrics specified in the profile into Elasticsearch in addition to leveraging Cerberus for understanding the health of the Kubernetes cluster under test. More information on the features is documented below. The infrastructure pieces can be easily installed and uninstalled by running:
 
 ```
 $ cd kraken
@@ -54,29 +57,30 @@ This will manage the Cerberus and Elasticsearch containers on the host on which
 Instructions on how to setup the config and the options supported can be found at [Config](docs/config.md).
 
 
-### Kubernetes/OpenShift chaos scenarios supported
+### Kubernetes chaos scenarios supported
 
-Scenario type               | Kubernetes    | OpenShift
---------------------------- | ------------- | -------------------- |  
-[Pod Scenarios](docs/pod_scenarios.md) | :heavy_check_mark: | :heavy_check_mark: |
-[Container Scenarios](docs/container_scenarios.md) | :heavy_check_mark: | :heavy_check_mark: |
-[Node Scenarios](docs/node_scenarios.md) | :heavy_check_mark: | :heavy_check_mark: |
-[Time Scenarios](docs/time_scenarios.md) | :x: | :heavy_check_mark: |
-[Litmus Scenarios](docs/litmus_scenarios.md) | :x: | :heavy_check_mark: |
-[Cluster Shut Down Scenarios](docs/cluster_shut_down_scenarios.md) | :heavy_check_mark: | :heavy_check_mark: |
-[Namespace Scenarios](docs/namespace_scenarios.md) | :heavy_check_mark: | :heavy_check_mark: |
-[Zone Outage Scenarios](docs/zone_outage.md) | :heavy_check_mark: | :heavy_check_mark: |
-[Application_outages](docs/application_outages.md) | :heavy_check_mark: | :heavy_check_mark: |
-[PVC scenario](docs/pvc_scenario.md) | :heavy_check_mark: | :heavy_check_mark: |
-[Network_Chaos](docs/network_chaos.md) | :heavy_check_mark: | :heavy_check_mark: |
-[ManagedCluster Scenarios](docs/managedcluster_scenarios.md) | :heavy_check_mark: | :question: |
+Scenario type               | Kubernetes    
+--------------------------- | ------------- | 
+[Pod Scenarios](docs/pod_scenarios.md) | :heavy_check_mark: |
+[Pod Network Scenarios](docs/pod_network_scenarios.md) | :x: |
+[Container Scenarios](docs/container_scenarios.md) | :heavy_check_mark: |
+[Node Scenarios](docs/node_scenarios.md) | :heavy_check_mark: |
+[Time Scenarios](docs/time_scenarios.md) | :heavy_check_mark: |
+[Hog Scenarios: CPU, Memory](docs/arcaflow_scenarios.md) | :heavy_check_mark: |
+[Cluster Shut Down Scenarios](docs/cluster_shut_down_scenarios.md) | :heavy_check_mark: |
+[Service Disruption Scenarios](docs/service_disruption_scenarios.md.md) | :heavy_check_mark: |
+[Zone Outage Scenarios](docs/zone_outage.md) | :heavy_check_mark: |
+[Application_outages](docs/application_outages.md) | :heavy_check_mark: |
+[PVC scenario](docs/pvc_scenario.md) | :heavy_check_mark: |
+[Network_Chaos](docs/network_chaos.md) | :heavy_check_mark: |
+[ManagedCluster Scenarios](docs/managedcluster_scenarios.md) | :heavy_check_mark: |
 
 
 ### Kraken scenario pass/fail criteria and report
-It is important to make sure to check if the targeted component recovered from the chaos injection and also if the Kubernetes/OpenShift cluster is healthy as failures in one component can have an adverse impact on other components. Kraken does this by:
+It is important to make sure to check if the targeted component recovered from the chaos injection and also if the Kubernetes cluster is healthy as failures in one component can have an adverse impact on other components. Kraken does this by:
 - Having built in checks for pod and node based scenarios to ensure the expected number of replicas and nodes are up. It also supports running custom scripts with the checks.
-- Leveraging [Cerberus](https://github.com/openshift-scale/cerberus) to monitor the cluster under test and consuming the aggregated go/no-go signal to determine pass/fail post chaos. It is highly recommended to turn on the Cerberus health check feature available in Kraken. Instructions on installing and setting up Cerberus can be found [here](https://github.com/openshift-scale/cerberus#installation) or can be installed from Kraken using the [instructions](https://github.com/redhat-chaos/krkn#setting-up-infrastructure-dependencies). Once Cerberus is up and running, set cerberus_enabled to True and cerberus_url to the url where Cerberus publishes go/no-go signal in the Kraken config file. Cerberus can monitor [application routes](https://github.com/redhat-chaos/cerberus/blob/main/docs/config.md#watch-routes) during the chaos and fails the run if it encounters downtime as it is a potential downtime in a customers, or users environment as well. It is especially important during the control plane chaos scenarios including the API server, Etcd, Ingress etc. It can be enabled by setting `check_applicaton_routes: True` in the [Kraken config](https://github.com/redhat-chaos/krkn/blob/main/config/config.yaml) provided application routes are being monitored in the [cerberus config](https://github.com/redhat-chaos/krkn/blob/main/config/cerberus.yaml).
-- Leveraging [kube-burner](docs/alerts.md) alerting feature to fail the runs in case of critical alerts.
+- Leveraging [Cerberus](https://github.com/krkn-chaos/cerberus) to monitor the cluster under test and consuming the aggregated go/no-go signal to determine pass/fail post chaos. It is highly recommended to turn on the Cerberus health check feature available in Kraken. Instructions on installing and setting up Cerberus can be found [here](https://github.com/openshift-scale/cerberus#installation) or can be installed from Kraken using the [instructions](https://github.com/krkn-chaos/krkn#setting-up-infrastructure-dependencies). Once Cerberus is up and running, set cerberus_enabled to True and cerberus_url to the url where Cerberus publishes go/no-go signal in the Kraken config file. Cerberus can monitor [application routes](https://github.com/redhat-chaos/cerberus/blob/main/docs/config.md#watch-routes) during the chaos and fails the run if it encounters downtime as it is a potential downtime in a customers, or users environment as well. It is especially important during the control plane chaos scenarios including the API server, Etcd, Ingress etc. It can be enabled by setting `check_applicaton_routes: True` in the [Kraken config](https://github.com/redhat-chaos/krkn/blob/main/config/config.yaml) provided application routes are being monitored in the [cerberus config](https://github.com/redhat-chaos/krkn/blob/main/config/cerberus.yaml).
+- Leveraging built-in alert collection feature to fail the runs in case of critical alerts.
 
 ### Signaling
 In CI runs or any external job it is useful to stop Kraken once a certain test or state gets reached. We created a way to signal to kraken to pause the chaos or stop it completely using a signal posted to a port of your choice.
@@ -90,29 +94,29 @@ More detailed information on enabling and leveraging this feature can be found [
 Monitoring the Kubernetes/OpenShift cluster to observe the impact of Kraken chaos scenarios on various components is key to find out the bottlenecks as it is important to make sure the cluster is healthy in terms if both recovery as well as performance during/after the failure has been injected. Instructions on enabling it can be found [here](docs/performance_dashboards.md).
 
 
-### Scraping and storing metrics long term
-Kraken supports capturing metrics for the duration of the scenarios defined in the config and indexes then into Elasticsearch to be able to store and evaluate the state of the runs long term. The indexed metrics can be visualized with the help of Grafana. It uses [Kube-burner](https://github.com/cloud-bulldozer/kube-burner) under the hood. The metrics to capture need to be defined in a metrics profile which Kraken consumes to query prometheus ( installed by default in OpenShift ) with the start and end timestamp of the run. Information on enabling and leveraging this feature can be found [here](docs/metrics.md).
+### SLOs validation during and post chaos
+- In addition to checking the recovery and health of the cluster and components under test, Kraken takes in a profile with the Prometheus expressions to validate and alerts, exits with a non-zero return code depending on the severity set. This feature can be used to determine pass/fail or alert on abnormalities observed in the cluster based on the metrics. 
+- Kraken also provides ability to check if any critical alerts are firing in the cluster post chaos and pass/fail's. 
 
+Information on enabling and leveraging this feature can be found [here](docs/SLOs_validation.md)
 
-### Alerts
-In addition to checking the recovery and health of the cluster and components under test, Kraken takes in a profile with the Prometheus expressions to validate and alerts, exits with a non-zero return code depending on the severity set. This feature can be used to determine pass/fail or alert on abnormalities observed in the cluster based on the metrics. Information on enabling and leveraging this feature can be found [here](docs/alerts.md).
 
 ### OCM / ACM integration
 
-Kraken supports injecting faults into [Open Cluster Management (OCM)](https://open-cluster-management.io/) and [Red Hat Advanced Cluster Management for Kubernetes (ACM)](https://www.redhat.com/en/technologies/management/advanced-cluster-management) managed clusters through [ManagedCluster Scenarios](docs/managedcluster_scenarios.md).
+Kraken supports injecting faults into [Open Cluster Management (OCM)](https://open-cluster-management.io/) and [Red Hat Advanced Cluster Management for Kubernetes (ACM)](https://www.krkn.com/en/technologies/management/advanced-cluster-management) managed clusters through [ManagedCluster Scenarios](docs/managedcluster_scenarios.md).
+
 
 ### Blogs and other useful resources
 - Blog post on introduction to Kraken: https://www.openshift.com/blog/introduction-to-kraken-a-chaos-tool-for-openshift/kubernetes
 - Discussion and demo on how Kraken can be leveraged to ensure OpenShift is reliable, performant and scalable: https://www.youtube.com/watch?v=s1PvupI5sD0&ab_channel=OpenShift
 - Blog post emphasizing the importance of making Chaos part of Performance and Scale runs to mimic the production environments: https://www.openshift.com/blog/making-chaos-part-of-kubernetes/openshift-performance-and-scalability-tests
-
+- Blog post on findings from Chaos test runs: https://cloud.redhat.com/blog/openshift/kubernetes-chaos-stories
+- Discussion with CNCF TAG App Delivery on Krkn workflow, features and addition to CNCF sandbox: [Github](https://github.com/cncf/sandbox/issues/44), [Tracker](https://github.com/cncf/tag-app-delivery/issues/465), [recording](https://www.youtube.com/watch?v=nXQkBFK_MWc&t=722s)
+- Blog post on supercharging chaos testing using AI integration in Krkn: https://www.redhat.com/en/blog/supercharging-chaos-testing-using-ai
+- Blog post announcing Krkn joining CNCF Sandbox: https://www.redhat.com/en/blog/krknchaos-joining-cncf-sandbox
 
 ### Roadmap
-Following is a list of enhancements that we are planning to work on adding support in Kraken. Of course any help/contributions are greatly appreciated.
-- [Ability to visualize the metrics that are being captured by Kraken and stored in Elasticsearch](https://github.com/redhat-chaos/krkn/issues/124)
-- Continue to improve [Chaos Testing Guide](https://cloud-bulldozer.github.io/kraken/) in terms of adding best practices, test environment recommendations and scenarios to make sure the OpenShift platform, as well the applications running on top it, are resilient and performant under chaotic conditions.
-- Support for running Kraken on Kubernetes distribution - see https://github.com/redhat-chaos/krkn/issues/185, https://github.com/redhat-chaos/krkn/issues/186
-- Sweet logo for Kraken - see https://github.com/redhat-chaos/krkn/issues/195
+Enhancements being planned can be found in the [roadmap](ROADMAP.md).
 
 
 ### Contributions
@@ -125,6 +129,7 @@ Please read [this file]((CI/README.md#adding-a-test-case)) for more information
 
 
 ### Community
-Key Members(slack_usernames/full name): paigerube14/Paige Rubendall, mffiedler/Mike Fiedler, ravielluri/Naga Ravi Chaitanya Elluri.
-* [**#sig-scalability on Kubernetes Slack**](https://kubernetes.slack.com)
-* [**#forum-chaos on CoreOS Slack internal to Red Hat**](https://coreos.slack.com)
+Key Members(slack_usernames/full name): paigerube14/Paige Rubendall, mffiedler/Mike Fiedler, tsebasti/Tullio Sebastiani, yogi/Yogananth Subramanian, sahil/Sahil Shah, pradeep/Pradeep Surisetty and ravielluri/Naga Ravi Chaitanya Elluri.
+* [**#krkn on Kubernetes Slack**](https://kubernetes.slack.com/messages/C05SFMHRWK1)
+
+The Linux Foundation® (TLF) has registered trademarks and uses trademarks. For a list of TLF trademarks, see [Trademark Usage](https://www.linuxfoundation.org/legal/trademark-usage).

ROADMAP.md

@@ -0,0 +1,15 @@
+## Krkn Roadmap
+
+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] [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] [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 and automate test coverage
+- [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)
+- [ ] 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
+- [ ] Continue to improve [Chaos Testing Guide](https://krkn-chaos.github.io/krkn) in terms of adding best practices, test environment recommendations and scenarios to make sure the OpenShift platform, as well the applications running on top it, are resilient and performant under chaotic conditions.
+- [ ] [Switch documentation references to Kubernetes](https://github.com/krkn-chaos/krkn/issues/495)
+- [ ] [OCP and Kubernetes functionalities segregation](https://github.com/krkn-chaos/krkn/issues/497)

config/alerts

@@ -1,11 +0,0 @@
-- expr: avg_over_time(histogram_quantile(0.99, rate(etcd_disk_wal_fsync_duration_seconds_bucket[2m]))[5m:]) > 0.01
-  description: 5 minutes avg. etcd fsync latency on {{$labels.pod}} higher than 10ms {{$value}}
-  severity: error
-
-- expr: avg_over_time(histogram_quantile(0.99, rate(etcd_network_peer_round_trip_time_seconds_bucket[5m]))[5m:]) > 0.1
-  description: 5 minutes avg. etcd netowrk peer round trip on {{$labels.pod}} higher than 100ms {{$value}}
-  severity: info
-
-- expr: increase(etcd_server_leader_changes_seen_total[2m]) > 0
-  description: etcd leader changes observed
-  severity: critical

config/alerts.yaml

@@ -0,0 +1,90 @@
+# etcd
+
+- expr: avg_over_time(histogram_quantile(0.99, rate(etcd_disk_wal_fsync_duration_seconds_bucket[2m]))[10m:]) > 0.01
+  description: 10 minutes avg. 99th etcd fsync latency on {{$labels.pod}} higher than 10ms. {{$value}}s
+  severity: warning
+
+- expr: avg_over_time(histogram_quantile(0.99, rate(etcd_disk_wal_fsync_duration_seconds_bucket[2m]))[10m:]) > 1
+  description: 10 minutes avg. 99th etcd fsync latency on {{$labels.pod}} higher than 1s. {{$value}}s
+  severity: error
+
+- expr: avg_over_time(histogram_quantile(0.99, rate(etcd_disk_backend_commit_duration_seconds_bucket[2m]))[10m:]) > 0.03
+  description: 10 minutes avg. 99th etcd commit latency on {{$labels.pod}} higher than 30ms. {{$value}}s
+  severity: warning
+
+- expr: rate(etcd_server_leader_changes_seen_total[2m]) > 0
+  description: etcd leader changes observed
+  severity: warning
+
+- expr: (last_over_time(etcd_mvcc_db_total_size_in_bytes[5m]) / last_over_time(etcd_server_quota_backend_bytes[5m]))*100 > 95
+  description: etcd cluster database is running full. 
+  severity: critical
+  
+- expr: (last_over_time(etcd_mvcc_db_total_size_in_use_in_bytes[5m]) / last_over_time(etcd_mvcc_db_total_size_in_bytes[5m])) < 0.5
+  description: etcd database size in use is less than 50% of the actual allocated storage.
+  severity: warning  
+
+- expr: rate(etcd_server_proposals_failed_total{job=~".*etcd.*"}[15m]) > 5
+  description: etcd cluster has high number of proposal failures.
+  severity: warning 
+
+- expr: histogram_quantile(0.99, rate(etcd_network_peer_round_trip_time_seconds_bucket{job=~".*etcd.*"}[5m])) > 0.15
+  description: etcd cluster member communication is slow.
+  severity: warning 
+
+- expr: histogram_quantile(0.99, sum(rate(grpc_server_handling_seconds_bucket{job=~".*etcd.*", grpc_method!="Defragment", grpc_type="unary"}[5m])) without(grpc_type)) > 0.15
+  description: etcd grpc requests are slow.
+  severity: critical
+      
+- expr: 100 * sum(rate(grpc_server_handled_total{job=~".*etcd.*", grpc_code=~"Unknown|FailedPrecondition|ResourceExhausted|Internal|Unavailable|DataLoss|DeadlineExceeded"}[5m])) without (grpc_type, grpc_code) / sum(rate(grpc_server_handled_total{job=~".*etcd.*"}[5m])) without (grpc_type, grpc_code) > 5
+  description: etcd cluster has high number of failed grpc requests.
+  severity: critical      
+      
+- expr: etcd_server_has_leader{job=~".*etcd.*"} == 0
+  description: etcd cluster has no leader.
+  severity: warning    
+    
+- expr: sum(up{job=~".*etcd.*"} == bool 1) without (instance) < ((count(up{job=~".*etcd.*"}) without (instance) + 1) / 2)
+  description: etcd cluster has insufficient number of members.
+  severity: warning      
+
+- expr: max without (endpoint) ( sum without (instance) (up{job=~".*etcd.*"} == bool 0) or count without (To) ( sum without (instance) (rate(etcd_network_peer_sent_failures_total{job=~".*etcd.*"}[120s])) > 0.01 )) > 0
+  description: etcd cluster members are down.
+  severity: warning  
+
+# API server
+- expr: avg_over_time(histogram_quantile(0.99, sum(irate(apiserver_request_duration_seconds_bucket{apiserver="kube-apiserver", verb=~"POST|PUT|DELETE|PATCH", subresource!~"log|exec|portforward|attach|proxy"}[2m])) by (le, resource, verb))[10m:]) > 1
+  description: 10 minutes avg. 99th mutating API call latency for {{$labels.verb}}/{{$labels.resource}} higher than 1 second. {{$value}}s
+  severity: error
+
+- expr: avg_over_time(histogram_quantile(0.99, sum(irate(apiserver_request_duration_seconds_bucket{apiserver="kube-apiserver", verb=~"LIST|GET", subresource!~"log|exec|portforward|attach|proxy", scope="resource"}[2m])) by (le, resource, verb, scope))[5m:]) > 1
+  description: 5 minutes avg. 99th read-only API call latency for {{$labels.verb}}/{{$labels.resource}} in scope {{$labels.scope}} higher than 1 second. {{$value}}s
+  severity: error
+
+- expr: avg_over_time(histogram_quantile(0.99, sum(irate(apiserver_request_duration_seconds_bucket{apiserver="kube-apiserver", verb=~"LIST|GET", subresource!~"log|exec|portforward|attach|proxy", scope="namespace"}[2m])) by (le, resource, verb, scope))[5m:]) > 5
+  description: 5 minutes avg. 99th read-only API call latency for {{$labels.verb}}/{{$labels.resource}} in scope {{$labels.scope}} higher than 5 seconds. {{$value}}s
+  severity: error
+
+- expr: avg_over_time(histogram_quantile(0.99, sum(irate(apiserver_request_duration_seconds_bucket{apiserver="kube-apiserver", verb=~"LIST|GET", subresource!~"log|exec|portforward|attach|proxy", scope="cluster"}[2m])) by (le, resource, verb, scope))[5m:]) > 30
+  description: 5 minutes avg. 99th read-only API call latency for {{$labels.verb}}/{{$labels.resource}} in scope {{$labels.scope}} higher than 30 seconds. {{$value}}s
+  severity: error
+
+# Control plane pods
+
+- expr: up{job=~"crio|kubelet"} == 0
+  description: "{{$labels.node}}/{{$labels.job}} down"
+  severity: warning
+
+- expr: up{job="ovnkube-node"} == 0
+  description: "{{$labels.instance}}/{{$labels.pod}} {{$labels.job}} down"
+  severity: warning
+
+# Service sync latency
+- expr: histogram_quantile(0.99, sum(rate(kubeproxy_network_programming_duration_seconds_bucket[2m])) by (le)) > 10
+  description: 99th Kubeproxy network programming latency higher than 10 seconds. {{$value}}s 
+  severity: warning
+
+# Prometheus alerts
+- expr: ALERTS{severity="critical", alertstate="firing"} > 0
+  description: Critical prometheus alert. {{$labels.alertname}}
+  severity: warning

config/alerts_openshift.yaml

@@ -0,0 +1,101 @@
+# etcd
+
+- expr: avg_over_time(histogram_quantile(0.99, rate(etcd_disk_wal_fsync_duration_seconds_bucket[2m]))[10m:]) > 0.01
+  description: 10 minutes avg. 99th etcd fsync latency on {{$labels.pod}} higher than 10ms. {{$value}}s
+  severity: warning
+
+- expr: avg_over_time(histogram_quantile(0.99, rate(etcd_disk_wal_fsync_duration_seconds_bucket[2m]))[10m:]) > 1
+  description: 10 minutes avg. 99th etcd fsync latency on {{$labels.pod}} higher than 1s. {{$value}}s
+  severity: error
+
+- expr: avg_over_time(histogram_quantile(0.99, rate(etcd_disk_backend_commit_duration_seconds_bucket[2m]))[10m:]) > 0.03
+  description: 10 minutes avg. 99th etcd commit latency on {{$labels.pod}} higher than 30ms. {{$value}}s
+  severity: warning
+
+- expr: rate(etcd_server_leader_changes_seen_total[2m]) > 0
+  description: etcd leader changes observed
+  severity: warning
+
+- expr: (last_over_time(etcd_mvcc_db_total_size_in_bytes[5m]) / last_over_time(etcd_server_quota_backend_bytes[5m]))*100 > 95
+  description: etcd cluster database is running full. 
+  severity: critical
+  
+- expr: (last_over_time(etcd_mvcc_db_total_size_in_use_in_bytes[5m]) / last_over_time(etcd_mvcc_db_total_size_in_bytes[5m])) < 0.5
+  description: etcd database size in use is less than 50% of the actual allocated storage.
+  severity: warning  
+
+- expr: rate(etcd_server_proposals_failed_total{job=~".*etcd.*"}[15m]) > 5
+  description: etcd cluster has high number of proposal failures.
+  severity: warning 
+
+- expr: histogram_quantile(0.99, rate(etcd_network_peer_round_trip_time_seconds_bucket{job=~".*etcd.*"}[5m])) > 0.15
+  description: etcd cluster member communication is slow.
+  severity: warning 
+
+- expr: histogram_quantile(0.99, sum(rate(grpc_server_handling_seconds_bucket{job=~".*etcd.*", grpc_method!="Defragment", grpc_type="unary"}[5m])) without(grpc_type)) > 0.15
+  description: etcd grpc requests are slow.
+  severity: critical
+      
+- expr: 100 * sum(rate(grpc_server_handled_total{job=~".*etcd.*", grpc_code=~"Unknown|FailedPrecondition|ResourceExhausted|Internal|Unavailable|DataLoss|DeadlineExceeded"}[5m])) without (grpc_type, grpc_code) / sum(rate(grpc_server_handled_total{job=~".*etcd.*"}[5m])) without (grpc_type, grpc_code) > 5
+  description: etcd cluster has high number of failed grpc requests.
+  severity: critical      
+      
+- expr: etcd_server_has_leader{job=~".*etcd.*"} == 0
+  description: etcd cluster has no leader.
+  severity: warning    
+    
+- expr: sum(up{job=~".*etcd.*"} == bool 1) without (instance) < ((count(up{job=~".*etcd.*"}) without (instance) + 1) / 2)
+  description: etcd cluster has insufficient number of members.
+  severity: warning      
+
+- expr: max without (endpoint) ( sum without (instance) (up{job=~".*etcd.*"} == bool 0) or count without (To) ( sum without (instance) (rate(etcd_network_peer_sent_failures_total{job=~".*etcd.*"}[120s])) > 0.01 )) > 0
+  description: etcd cluster members are down.
+  severity: warning  
+
+# API server
+- expr: avg_over_time(histogram_quantile(0.99, sum(irate(apiserver_request_duration_seconds_bucket{apiserver="kube-apiserver", verb=~"POST|PUT|DELETE|PATCH", subresource!~"log|exec|portforward|attach|proxy"}[2m])) by (le, resource, verb))[10m:]) > 1
+  description: 10 minutes avg. 99th mutating API call latency for {{$labels.verb}}/{{$labels.resource}} higher than 1 second. {{$value}}s
+  severity: error
+
+- expr: avg_over_time(histogram_quantile(0.99, sum(irate(apiserver_request_duration_seconds_bucket{apiserver="kube-apiserver", verb=~"LIST|GET", subresource!~"log|exec|portforward|attach|proxy", scope="resource"}[2m])) by (le, resource, verb, scope))[5m:]) > 1
+  description: 5 minutes avg. 99th read-only API call latency for {{$labels.verb}}/{{$labels.resource}} in scope {{$labels.scope}} higher than 1 second. {{$value}}s
+  severity: error
+
+- expr: avg_over_time(histogram_quantile(0.99, sum(irate(apiserver_request_duration_seconds_bucket{apiserver="kube-apiserver", verb=~"LIST|GET", subresource!~"log|exec|portforward|attach|proxy", scope="namespace"}[2m])) by (le, resource, verb, scope))[5m:]) > 5
+  description: 5 minutes avg. 99th read-only API call latency for {{$labels.verb}}/{{$labels.resource}} in scope {{$labels.scope}} higher than 5 seconds. {{$value}}s
+  severity: error
+
+- expr: avg_over_time(histogram_quantile(0.99, sum(irate(apiserver_request_duration_seconds_bucket{apiserver="kube-apiserver", verb=~"LIST|GET", subresource!~"log|exec|portforward|attach|proxy", scope="cluster"}[2m])) by (le, resource, verb, scope))[5m:]) > 30
+  description: 5 minutes avg. 99th read-only API call latency for {{$labels.verb}}/{{$labels.resource}} in scope {{$labels.scope}} higher than 30 seconds. {{$value}}s
+  severity: error
+
+# Control plane pods
+- expr: up{apiserver=~"kube-apiserver|openshift-apiserver"} == 0
+  description: "{{$labels.apiserver}} {{$labels.instance}} down"
+  severity: warning
+
+- expr: up{namespace=~"openshift-etcd"} == 0
+  description: "{{$labels.namespace}}/{{$labels.pod}} down"
+  severity: warning
+
+- expr: up{namespace=~"openshift-.*(kube-controller-manager|scheduler|controller-manager|sdn|ovn-kubernetes|dns)"} == 0
+  description: "{{$labels.namespace}}/{{$labels.pod}} down"
+  severity: warning
+
+- expr: up{job=~"crio|kubelet"} == 0
+  description: "{{$labels.node}}/{{$labels.job}} down"
+  severity: warning
+
+- expr: up{job="ovnkube-node"} == 0
+  description: "{{$labels.instance}}/{{$labels.pod}} {{$labels.job}} down"
+  severity: warning
+
+# Service sync latency
+- expr: histogram_quantile(0.99, sum(rate(kubeproxy_network_programming_duration_seconds_bucket[2m])) by (le)) > 10
+  description: 99th Kubeproxy network programming latency higher than 10 seconds. {{$value}}s 
+  severity: warning
+
+# Prometheus alerts
+- expr: ALERTS{severity="critical", alertstate="firing"} > 0
+  description: Critical prometheus alert. {{$labels.alertname}}
+  severity: warning

config/config.yaml

@@ -1,51 +1,46 @@
 kraken:
-    distribution: openshift                                # Distribution can be kubernetes or openshift
+    distribution: kubernetes                                # Distribution can be kubernetes or openshift
     kubeconfig_path: ~/.kube/config                        # Path to kubeconfig
     exit_on_failure: False                                 # Exit when a post action scenario fails
     publish_kraken_status: True                            # Can be accessed at http://0.0.0.0:8081
     signal_state: RUN                                      # Will wait for the RUN signal when set to PAUSE before running the scenarios, refer docs/signal.md for more details
     signal_address: 0.0.0.0                                # Signal listening address
     port: 8081                                             # Signal port
-    litmus_install: True                                   # Installs specified version, set to False if it's already setup
-    litmus_version: v1.13.6                                # Litmus version to install
-    litmus_uninstall: False                                # If you want to uninstall litmus if failure
-    litmus_uninstall_before_run: True                      # If you want to uninstall litmus before a new run starts
-    chaos_scenarios:                                       # List of policies/chaos scenarios to load
-        -   container_scenarios:                                 # List of chaos pod scenarios to load
+    chaos_scenarios:
+        # List of policies/chaos scenarios to load
+        - arcaflow_scenarios:
+            - scenarios/arcaflow/cpu-hog/input.yaml
+            - scenarios/arcaflow/memory-hog/input.yaml
+            - scenarios/arcaflow/io-hog/input.yaml
+        - application_outages:
+            - scenarios/openshift/app_outage.yaml
+        - container_scenarios:                             # List of chaos pod scenarios to load
             - -    scenarios/openshift/container_etcd.yml
-        -   plugin_scenarios:
+        - plugin_scenarios:
             - scenarios/openshift/etcd.yml
             - scenarios/openshift/regex_openshift_pod_kill.yml
             - scenarios/openshift/vmware_node_scenarios.yml
             - scenarios/openshift/network_chaos_ingress.yml
-        -   node_scenarios:                                # List of chaos node scenarios to load
+            - scenarios/openshift/prom_kill.yml
+        - node_scenarios:                                  # List of chaos node scenarios to load
             -   scenarios/openshift/node_scenarios_example.yml
-        -   plugin_scenarios:
+        - plugin_scenarios:
             - scenarios/openshift/openshift-apiserver.yml
             - scenarios/openshift/openshift-kube-apiserver.yml
-        -   time_scenarios:                                # List of chaos time scenarios to load
+        - time_scenarios:                                  # List of chaos time scenarios to load
             - scenarios/openshift/time_scenarios_example.yml
-        -   litmus_scenarios:                              # List of litmus scenarios to load
-            - - scenarios/openshift/templates/litmus-rbac.yaml
-              - scenarios/openshift/node_cpu_hog_engine.yaml
-            - - scenarios/openshift/templates/litmus-rbac.yaml
-              - scenarios/openshift/node_mem_engine.yaml
-            - - scenarios/openshift/templates/litmus-rbac.yaml
-              - scenarios/openshift/node_io_engine.yaml
-        -   cluster_shut_down_scenarios:
+        - cluster_shut_down_scenarios:
             - - scenarios/openshift/cluster_shut_down_scenario.yml
               - scenarios/openshift/post_action_shut_down.py
-        -   namespace_scenarios:
+        - service_disruption_scenarios:
              - - scenarios/openshift/regex_namespace.yaml
              - - scenarios/openshift/ingress_namespace.yaml
                - scenarios/openshift/post_action_namespace.py
-        -   zone_outages:
+        - zone_outages:
             - scenarios/openshift/zone_outage.yaml
-        -   application_outages:
-            - scenarios/openshift/app_outage.yaml
-        -   pvc_scenarios:
+        - pvc_scenarios:
             - scenarios/openshift/pvc_scenario.yaml
-        -   network_chaos:
+        - network_chaos:
             - scenarios/openshift/network_chaos.yaml
 
 cerberus:
@@ -56,17 +51,49 @@ cerberus:
 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"
-    kube_burner_binary_url: "https://github.com/cloud-bulldozer/kube-burner/releases/download/v0.9.1/kube-burner-0.9.1-Linux-x86_64.tar.gz"
-    capture_metrics: False
-    config_path: config/kube_burner.yaml                  # Define the Elasticsearch url and index name in this config
-    metrics_profile_path: config/metrics-aggregated.yaml
-    prometheus_url:                                       # The prometheus url/route is automatically obtained in case of OpenShift, please set it when the distribution is Kubernetes.
+    prometheus_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                          # Path to alert profile with the prometheus queries
-
+    alert_profile: config/alerts.yaml                          # Path or URL to alert profile with the prometheus queries
+    check_critical_alerts: False                          # When enabled will check prometheus for critical alerts firing post chaos
 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
+    api_url: https://ulnmf9xv7j.execute-api.us-west-2.amazonaws.com/production #telemetry service endpoint
+    username: username                                      # telemetry service username
+    password: password                                    # telemetry service password
+    prometheus_backup: True                                 # enables/disables prometheus data collection
+    prometheus_namespace: ""                                # namespace where prometheus is deployed (if distribution is kubernetes)
+    prometheus_container_name: ""                           # name of the prometheus container name (if distribution is kubernetes)
+    prometheus_pod_name: ""                                 # name of the prometheus pod (if distribution is kubernetes)
+    full_prometheus_backup: False                           # if is set to False only the /prometheus/wal folder will be downloaded.
+    backup_threads: 5                                       # number of telemetry download/upload threads
+    archive_path: /tmp                                      # local path where the archive files will be temporarly stored
+    max_retries: 0                                          # maximum number of upload retries (if 0 will retry forever)
+    run_tag: ''                                             # if set, this will be appended to the run folder in the bucket (useful to group the runs)
+    archive_size: 500000
+    telemetry_group: ''                                     # if set will archive the telemetry in the S3 bucket on a folder named after the value, otherwise will use "default"
+    # the size of the prometheus data archive size in KB. The lower the size of archive is
+                                                            # the higher the number of archive files will be produced and uploaded (and processed by backup_threads
+                                                            # simultaneously).
+                                                            # For unstable/slow connection is better to keep this value low
+                                                            # increasing the number of backup_threads, in this way, on upload failure, the retry will happen only on the
+                                                            # failed chunk without affecting the whole upload.
+    logs_backup: True
+    logs_filter_patterns:
+     - "(\\w{3}\\s\\d{1,2}\\s\\d{2}:\\d{2}:\\d{2}\\.\\d+).+"         # Sep 9 11:20:36.123425532
+     - "kinit (\\d+/\\d+/\\d+\\s\\d{2}:\\d{2}:\\d{2})\\s+"          # kinit 2023/09/15 11:20:36 log
+     - "(\\d{4}-\\d{2}-\\d{2}T\\d{2}:\\d{2}:\\d{2}\\.\\d+Z).+"      # 2023-09-15T11:20:36.123425532Z log
+    oc_cli_path: /usr/bin/oc                                # optional, if not specified will be search in $PATH
+    events_backup: True                                     # enables/disables cluster events collection
+elastic: 
+    elastic_url: ""                                         # To track results in elasticsearch, give url to server here; will post telemetry details when url and index not blank
+    elastic_index: ""                                       # Elastic search index pattern to post results to
+
+
+
+

config/config_kind.yaml

@@ -6,11 +6,7 @@ kraken:
     publish_kraken_status: True                            # Can be accessed at http://0.0.0.0:8081
     signal_state: RUN                                      # Will wait for the RUN signal when set to PAUSE before running the scenarios, refer docs/signal.md for more details
     signal_address: 0.0.0.0                                # Signal listening address
-    litmus_install: True                                   # Installs specified version, set to False if it's already setup
-    litmus_version: v1.13.6                                # Litmus version to install
-    litmus_uninstall: False                                # If you want to uninstall litmus if failure
-    litmus_uninstall_before_run: True                      # If you want to uninstall litmus before a new run starts
-    chaos_scenarios:                                       # List of policies/chaos scenarios to load
+   chaos_scenarios:                                       # List of policies/chaos scenarios to load
         - plugin_scenarios:
             - scenarios/kind/scheduler.yml
         - node_scenarios:
@@ -24,15 +20,11 @@ cerberus:
 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"
-    kube_burner_binary_url: "https://github.com/cloud-bulldozer/kube-burner/releases/download/v0.9.1/kube-burner-0.9.1-Linux-x86_64.tar.gz"
-    capture_metrics: False
-    config_path: config/kube_burner.yaml                  # Define the Elasticsearch url and index name in this config
-    metrics_profile_path: config/metrics-aggregated.yaml
     prometheus_url:                                       # The prometheus url/route is automatically obtained in case of OpenShift, please set it when the distribution is Kubernetes.
     prometheus_bearer_token:                              # The bearer token is automatically obtained in case of OpenShift, please set it when the distribution is Kubernetes. This is needed to authenticate with prometheus.
     uuid:                                                 # uuid for the run is generated by default if not set
     enable_alerts: False                                  # Runs the queries specified in the alert profile and displays the info or exits 1 when severity=error
-    alert_profile: config/alerts                          # Path to alert profile with the prometheus queries
+    alert_profile: config/alerts.yaml                          # Path to alert profile with the prometheus queries
 
 tunings:
     wait_duration: 60                                      # Duration to wait between each chaos scenario

config/config_kubernetes.yaml

@@ -5,10 +5,6 @@ kraken:
     port: 8081
     publish_kraken_status: True                            # Can be accessed at http://0.0.0.0:8081
     signal_state: RUN                                      # Will wait for the RUN signal when set to PAUSE before running the scenarios, refer docs/signal.md for more details
-    litmus_install: True                                   # Installs specified version, set to False if it's already setup
-    litmus_version: v1.13.6                                # Litmus version to install
-    litmus_uninstall: False                                # If you want to uninstall litmus if failure
-    litmus_uninstall_before_run: True                      # If you want to uninstall litmus before a new run starts
     chaos_scenarios:                                       # List of policies/chaos scenarios to load
         -   container_scenarios:                                 # List of chaos pod scenarios to load
             - -    scenarios/kube/container_dns.yml
@@ -23,16 +19,12 @@ cerberus:
 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"
-    kube_burner_binary_url: "https://github.com/cloud-bulldozer/kube-burner/releases/download/v0.9.1/kube-burner-0.9.1-Linux-x86_64.tar.gz"
-    capture_metrics: False
-    config_path: config/kube_burner.yaml                  # Define the Elasticsearch url and index name in this config
-    metrics_profile_path: config/metrics-aggregated.yaml
     prometheus_url:                                       # The prometheus url/route is automatically obtained in case of OpenShift, please set it when the distribution is Kubernetes.
     prometheus_bearer_token:                              # The bearer token is automatically obtained in case of OpenShift, please set it when the distribution is Kubernetes. This is needed to authenticate with prometheus.
     uuid:                                                 # uuid for the run is generated by default if not set
     enable_alerts: False                                  # Runs the queries specified in the alert profile and displays the info or exits 1 when severity=error
-    alert_profile: config/alerts                          # Path to alert profile with the prometheus queries
-
+    alert_profile: config/alerts.yaml                         # Path to alert profile with the prometheus queries
+    check_critical_alerts: False                          # When enabled will check prometheus for critical alerts firing post chaos after soak time for the cluster to settle down
 tunings:
     wait_duration: 60                                      # Duration to wait between each chaos scenario
     iterations: 1                                          # Number of times to execute the scenarios

config/config_performance.yaml

@@ -6,13 +6,11 @@ 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
     port: 8081                                             # Signal port
-    litmus_version: v1.13.6                                # Litmus version to install
-    litmus_uninstall: False                                # If you want to uninstall litmus if failure
-    litmus_uninstall_before_run: True                      # If you want to uninstall litmus before a new run starts
     chaos_scenarios:                                       # List of policies/chaos scenarios to load
         -   plugin_scenarios:                                 # List of chaos pod scenarios to load
             - scenarios/openshift/etcd.yml
             - scenarios/openshift/regex_openshift_pod_kill.yml
+            - scenarios/openshift/prom_kill.yml
         -   node_scenarios:                                # List of chaos node scenarios to load
             -   scenarios/openshift/node_scenarios_example.yml
         -   plugin_scenarios:
@@ -20,13 +18,10 @@ kraken:
             - scenarios/openshift/openshift-kube-apiserver.yml
         -   time_scenarios:                                # List of chaos time scenarios to load
             - scenarios/openshift/time_scenarios_example.yml
-        -   litmus_scenarios:                              # List of litmus scenarios to load
-            - - https://hub.litmuschaos.io/api/chaos/1.10.0?file=charts/generic/node-cpu-hog/rbac.yaml
-              - scenarios/openshift/node_cpu_hog_engine.yaml
         -   cluster_shut_down_scenarios:
             - - scenarios/openshift/cluster_shut_down_scenario.yml
               - scenarios/openshift/post_action_shut_down.py
-        -   namespace_scenarios:
+        -   service_disruption_scenarios:
             - scenarios/openshift/regex_namespace.yaml
             - scenarios/openshift/ingress_namespace.yaml
         -   zone_outages:
@@ -46,17 +41,44 @@ cerberus:
 performance_monitoring:
     deploy_dashboards: True                               # 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"
-    kube_burner_binary_url: "https://github.com/cloud-bulldozer/kube-burner/releases/download/v0.9.1/kube-burner-0.9.1-Linux-x86_64.tar.gz"
     capture_metrics: True
-    config_path: config/kube_burner.yaml                  # Define the Elasticsearch url and index name in this config
     metrics_profile_path: config/metrics-aggregated.yaml
     prometheus_url:                                       # The prometheus url/route is automatically obtained in case of OpenShift, please set it when the distribution is Kubernetes.
     prometheus_bearer_token:                              # The bearer token is automatically obtained in case of OpenShift, please set it when the distribution is Kubernetes. This is needed to authenticate with prometheus.
     uuid:                                                 # uuid for the run is generated by default if not set
     enable_alerts: True                                   # Runs the queries specified in the alert profile and displays the info or exits 1 when severity=error
-    alert_profile: config/alerts                          # Path to alert profile with the prometheus queries
+    alert_profile: config/alerts.yaml                          # Path to alert profile with the prometheus queries
 
 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
+    api_url: https://ulnmf9xv7j.execute-api.us-west-2.amazonaws.com/production #telemetry service endpoint
+    username: username                                      # telemetry service username
+    password: password                                      # telemetry service password
+    prometheus_backup: True                                 # enables/disables prometheus data collection
+    full_prometheus_backup: False                           # if is set to False only the /prometheus/wal folder will be downloaded.
+    backup_threads: 5                                       # number of telemetry download/upload threads
+    archive_path: /tmp                                      # local path where the archive files will be temporarly stored
+    max_retries: 0                                          # maximum number of upload retries (if 0 will retry forever)
+    run_tag: ''                                             # if set, this will be appended to the run folder in the bucket (useful to group the runs)
+    archive_size: 500000                                     # the size of the prometheus data archive size in KB. The lower the size of archive is
+                                                            # the higher the number of archive files will be produced and uploaded (and processed by backup_threads
+                                                            # simultaneously).
+                                                            # For unstable/slow connection is better to keep this value low
+                                                            # increasing the number of backup_threads, in this way, on upload failure, the retry will happen only on the
+                                                            # failed chunk without affecting the whole upload.
+    logs_backup: True
+    logs_filter_patterns:
+     - "(\\w{3}\\s\\d{1,2}\\s\\d{2}:\\d{2}:\\d{2}\\.\\d+).+"         # Sep 9 11:20:36.123425532
+     - "kinit (\\d+/\\d+/\\d+\\s\\d{2}:\\d{2}:\\d{2})\\s+"          # kinit 2023/09/15 11:20:36 log
+     - "(\\d{4}-\\d{2}-\\d{2}T\\d{2}:\\d{2}:\\d{2}\\.\\d+Z).+"      # 2023-09-15T11:20:36.123425532Z log
+    oc_cli_path: /usr/bin/oc                                # optional, if not specified will be search in $PATH
+elastic: 
+    elastic_url: ""                                         # To track results in elasticsearch, give url to server here; will post telemetry details when url and index not blank
+    elastic_index: ""                                       # Elastic search index pattern to post results to
+
+

config/kube_burner.yaml

@@ -1,15 +0,0 @@
----
-
-global:
-  writeToFile: true
-  metricsDirectory: collected-metrics
-  measurements:
-    - name: podLatency
-      esIndex: kraken
-
-  indexerConfig:
-    enabled: true
-    esServers: [http://0.0.0.0:9200]  # Please change this to the respective Elasticsearch in use if you haven't run the podman-compose command to setup the infrastructure containers
-    insecureSkipVerify: true
-    defaultIndex: kraken
-    type: elastic

config/metrics-aggregated.yaml

@@ -139,6 +139,39 @@ metrics:
   - query: histogram_quantile(0.99,sum(rate(etcd_request_duration_seconds_bucket[2m])) by (le,operation,apiserver)) > 0
     metricName: P99APIEtcdRequestLatency
 
+  - query: sum(grpc_server_started_total{namespace="openshift-etcd",grpc_service="etcdserverpb.Watch",grpc_type="bidi_stream"}) - sum(grpc_server_handled_total{namespace="openshift-etcd",grpc_service="etcdserverpb.Watch",grpc_type="bidi_stream"})
+    metricName: ActiveWatchStreams
+
+  - query: sum(grpc_server_started_total{namespace="openshift-etcd",grpc_service="etcdserverpb.Lease",grpc_type="bidi_stream"}) - sum(grpc_server_handled_total{namespace="openshift-etcd",grpc_service="etcdserverpb.Lease",grpc_type="bidi_stream"})
+    metricName: ActiveLeaseStreams
+
+  - query: sum(rate(etcd_debugging_snap_save_total_duration_seconds_sum{namespace="openshift-etcd"}[2m]))
+    metricName: snapshotSaveLatency
+
+  - query: sum(rate(etcd_server_heartbeat_send_failures_total{namespace="openshift-etcd"}[2m]))
+    metricName: HeartBeatFailures
+
+  - query: sum(rate(etcd_server_health_failures{namespace="openshift-etcd"}[2m]))
+    metricName: HealthFailures
+
+  - query: sum(rate(etcd_server_slow_apply_total{namespace="openshift-etcd"}[2m]))
+    metricName: SlowApplies
+
+  - query: sum(rate(etcd_server_slow_read_indexes_total{namespace="openshift-etcd"}[2m]))
+    metricName: SlowIndexRead
+
+  - query: sum(etcd_server_proposals_pending)
+    metricName: PendingProposals
+
+  - query: histogram_quantile(1.0, sum(rate(etcd_debugging_mvcc_db_compaction_pause_duration_milliseconds_bucket[1m])) by (le, instance))
+    metricName: CompactionMaxPause
+
+  - query: sum by (instance) (apiserver_storage_objects)
+    metricName: etcdTotalObjectCount 
+
+  - query: topk(500, max by(resource) (apiserver_storage_objects))
+    metricName: etcdTopObectCount    
+
 # Cluster metrics
   - query: count(kube_namespace_created)
     metricName: namespaceCount

config/recommender_config.yaml

@@ -0,0 +1,35 @@
+application: openshift-etcd
+namespace: openshift-etcd
+labels: app=openshift-etcd
+kubeconfig: ~/.kube/config.yaml
+prometheus_endpoint: <Prometheus_Endpoint>
+auth_token: <Auth_Token>
+scrape_duration: 10m
+chaos_library: "kraken"
+log_level: INFO
+json_output_file: False
+json_output_folder_path:
+
+# for output purpose only do not change if not needed
+chaos_tests:
+  GENERIC:
+    - pod_failure
+    - container_failure
+    - node_failure
+    - zone_outage
+    - time_skew
+    - namespace_failure
+    - power_outage
+  CPU:
+    - node_cpu_hog
+  NETWORK:
+    - application_outage
+    - node_network_chaos
+    - pod_network_chaos
+  MEM:
+    - node_memory_hog
+    - pvc_disk_fill
+
+threshold: .7
+cpu_threshold: .5
+mem_threshold: .5

containers/Dockerfile

@@ -1,29 +1,27 @@
 # Dockerfile for kraken
 
-FROM quay.io/openshift/origin-tests:latest as origintests
-
 FROM mcr.microsoft.com/azure-cli:latest as azure-cli
 
-FROM quay.io/centos/centos:stream9
-
-LABEL org.opencontainers.image.authors="Red Hat OpenShift Chaos Engineering"
+FROM registry.access.redhat.com/ubi8/ubi:latest
 
 ENV KUBECONFIG /root/.kube/config
-
-# Copy OpenShift CLI, Kubernetes CLI from origin-tests image
-COPY --from=origintests /usr/bin/oc /usr/bin/oc
-COPY --from=origintests /usr/bin/kubectl /usr/bin/kubectl
+ENV PATH=$PATH:/usr/local/bin
 
 # Copy azure client binary from azure-cli image
 COPY --from=azure-cli /usr/local/bin/az /usr/bin/az
 
 # Install dependencies
-RUN yum install epel-release -y && \
-    yum install -y git python39 python3-pip jq gettext && \
+RUN yum install -y git python39 python3-pip jq gettext wget && \
     python3.9 -m pip install -U pip && \
-    git clone https://github.com/redhat-chaos/krkn.git --branch v1.1.1 /root/kraken && \
+    git clone https://github.com/krkn-chaos/krkn.git --branch v1.5.9 /root/kraken && \
     mkdir -p /root/.kube && cd /root/kraken && \
-    pip3.9 install -r requirements.txt
+    pip3.9 install -r requirements.txt && \
+    pip3.9 install virtualenv && \
+    wget https://github.com/mikefarah/yq/releases/latest/download/yq_linux_amd64 -O /usr/bin/yq && chmod +x /usr/bin/yq
+
+# Get Kubernetes and OpenShift clients from stable releases
+WORKDIR /tmp
+RUN wget https://mirror.openshift.com/pub/openshift-v4/clients/ocp/stable/openshift-client-linux.tar.gz && tar -xvf openshift-client-linux.tar.gz && cp oc /usr/local/bin/oc && cp kubectl /usr/local/bin/kubectl
 
 WORKDIR /root/kraken
 

containers/Dockerfile-ppc64le

@@ -2,24 +2,29 @@
 
 FROM ppc64le/centos:8
 
-MAINTAINER Red Hat OpenShift Performance and Scale
+FROM mcr.microsoft.com/azure-cli:latest as azure-cli
+
+LABEL org.opencontainers.image.authors="Red Hat OpenShift Chaos Engineering"
 
 ENV KUBECONFIG /root/.kube/config
+ENV PATH=$PATH:/usr/local/bin
 
-RUN curl -L -o kubernetes-client-linux-ppc64le.tar.gz https://dl.k8s.io/v1.19.0/kubernetes-client-linux-ppc64le.tar.gz \
-&& tar xf kubernetes-client-linux-ppc64le.tar.gz && mv kubernetes/client/bin/kubectl /usr/bin/ && rm -rf kubernetes-client-linux-ppc64le.tar.gz
-
-RUN curl -L -o openshift-client-linux.tar.gz https://mirror.openshift.com/pub/openshift-v4/ppc64le/clients/ocp/stable/openshift-client-linux.tar.gz \
-&& tar xf openshift-client-linux.tar.gz -C /usr/bin && rm -rf openshift-client-linux.tar.gz
+# Copy azure client binary from azure-cli image
+COPY --from=azure-cli /usr/local/bin/az /usr/bin/az
 
 # Install dependencies
-RUN yum install epel-release -y && \
-yum install -y git python36 python3-pip gcc libffi-devel python36-devel openssl-devel gcc-c++ make jq gettext && \
-git clone https://github.com/redhat-chaos/krkn.git --branch main /root/kraken && \
-mkdir -p /root/.kube && cd /root/kraken && \
-pip3 install cryptography==3.3.2 && \
-pip3 install -r requirements.txt setuptools==40.3.0 urllib3==1.25.4
+RUN yum install -y git python39 python3-pip jq gettext wget && \
+    python3.9 -m pip install -U pip && \
+    git clone https://github.com/redhat-chaos/krkn.git --branch v1.5.9 /root/kraken && \
+    mkdir -p /root/.kube && cd /root/kraken && \
+    pip3.9 install -r requirements.txt && \
+    pip3.9 install virtualenv && \
+    wget https://github.com/mikefarah/yq/releases/latest/download/yq_linux_amd64 -O /usr/bin/yq && chmod +x /usr/bin/yq
+
+# Get Kubernetes and OpenShift clients from stable releases
+WORKDIR /tmp
+RUN wget https://mirror.openshift.com/pub/openshift-v4/clients/ocp/stable/openshift-client-linux.tar.gz && tar -xvf openshift-client-linux.tar.gz && cp oc /usr/local/bin/oc && cp kubectl /usr/local/bin/kubectl
 
 WORKDIR /root/kraken
 
-ENTRYPOINT python3 run_kraken.py --config=config/config.yaml
+ENTRYPOINT python3.9 run_kraken.py --config=config/config.yaml

containers/README.md

@@ -1,27 +1,20 @@
 
 ### Kraken image
 
-  
+Container image gets automatically built by quay.io at [Kraken image](https://quay.io/redhat-chaos/krkn).
 
-Container image gets automatically built by quay.io at [Kraken image](https://quay.io/chaos-kubox/krkn).
-
-  
 
 ### Run containerized version
 
 Refer [instructions](https://github.com/redhat-chaos/krkn/blob/main/docs/installation.md#run-containerized-version) for information on how to run the containerized version of kraken.
 
-  
-  
 
 ### Run Custom Kraken Image
 
 Refer to [instructions](https://github.com/redhat-chaos/krkn/blob/main/containers/build_own_image-README.md) for information on how to run a custom containerized version of kraken using podman.
 
-  
-  
 
-### Kraken as a KubeApp
+### Kraken as a KubeApp ( Unsupported and not recommended )
 
 #### GENERAL NOTES:
 
@@ -50,4 +43,4 @@ To run containerized Kraken as a Kubernetes/OpenShift Deployment, follow these s
 8. Create a ConfigMap named scenarios-kube-config using `kubectl create configmap scenarios-kube-config --from-file=<path_to_kraken>/scenarios/kube` 
 9. Create a service account to run the kraken pod `kubectl create serviceaccount useroot`.
 10.  In Openshift, add privileges to service account and execute `oc adm policy add-scc-to-user privileged -z useroot`.
-11.  Create a Job using `kubectl apply -f <path_to_kraken>/containers/kraken.yml` and monitor the status using `oc get jobs` and `oc get pods`.
+11.  Create a Job using `kubectl apply -f <path_to_kraken>/containers/kraken.yml` and monitor the status using `oc get jobs` and `oc get pods`.

containers/build_own_image-README.md

@@ -1,13 +1,13 @@
 # Building your own Kraken image
 
-1. Git clone the Kraken repository using `git clone https://github.com/openshift-scale/kraken.git`.
+1. Git clone the Kraken repository using `git clone https://github.com/redhat-chaos/krkn.git`.
 2. Modify the python code and yaml files to address your needs.
 3. Execute `podman build -t <new_image_name>:latest .` in the containers directory within kraken to build an image from a Dockerfile.
 4. Execute `podman run --detach --name <container_name> <new_image_name>:latest` to start a container based on your new image.
 
 # Building the Kraken image on IBM Power (ppc64le)
 
-1. Git clone the Kraken repository using `git clone https://github.com/cloud-bulldozer/kraken.git` on an IBM Power Systems server.
+1. Git clone the Kraken repository using `git clone https://github.com/redhat-chaos/krkn.git` on an IBM Power Systems server.
 2. Modify the python code and yaml files to address your needs.
 3. Execute `podman build -t <new_image_name>:latest -f Dockerfile-ppc64le` in the containers directory within kraken to build an image from the Dockerfile for Power.
 4. Execute `podman run --detach --name <container_name> <new_image_name>:latest` to start a container based on your new image.

containers/kraken.yml

@@ -16,7 +16,7 @@ spec:
         - name: kraken
           securityContext:
             privileged: true
-          image: quay.io/chaos-kubox/krkn
+          image: quay.io/redhat-chaos/krkn
           command: ["/bin/sh", "-c"]
           args: ["python3.9 run_kraken.py -c config/config.yaml"]
           volumeMounts:

docs/SLOs_validation.md

@@ -1,18 +1,28 @@
-## Alerts
+## SLOs validation
 
-Pass/fail based on metrics captured from the cluster is important in addition to checking the health status and recovery. Kraken supports alerting based on the queries defined by the user and modifies the return code of the run to determine pass/fail. It's especially useful in case of automated runs in CI where user won't be able to monitor the system. It uses [Kube-burner](https://kube-burner.readthedocs.io/en/latest/) under the hood. This feature can be enabled in the [config](https://github.com/redhat-chaos/krkn/blob/main/config/config.yaml) by setting the following:
+Pass/fail based on metrics captured from the cluster is important in addition to checking the health status and recovery. Kraken supports:
+
+###  Checking for critical alerts post chaos 
+If enabled, the check runs at the end of each scenario ( post chaos ) and Kraken exits in case critical alerts are firing to allow user to debug. You can enable it in the config:
+
+```
+performance_monitoring:
+    check_critical_alerts: False                          # When enabled will check prometheus for critical alerts firing post chaos
+```
+
+### Validation and alerting based on the queries defined by the user during chaos
+Takes PromQL queries as input and modifies the return code of the run to determine pass/fail. It's especially useful in case of automated runs in CI where user won't be able to monitor the system. This feature can be enabled in the [config](https://github.com/redhat-chaos/krkn/blob/main/config/config.yaml) by setting the following:
 
 ```
 performance_monitoring:
-    kube_burner_binary_url: "https://github.com/cloud-bulldozer/kube-burner/releases/download/v0.9.1/kube-burner-0.9.1-Linux-x86_64.tar.gz"
     prometheus_url:                                       # The prometheus url/route is automatically obtained in case of OpenShift, please set it when the distribution is Kubernetes.
     prometheus_bearer_token:                              # The bearer token is automatically obtained in case of OpenShift, please set it when the distribution is Kubernetes. This is needed to authenticate with prometheus.
     enable_alerts: True                                   # Runs the queries specified in the alert profile and displays the info or exits 1 when severity=error.
-    alert_profile: config/alerts                          # Path to alert profile with the prometheus queries.
+    alert_profile: config/alerts.yaml                          # Path to alert profile with the prometheus queries.
 ```
 
-### Alert profile
-A couple of [alert profiles](https://github.com/redhat-chaos/krkn/tree/main/config) [alerts](https://github.com/redhat-chaos/krkn/blob/main/config/alerts) are shipped by default and can be tweaked to add more queries to alert on. The following are a few alerts examples:
+#### Alert profile
+A couple of [alert profiles](https://github.com/redhat-chaos/krkn/tree/main/config) [alerts](https://github.com/redhat-chaos/krkn/blob/main/config/alerts.yaml) are shipped by default and can be tweaked to add more queries to alert on. User can provide a URL or path to the file in the [config](https://github.com/redhat-chaos/krkn/blob/main/config/config.yaml). The following are a few alerts examples:
 
 ```
 - expr: avg_over_time(histogram_quantile(0.99, rate(etcd_disk_wal_fsync_duration_seconds_bucket[2m]))[5m:]) > 0.01

docs/arcaflow_scenarios.md

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

docs/arcaflow_scenarios/cpu_hog.md

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

docs/arcaflow_scenarios/io_hog.md

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

docs/arcaflow_scenarios/memory_hog.md

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

docs/cloud_setup.md

@@ -1,11 +1,12 @@
 Supported Cloud Providers:
 
-* [AWS](#aws)
-* [GCP](#gcp)
-* [Openstack](#openstack)
-* [Azure](#azure)
-* [Alibaba](#alibaba)
-* [VMware](#vmware)
+- [AWS](#aws)
+- [GCP](#gcp)
+- [Openstack](#openstack)
+- [Azure](#azure)
+- [Alibaba](#alibaba)
+- [VMware](#vmware)
+- [IBMCloud](#ibmcloud)
 
 ## AWS
 
@@ -65,4 +66,24 @@ Set the following environment variables
 
 3. ```export VSPHERE_PASSWORD=<vSphere_client_password>```
 
-These are the credentials that you would normally use to access the vSphere client.
+These are the credentials that you would normally use to access the vSphere client.
+
+
+## IBMCloud
+If no api key is set up with proper VPC resource permissions, use the following to create: 
+* Access group
+* Service id with the following access
+  * With policy **VPC Infrastructure Services**
+  * Resources = All
+  * Roles: 
+    * Editor
+    * Administrator 
+    * Operator  
+    * Viewer
+* API Key
+
+Set the following environment variables
+
+1. ```export IBMC_URL=https://<region>.iaas.cloud.ibm.com/v1```
+
+2. ```export IBMC_APIKEY=<ibmcloud_api_key>```

docs/cluster_shut_down_scenarios.md

@@ -1,5 +1,5 @@
-#### Kubernetes/OpenShift cluster shut down scenario
-Scenario to shut down all the nodes including the masters and restart them after specified duration. Cluster shut down scenario can be injected by placing the shut_down config file under cluster_shut_down_scenario option in the kraken config. Refer to [cluster_shut_down_scenario](https://github.com/redhat-chaos/krkn/blob/main/scenarios/cluster_shut_down_scenario.yml) config file.
+#### Kubernetes cluster shut down scenario
+Scenario to shut down all the nodes including the masters and restart them after specified duration. Cluster shut down scenario can be injected by placing the shut_down config file under cluster_shut_down_scenario option in the kraken config. Refer to [cluster_shut_down_scenario](https://github.com/krkn-chaos/krkn/blob/main/scenarios/cluster_shut_down_scenario.yml) config file.
 
 Refer to [cloud setup](cloud_setup.md) to configure your cli properly for the cloud provider of the cluster you want to shut down.
 

docs/config.md

@@ -27,14 +27,6 @@ The prometheus url/route and bearer token are automatically obtained in case of
 **signal_address**: Address to listen/post the signal state to
 **port**: port to listen/post the signal state to
 
-## Litmus Variables
-Litmus installation specifics if you are running one of the hog scenarios. See [litmus doc](litmus_scenarios.md) for more information on these types of scenarios 
-**litmus_install**: Installs specified version of litmus, set to False if it's already setup
-**litmus_version**: Litmus version to install
-**litmus_uninstall**: If you want to uninstall litmus if failure
-**litmus_uninstall_before_run**: If you want to uninstall litmus before a new run starts, True or False values
-
-
 ## Chaos Scenarios 
 
 **chaos_scenarios**: List of different types of chaos scenarios you want to run with paths to their specific yaml file configurations
@@ -48,7 +40,6 @@ Chaos scenario types:
 - plugin_scenarios
 - node_scenarios
 - time_scenarios
-- litmus_scenarios
 - cluster_shut_down_scenarios
 - namespace_scenarios
 - zone_outages

docs/container_scenarios.md

@@ -4,17 +4,19 @@ This can be based on the pods namespace or labels. If you know the exact object
 These scenarios are in a simple yaml format that you can manipulate to run your specific tests or use the pre-existing scenarios to see how it works.
 
 ####  Example Config
-The following are the components of Kubernetes/OpenShift for which a basic chaos scenario config exists today.
+The following are the components of Kubernetes for which a basic chaos scenario config exists today.
 
 ```
 scenarios:
-- name: "<Name of scenario>"
+- name: "<name of scenario>"
   namespace: "<specific namespace>" # can specify "*" if you want to find in all namespaces
   label_selector: "<label of pod(s)>"
   container_name: "<specific container name>"  # This is optional, can take out and will kill all containers in all pods found under namespace and label
   pod_names:  # This is optional, can take out and will select all pods with given namespace and label
   - <pod_name>
-  retry_wait: <number of seconds to wait for container to be running again> (defaults to 120seconds)
+  count: <number of containers to disrupt, default=1>
+  action: <kill signal to run. For example 1 ( hang up ) or 9. Default is set to 1>
+  expected_recovery_time: <number of seconds to wait for container to be running again> (defaults to 120seconds)
 ```
 
 #### Post Action
@@ -23,7 +25,7 @@ In all scenarios we do a post chaos check to wait and verify the specific compon
 Here there are two options:
 1. Pass a custom script in the main config scenario list that will run before the chaos and verify the output matches post chaos scenario.
 
-See [scenarios/post_action_etcd_container.py](https://github.com/redhat-chaos/krkn/blob/main/scenarios/post_action_etcd_container.py) for an example.
+See [scenarios/post_action_etcd_container.py](https://github.com/krkn-chaos/krkn/blob/main/scenarios/post_action_etcd_container.py) for an example.
 ```
 -   container_scenarios:                                 # List of chaos pod scenarios to load.
             - -    scenarios/container_etcd.yml
@@ -34,5 +36,5 @@ See [scenarios/post_action_etcd_container.py](https://github.com/redhat-chaos/kr
 containers that were killed as well as the namespaces and pods to verify all containers that were affected recover properly.
 
 ```
-retry_wait: <seconds to wait for container to recover>
+expected_recovery_time: <seconds to wait for container to recover>
 ```

docs/contribute.md

@@ -62,7 +62,7 @@ If changes go into the main repository while you're working on your code it is b
 
 If not already configured, set the upstream url for kraken.
 ```
- git remote add upstream https://github.com/cloud-bulldozer/kraken.git
+ git remote add upstream https://github.com/krkn-chaos/krkn.git
 ```
 
 Rebase to upstream master branch.

docs/index.md

@@ -10,10 +10,9 @@
   * [Cluster recovery checks, metrics evaluation and pass/fail criteria](#cluster-recovery-checks-metrics-evaluation-and-passfail-criteria)
 * [Scenarios](#scenarios)
 * [Test Environment Recommendations - how and where to run chaos tests](#test-environment-recommendations---how-and-where-to-run-chaos-tests)
-* [Chaos testing in Practice within the OpenShift Organization](#chaos-testing-in-practice-within-the-OpenShift-Organization)
-* [Using kraken as part of a tekton pipeline](#using-kraken-as-part-of-a-tekton-pipeline)
-  * [Start as a single taskrun](#start-as-a-single-taskrun)
-  * [Start as a pipelinerun](#start-as-a-pipelinerun)
+* [Chaos testing in Practice](#chaos-testing-in-practice)
+  * [OpenShift oraganization](#openshift-organization)
+  * [startx-lab](#startx-lab)
 
 
 ### Introduction
@@ -49,7 +48,7 @@ Failures in production are costly. To help mitigate risk to service health, cons
 
 
 ### Best Practices
-Now that we understand the test methodology, let us take a look at the best practices for an OpenShift cluster.  On that platform there are user applications and cluster workloads that need to be designed for stability and to provide the best user experience possible:
+Now that we understand the test methodology, let us take a look at the best practices for an Kubernetes cluster.  On that platform there are user applications and cluster workloads that need to be designed for stability and to provide the best user experience possible:
 
 - Alerts with appropriate severity should get fired.
   - Alerts are key to identify when a component starts degrading, and can help focus the investigation effort on affected system components.
@@ -78,11 +77,11 @@ We want to look at this in terms of CPU, Memory, Disk, Throughput, Network etc.
   - The controller watching the component should recognize a failure as soon as possible. The component needs to have minimal initialization time to avoid extended downtime or overloading the replicas if it is a highly available configuration. The cause of failure can be because of issues with the infrastructure on top of which it is running, application failures, or because of service failures that it depends on.
 
 - High Availability deployment strategy.
-  - There should be multiple replicas ( both OpenShift and application control planes ) running preferably in different availability zones to survive outages while still serving the user/system requests. Avoid single points of failure.
+  - There should be multiple replicas ( both Kubernetes and application control planes ) running preferably in different availability zones to survive outages while still serving the user/system requests. Avoid single points of failure.
 - Backed by persistent storage
   - It is important to have the system/application backed by persistent storage. This is especially important in cases where the application is a database or a stateful application given that a node, pod, or container failure will wipe off the data.
 
-- There should be fallback routes to the backend in case of using CDN, for example, Akamai in case of console.redhat.com - a managed service deployed on top of OpenShift dedicated:
+- There should be fallback routes to the backend in case of using CDN, for example, Akamai in case of console.redhat.com - a managed service deployed on top of Kubernetes dedicated:
   - Content delivery networks (CDNs) are commonly used to host resources such as images, JavaScript files, and CSS. The average web page is nearly 2 MB in size, and offloading heavy resources to third-parties is extremely effective for reducing backend server traffic and latency. However, this makes each CDN an additional point of failure for every site that relies on it. If the CDN fails, its customers could also fail.
   - To test how the application reacts to failures, drop all network traffic between the system and CDN. The application should still serve the content to the user irrespective of the failure.
 
@@ -93,10 +92,10 @@ We want to look at this in terms of CPU, Memory, Disk, Throughput, Network etc.
 
 
 ### Tooling
-Now that we looked at the best practices, In this section, we will go through how [Kraken](https://github.com/redhat-chaos/krkn) - a chaos testing framework can help test the resilience of OpenShift and make sure the applications and services are following the best practices.
+Now that we looked at the best practices, In this section, we will go through how [Kraken](https://github.com/redhat-chaos/krkn) - a chaos testing framework can help test the resilience of Kubernetes and make sure the applications and services are following the best practices.
 
 #### Workflow
-Let us start by understanding the workflow of kraken: the user will start by running kraken by pointing to a specific OpenShift cluster using kubeconfig to be able to talk to the platform on top of which the OpenShift cluster is hosted. This can be done by either the oc/kubectl API or the cloud API. Based on the configuration of kraken, it will inject specific chaos scenarios as shown below, talk to [Cerberus](https://github.com/redhat-chaos/cerberus) to get the go/no-go signal representing the overall health of the cluster ( optional - can be turned off ), scrapes metrics from in-cluster prometheus given a metrics profile with the promql queries and stores them long term in Elasticsearch configured  ( optional - can be turned off ), evaluates the promql expressions specified in the alerts profile ( optional - can be turned off ) and aggregated everything to set the pass/fail i.e. exits 0 or 1. More about the metrics collection, cerberus and metrics evaluation can be found in the next section.
+Let us start by understanding the workflow of kraken: the user will start by running kraken by pointing to a specific Kubernetes cluster using kubeconfig to be able to talk to the platform on top of which the Kubernetes cluster is hosted. This can be done by either the oc/kubectl API or the cloud API. Based on the configuration of kraken, it will inject specific chaos scenarios as shown below, talk to [Cerberus](https://github.com/redhat-chaos/cerberus) to get the go/no-go signal representing the overall health of the cluster ( optional - can be turned off ), scrapes metrics from in-cluster prometheus given a metrics profile with the promql queries and stores them long term in Elasticsearch configured  ( optional - can be turned off ), evaluates the promql expressions specified in the alerts profile ( optional - can be turned off ) and aggregated everything to set the pass/fail i.e. exits 0 or 1. More about the metrics collection, cerberus and metrics evaluation can be found in the next section.
 
 ![Kraken workflow](../media/kraken-workflow.png)
 
@@ -113,15 +112,15 @@ If the monitoring tool, cerberus is enabled it will consume the signal and conti
 
 ### Scenarios
 
-Let us take a look at how to run the chaos scenarios on your OpenShift clusters using Kraken-hub - a lightweight wrapper around Kraken to ease the runs by providing the ability to run them by just running container images using podman with parameters set as environment variables. This eliminates the need to carry around and edit configuration files and makes it easy for any CI framework integration. Here are the scenarios supported:
+Let us take a look at how to run the chaos scenarios on your Kubernetes clusters using Kraken-hub - a lightweight wrapper around Kraken to ease the runs by providing the ability to run them by just running container images using podman with parameters set as environment variables. This eliminates the need to carry around and edit configuration files and makes it easy for any CI framework integration. Here are the scenarios supported:
 
 - Pod Scenarios ([Documentation](https://github.com/redhat-chaos/krkn-hub/blob/main/docs/pod-scenarios.md))
-  - Disrupts OpenShift/Kubernetes and applications deployed as pods:
+  - Disrupts Kubernetes/Kubernetes and applications deployed as pods:
     - Helps understand the availability of the application, the initialization timing and recovery status.
   - [Demo](https://asciinema.org/a/452351?speed=3&theme=solarized-dark)
 
 - Container Scenarios ([Documentation](https://github.com/redhat-chaos/krkn-hub/blob/main/docs/container-scenarios.md))
-  - Disrupts OpenShift/Kubernetes and applications deployed as containers running as part of a pod(s) using a specified kill signal to mimic failures:
+  - Disrupts Kubernetes/Kubernetes and applications deployed as containers running as part of a pod(s) using a specified kill signal to mimic failures:
     - Helps understand the impact and recovery timing when the program/process running in the containers are disrupted - hangs, paused, killed etc., using various kill signals, i.e. SIGHUP, SIGTERM, SIGKILL etc.
   - [Demo](https://asciinema.org/a/BXqs9JSGDSEKcydTIJ5LpPZBM?speed=3&theme=solarized-dark)
 
@@ -135,8 +134,8 @@ Let us take a look at how to run the chaos scenarios on your OpenShift clusters
   - [Demo](https://asciinema.org/a/ANZY7HhPdWTNaWt4xMFanF6Q5)
 
 - Zone Outages ([Documentation](https://github.com/redhat-chaos/krkn-hub/blob/main/docs/zone-outages.md))
-  - Creates outage of availability zone(s) in a targeted region in the public cloud where the OpenShift cluster is running by tweaking the network acl of the zone to simulate the failure, and that in turn will stop both ingress and egress traffic from all nodes in a particular zone for the specified duration and reverts it back to the previous state.
-    - Helps understand the impact on both Kubernetes/OpenShift control plane as well as applications and services running on the worker nodes in that zone.
+  - Creates outage of availability zone(s) in a targeted region in the public cloud where the Kubernetes cluster is running by tweaking the network acl of the zone to simulate the failure, and that in turn will stop both ingress and egress traffic from all nodes in a particular zone for the specified duration and reverts it back to the previous state.
+    - Helps understand the impact on both Kubernetes/Kubernetes control plane as well as applications and services running on the worker nodes in that zone.
     - Currently, only set up for AWS cloud platform: 1 VPC and multiples subnets within the VPC can be specified.
     - [Demo](https://asciinema.org/a/452672?speed=3&theme=solarized-dark)
 
@@ -156,7 +155,6 @@ Let us take a look at how to run the chaos scenarios on your OpenShift clusters
     - Helps understand if the application/system components have reserved resources to not get disrupted because of rogue applications, or get performance throttled.
       - CPU Hog ([Documentation](https://github.com/redhat-chaos/krkn-hub/blob/main/docs/node-cpu-hog.md), [Demo](https://asciinema.org/a/452762))
       - Memory Hog ([Documentation](https://github.com/redhat-chaos/krkn-hub/blob/main/docs/node-memory-hog.md), [Demo](https://asciinema.org/a/452742?speed=3&theme=solarized-dark))
-      - IO Hog ([Documentation](https://github.com/redhat-chaos/krkn-hub/blob/main/docs/node-io-hog.md))
 
 - Time Skewing ([Documentation](https://github.com/redhat-chaos/krkn-hub/blob/main/docs/time-scenarios.md))
   - Manipulate the system time and/or date of specific pods/nodes.
@@ -202,7 +200,7 @@ Let us take a look at few recommendations on how and where to run the chaos test
 - Enable Observability:
   - Chaos Engineering Without Observability ... Is Just Chaos.
   - Make sure to have logging and monitoring installed on the cluster to help with understanding the behaviour as to why it is happening. In case of running the tests in the CI where it is not humanly possible to monitor the cluster all the time, it is recommended to leverage Cerberus to capture the state during the runs and metrics collection in Kraken to store metrics long term even after the cluster is gone.
-  - Kraken ships with dashboards that will help understand API, Etcd and OpenShift cluster level stats and performance metrics.
+  - Kraken ships with dashboards that will help understand API, Etcd and Kubernetes cluster level stats and performance metrics.
   - Pay attention to Prometheus alerts. Check if they are firing as expected.
 
 - Run multiple chaos tests at once to mimic the production outages:
@@ -210,8 +208,9 @@ Let us take a look at few recommendations on how and where to run the chaos test
   - You might have existing test cases, be it related to Performance, Scalability or QE. Run the chaos in the background during the test runs to observe the impact. Signaling feature in Kraken can help with coordinating the chaos runs i.e., start, stop, pause the scenarios based on the state of the other test jobs.
 
 
-#### Chaos testing in Practice within the OpenShift Organization
+#### Chaos testing in Practice
 
+##### OpenShift organization
 Within the OpenShift organization we use kraken to perform chaos testing throughout a release before the code is available to customers.
 
     1. We execute kraken during our regression test suite.
@@ -230,7 +229,14 @@ Within the OpenShift organization we use kraken to perform chaos testing through
 
     3. We are starting to add in test cases that perform chaos testing during an upgrade (not many iterations of this have been completed).
 
-### Using kraken as part of a tekton pipeline
+
+##### startx-lab
+
+**NOTE**: Requests for enhancements and any issues need to be filed at the mentioned links given that they are not natively supported in Kraken.
+
+The following content covers the implementation details around how Startx is leveraging Kraken:
+
+* Using kraken as part of a tekton pipeline
 
 You can find on [artifacthub.io](https://artifacthub.io/packages/search?kind=7&ts_query_web=kraken) the 
 [kraken-scenario](https://artifacthub.io/packages/tekton-task/startx-tekton-catalog/kraken-scenario) `tekton-task`
@@ -258,14 +264,47 @@ to reflect your cluster configuration. Refer to the [kraken configuration](https
 and [configuration examples](https://github.com/startxfr/tekton-catalog/blob/stable/task/kraken-scenario/0.1/samples/) 
 for details on how to configure theses resources.
 
-#### Start as a single taskrun
+* Start as a single taskrun
 
 ```bash
 oc apply -f https://github.com/startxfr/tekton-catalog/raw/stable/task/kraken-scenario/0.1/samples/taskrun.yaml
 ```
 
-#### Start as a pipelinerun
+* Start as a pipelinerun
 
 ```yaml
 oc apply -f https://github.com/startxfr/tekton-catalog/raw/stable/task/kraken-scenario/0.1/samples/pipelinerun.yaml
 ```
+
+* Deploying kraken using a helm-chart
+
+You can find on [artifacthub.io](https://artifacthub.io/packages/search?kind=0&ts_query_web=kraken) the
+[chaos-kraken](https://artifacthub.io/packages/helm/startx/chaos-kraken) `helm-chart`
+which can be used to deploy a kraken chaos scenarios.
+
+Default configuration create the following resources :
+
+  - 1 project named **chaos-kraken**
+  - 1 scc with privileged context for kraken deployment
+  - 1 configmap with kraken 21 generic scenarios, various scripts and configuration
+  - 1 configmap with kubeconfig of the targeted cluster
+  - 1 job named kraken-test-xxx
+  - 1 service to the kraken pods
+  - 1 route to the kraken service
+
+```bash
+# Install the startx helm repository
+helm repo add startx https://startxfr.github.io/helm-repository/packages/
+# Install the kraken project
+helm install --set project.enabled=true chaos-kraken-project  startx/chaos-kraken
+# Deploy the kraken instance
+helm install \
+--set kraken.enabled=true \
+--set kraken.aws.credentials.region="eu-west-3" \
+--set kraken.aws.credentials.key_id="AKIAXXXXXXXXXXXXXXXX" \
+--set kraken.aws.credentials.secret="xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx" \
+--set kraken.kubeconfig.token.server="https://api.mycluster:6443" \
+--set kraken.kubeconfig.token.token="sha256~XXXXXXXXXX_PUT_YOUR_TOKEN_HERE_XXXXXXXXXXXX" \
+-n chaos-kraken \
+chaos-kraken-instance startx/chaos-kraken
+```

docs/installation.md

@@ -3,21 +3,25 @@
 The following ways are supported to run Kraken:
 
 - Standalone python program through Git.
-- Containerized version using either Podman or Docker as the runtime.
-- Kubernetes or OpenShift deployment.
-- Using chaos-kraken helm chart.
+- Containerized version using either Podman or Docker as the runtime via [Krkn-hub](https://github.com/krkn-chaos/krkn-hub)
+- Kubernetes or OpenShift deployment ( unsupported )
 
 **NOTE**: It is recommended to run Kraken external to the cluster ( Standalone or Containerized ) hitting the Kubernetes/OpenShift API as running it internal to the cluster might be disruptive to itself and also might not report back the results if the chaos leads to cluster's API server instability.
 
 **NOTE**: To run Kraken on Power (ppc64le) architecture, build and run a containerized version by following the
- instructions given [here](https://github.com/redhat-chaos/krkn/blob/main/containers/build_own_image-README.md).
+ instructions given [here](https://github.com/krkn-chaos/krkn/blob/main/containers/build_own_image-README.md).
+
+**NOTE**: Helper functions for interactions in Krkn are part of [krkn-lib](https://github.com/redhat-chaos/krkn-lib). 
+Please feel free to reuse and expand them as you see fit when adding a new scenario or expanding 
+the capabilities of the current supported scenarios.
+
 
 ### Git
 
 #### Clone the repository
-Pick the latest stable release to install [here](https://github.com/redhat-chaos/krkn/releases).
+Pick the latest stable release to install [here](https://github.com/krkn-chaos/krkn/releases).
 ```
-$ git clone https://github.com/redhat-chaos/krkn.git --branch <release version>
+$ git clone https://github.com/krkn-chaos/krkn.git --branch <release version>
 $ cd kraken
 ```
 
@@ -36,62 +40,15 @@ $ python3.9 run_kraken.py --config <config_file_location>
 ```
 
 ### Run containerized version
-Assuming that the latest docker ( 17.05 or greater with multi-build support ) is installed on the host, run:
-```
-$ docker pull quay.io/chaos-kubox/krkn:latest
-$ docker run --name=kraken --net=host -v <path_to_kubeconfig>:/root/.kube/config:Z -v <path_to_kraken_config>:/root/kraken/config/config.yaml:Z -d quay.io/chaos-kubox/krkn:latest
-$ docker run --name=kraken --net=host -v <path_to_kubeconfig>:/root/.kube/config:Z -v <path_to_kraken_config>:/root/kraken/config/config.yaml:Z -v <path_to_scenarios_directory>:/root/kraken/scenarios:Z -d quay.io/chaos-kubox/krkn:latest #custom or tweaked scenario configs
-$ docker logs -f kraken
-```
+[Krkn-hub](https://github.com/krkn-chaos/krkn-hub) is a wrapper that allows running Krkn chaos scenarios via podman or docker runtime with scenario parameters/configuration defined as environment variables.
 
-Similarly, podman can be used to achieve the same:
-```
-$ podman pull quay.io/chaos-kubox/krkn
-$ podman run --name=kraken --net=host -v <path_to_kubeconfig>:/root/.kube/config:Z -v <path_to_kraken_config>:/root/kraken/config/config.yaml:Z -d quay.io/chaos-kubox/krkn:latest
-$ podman run --name=kraken --net=host -v <path_to_kubeconfig>:/root/.kube/config:Z -v <path_to_kraken_config>:/root/kraken/config/config.yaml:Z -v <path_to_scenarios_directory>:/root/kraken/scenarios:Z -d quay.io/chaos-kubox/krkn:latest #custom or tweaked scenario configs
-$ podman logs -f kraken
-```
-
-If you want to build your own kraken image see [here](https://github.com/redhat-chaos/krkn/blob/main/containers/build_own_image-README.md)
+Refer [instructions](https://github.com/krkn-chaos/krkn-hub#supported-chaos-scenarios) to get started.
 
 
-### Run Kraken as a Kubernetes deployment
-Refer [Instructions](https://github.com/redhat-chaos/krkn/blob/main/containers/README.md) on how to deploy and run Kraken as a Kubernetes/OpenShift deployment.
+### Run Kraken as a Kubernetes deployment ( unsupported option - standalone or containerized deployers are recommended )
+Refer [Instructions](https://github.com/krkn-chaos/krkn/blob/main/containers/README.md) on how to deploy and run Kraken as a Kubernetes/OpenShift deployment.
 
 
-### Deploying kraken using a helm-chart
-
-You can find on [artifacthub.io](https://artifacthub.io/packages/search?kind=0&ts_query_web=kraken) the 
-[chaos-kraken](https://artifacthub.io/packages/helm/startx/chaos-kraken) `helm-chart`
-which can be used to deploy a kraken chaos scenarios.
-
-Default configuration create the following resources :
-
-  - 1 project named **chaos-kraken**
-  - 1 scc with privileged context for kraken deployment
-  - 1 configmap with kraken 21 generic scenarios, various scripts and configuration
-  - 1 configmap with kubeconfig of the targeted cluster
-  - 1 job named kraken-test-xxx
-  - 1 service to the kraken pods
-  - 1 route to the kraken service
-
-```bash
-# Install the startx helm repository
-helm repo add startx https://startxfr.github.io/helm-repository/packages/
-# Install the kraken project
-helm install --set project.enabled=true chaos-kraken-project  startx/chaos-kraken
-# Deploy the kraken instance
-helm install \
---set kraken.enabled=true \
---set kraken.aws.credentials.region="eu-west-3" \
---set kraken.aws.credentials.key_id="AKIAXXXXXXXXXXXXXXXX" \
---set kraken.aws.credentials.secret="xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx" \
---set kraken.kubeconfig.token.server="https://api.mycluster:6443" \
---set kraken.kubeconfig.token.token="sha256~XXXXXXXXXX_PUT_YOUR_TOKEN_HERE_XXXXXXXXXXXX" \
--n chaos-kraken \
-chaos-kraken-instance startx/chaos-kraken
-```
-
 Refer to the [chaos-kraken chart manpage](https://artifacthub.io/packages/helm/startx/chaos-kraken)
 and especially the [kraken configuration values](https://artifacthub.io/packages/helm/startx/chaos-kraken#chaos-kraken-values-dictionary) 
 for details on how to configure this chart.

docs/litmus_scenarios.md

@@ -1,41 +0,0 @@
-### Litmus Scenarios
-Kraken consumes [Litmus](https://github.com/litmuschaos/litmus) under the hood for some scenarios
-
-Official Litmus documentation and specifics of Litmus resources can be found [here](https://docs.litmuschaos.io/docs/next/getstarted/)
-
-
-#### Litmus Chaos Custom Resources
-There are 3 custom resources that are created during each Litmus scenario. Below is a description of the resources:
-* ChaosEngine: A resource to link a Kubernetes application or Kubernetes node to a ChaosExperiment. ChaosEngine is watched by Litmus' Chaos-Operator which then invokes Chaos-Experiments.
-* ChaosExperiment: A resource to group the configuration parameters of a chaos experiment. ChaosExperiment CRs are created by the operator when experiments are invoked by ChaosEngine.
-* ChaosResult : A resource to hold the results of a chaos-experiment. The Chaos-exporter reads the results and exports the metrics into a configured Prometheus server.
-
-### Understanding Litmus Scenarios
-
-To run Litmus scenarios we need to apply 3 different resources/yaml files to our cluster.
-1. **Chaos experiments** contain the actual chaos details of a scenario.
-
-    i. This is installed automatically by Kraken (does not need to be specified in kraken scenario configuration).
-
-2. **Service Account**: should be created to allow chaosengine to run experiments in your application namespace. Usually it sets just enough permissions to a specific namespace to be able to run the experiment properly.
-
-    i. This can be defined using either a link to a yaml file or a downloaded file in the scenarios' folder.
-
-3. **Chaos Engine** connects the application instance to a Chaos Experiment. This is where you define the specifics of your scenario; i.e.: the node or pod name you want to cause chaos within.
-
-    i. This is a downloaded yaml file in the scenarios' folder. A full list of scenarios can be found [here](https://hub.litmuschaos.io/)
-
-**NOTE**: By default, all chaos experiments will be installed based on the version you give in the config file.
-
-Adding a new Litmus based scenario is as simple as adding references to 2 new yaml files (the Service Account and Chaos engine files for your scenario ) in the Kraken config.
-
-
-### Supported scenarios
-
-The following are the start of scenarios for which a chaos scenario config exists today.
-
-Scenario                 | Description                                                                             | Working
------------------------- |-----------------------------------------------------------------------------------------| ------------------------- |
-[Node CPU Hog](https://github.com/redhat-chaos/krkn/blob/main/scenarios/node_cpu_hog_engine.yaml)             | Chaos scenario that hogs up the CPU on a defined node for a specific amount of time.    | :heavy_check_mark:        |
-[Node Memory Hog](https://github.com/redhat-chaos/krkn/blob/main/scenarios/node_mem_engine.yaml)          | Chaos scenario that hogs up the memory on a defined node for a specific amount of time. | :heavy_check_mark:        |
-[Node IO Hog](https://github.com/redhat-chaos/krkn/blob/main/scenarios/node_io_engine.yaml)                   | Chaos scenario that hogs up the IO on a defined node for a specific amount of time.     | :heavy_check_mark:        |

docs/metrics.md

@@ -1,51 +0,0 @@
-## Scraping and storing metrics for the run
-
-There are cases where the state of the cluster and metrics on the cluster during the chaos test run need to be stored long term to review after the cluster is terminated, for example CI and automation test runs. To help with this, Kraken supports capturing metrics for the duration of the scenarios defined in the config and indexes them into Elasticsearch. The indexed metrics can be visualized with the help of Grafana.
-
-It uses [Kube-burner](https://github.com/cloud-bulldozer/kube-burner) under the hood. The metrics to capture need to be defined in a metrics profile which Kraken consumes to query prometheus ( installed by default in OpenShift ) with the start and end timestamp of the run. Each run has a unique identifier ( uuid ) and all the metrics/documents in Elasticsearch will be associated with it. The uuid is generated automatically if not set in the config. This feature can be enabled in the [config](https://github.com/redhat-chaos/krkn/blob/main/config/config.yaml) by setting the following:
-
-```
-performance_monitoring:
-    kube_burner_binary_url: "https://github.com/cloud-bulldozer/kube-burner/releases/download/v0.9.1/kube-burner-0.9.1-Linux-x86_64.tar.gz"
-    capture_metrics: True
-    config_path: config/kube_burner.yaml                  # Define the Elasticsearch url and index name in this config.
-    metrics_profile_path: config/metrics-aggregated.yaml
-    prometheus_url:                                       # The prometheus url/route is automatically obtained in case of OpenShift, please set it when the distribution is Kubernetes.
-    prometheus_bearer_token:                              # The bearer token is automatically obtained in case of OpenShift, please set it when the distribution is Kubernetes. This is needed to authenticate with prometheus.
-    uuid:                                                 # uuid for the run is generated by default if not set.
-```
-
-### Metrics profile
-A couple of [metric profiles](https://github.com/redhat-chaos/krkn/tree/main/config), [metrics.yaml](https://github.com/redhat-chaos/krkn/blob/main/config/metrics.yaml), and [metrics-aggregated.yaml](https://github.com/redhat-chaos/krkn/blob/main/config/metrics-aggregated.yaml) are shipped by default and can be tweaked to add more metrics to capture during the run. The following are the API server metrics for example:
-
-```
-metrics:
-# API server
-  - query: histogram_quantile(0.99, sum(rate(apiserver_request_duration_seconds_bucket{apiserver="kube-apiserver", verb!~"WATCH", subresource!="log"}[2m])) by (verb,resource,subresource,instance,le)) > 0
-    metricName: API99thLatency
-
-  - query: sum(irate(apiserver_request_total{apiserver="kube-apiserver",verb!="WATCH",subresource!="log"}[2m])) by (verb,instance,resource,code) > 0
-    metricName: APIRequestRate
-
-  - query: sum(apiserver_current_inflight_requests{}) by (request_kind) > 0
-    metricName: APIInflightRequests
-```
-
-### Indexing
-Define the Elasticsearch and index to store the metrics/documents in the kube_burner config:
-
-```
-global:
-  writeToFile: true
-  metricsDirectory: collected-metrics
-  measurements:
-    - name: podLatency
-      esIndex: kube-burner
-
-  indexerConfig:
-    enabled: true
-    esServers: [https://elastic.example.com:9200]
-    insecureSkipVerify: true
-    defaultIndex: kraken
-    type: elastic
-```

docs/network_chaos.md

@@ -12,9 +12,9 @@ network_chaos:                                    # Scenario to create an outage
   - "ens5"                                        # Interface name would be the Kernel host network interface name.
   execution: serial|parallel                      # Execute each of the egress options as a single scenario(parallel) or as separate scenario(serial).
   egress:
-    latency: 50ms
-    loss: 0.02                                    # percentage
-    bandwidth: 100mbit
+    latency: 500ms
+    loss: 50%                                    # percentage
+    bandwidth: 10mbit
 ```
 
 ##### Sample scenario config for ingress traffic shaping (using a plugin)
@@ -30,9 +30,9 @@ network_chaos:                                    # Scenario to create an outage
     kubeconfig_path: ~/.kube/config                 # Path to kubernetes config file. If not specified, it defaults to ~/.kube/config
     execution_type: parallel                        # Execute each of the ingress options as a single scenario(parallel) or as separate scenario(serial).
     network_params:
-        latency: 50ms
-        loss: '0.02'
-        bandwidth: 100mbit
+        latency: 500ms
+        loss: '50%'
+        bandwidth: 10mbit
     wait_duration: 120
     test_duration: 60
   '''

docs/node_scenarios.md

@@ -76,6 +76,42 @@ How to set up Alibaba cli to run node scenarios is defined [here](cloud_setup.md
 #### VMware
 How to set up VMware vSphere to run node scenarios is defined [here](cloud_setup.md#vmware)
 
+This cloud type uses a different configuration style, see actions below and [example config file](../scenarios/openshift/vmware_node_scenarios.yml)
+
+*vmware-node-terminate, vmware-node-reboot, vmware-node-stop, vmware-node-start*
+
+#### IBMCloud
+How to set up IBMCloud to run node scenarios is defined [here](cloud_setup.md#ibmcloud)
+
+This cloud type uses a different configuration style, see actions below and [example config file](../scenarios/openshift/ibmcloud_node_scenarios.yml)
+
+*ibmcloud-node-terminate, ibmcloud-node-reboot, ibmcloud-node-stop, ibmcloud-node-start
+*
+
+
+#### IBMCloud and Vmware example 
+
+
+```
+- id: ibmcloud-node-stop
+  config:
+    name: "<node_name>"        
+    label_selector: "node-role.kubernetes.io/worker"    # When node_name is not specified, a node with matching label_selector is selected for node chaos scenario injection 
+    runs: 1                             # Number of times to inject each scenario under actions (will perform on same node each time)                                                           
+    instance_count: 1                   # Number of nodes to perform action/select that match the label selector                                             
+    timeout: 30                        # Duration to wait for completion of node scenario injection
+    skip_openshift_checks: False       # Set to True if you don't want to wait for the status of the nodes to change on OpenShift before passing the scenario 
+- id: ibmcloud-node-start
+  config:
+    name: "<node_name>" #Same name as before       
+    label_selector: "node-role.kubernetes.io/worker"    # When node_name is not specified, a node with matching label_selector is selected for node chaos scenario injection 
+    runs: 1                             # Number of times to inject each scenario under actions (will perform on same node each time)                                                           
+    instance_count: 1                   # Number of nodes to perform action/select that match the label selector                                             
+    timeout: 30                        # Duration to wait for completion of node scenario injection
+    skip_openshift_checks: False       # Set to True if you don't want to wait for the status of the nodes to change on OpenShift before passing the scenario 
+    ```
+
+
 
 #### General
 

docs/pod_network_scenarios.md

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

docs/service_disruption_scenarios.md

@@ -1,6 +1,6 @@
-###  Delete Namespace Scenarios
+###  Service Disruption Scenarios (Previously Delete Namespace Scenario)
 
-Using this type of scenario configuration one is able to delete a specific namespace, or a namespace matching a certain regex string.
+Using this type of scenario configuration one is able to delete crucial objects in a specific namespace, or a namespace matching a certain regex string.
 
 Configuration Options:
 
@@ -16,7 +16,7 @@ Set to '^.*$' and label_selector to "" to randomly select any namespace in your
 
 **sleep:** Number of seconds to wait between each iteration/count of killing namespaces. Defaults to 10 seconds if not set
 
-Refer to [namespace_scenarios_example](https://github.com/redhat-chaos/krkn/blob/main/scenarios/regex_namespace.yaml) config file.
+Refer to [namespace_scenarios_example](https://github.com/krkn-chaos/krkn/blob/main/scenarios/regex_namespace.yaml) config file.
 
 ```
 scenarios:
@@ -27,12 +27,20 @@ scenarios:
   sleep: 15
 ```
 
-**NOTE:** Many openshift namespaces have finalizers built that protect the namespace from being fully deleted: see documentation [here](https://kubernetes.io/blog/2021/05/14/using-finalizers-to-control-deletion/).
-The namespaces that do have finalizers enabled will be in left in a terminating state but all the pods running on that namespace will get deleted.
+
+### Steps
+
+This scenario will select a namespace (or multiple) dependent on the configuration and will kill all of the below object types in that namespace and will wait for them to be Running in the post action 
+1. Services 
+2. Daemonsets
+3. Statefulsets
+4. Replicasets
+5. Deployments 
+
 
 #### Post Action
 
-In all scenarios we do a post chaos check to wait and verify the specific component.
+We do a post chaos check to wait and verify the specific objects in each namespace are Ready
 
 Here there are two options:
 
@@ -47,8 +55,8 @@ See [scenarios/post_action_namespace.py](https://github.com/cloud-bulldozer/krak
 ```
 
 
-2. Allow kraken to wait and check the killed namespaces become 'Active' again. Kraken keeps a list of the specific
-namespaces that were killed to verify all that were affected recover properly.
+1. Allow kraken to wait and check all killed objects in the namespaces become 'Running' again. Kraken keeps a list of the specific
+objects in namespaces that were killed to verify all that were affected recover properly.
 
 ```
 wait_time: <seconds to wait for namespace to recover>

docs/time_scenarios.md

@@ -16,7 +16,7 @@ Configuration Options:
 
 **object_name:** List of the names of pods or nodes you want to skew.
 
-Refer to [time_scenarios_example](https://github.com/redhat-chaos/krkn/blob/main/scenarios/time_scenarios_example.yml) config file.
+Refer to [time_scenarios_example](https://github.com/krkn-chaos/krkn/blob/main/scenarios/time_scenarios_example.yml) config file.
 
 ```
 time_scenarios:

kraken/application_outage/actions.py

@@ -4,25 +4,43 @@ import time
 import kraken.cerberus.setup as cerberus
 from jinja2 import Template
 import kraken.invoke.command as runcommand
+from krkn_lib.telemetry.k8s import KrknTelemetryKubernetes
+from krkn_lib.models.telemetry import ScenarioTelemetry
+from krkn_lib.utils.functions import get_yaml_item_value, log_exception
 
 
 # Reads the scenario config, applies and deletes a network policy to
 # block the traffic for the specified duration
-def run(scenarios_list, config, wait_duration):
+def run(scenarios_list, config, wait_duration, telemetry: KrknTelemetryKubernetes) -> (list[str], list[ScenarioTelemetry]):
     failed_post_scenarios = ""
+    scenario_telemetries: list[ScenarioTelemetry] = []
+    failed_scenarios = []
     for app_outage_config in scenarios_list:
+        scenario_telemetry = ScenarioTelemetry()
+        scenario_telemetry.scenario = app_outage_config
+        scenario_telemetry.startTimeStamp = time.time()
+        telemetry.set_parameters_base64(scenario_telemetry, app_outage_config)
         if len(app_outage_config) > 1:
-            with open(app_outage_config, "r") as f:
-                app_outage_config_yaml = yaml.full_load(f)
-                scenario_config = app_outage_config_yaml["application_outage"]
-                pod_selector = scenario_config.get("pod_selector", "{}")
-                traffic_type = scenario_config.get("block", "[Ingress, Egress]")
-                namespace = scenario_config.get("namespace", "")
-                duration = scenario_config.get("duration", 60)
+            try:
+                with open(app_outage_config, "r") as f:
+                    app_outage_config_yaml = yaml.full_load(f)
+                    scenario_config = app_outage_config_yaml["application_outage"]
+                    pod_selector = get_yaml_item_value(
+                        scenario_config, "pod_selector", "{}"
+                    )
+                    traffic_type = get_yaml_item_value(
+                        scenario_config, "block", "[Ingress, Egress]"
+                    )
+                    namespace = get_yaml_item_value(
+                        scenario_config, "namespace", ""
+                    )
+                    duration = get_yaml_item_value(
+                        scenario_config, "duration", 60
+                    )
 
-                start_time = int(time.time())
+                    start_time = int(time.time())
 
-                network_policy_template = """---
+                    network_policy_template = """---
 apiVersion: networking.k8s.io/v1
 kind: NetworkPolicy
 metadata:
@@ -31,28 +49,38 @@ spec:
   podSelector:
     matchLabels: {{ pod_selector }}
   policyTypes: {{ traffic_type }}
-                """
-                t = Template(network_policy_template)
-                rendered_spec = t.render(pod_selector=pod_selector, traffic_type=traffic_type)
-                # Write the rendered template to a file
-                with open("kraken_network_policy.yaml", "w") as f:
-                    f.write(rendered_spec)
-                # Block the traffic by creating network policy
-                logging.info("Creating the network policy")
-                runcommand.invoke(
-                    "kubectl create -f %s -n %s --validate=false" % ("kraken_network_policy.yaml", namespace)
-                )
+                    """
+                    t = Template(network_policy_template)
+                    rendered_spec = t.render(pod_selector=pod_selector, traffic_type=traffic_type)
+                    # Write the rendered template to a file
+                    with open("kraken_network_policy.yaml", "w") as f:
+                        f.write(rendered_spec)
+                    # Block the traffic by creating network policy
+                    logging.info("Creating the network policy")
+                    runcommand.invoke(
+                        "kubectl create -f %s -n %s --validate=false" % ("kraken_network_policy.yaml", namespace)
+                    )
 
-                # wait for the specified duration
-                logging.info("Waiting for the specified duration in the config: %s" % (duration))
-                time.sleep(duration)
+                    # wait for the specified duration
+                    logging.info("Waiting for the specified duration in the config: %s" % (duration))
+                    time.sleep(duration)
 
-                # unblock the traffic by deleting the network policy
-                logging.info("Deleting the network policy")
-                runcommand.invoke("kubectl delete -f %s -n %s" % ("kraken_network_policy.yaml", namespace))
+                    # unblock the traffic by deleting the network policy
+                    logging.info("Deleting the network policy")
+                    runcommand.invoke("kubectl delete -f %s -n %s" % ("kraken_network_policy.yaml", namespace))
 
-                logging.info("End of scenario. Waiting for the specified duration: %s" % (wait_duration))
-                time.sleep(wait_duration)
+                    logging.info("End of scenario. Waiting for the specified duration: %s" % (wait_duration))
+                    time.sleep(wait_duration)
+
+                    end_time = int(time.time())
+                    cerberus.publish_kraken_status(config, failed_post_scenarios, start_time, end_time)
+            except Exception as e :
+                scenario_telemetry.exitStatus = 1
+                failed_scenarios.append(app_outage_config)
+                log_exception(app_outage_config)
+            else:
+                scenario_telemetry.exitStatus = 0
+            scenario_telemetry.endTimeStamp = time.time()
+            scenario_telemetries.append(scenario_telemetry)
+    return failed_scenarios, scenario_telemetries
 
-                end_time = int(time.time())
-                cerberus.publish_kraken_status(config, failed_post_scenarios, start_time, end_time)

kraken/arcaflow_plugin/__init__.py

@@ -0,0 +1,2 @@
+from .arcaflow_plugin import *
+from .context_auth import ContextAuth

kraken/arcaflow_plugin/arcaflow_plugin.py

@@ -0,0 +1,178 @@
+import time
+import arcaflow
+import os
+import yaml
+import logging
+from pathlib import Path
+from typing import List
+from .context_auth import ContextAuth
+from krkn_lib.telemetry.k8s import KrknTelemetryKubernetes
+from krkn_lib.models.telemetry import ScenarioTelemetry
+
+
+def run(scenarios_list: List[str], kubeconfig_path: str, telemetry: KrknTelemetryKubernetes) -> (list[str], list[ScenarioTelemetry]):
+    scenario_telemetries: list[ScenarioTelemetry] = []
+    failed_post_scenarios = []
+    for scenario in scenarios_list:
+        scenario_telemetry = ScenarioTelemetry()
+        scenario_telemetry.scenario = scenario
+        scenario_telemetry.startTimeStamp = time.time()
+        telemetry.set_parameters_base64(scenario_telemetry,scenario)
+        engine_args = build_args(scenario)
+        status_code = run_workflow(engine_args, kubeconfig_path)
+        scenario_telemetry.endTimeStamp = time.time()
+        scenario_telemetry.exitStatus = status_code
+        scenario_telemetries.append(scenario_telemetry)
+        if status_code != 0:
+            failed_post_scenarios.append(scenario)
+    return failed_post_scenarios, scenario_telemetries
+
+
+def run_workflow(engine_args: arcaflow.EngineArgs, kubeconfig_path: str) -> int:
+    set_arca_kubeconfig(engine_args, kubeconfig_path)
+    exit_status = arcaflow.run(engine_args)
+    return exit_status
+
+
+def build_args(input_file: str) -> arcaflow.EngineArgs:
+    """sets the kubeconfig parsed by setArcaKubeConfig as an input to the arcaflow workflow"""
+    context = Path(input_file).parent
+    workflow = "{}/workflow.yaml".format(context)
+    config = "{}/config.yaml".format(context)
+    if not os.path.exists(context):
+        raise Exception(
+            "context folder for arcaflow workflow not found: {}".format(
+                context)
+        )
+    if not os.path.exists(input_file):
+        raise Exception(
+            "input file for arcaflow workflow not found: {}".format(input_file))
+    if not os.path.exists(workflow):
+        raise Exception(
+            "workflow file for arcaflow workflow not found: {}".format(
+                workflow)
+        )
+    if not os.path.exists(config):
+        raise Exception(
+            "configuration file for arcaflow workflow not found: {}".format(
+                config)
+        )
+
+    engine_args = arcaflow.EngineArgs()
+    engine_args.context = context
+    engine_args.config = config
+    engine_args.input = input_file
+    return engine_args
+
+
+def set_arca_kubeconfig(engine_args: arcaflow.EngineArgs, kubeconfig_path: str):
+
+    context_auth = ContextAuth()
+    if not os.path.exists(kubeconfig_path):
+        raise Exception("kubeconfig not found in {}".format(kubeconfig_path))
+
+    with open(kubeconfig_path, "r") as stream:
+        try:
+            kubeconfig = yaml.safe_load(stream)
+            context_auth.fetch_auth_data(kubeconfig)
+        except Exception as e:
+            logging.error("impossible to read kubeconfig file in: {}".format(
+                    kubeconfig_path))
+            raise e
+
+    kubeconfig_str = set_kubeconfig_auth(kubeconfig, context_auth)
+
+    with open(engine_args.input, "r") as stream:
+        input_file = yaml.safe_load(stream)
+        if "input_list" in input_file and isinstance(input_file["input_list"],list):
+            for index, _ in enumerate(input_file["input_list"]):
+                if isinstance(input_file["input_list"][index], dict):
+                    input_file["input_list"][index]["kubeconfig"] = kubeconfig_str
+        else:
+            input_file["kubeconfig"] = kubeconfig_str
+        stream.close()
+    with open(engine_args.input, "w") as stream:
+        yaml.safe_dump(input_file, stream)
+
+    with open(engine_args.config, "r") as stream:
+        config_file = yaml.safe_load(stream)
+    if config_file["deployers"]["image"]["deployer_name"] == "kubernetes":
+        kube_connection = set_kubernetes_deployer_auth(config_file["deployers"]["image"]["connection"], context_auth)
+        config_file["deployers"]["image"]["connection"]=kube_connection
+        with open(engine_args.config, "w") as stream:
+            yaml.safe_dump(config_file, stream,explicit_start=True, width=4096)
+
+
+def set_kubernetes_deployer_auth(deployer: any, context_auth: ContextAuth) -> any:
+    if context_auth.clusterHost is not None :
+        deployer["host"] = context_auth.clusterHost
+    if context_auth.clientCertificateData is not None :
+        deployer["cert"] = context_auth.clientCertificateData
+    if context_auth.clientKeyData is not None:
+        deployer["key"] = context_auth.clientKeyData
+    if context_auth.clusterCertificateData is not None:
+        deployer["cacert"] = context_auth.clusterCertificateData
+    if context_auth.username is not None:
+        deployer["username"] = context_auth.username
+    if context_auth.password is not None:
+        deployer["password"] = context_auth.password
+    if context_auth.bearerToken is not None:
+        deployer["bearerToken"] = context_auth.bearerToken
+    return deployer
+
+
+def set_kubeconfig_auth(kubeconfig: any, context_auth: ContextAuth) -> str:
+    """
+    Builds an arcaflow-compatible kubeconfig representation and returns it as a string.
+    In order to run arcaflow plugins in kubernetes/openshift the kubeconfig must contain client certificate/key
+    and server certificate base64 encoded within the kubeconfig file itself in *-data fields. That is not always the
+    case, infact kubeconfig may contain filesystem paths to those files, this function builds an arcaflow-compatible
+    kubeconfig file and returns it as a string that can be safely included in input.yaml 
+    """
+
+    if "current-context" not in kubeconfig.keys():
+        raise Exception(
+            "invalid kubeconfig file, impossible to determine current-context"
+        )
+    user_id = None
+    cluster_id = None
+    user_name = None
+    cluster_name = None
+    current_context = kubeconfig["current-context"]
+    for context in kubeconfig["contexts"]:
+        if context["name"] == current_context:
+            user_name = context["context"]["user"]
+            cluster_name = context["context"]["cluster"]
+    if user_name is None:
+        raise Exception(
+            "user not set for context {} in kubeconfig file".format(current_context)
+        )
+    if cluster_name is None:
+        raise Exception(
+            "cluster not set for context {} in kubeconfig file".format(current_context)
+        )
+
+    for index, user in enumerate(kubeconfig["users"]):
+        if user["name"] == user_name:
+            user_id = index
+    for index, cluster in enumerate(kubeconfig["clusters"]):
+        if cluster["name"] == cluster_name:
+            cluster_id = index
+
+    if cluster_id is None:
+        raise Exception(
+            "no cluster {} found in kubeconfig users".format(cluster_name)
+        )
+    if "client-certificate" in kubeconfig["users"][user_id]["user"]:
+        kubeconfig["users"][user_id]["user"]["client-certificate-data"] = context_auth.clientCertificateDataBase64
+        del kubeconfig["users"][user_id]["user"]["client-certificate"]
+
+    if "client-key" in kubeconfig["users"][user_id]["user"]:
+        kubeconfig["users"][user_id]["user"]["client-key-data"] = context_auth.clientKeyDataBase64
+        del kubeconfig["users"][user_id]["user"]["client-key"]
+
+    if "certificate-authority" in kubeconfig["clusters"][cluster_id]["cluster"]:
+        kubeconfig["clusters"][cluster_id]["cluster"]["certificate-authority-data"] = context_auth.clusterCertificateDataBase64
+        del kubeconfig["clusters"][cluster_id]["cluster"]["certificate-authority"]
+    kubeconfig_str = yaml.dump(kubeconfig)
+    return kubeconfig_str

kraken/arcaflow_plugin/context_auth.py

@@ -0,0 +1,142 @@
+import yaml
+import os
+import base64
+
+
+class ContextAuth:
+    clusterCertificate: str = None
+    clusterCertificateData: str = None
+    clusterHost: str = None
+    clientCertificate: str = None
+    clientCertificateData: str = None
+    clientKey: str = None
+    clientKeyData: str = None
+    clusterName: str = None
+    username: str = None
+    password: str = None
+    bearerToken: str = None
+    # TODO: integrate in krkn-lib-kubernetes in the next iteration
+
+    @property
+    def clusterCertificateDataBase64(self):
+        if self.clusterCertificateData is not None:
+            return base64.b64encode(bytes(self.clusterCertificateData,'utf8')).decode("ascii")
+        return
+
+    @property
+    def clientCertificateDataBase64(self):
+        if self.clientCertificateData is not None:
+            return base64.b64encode(bytes(self.clientCertificateData,'utf8')).decode("ascii")
+        return
+
+    @property
+    def clientKeyDataBase64(self):
+        if self.clientKeyData is not None:
+            return base64.b64encode(bytes(self.clientKeyData,"utf-8")).decode("ascii")
+        return
+
+
+
+    def fetch_auth_data(self, kubeconfig: any):
+        context_username = None
+        current_context = kubeconfig["current-context"]
+        if current_context is None:
+            raise Exception("no current-context found in kubeconfig")
+
+        for context in kubeconfig["contexts"]:
+            if context["name"] == current_context:
+                context_username = context["context"]["user"]
+                self.clusterName = context["context"]["cluster"]
+        if context_username is None:
+            raise Exception("user not found for context {0}".format(current_context))
+        if self.clusterName is None:
+            raise Exception("cluster not found for context {0}".format(current_context))
+        cluster_id = None
+        user_id = None
+        for index, user in enumerate(kubeconfig["users"]):
+            if user["name"] == context_username:
+                user_id = index
+        if user_id is None :
+            raise Exception("user {0} not found in kubeconfig users".format(context_username))
+
+        for index, cluster in enumerate(kubeconfig["clusters"]):
+            if cluster["name"] == self.clusterName:
+                cluster_id = index
+
+        if cluster_id is None:
+            raise Exception(
+                "no cluster {} found in kubeconfig users".format(self.clusterName)
+            )
+
+        user = kubeconfig["users"][user_id]["user"]
+        cluster = kubeconfig["clusters"][cluster_id]["cluster"]
+        # sets cluster api URL
+        self.clusterHost = cluster["server"]
+        # client certificates
+
+        if "client-key" in user:
+            try:
+                self.clientKey = user["client-key"]
+                self.clientKeyData = self.read_file(user["client-key"])
+            except Exception as e:
+                raise e
+
+        if "client-key-data" in user:
+            try:
+                self.clientKeyData = base64.b64decode(user["client-key-data"]).decode('utf-8')
+            except Exception as e:
+                raise Exception("impossible to decode client-key-data")
+
+        if "client-certificate" in user:
+            try:
+                self.clientCertificate = user["client-certificate"]
+                self.clientCertificateData = self.read_file(user["client-certificate"])
+            except Exception as e:
+                raise e
+
+        if "client-certificate-data" in user:
+            try:
+                self.clientCertificateData = base64.b64decode(user["client-certificate-data"]).decode('utf-8')
+            except Exception as e:
+                raise Exception("impossible to decode client-certificate-data")
+
+        # cluster certificate authority
+
+        if "certificate-authority" in cluster:
+            try:
+                self.clusterCertificate = cluster["certificate-authority"]
+                self.clusterCertificateData = self.read_file(cluster["certificate-authority"])
+            except Exception as e:
+                raise e
+
+        if "certificate-authority-data" in cluster:
+            try:
+                self.clusterCertificateData = base64.b64decode(cluster["certificate-authority-data"]).decode('utf-8')
+            except Exception as e:
+                raise Exception("impossible to decode certificate-authority-data")
+
+        if "username" in user:
+            self.username = user["username"]
+
+        if "password" in user:
+            self.password = user["password"]
+
+        if "token" in user:
+            self.bearerToken = user["token"]
+
+    def read_file(self, filename:str) -> str:
+        if not os.path.exists(filename):
+            raise Exception("file not found {0} ".format(filename))
+        with open(filename, "rb") as file_stream:
+            return file_stream.read().decode('utf-8')
+
+
+
+
+
+
+
+
+
+
+

kraken/arcaflow_plugin/fixtures/ca.crt

@@ -0,0 +1,19 @@
+-----BEGIN CERTIFICATE-----
+MIIDBjCCAe6gAwIBAgIBATANBgkqhkiG9w0BAQsFADAVMRMwEQYDVQQDEwptaW5p
+a3ViZUNBMB4XDTIzMDMxMzE1NDAxM1oXDTMzMDMxMTE1NDAxM1owFTETMBEGA1UE
+AxMKbWluaWt1YmVDQTCCASIwDQYJKoZIhvcNAQEBBQADggEPADCCAQoCggEBAMnz
+U/gIbJBRGOgNYVKX2fV03ANOwnM4VjquR28QMAdxURqgOFZ6IxYNysHEyxxE9I+I
+DAm9hi4vQPbOX7FlxUezuzw+ExEfa6RRJ+n+AGJOV1lezCVph6OaJxB1+L1UqaDZ
+eM3B4cUf/iCc5Y4bs927+CBG3MJL/jmCVPCO+MiSn/l73PXSFNJAYMvRj42zkXqD
+CVG9CwY2vWgZnnzl01l7jNGtie871AmV2uqKakJrQ2ILhD+8fZk4jE5JBDTCZnqQ
+pXIc+vERNKLUS8cvjO6Ux8dMv/Z7+xonpXOU59LlpUdHWP9jgCvMTwiOriwqGjJ+
+pQJWpX9Dm+oxJiVOJzsCAwEAAaNhMF8wDgYDVR0PAQH/BAQDAgKkMB0GA1UdJQQW
+MBQGCCsGAQUFBwMCBggrBgEFBQcDATAPBgNVHRMBAf8EBTADAQH/MB0GA1UdDgQW
+BBQU9pDMtbayJdNM6bp0IG8dcs15qTANBgkqhkiG9w0BAQsFAAOCAQEAtl9TVKPA
+hTnPODqv0AGTqreS9kLg4WUUjZRaPUkPWmtCoTh2Yf55nRWdHOHeZnCWDSg24x42
+lpt+13IdqKew1RKTpKCTkicMFi090A01bYu/w39Cm6nOAA5h8zkgSkV5czvQotuV
+SoN2vB+nbuY28ah5PkdqjMHEZbNwa59cgEke8wB1R1DWFQ/pqflrH2v9ACAuY+5Q
+i673tA6CXrb1YfaCQnVBzcfvjGS1MqShPKpOLMF+/GccPczNimaBxMnKvYLvf3pN
+qEUrJC00mAcein8HmxR2Xz8wredbMUUyrQxW29pZJwfGE5GU0olnlsA0lZLbTwio
+xoolo5y+fsK/dA==
+-----END CERTIFICATE-----

kraken/arcaflow_plugin/fixtures/client.crt

@@ -0,0 +1,19 @@
+-----BEGIN CERTIFICATE-----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+-----END CERTIFICATE-----

kraken/arcaflow_plugin/fixtures/client.key

@@ -0,0 +1,27 @@
+-----BEGIN RSA PRIVATE KEY-----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+-----END RSA PRIVATE KEY-----

kraken/arcaflow_plugin/test_context_auth.py

@@ -0,0 +1,100 @@
+import os
+import unittest
+
+from context_auth import ContextAuth
+
+
+class TestCurrentContext(unittest.TestCase):
+
+    def get_kubeconfig_with_data(self) -> str:
+        """
+        This function returns a test kubeconfig file as a string.
+    
+        :return: a test kubeconfig file in string format (for unit testing purposes)
+        """  # NOQA
+        return """apiVersion: v1
+clusters:
+- cluster:
+    certificate-authority-data: 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
+    server: https://127.0.0.1:6443
+  name: default
+contexts:
+- context:
+    cluster: default
+    namespace: default
+    user: testuser
+  name: default
+current-context: default
+kind: Config
+preferences: {}
+users:
+- name: testuser
+  user:
+    client-certificate-data: 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
+    client-key-data: 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
+    username: testuser
+    password: testpassword
+    token: sha256~fFyEqjf1xxFMO0tbEyGRvWeNOd7QByuEgS4hyEq_A9o
+    """  # NOQA
+
+    def get_kubeconfig_with_paths(self) -> str:
+        """
+        This function returns a test kubeconfig file as a string.
+
+        :return: a test kubeconfig file in string format (for unit testing purposes)
+        """  # NOQA
+        return """apiVersion: v1
+clusters:
+- cluster:
+    certificate-authority: fixtures/ca.crt
+    server: https://127.0.0.1:6443
+  name: default
+contexts:
+- context:
+    cluster: default
+    namespace: default
+    user: testuser
+  name: default
+current-context: default
+kind: Config
+preferences: {}
+users:
+- name: testuser
+  user:
+    client-certificate: fixtures/client.crt
+    client-key: fixtures/client.key
+    username: testuser
+    password: testpassword
+    token: sha256~fFyEqjf1xxFMO0tbEyGRvWeNOd7QByuEgS4hyEq_A9o
+    """  # NOQA
+
+    def test_current_context(self):
+        cwd = os.getcwd()
+        current_context_data = ContextAuth()
+        current_context_data.fetch_auth_data(self.get_kubeconfig_with_data())
+        self.assertIsNotNone(current_context_data.clusterCertificateData)
+        self.assertIsNotNone(current_context_data.clientCertificateData)
+        self.assertIsNotNone(current_context_data.clientKeyData)
+        self.assertIsNotNone(current_context_data.username)
+        self.assertIsNotNone(current_context_data.password)
+        self.assertIsNotNone(current_context_data.bearerToken)
+        self.assertIsNotNone(current_context_data.clusterHost)
+
+        current_context_no_data = ContextAuth()
+        current_context_no_data.fetch_auth_data(self.get_kubeconfig_with_paths())
+        self.assertIsNotNone(current_context_no_data.clusterCertificate)
+        self.assertIsNotNone(current_context_no_data.clusterCertificateData)
+        self.assertIsNotNone(current_context_no_data.clientCertificate)
+        self.assertIsNotNone(current_context_no_data.clientCertificateData)
+        self.assertIsNotNone(current_context_no_data.clientKey)
+        self.assertIsNotNone(current_context_no_data.clientKeyData)
+        self.assertIsNotNone(current_context_no_data.username)
+        self.assertIsNotNone(current_context_no_data.password)
+        self.assertIsNotNone(current_context_no_data.bearerToken)
+        self.assertIsNotNone(current_context_data.clusterHost)
+
+
+
+
+
+

kraken/chaos_recommender/__init__.py

@@ -0,0 +1,3 @@
+from .analysis import *
+from .kraken_tests import *
+from .prometheus import *

kraken/chaos_recommender/analysis.py

@@ -0,0 +1,109 @@
+import logging
+
+import pandas as pd
+import kraken.chaos_recommender.kraken_tests as kraken_tests
+import time
+
+KRAKEN_TESTS_PATH = "./kraken_chaos_tests.txt"
+
+
+# Placeholder, this should be done with topology
+def return_critical_services():
+    return ["web", "cart"]
+
+
+def load_telemetry_data(file_path):
+    data = pd.read_csv(file_path, delimiter=r"\s+")
+    return data
+
+
+def calculate_zscores(data):
+    zscores = pd.DataFrame()
+    zscores["Service"] = data["service"]
+    zscores["CPU"] = (data["CPU"] - data["CPU"].mean()) / data["CPU"].std()
+    zscores["Memory"] = (data["MEM"] - data["MEM"].mean()) / data["MEM"].std()
+    zscores["Network"] = (data["NETWORK"] - data["NETWORK"].mean()) / data["NETWORK"].std()
+    return zscores
+
+
+def identify_outliers(data, threshold):
+    outliers_cpu = data[data["CPU"] > threshold]["Service"].tolist()
+    outliers_memory = data[data["Memory"] > threshold]["Service"].tolist()
+    outliers_network = data[data["Network"] > threshold]["Service"].tolist()
+
+    return outliers_cpu, outliers_memory, outliers_network
+
+
+def get_services_above_heatmap_threshold(dataframe, cpu_threshold, mem_threshold):
+    # Filter the DataFrame based on CPU_HEATMAP and MEM_HEATMAP thresholds
+    filtered_df = dataframe[((dataframe['CPU']/dataframe['CPU_LIMITS']) > cpu_threshold)]
+    # Get the lists of services
+    cpu_services = filtered_df['service'].tolist()
+
+    filtered_df = dataframe[((dataframe['MEM']/dataframe['MEM_LIMITS']) > mem_threshold)]
+    mem_services = filtered_df['service'].tolist()
+
+    return cpu_services, mem_services
+
+
+def analysis(file_path, chaos_tests_config, threshold, heatmap_cpu_threshold, heatmap_mem_threshold):
+    # Load the telemetry data from file
+    logging.info("Fetching the Telemetry data")
+    data = load_telemetry_data(file_path)
+
+    # Calculate Z-scores for CPU, Memory, and Network columns
+    zscores = calculate_zscores(data)
+
+    # Identify outliers
+    logging.info("Identifying outliers")
+    outliers_cpu, outliers_memory, outliers_network = identify_outliers(zscores, threshold)
+    cpu_services, mem_services = get_services_above_heatmap_threshold(data, heatmap_cpu_threshold, heatmap_mem_threshold)
+
+    analysis_data = analysis_json(outliers_cpu, outliers_memory,
+                                  outliers_network, cpu_services,
+                                  mem_services, chaos_tests_config)
+
+    if not cpu_services:
+        logging.info("There are no services that are using significant CPU compared to their assigned limits (infinite in case no limits are set).")
+    if not mem_services:
+        logging.info("There are no services that are using significant MEMORY compared to their assigned limits (infinite in case no limits are set).")
+    time.sleep(2)
+
+    logging.info("Please check data in utilisation.txt for further analysis")
+
+    return analysis_data
+
+
+def analysis_json(outliers_cpu, outliers_memory, outliers_network,
+                  cpu_services, mem_services, chaos_tests_config):
+
+    profiling = {
+        "cpu_outliers": outliers_cpu,
+        "memory_outliers": outliers_memory,
+        "network_outliers": outliers_network
+    }
+
+    heatmap = {
+        "services_with_cpu_heatmap_above_threshold": cpu_services,
+        "services_with_mem_heatmap_above_threshold": mem_services
+    }
+
+    recommendations = {}
+
+    if cpu_services:
+        cpu_recommend = {"services": cpu_services,
+                         "tests": chaos_tests_config['CPU']}
+        recommendations["cpu_services_recommendations"] = cpu_recommend
+
+    if mem_services:
+        mem_recommend = {"services": mem_services,
+                         "tests": chaos_tests_config['MEM']}
+        recommendations["mem_services_recommendations"] = mem_recommend
+
+    if outliers_network:
+        outliers_network_recommend = {"outliers_networks": outliers_network,
+                                      "tests": chaos_tests_config['NETWORK']}
+        recommendations["outliers_network_recommendations"] = (
+            outliers_network_recommend)
+
+    return [profiling, heatmap, recommendations]

kraken/chaos_recommender/kraken_tests.py

@@ -0,0 +1,30 @@
+def get_entries_by_category(filename, category):
+    # Read the file
+    with open(filename, 'r') as file:
+        content = file.read()
+
+    # Split the content into sections based on the square brackets
+    sections = content.split('\n\n')
+
+    # Define the categories
+    valid_categories = ['CPU', 'NETWORK', 'MEM', 'GENERIC']
+
+    # Validate the provided category
+    if category not in valid_categories:
+        return []
+
+    # Find the section corresponding to the specified category
+    target_section = None
+    for section in sections:
+        if section.startswith(f"[{category}]"):
+            target_section = section
+            break
+
+    # If the category section was not found, return an empty list
+    if target_section is None:
+        return []
+
+    # Extract the entries from the category section
+    entries = [entry.strip() for entry in target_section.split('\n') if entry and not entry.startswith('[')]
+
+    return entries

kraken/chaos_recommender/prometheus.py

@@ -0,0 +1,94 @@
+import logging
+
+from prometheus_api_client import PrometheusConnect
+import pandas as pd
+import urllib3
+
+
+saved_metrics_path = "./utilisation.txt"
+
+
+def convert_data_to_dataframe(data, label):
+    df = pd.DataFrame()
+    df['service'] = [item['metric']['pod'] for item in data]
+    df[label] = [item['value'][1] for item in data]
+
+    return df
+
+
+def convert_data(data, service):
+
+    result = {}
+    for entry in data:
+        pod_name = entry['metric']['pod']
+        value = entry['value'][1]
+        result[pod_name] = value
+    return result.get(service, '100000000000') # for those pods whose limits are not defined they can take as much resources, there assigning a very high value
+
+
+def save_utilization_to_file(cpu_data, cpu_limits_result, mem_data, mem_limits_result, network_data, filename):
+    df_cpu = convert_data_to_dataframe(cpu_data, "CPU")
+    merged_df = pd.DataFrame(columns=['service','CPU','CPU_LIMITS','MEM','MEM_LIMITS','NETWORK'])
+    services = df_cpu.service.unique()
+    logging.info(services)
+
+    for s in services:
+
+        new_row_df = pd.DataFrame( {"service": s, "CPU" : convert_data(cpu_data, s),
+                    "CPU_LIMITS" : convert_data(cpu_limits_result, s),
+                    "MEM" : convert_data(mem_data, s), "MEM_LIMITS" : convert_data(mem_limits_result, s),
+                    "NETWORK" : convert_data(network_data, s)}, index=[0])
+        merged_df = pd.concat([merged_df, new_row_df], ignore_index=True)
+
+    # Convert columns to string
+    merged_df['CPU'] = merged_df['CPU'].astype(str)
+    merged_df['MEM'] = merged_df['MEM'].astype(str)
+    merged_df['CPU_LIMITS'] = merged_df['CPU_LIMITS'].astype(str)
+    merged_df['MEM_LIMITS'] = merged_df['MEM_LIMITS'].astype(str)
+    merged_df['NETWORK'] = merged_df['NETWORK'].astype(str)
+
+    # Extract integer part before the decimal point
+    merged_df['CPU'] = merged_df['CPU'].str.split('.').str[0]
+    merged_df['MEM'] = merged_df['MEM'].str.split('.').str[0]
+    merged_df['CPU_LIMITS'] = merged_df['CPU_LIMITS'].str.split('.').str[0]
+    merged_df['MEM_LIMITS'] = merged_df['MEM_LIMITS'].str.split('.').str[0]
+    merged_df['NETWORK'] = merged_df['NETWORK'].str.split('.').str[0]
+
+    merged_df.to_csv(filename, sep='\t', index=False)
+
+
+def fetch_utilization_from_prometheus(prometheus_endpoint, auth_token, namespace, scrape_duration):
+    urllib3.disable_warnings()
+    prometheus = PrometheusConnect(url=prometheus_endpoint, headers={'Authorization':'Bearer {}'.format(auth_token)}, disable_ssl=True)
+
+    # Fetch CPU utilization
+    logging.info("Fetching utilization")
+    cpu_query = 'sum (rate (container_cpu_usage_seconds_total{image!="", namespace="%s"}[%s])) by (pod) *1000' % (namespace,scrape_duration)
+    cpu_result = prometheus.custom_query(cpu_query)
+
+    cpu_limits_query = '(sum by (pod) (kube_pod_container_resource_limits{resource="cpu", namespace="%s"}))*1000' %(namespace)
+    cpu_limits_result = prometheus.custom_query(cpu_limits_query)
+
+    mem_query = 'sum by (pod) (avg_over_time(container_memory_usage_bytes{image!="", namespace="%s"}[%s]))' % (namespace, scrape_duration)
+    mem_result = prometheus.custom_query(mem_query)
+
+    mem_limits_query = 'sum by (pod) (kube_pod_container_resource_limits{resource="memory", namespace="%s"})  ' %(namespace)
+    mem_limits_result = prometheus.custom_query(mem_limits_query)
+
+    network_query = 'sum by (pod) ((avg_over_time(container_network_transmit_bytes_total{namespace="%s"}[%s])) + \
+    (avg_over_time(container_network_receive_bytes_total{namespace="%s"}[%s])))' % (namespace, scrape_duration, namespace, scrape_duration)
+    network_result = prometheus.custom_query(network_query)
+
+    save_utilization_to_file(cpu_result, cpu_limits_result, mem_result, mem_limits_result, network_result, saved_metrics_path)
+    queries = json_queries(cpu_query, cpu_limits_query, mem_query, mem_limits_query)
+    return saved_metrics_path, queries
+
+
+def json_queries(cpu_query, cpu_limits_query, mem_query, mem_limits_query):
+    queries = {
+        "cpu_query": cpu_query,
+        "cpu_limit_query": cpu_limits_query,
+        "memory_query": mem_query,
+        "memory_limit_query": mem_limits_query
+    }
+    return queries

kraken/kube_burner/client.py

@@ -1,102 +0,0 @@
-import subprocess
-import logging
-import urllib.request
-import shutil
-import sys
-import kraken.prometheus.client as prometheus
-
-
-def setup(url):
-    """
-    Downloads and unpacks kube-burner binary
-    """
-
-    filename = "kube_burner.tar"
-    try:
-        logging.info("Fetching kube-burner binary")
-        urllib.request.urlretrieve(url, filename)
-    except Exception as e:
-        logging.error("Failed to download kube-burner binary located at %s" % url, e)
-        sys.exit(1)
-    try:
-        logging.info("Unpacking kube-burner tar ball")
-        shutil.unpack_archive(filename)
-    except Exception as e:
-        logging.error("Failed to unpack the kube-burner binary tarball: %s" % e)
-        sys.exit(1)
-
-
-def scrape_metrics(
-    distribution, uuid, prometheus_url, prometheus_bearer_token, start_time, end_time, config_path, metrics_profile
-):
-    """
-    Scrapes metrics defined in the profile from Prometheus and indexes them into Elasticsearch
-    """
-
-    if not prometheus_url:
-        if distribution == "openshift":
-            logging.info("Looks like prometheus_url is not defined, trying to use the default instance on the cluster")
-            prometheus_url, prometheus_bearer_token = prometheus.instance(
-                distribution, prometheus_url, prometheus_bearer_token
-            )
-        else:
-            logging.error("Looks like proemtheus url is not defined, exiting")
-            sys.exit(1)
-    command = (
-        "./kube-burner index --uuid "
-        + str(uuid)
-        + " -u "
-        + str(prometheus_url)
-        + " -t "
-        + str(prometheus_bearer_token)
-        + " -m "
-        + str(metrics_profile)
-        + " --start "
-        + str(start_time)
-        + " --end "
-        + str(end_time)
-        + " -c "
-        + str(config_path)
-    )
-    try:
-        logging.info("Running kube-burner to capture the metrics: %s" % command)
-        logging.info("UUID for the run: %s" % uuid)
-        subprocess.run(command, shell=True, universal_newlines=True)
-    except Exception as e:
-        logging.error("Failed to run kube-burner, error: %s" % (e))
-        sys.exit(1)
-
-
-def alerts(distribution, prometheus_url, prometheus_bearer_token, start_time, end_time, alert_profile):
-    """
-    Scrapes metrics defined in the profile from Prometheus and alerts based on the severity defined
-    """
-
-    if not prometheus_url:
-        if distribution == "openshift":
-            logging.info("Looks like prometheus_url is not defined, trying to use the default instance on the cluster")
-            prometheus_url, prometheus_bearer_token = prometheus.instance(
-                distribution, prometheus_url, prometheus_bearer_token
-            )
-        else:
-            logging.error("Looks like proemtheus url is not defined, exiting")
-            sys.exit(1)
-    command = (
-        "./kube-burner check-alerts "
-        + " -u "
-        + str(prometheus_url)
-        + " -t "
-        + str(prometheus_bearer_token)
-        + " -a "
-        + str(alert_profile)
-        + " --start "
-        + str(start_time)
-        + " --end "
-        + str(end_time)
-    )
-    try:
-        logging.info("Running kube-burner to capture the metrics: %s" % command)
-        subprocess.run(command, shell=True, universal_newlines=True)
-    except Exception as e:
-        logging.error("Failed to run kube-burner, error: %s" % (e))
-        sys.exit(1)