krkn-lib update v2.1.6 to fix pod monitoring time calculations (#674)

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

.github/workflows/build.yml

@@ -1,51 +0,0 @@
-name: Build Krkn
-on:
-  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
-      

.github/workflows/docker-image.yml

@@ -1,8 +1,7 @@
 name: Docker Image CI
 on:
   push:
-    branches:
-      - main
+    tags: ['v[0-9].[0-9]+.[0-9]+']
   pull_request:
 
 jobs:
@@ -12,19 +11,43 @@ jobs:
     - name: Check out code
       uses: actions/checkout@v3
     - name: Build the Docker images
-      run: docker build --no-cache -t quay.io/redhat-chaos/krkn containers/
+      if: startsWith(github.ref, 'refs/tags')
+      run:  |
+        docker build --no-cache -t quay.io/krkn-chaos/krkn containers/ --build-arg TAG=${GITHUB_REF#refs/tags/}
+        docker tag quay.io/krkn-chaos/krkn quay.io/redhat-chaos/krkn
+        docker tag quay.io/krkn-chaos/krkn quay.io/krkn-chaos/krkn:${GITHUB_REF#refs/tags/}
+        docker tag quay.io/krkn-chaos/krkn quay.io/redhat-chaos/krkn:${GITHUB_REF#refs/tags/}
+
+    - name: Test Build the Docker images
+      if: ${{ github.event_name == 'pull_request' }}
+      run: |
+        docker build --no-cache -t quay.io/krkn-chaos/krkn containers/ --build-arg PR_NUMBER=${{ github.event.pull_request.number }}
     - name: Login in quay
-      if: github.ref == 'refs/heads/main' && github.event_name == 'push'
+      if: startsWith(github.ref, 'refs/tags')
+      run: docker login quay.io -u ${QUAY_USER} -p ${QUAY_TOKEN}
+      env:
+        QUAY_USER: ${{ secrets.QUAY_USERNAME }}
+        QUAY_TOKEN: ${{ secrets.QUAY_PASSWORD }}
+    - name: Push the KrknChaos Docker images
+      if: startsWith(github.ref, 'refs/tags')
+      run: |
+        docker push quay.io/krkn-chaos/krkn
+        docker push quay.io/krkn-chaos/krkn:${GITHUB_REF#refs/tags/}
+    - name: Login in to redhat-chaos quay
+      if: startsWith(github.ref, 'refs/tags/v')
       run: docker login quay.io -u ${QUAY_USER} -p ${QUAY_TOKEN}
       env:
         QUAY_USER: ${{ secrets.QUAY_USER_1 }}
         QUAY_TOKEN: ${{ secrets.QUAY_TOKEN_1 }}
-    - name: Push the Docker images
-      if: github.ref == 'refs/heads/main' && github.event_name == 'push'
-      run: docker push quay.io/redhat-chaos/krkn
+    - name: Push the RedHat Chaos Docker images
+      if: startsWith(github.ref, 'refs/tags')
+      run: | 
+        docker push quay.io/redhat-chaos/krkn
+        docker push quay.io/redhat-chaos/krkn:${GITHUB_REF#refs/tags/}
     - name: Rebuild krkn-hub
-      if: github.ref == 'refs/heads/main' && github.event_name == 'push'
+      if: startsWith(github.ref, 'refs/tags')
       uses: redhat-chaos/actions/krkn-hub@main
       with:
-        QUAY_USER: ${{ secrets.QUAY_USER_1 }}
-        QUAY_TOKEN: ${{ secrets.QUAY_TOKEN_1 }}
+        QUAY_USER: ${{ secrets.QUAY_USERNAME }}
+        QUAY_TOKEN: ${{ secrets.QUAY_PASSWORD }}
+        AUTOPUSH: ${{ secrets.AUTOPUSH }}

.github/workflows/functional_tests.yaml

@@ -1,129 +0,0 @@
-on: issue_comment
-
-jobs:
-  check_user:
-    # This job only runs for pull request comments
-    name: Check User Authorization
-    env:
-      USERS: ${{vars.USERS}}
-    if: contains(github.event.comment.body, '/funtest') && contains(github.event.comment.html_url, '/pull/')
-    runs-on: ubuntu-latest
-    steps:
-      - name: Check User
-        run: |
-          for name in `echo $USERS`
-          do 
-            name="${name//$'\r'/}"
-            name="${name//$'\n'/}"
-            if [ $name == "${{github.event.sender.login}}" ]
-            then
-              echo "user ${{github.event.sender.login}} authorized, action started..."
-              exit 0
-            fi
-          done
-          echo "user ${{github.event.sender.login}} is not allowed to run functional tests Action"
-          exit 1
-  pr_commented:
-    # This job only runs for pull request comments containing /functional
-    name: Functional Tests
-    if: contains(github.event.comment.body, '/funtest') && contains(github.event.comment.html_url, '/pull/')
-    runs-on: ubuntu-latest
-    needs:
-      - check_user
-    steps:
-      - name: Check out Kraken
-        uses: actions/checkout@v3
-      - name: Checkout Pull Request
-        run: gh pr checkout ${{ github.event.issue.number }}
-        env:
-          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
-      - name: Install OC CLI
-        uses: redhat-actions/oc-installer@v1
-        with:
-          oc_version: latest
-      - name: Install python 3.9
-        uses: actions/setup-python@v4
-        with:
-          python-version: '3.9'
-      - name: Setup kraken dependencies
-        run:  pip install -r requirements.txt
-      - name: Create Workdir & export the path
-        run: |
-         mkdir workdir
-         echo "WORKDIR_PATH=`pwd`/workdir" >> $GITHUB_ENV
-      - name: Generate run id
-        run: |
-          echo "RUN_ID=`date +%s`" > $GITHUB_ENV
-          echo "Run Id: ${RUN_ID}"
-      - name: Write Pull Secret
-        env:
-          PULLSECRET_BASE64: ${{ secrets.PS_64 }}
-        run: |
-          echo "$PULLSECRET_BASE64" | base64 --decode > pullsecret.txt
-      - name: Write Boot Private Key
-        env:
-          BOOT_KEY: ${{ secrets.CRC_KEY_FILE }}
-        run: |
-          echo -n "$BOOT_KEY" > key.txt
-      - name: Teardown CRC (Post Action)
-        uses: webiny/action-post-run@3.0.0
-        id: post-run-command
-        with:
-          run: podman run --rm -v "${{ github.workspace }}:/workspace:z" -e AWS_ACCESS_KEY_ID="${{ secrets.AWS_ACCESS_KEY_ID }}" -e AWS_SECRET_ACCESS_KEY="${{ secrets.AWS_SECRET_ACCESS_KEY }}" -e AWS_DEFAULT_REGION=us-west-2 quay.io/crcont/crc-cloud:v0.0.2 destroy --project-name "chaos-funtest-${{ env.RUN_ID }}" --backed-url "s3://krkn-crc-state/${{ env.RUN_ID }}" --provider "aws"
-      - name: Create cluster
-        run: |
-          podman run  --name crc-cloud-create --rm \
-          -v ${PWD}:/workspace:z \
-          -e AWS_ACCESS_KEY_ID="${{ secrets.AWS_ACCESS_KEY_ID }}" \
-          -e AWS_SECRET_ACCESS_KEY="${{ secrets.AWS_SECRET_ACCESS_KEY }}" \
-          -e AWS_DEFAULT_REGION="us-west-2" \
-          quay.io/crcont/crc-cloud:v0.0.2 \
-          create aws \
-          --project-name "chaos-funtest-${RUN_ID}" \
-          --backed-url "s3://krkn-crc-state/${RUN_ID}" \
-          --output "/workspace" \
-          --aws-ami-id "ami-00f5eaf98cf42ef9f" \
-          --pullsecret-filepath /workspace/pullsecret.txt \
-          --key-filepath /workspace/key.txt
-
-      - name: Setup kubeconfig
-        continue-on-error: true
-        run: |
-          ssh  -o StrictHostKeyChecking=no -i id_rsa core@$(cat host) "cat /opt/kubeconfig" > kubeconfig
-          sed -i "s/https:\/\/api.crc.testing:6443/https:\/\/`cat host`.nip.io:6443/g" kubeconfig
-          echo "KUBECONFIG=${PWD}/kubeconfig" > $GITHUB_ENV
-
-      - name: Example deployment, GitHub Action env init
-        env:
-          NAMESPACE: test-namespace
-          DEPLOYMENT_NAME: test-nginx
-        run: ./CI/CRC/init_github_action.sh
-      - name: Setup test suite
-        run: |
-          yq -i '.kraken.port="8081"' CI/config/common_test_config.yaml
-          yq -i '.kraken.signal_address="0.0.0.0"' CI/config/common_test_config.yaml
-          yq -i '.kraken.kubeconfig_path="'${KUBECONFIG}'"' CI/config/common_test_config.yaml
-          echo "test_app_outages_gh" > ./CI/tests/my_tests
-          echo "test_container"      >> ./CI/tests/my_tests
-          echo "test_namespace"      >> ./CI/tests/my_tests
-          echo "test_net_chaos"      >> ./CI/tests/my_tests
-          echo "test_time"           >> ./CI/tests/my_tests
-
-      - name: Print affected config files
-        run: |
-          echo -e "## CI/config/common_test_config.yaml\n\n"
-          cat CI/config/common_test_config.yaml
-
-      - name: Running test suite
-        run: |
-          ./CI/run.sh
-      - name: Print test output
-        run:  cat CI/out/*
-      - name: Create coverage report
-        run: |
-          echo "# Test results" > $GITHUB_STEP_SUMMARY
-          cat CI/results.markdown >> $GITHUB_STEP_SUMMARY
-          echo "# Test coverage" >> $GITHUB_STEP_SUMMARY
-          python -m coverage report --format=markdown >> $GITHUB_STEP_SUMMARY
-
-

.github/workflows/tests.yml

@@ -0,0 +1,198 @@
+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
+          kubectl apply -f CI/templates/service_hijacking.yaml
+          kubectl wait --for=condition=ready pod -l "app.kubernetes.io/name=proxy" --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_service_hijacking" > ./CI/tests/functional_tests
+            echo "test_app_outages" >> ./CI/tests/functional_tests
+            echo "test_container"      >> ./CI/tests/functional_tests
+            echo "test_namespace"      >> ./CI/tests/functional_tests
+            echo "test_net_chaos"      >> ./CI/tests/functional_tests
+            echo "test_time"           >> ./CI/tests/functional_tests
+            echo "test_arca_cpu_hog" >> ./CI/tests/functional_tests
+            echo "test_arca_memory_hog" >> ./CI/tests/functional_tests
+            echo "test_arca_io_hog" >> ./CI/tests/functional_tests
+
+
+      # Push on main only steps + all other functional to collect coverage
+      # for the badge
+      - 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
+          echo "test_service_hijacking" >> ./CI/tests/functional_tests
+          echo "test_app_outages" >> ./CI/tests/functional_tests
+          echo "test_container"      >> ./CI/tests/functional_tests
+          echo "test_namespace"      >> ./CI/tests/functional_tests
+          echo "test_net_chaos"      >> ./CI/tests/functional_tests
+          echo "test_time"           >> ./CI/tests/functional_tests
+          echo "test_arca_cpu_hog" >> ./CI/tests/functional_tests
+          echo "test_arca_memory_hog" >> ./CI/tests/functional_tests
+          echo "test_arca_io_hog" >> ./CI/tests/functional_tests
+
+      # 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
+          python -m coverage json
+      - 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: Upload json coverage
+        uses: actions/upload-artifact@v3
+        with:
+          name: coverage.json
+          path: coverage.json
+          if-no-files-found: error
+      - name: Check CI results
+        run: grep Fail CI/results.markdown && false || true
+  badge:
+    permissions:
+      contents: write
+    name: Generate Coverage Badge
+    runs-on: ubuntu-latest
+    needs:
+      - tests
+    if: github.ref == 'refs/heads/main' && github.event_name == 'push'
+    steps:
+        - name: Check out doc repo
+          uses: actions/checkout@master
+          with:
+            repository: krkn-chaos/krkn-lib-docs
+            path: krkn-lib-docs
+            ssh-key: ${{ secrets.KRKN_LIB_DOCS_PRIV_KEY }}
+        - name: Download json coverage
+          uses: actions/download-artifact@v3
+          with:
+            name: coverage.json
+        - name: Set up Python
+          uses: actions/setup-python@v4
+          with:
+            python-version: 3.9
+        - name: Copy badge on GitHub Page Repo
+          env:
+            COLOR: yellow
+          run: |
+            # generate coverage badge on previously calculated total coverage
+            # and copy in the docs page
+            export TOTAL=$(python -c "import json;print(json.load(open('coverage.json'))['totals']['percent_covered_display'])")
+            [[ $TOTAL > 40 ]] && COLOR=green
+            echo "TOTAL: $TOTAL"
+            echo "COLOR: $COLOR"
+            curl "https://img.shields.io/badge/coverage-$TOTAL%25-$COLOR" > ./krkn-lib-docs/coverage_badge_krkn.svg
+        - name: Push updated Coverage Badge
+          run: |
+            cd krkn-lib-docs
+            git add .
+            git config user.name "krkn-chaos"
+            git config user.email "<>"
+            git commit -m "[KRKN] Coverage Badge ${GITHUB_REF##*/}" || echo "no changes to commit"
+            git push
+      

.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

CI/CRC/deployment.yaml

@@ -1,44 +0,0 @@
-apiVersion: v1
-kind: Namespace
-metadata:
-  name: $NAMESPACE
-
----
-
-apiVersion: v1
-kind: Service
-metadata:
-  name: $DEPLOYMENT_NAME-service
-  namespace: $NAMESPACE
-spec:
-  selector:
-    app: $DEPLOYMENT_NAME
-  ports:
-    - name: http
-      port: 80
-      targetPort: 8080
-  type: ClusterIP
-
---- 
-
-apiVersion: apps/v1
-kind: Deployment
-metadata:
-  namespace: $NAMESPACE
-  name: $DEPLOYMENT_NAME-deployment
-spec:
-  replicas: 3
-  selector:
-    matchLabels:
-      app: $DEPLOYMENT_NAME
-  template:
-    metadata:
-      labels:
-        app: $DEPLOYMENT_NAME
-    spec:
-      containers:
-        - name: $DEPLOYMENT_NAME
-          image: nginxinc/nginx-unprivileged:stable-alpine
-          ports:
-            - name: http
-              containerPort: 8080

CI/CRC/init_github_action.sh

@@ -1,58 +0,0 @@
-#!/bin/bash
-SCRIPT_PATH=./CI/CRC
-DEPLOYMENT_PATH=$SCRIPT_PATH/deployment.yaml
-
-[[ ! -f $DEPLOYMENT_PATH ]] && echo "[ERROR] please run $0 from GitHub action root directory" && exit 1
-[[ -z $DEPLOYMENT_NAME ]] && echo "[ERROR] please set \$DEPLOYMENT_NAME environment variable" && exit 1
-[[ -z $NAMESPACE ]] && echo "[ERROR] please set \$NAMESPACE environment variable" && exit 1
-
-
-OPENSSL=`which openssl 2>/dev/null`
-[[ $? != 0 ]] && echo "[ERROR]: openssl missing, please install it and try again" && exit 1
-OC=`which oc 2>/dev/null`
-[[ $? != 0 ]] && echo "[ERROR]: oc missing, please install it and try again" && exit 1
-SED=`which sed 2>/dev/null`
-[[ $? != 0 ]] && echo "[ERROR]: sed missing, please install it and try again" && exit 1
-JQ=`which jq 2>/dev/null`
-[[ $? != 0 ]] && echo "[ERROR]: jq missing, please install it and try again" && exit 1
-ENVSUBST=`which envsubst 2>/dev/null`
-[[ $? != 0 ]] && echo "[ERROR]: envsubst missing, please install it and try again" && exit 1
-
-
-API_PORT="6443"
-API_ADDRESS="https://api.`cat host`.nip.io:${API_PORT}"
-FQN=$DEPLOYMENT_NAME.apps.$API_ADDRESS
-
-
-echo "[INF] deploying example deployment: $DEPLOYMENT_NAME in namespace: $NAMESPACE"
-$ENVSUBST < $DEPLOYMENT_PATH | $OC apply -f - > /dev/null 2>&1
-
-echo "[INF] creating SSL self-signed certificates for route https://$FQN"
-$OPENSSL genrsa -out servercakey.pem > /dev/null 2>&1
-$OPENSSL req -new -x509 -key servercakey.pem -out serverca.crt -subj "/CN=$FQN/O=Red Hat Inc./C=US" > /dev/null 2>&1
-$OPENSSL genrsa -out server.key > /dev/null 2>&1
-$OPENSSL req -new -key server.key -out server_reqout.txt -subj "/CN=$FQN/O=Red Hat Inc./C=US" > /dev/null 2>&1
-$OPENSSL x509 -req -in server_reqout.txt -days 3650 -sha256 -CAcreateserial -CA serverca.crt -CAkey servercakey.pem -out server.crt > /dev/null 2>&1
-echo "[INF] creating deployment: $DEPLOYMENT_NAME public route: https://$FQN"
-$OC create route --namespace $NAMESPACE  edge --service=$DEPLOYMENT_NAME-service --cert=server.crt --key=server.key --ca-cert=serverca.crt --hostname="$FQN" > /dev/null 2>&1
-
-
-echo "[INF] setting github action environment variables"
-
-NODE_NAME="`$OC get nodes  -o json | $JQ -r '.items[0].metadata.name'`"
-COVERAGE_FILE="`pwd`/coverage.md"
-echo "DEPLOYMENT_NAME=$DEPLOYMENT_NAME" >> $GITHUB_ENV
-echo "DEPLOYMENT_FQN=$FQN" >> $GITHUB_ENV
-echo "API_ADDRESS=$API_ADDRESS" >> $GITHUB_ENV
-echo "API_PORT=$API_PORT" >> $GITHUB_ENV
-echo "NODE_NAME=$NODE_NAME" >> $GITHUB_ENV
-echo "NAMESPACE=$NAMESPACE" >> $GITHUB_ENV
-echo "COVERAGE_FILE=$COVERAGE_FILE" >> $GITHUB_ENV
-
-echo "[INF] deployment fully qualified name will be available in \${{ env.DEPLOYMENT_NAME }} with value $DEPLOYMENT_NAME"
-echo "[INF] deployment name will be available in \${{ env.DEPLOYMENT_FQN }} with value $FQN"
-echo "[INF] OCP API address will be available in \${{ env.API_ADDRESS }} with value $API_ADDRESS"
-echo "[INF] OCP API port will be available in \${{ env.API_PORT }} with value $API_PORT"
-echo "[INF] OCP node name will be available in \${{ env.NODE_NAME }} with value $NODE_NAME"
-echo "[INF] coverage file will ve available in \${{ env.COVERAGE_FILE }} with value $COVERAGE_FILE"
-

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.
@@ -29,9 +29,12 @@ tunings:
     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
+    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
@@ -39,3 +42,11 @@ telemetry:
     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/run.sh

@@ -1,15 +1,14 @@
 #!/bin/bash
-set -x
 MAX_RETRIES=60
 
-OC=`which oc 2>/dev/null`
-[[ $? != 0 ]] && echo "[ERROR]: oc missing, please install it and try again" && exit 1
+KUBECTL=`which kubectl 2>/dev/null`
+[[ $? != 0 ]] && echo "[ERROR]: kubectl missing, please install it and try again" && exit 1
 
 wait_cluster_become_ready() {
   COUNT=1
-  until `$OC get namespace > /dev/null 2>&1`
+  until `$KUBECTL get namespace > /dev/null 2>&1`
   do
-    echo "[INF] waiting OpenShift to become ready, after $COUNT check"
+    echo "[INF] waiting Kubernetes to become ready, after $COUNT check"
     sleep 3
     [[ $COUNT == $MAX_RETRIES ]] && echo "[ERR] max retries exceeded, failing" && exit 1
     ((COUNT++))
@@ -18,9 +17,9 @@ wait_cluster_become_ready() {
 
 
 
-ci_tests_loc="CI/tests/my_tests"
+ci_tests_loc="CI/tests/functional_tests"
 
-echo "running test suit consisting of ${ci_tests}"
+echo -e "********* Running Functional Tests Suite *********\n\n"
 
 rm -rf CI/out
 
@@ -37,9 +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
-  wait_cluster_become_ready
-  ./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/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/network_diagnostics_namespace.yaml

@@ -1,7 +0,0 @@
-scenarios:
-  - action: delete
-    namespace: "^$openshift-network-diagnostics$"
-    label_selector:
-    runs: 1
-    sleep: 15
-    wait_time: 30

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/service_hijacking.yaml

@@ -0,0 +1,29 @@
+apiVersion: v1
+kind: Pod
+metadata:
+  name: nginx
+  labels:
+    app.kubernetes.io/name: proxy
+spec:
+  containers:
+  - name: nginx
+    image: nginx:stable
+    ports:
+      - containerPort: 80
+        name: http-web-svc
+
+---
+apiVersion: v1
+kind: Service
+metadata:
+  name: nginx-service
+spec:
+  selector:
+    app.kubernetes.io/name: proxy
+  type: NodePort
+  ports:
+  - name: name-of-service-port
+    protocol: TCP
+    port: 80
+    targetPort: http-web-svc
+    nodePort: 30036

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

@@ -1,18 +1,26 @@
 ERRORED=false
 
 function finish {
-    if [ $? -eq 1 ] && [ $ERRORED != "true" ]
+    if [ $? != 0 ] && [ $ERRORED != "true" ]
     then
         error
     fi
 }
 
 function error {
-    echo "Error caught."
-    ERRORED=true
+    exit_code=$?
+    if [ $exit_code == 1 ]
+    then
+      echo "Error caught."
+      ERRORED=true
+    elif [ $exit_code == 2 ]
+    then
+      echo "Run with exit code 2 detected, it is expected, wrapping the exit code with 0 to avoid pipeline failure"
+      exit 0
+    fi
 }
 
 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_app_outages_gh.sh

@@ -1,21 +0,0 @@
-set -xeEo pipefail
-
-source CI/tests/common.sh
-
-trap error ERR
-trap finish EXIT
-
-
-function functional_test_app_outage {
-  [ -z $DEPLOYMENT_NAME ] && echo "[ERR] DEPLOYMENT_NAME variable not set, failing." && exit 1
-  yq -i '.application_outage.pod_selector={"app":"'$DEPLOYMENT_NAME'"}' CI/scenarios/app_outage.yaml
-  yq -i '.application_outage.namespace="'$NAMESPACE'"' CI/scenarios/app_outage.yaml
-  export scenario_type="application_outages"
-  export scenario_file="CI/scenarios/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
-  echo "App outage scenario test: Success"
-}
-
-functional_test_app_outage

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/container_etcd.yml
+  yq -i '.scenarios[0].label_selector="scenario=container"' scenarios/openshift/container_etcd.yml
+  yq -i '.scenarios[0].container_name="fedtools"' scenarios/openshift/container_etcd.yml
   export scenario_type="container_scenarios"
-  export scenario_file="- CI/scenarios/container_scenario.yml"
+  export scenario_file="- scenarios/openshift/container_etcd.yml"
   export post_config=""
   envsubst < CI/config/common_test_config.yaml > CI/config/container_config.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/network_diagnostics_namespace.yaml"
+  export scenario_file="-  scenarios/openshift/ingress_namespace.yaml"
   export post_config=""
-  yq '.scenarios.[0].namespace="^openshift-network-diagnostics$"' -i CI/scenarios/network_diagnostics_namespace.yaml
+  yq '.scenarios[0].namespace="^namespace-scenario$"' -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_service_hijacking.sh

@@ -0,0 +1,107 @@
+set -xeEo pipefail
+
+source CI/tests/common.sh
+
+trap error ERR
+trap finish EXIT
+# port mapping has been configured in kind-config.yml
+SERVICE_URL=http://localhost:8888
+PAYLOAD_GET_1="{ \
+  \"status\":\"internal server error\" \
+}"
+STATUS_CODE_GET_1=500
+
+PAYLOAD_PATCH_1="resource patched"
+STATUS_CODE_PATCH_1=201
+
+PAYLOAD_POST_1="{ \
+  \"status\": \"unauthorized\" \
+}"
+STATUS_CODE_POST_1=401
+
+PAYLOAD_GET_2="{ \
+  \"status\":\"resource created\" \
+}"
+STATUS_CODE_GET_2=201
+
+PAYLOAD_PATCH_2="bad request"
+STATUS_CODE_PATCH_2=400
+
+PAYLOAD_POST_2="not found"
+STATUS_CODE_POST_2=404
+
+JSON_MIME="application/json"
+TEXT_MIME="text/plain; charset=utf-8"
+
+function functional_test_service_hijacking {
+
+  export scenario_type="service_hijacking"
+  export scenario_file="scenarios/kube/service_hijacking.yaml"
+  export post_config=""
+  envsubst < CI/config/common_test_config.yaml > CI/config/service_hijacking.yaml
+  python3 -m coverage run -a run_kraken.py -c CI/config/service_hijacking.yaml  > /dev/null 2>&1 &
+  PID=$!
+  #Waiting the hijacking to have effect
+  while [ `curl -X GET -s -o /dev/null -I -w "%{http_code}" $SERVICE_URL/list/index.php` == 404 ]; do echo "waiting scenario to kick in."; sleep 1; done;
+
+  #Checking Step 1 GET on /list/index.php
+  OUT_GET="`curl -X GET -s $SERVICE_URL/list/index.php`"
+  OUT_CONTENT=`curl -X GET -s -o /dev/null -I -w "%{content_type}" $SERVICE_URL/list/index.php`
+  OUT_STATUS_CODE=`curl -X GET -s -o /dev/null -I -w "%{http_code}" $SERVICE_URL/list/index.php`
+  [ "${PAYLOAD_GET_1//[$'\t\r\n ']}" == "${OUT_GET//[$'\t\r\n ']}" ] && echo "Step 1 GET Payload OK" || (echo "Payload did not match. Test failed." && exit 1)
+  [ "$OUT_STATUS_CODE" == "$STATUS_CODE_GET_1" ] && echo "Step 1 GET Status Code OK" || (echo " Step 1 GET status code did not match. Test failed." && exit 1)
+  [ "$OUT_CONTENT" == "$JSON_MIME" ] && echo "Step 1 GET MIME OK" || (echo " Step 1 GET MIME did not match. Test failed." && exit 1)
+
+  #Checking Step 1 POST on /list/index.php
+  OUT_POST="`curl -s -X POST $SERVICE_URL/list/index.php`"
+  OUT_STATUS_CODE=`curl -X POST -s -o /dev/null -I -w "%{http_code}" $SERVICE_URL/list/index.php`
+  OUT_CONTENT=`curl -X POST -s -o /dev/null -I -w "%{content_type}" $SERVICE_URL/list/index.php`
+  [ "${PAYLOAD_POST_1//[$'\t\r\n ']}" == "${OUT_POST//[$'\t\r\n ']}" ] && echo "Step 1 POST Payload OK" || (echo "Payload did not match. Test failed." && exit 1)
+  [ "$OUT_STATUS_CODE" == "$STATUS_CODE_POST_1" ] && echo "Step 1 POST Status Code OK" || (echo "Step 1 POST status code did not match. Test failed." && exit 1)
+  [ "$OUT_CONTENT" == "$JSON_MIME" ] && echo "Step 1 POST MIME OK" || (echo " Step 1 POST MIME did not match. Test failed." && exit 1)
+
+  #Checking Step 1 PATCH on /patch
+  OUT_PATCH="`curl -s -X PATCH $SERVICE_URL/patch`"
+  OUT_STATUS_CODE=`curl -X PATCH -s -o /dev/null -I -w "%{http_code}" $SERVICE_URL/patch`
+  OUT_CONTENT=`curl -X PATCH -s -o /dev/null -I -w "%{content_type}" $SERVICE_URL/patch`
+  [ "${PAYLOAD_PATCH_1//[$'\t\r\n ']}" == "${OUT_PATCH//[$'\t\r\n ']}" ] && echo "Step 1 PATCH Payload OK" || (echo "Payload did not match. Test failed." && exit 1)
+  [ "$OUT_STATUS_CODE" == "$STATUS_CODE_PATCH_1" ] && echo "Step 1 PATCH Status Code OK" || (echo "Step 1 PATCH status code did not match. Test failed." && exit 1)
+  [ "$OUT_CONTENT" == "$TEXT_MIME" ] && echo "Step 1 PATCH MIME OK" || (echo " Step 1 PATCH MIME did not match. Test failed." && exit 1)
+  # wait for the next step
+  sleep 16
+
+  #Checking Step 2 GET on /list/index.php
+  OUT_GET="`curl -X GET -s $SERVICE_URL/list/index.php`"
+  OUT_CONTENT=`curl -X GET -s -o /dev/null -I -w "%{content_type}" $SERVICE_URL/list/index.php`
+  OUT_STATUS_CODE=`curl -X GET -s -o /dev/null -I -w "%{http_code}" $SERVICE_URL/list/index.php`
+  [ "${PAYLOAD_GET_2//[$'\t\r\n ']}" == "${OUT_GET//[$'\t\r\n ']}" ] && echo "Step 2 GET Payload OK" || (echo "Step 2 GET Payload did not match. Test failed." && exit 1)
+  [ "$OUT_STATUS_CODE" == "$STATUS_CODE_GET_2" ] && echo "Step 2 GET Status Code OK" || (echo "Step 2 GET status code did not match. Test failed." && exit 1)
+  [ "$OUT_CONTENT" == "$JSON_MIME" ] && echo "Step 2 GET MIME OK" || (echo " Step 2 GET MIME did not match. Test failed." && exit 1)
+
+  #Checking Step 2 POST on /list/index.php
+  OUT_POST="`curl -s -X POST $SERVICE_URL/list/index.php`"
+  OUT_CONTENT=`curl -X POST -s -o /dev/null -I -w "%{content_type}" $SERVICE_URL/list/index.php`
+  OUT_STATUS_CODE=`curl -X POST -s -o /dev/null -I -w "%{http_code}" $SERVICE_URL/list/index.php`
+  [ "${PAYLOAD_POST_2//[$'\t\r\n ']}" == "${OUT_POST//[$'\t\r\n ']}" ] && echo "Step 2 POST Payload OK" || (echo "Step 2 POST Payload did not match. Test failed." && exit 1)
+  [ "$OUT_STATUS_CODE" == "$STATUS_CODE_POST_2" ] && echo "Step 2 POST Status Code OK" || (echo "Step 2 POST status code did not match. Test failed." && exit 1)
+  [ "$OUT_CONTENT" == "$TEXT_MIME" ] && echo "Step 2 POST MIME OK" || (echo " Step 2 POST MIME did not match. Test failed." && exit 1)
+
+  #Checking Step 2 PATCH on /patch
+  OUT_PATCH="`curl -s -X PATCH $SERVICE_URL/patch`"
+  OUT_CONTENT=`curl -X PATCH -s -o /dev/null -I -w "%{content_type}" $SERVICE_URL/patch`
+  OUT_STATUS_CODE=`curl -X PATCH -s -o /dev/null -I -w "%{http_code}" $SERVICE_URL/patch`
+  [ "${PAYLOAD_PATCH_2//[$'\t\r\n ']}" == "${OUT_PATCH//[$'\t\r\n ']}" ] && echo "Step 2 PATCH Payload OK" || (echo "Step 2 PATCH Payload did not match. Test failed." && exit 1)
+  [ "$OUT_STATUS_CODE" == "$STATUS_CODE_PATCH_2" ] && echo "Step 2 PATCH Status Code OK" || (echo "Step 2 PATCH status code did not match. Test failed." && exit 1)
+  [ "$OUT_CONTENT" == "$TEXT_MIME" ] && echo "Step 2 PATCH MIME OK" || (echo " Step 2 PATCH MIME did not match. Test failed." && exit 1)
+  wait $PID
+
+  # now checking  if service has been restore correctly and nginx responds correctly
+  curl -s  $SERVICE_URL | grep nginx! && echo "BODY: Service restored!" || (echo "BODY: failed to restore service" && exit 1)
+  OUT_STATUS_CODE=`curl -X GET -s -o /dev/null -I -w "%{http_code}" $SERVICE_URL`
+  [ "$OUT_STATUS_CODE" == "200" ] && echo "STATUS_CODE: Service restored!" || (echo "STATUS_CODE: failed to restore service" && exit 1)
+
+  echo "Service Hijacking Chaos test: Success"
+}
+
+
+functional_test_service_hijacking

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
+  retval=$(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.log || ( echo "FAILED: critical-alerts-00.log 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
 

README.md

@@ -1,11 +1,12 @@
-# KrknChaos aka Kraken
-[![Docker Repository on Quay](https://quay.io/repository/redhat-chaos/krkn/status "Docker Repository on Quay")](https://quay.io/repository/redhat-chaos/krkn?tab=tags&tag=latest)
-![Workflow-Status](https://github.com/redhat-chaos/krkn/actions/workflows/docker-image.yml/badge.svg)
+# Krkn aka Kraken
+![Workflow-Status](https://github.com/krkn-chaos/krkn/actions/workflows/docker-image.yml/badge.svg)
+![coverage](https://krkn-chaos.github.io/krkn-lib-docs/coverage_badge_krkn.svg)
+![action](https://github.com/krkn-chaos/krkn/actions/workflows/tests.yml/badge.svg)
 
 ![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
@@ -18,13 +19,13 @@ 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/krknChoas.
+The guide is hosted at https://krkn-chaos.github.io/krkn.
 
 
 ### How to Get Started
@@ -38,48 +39,37 @@ After installation, refer back to the below sections for supported scenarios and
 
 
 #### 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/krknChaos-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:
-
-```
-$ cd kraken
-$ podman-compose up or $ docker-compose up      # Spins up the containers specified in the docker-compose.yml file present in the run directory.
-$ podman-compose down or $ docker-compose down  # Delete the containers installed.
-```
-This will manage the Cerberus and Elasticsearch containers on the host on which you are running Kraken.
-
-**NOTE**: Make sure you have enough resources (memory and disk) on the machine on top of which the containers are running as Elasticsearch is resource intensive. Cerberus monitors the system components by default, the [config](config/cerberus.yaml) can be tweaked to add applications namespaces, routes and other components to monitor as well. The command will keep running until killed since detached mode is not supported as of now.
+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.
 
 
 ### Config
 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: |
-[Pod Network Scenarios](docs/pod_network_scenarios.md) | :x: | :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: |
-[Hog Scenarios: CPU, Memory](docs/arcaflow_scenarios.md) | :heavy_check_mark: | :heavy_check_mark: |
-[Cluster Shut Down Scenarios](docs/cluster_shut_down_scenarios.md) | :heavy_check_mark: | :heavy_check_mark: |
-[Service Disruption Scenarios](docs/service_disruption_scenarios.md.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: |
+[Service Hijacking Scenarios](docs/service_hijacking_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 [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
@@ -94,10 +84,6 @@ 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/kube-burner/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. 
@@ -107,7 +93,7 @@ Information on enabling and leveraging this feature can be found [here](docs/SLO
 
 ### 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
@@ -116,7 +102,8 @@ Kraken supports injecting faults into [Open Cluster Management (OCM)](https://op
 - Blog post emphasizing the importance of making Chaos part of Performance and Scale runs to mimic the production environments: https://www.openshift.com/blog/making-chaos-part-of-kubernetes/openshift-performance-and-scalability-tests
 - Blog post on findings from Chaos test runs: https://cloud.redhat.com/blog/openshift/kubernetes-chaos-stories
 - Discussion with CNCF TAG App Delivery on Krkn workflow, features and addition to CNCF sandbox: [Github](https://github.com/cncf/sandbox/issues/44), [Tracker](https://github.com/cncf/tag-app-delivery/issues/465), [recording](https://www.youtube.com/watch?v=nXQkBFK_MWc&t=722s)
-
+- Blog post on supercharging chaos testing using AI integration in Krkn: https://www.redhat.com/en/blog/supercharging-chaos-testing-using-ai
+- Blog post announcing Krkn joining CNCF Sandbox: https://www.redhat.com/en/blog/krknchaos-joining-cncf-sandbox
 
 ### Roadmap
 Enhancements being planned can be found in the [roadmap](ROADMAP.md).
@@ -132,6 +119,7 @@ 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.
-* [**#krkn 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

@@ -2,14 +2,14 @@
 
 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/redhat-chaos/krkn/issues/424)
-- [x] [Centralized storage for chaos experiments artifacts](https://github.com/redhat-chaos/krkn/issues/423)
-- [ ] [Support for causing DNS outages](https://github.com/redhat-chaos/krkn/issues/394)
-- [x] [Chaos recommender](https://github.com/redhat-chaos/krkn/tree/main/utils/chaos-recommender) to suggest scenarios having probability of impacting the service under test using profiling results 
+- [ ] [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/redhat-chaos/krkn/issues/393)
-- [ ] [Ability to visualize the metrics that are being captured by Kraken and stored in Elasticsearch](https://github.com/redhat-chaos/krkn/issues/124)
-- [ ] Support for running all the scenarios of Kraken on Kubernetes distribution - see https://github.com/redhat-chaos/krkn/issues/185, https://github.com/redhat-chaos/krkn/issues/186
-- [ ] Continue to improve [Chaos Testing Guide](https://redhat-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/redhat-chaos/krkn/issues/495)
-- [ ] [OCP and Kubernetes functionalities segregation](https://github.com/redhat-chaos/krkn/issues/497)
+- [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.yaml

@@ -8,7 +8,7 @@
   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:]) > 0.007
+- 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
 

config/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
     publish_kraken_status: True                            # Can be accessed at http://0.0.0.0:8081
@@ -15,7 +15,7 @@ kraken:
         - application_outages:
             - scenarios/openshift/app_outage.yaml
         - container_scenarios:                             # List of chaos pod scenarios to load
-            - -    scenarios/openshift/container_etcd.yml
+            - - scenarios/openshift/container_etcd.yml
         - plugin_scenarios:
             - scenarios/openshift/etcd.yml
             - scenarios/openshift/regex_openshift_pod_kill.yml
@@ -23,7 +23,7 @@ kraken:
             - scenarios/openshift/network_chaos_ingress.yml
             - scenarios/openshift/prom_kill.yml
         - node_scenarios:                                  # List of chaos node scenarios to load
-            -   scenarios/openshift/node_scenarios_example.yml
+            - scenarios/openshift/node_scenarios_example.yml
         - plugin_scenarios:
             - scenarios/openshift/openshift-apiserver.yml
             - scenarios/openshift/openshift-kube-apiserver.yml
@@ -42,6 +42,8 @@ kraken:
             - scenarios/openshift/pvc_scenario.yaml
         - network_chaos:
             - scenarios/openshift/network_chaos.yaml
+        - service_hijacking:
+              - scenarios/kube/service_hijacking.yaml
 
 cerberus:
     cerberus_enabled: False                                # Enable it when cerberus is previously installed
@@ -51,9 +53,7 @@ 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"
-    capture_metrics: False
-    metrics_profile_path: config/metrics-aggregated.yaml
-    prometheus_url:                                       # The prometheus url/route is automatically obtained in case of OpenShift, please set it when the distribution is Kubernetes.
+    prometheus_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
@@ -67,14 +67,19 @@ 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
+    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                                     # the size of the prometheus data archive size in KB. The lower the size of archive is
+    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
@@ -87,6 +92,9 @@ telemetry:
      - "(\\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

@@ -20,8 +20,6 @@ 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"
-    capture_metrics: False
-    metrics_profile_path: config/metrics-aggregated.yaml
     prometheus_url:                                       # The prometheus url/route is automatically obtained in case of OpenShift, please set it when the distribution is Kubernetes.
     prometheus_bearer_token:                              # The bearer token is automatically obtained in case of OpenShift, please set it when the distribution is Kubernetes. This is needed to authenticate with prometheus.
     uuid:                                                 # uuid for the run is generated by default if not set

config/config_kubernetes.yaml

@@ -19,8 +19,6 @@ 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"
-    capture_metrics: False
-    metrics_profile_path: config/metrics-aggregated.yaml
     prometheus_url:                                       # The prometheus url/route is automatically obtained in case of OpenShift, please set it when the distribution is Kubernetes.
     prometheus_bearer_token:                              # The bearer token is automatically obtained in case of OpenShift, please set it when the distribution is Kubernetes. This is needed to authenticate with prometheus.
     uuid:                                                 # uuid for the run is generated by default if not set

config/config_performance.yaml

@@ -77,3 +77,8 @@ telemetry:
      - "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/recommender_config.yaml

@@ -1,5 +1,5 @@
 application: openshift-etcd
-namespace: openshift-etcd
+namespaces: openshift-etcd
 labels: app=openshift-etcd
 kubeconfig: ~/.kube/config.yaml
 prometheus_endpoint: <Prometheus_Endpoint>
@@ -7,6 +7,8 @@ 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:
@@ -26,4 +28,8 @@ chaos_tests:
     - pod_network_chaos
   MEM:
     - node_memory_hog
-    - pvc_disk_fill
+    - pvc_disk_fill
+
+threshold: .7
+cpu_threshold: .5
+mem_threshold: .5

containers/Dockerfile

@@ -1,30 +1,57 @@
-# Dockerfile for kraken
-
-FROM mcr.microsoft.com/azure-cli:latest as azure-cli
-
-FROM registry.access.redhat.com/ubi8/ubi:latest
-
-LABEL org.opencontainers.image.authors="Red Hat OpenShift Chaos Engineering"
-
-ENV KUBECONFIG /root/.kube/config
-
-# Copy azure client binary from azure-cli image
-COPY --from=azure-cli /usr/local/bin/az /usr/bin/az
-
-# Install dependencies
-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 v1.5.3 /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
+# oc build
+FROM golang:1.22.4 AS oc-build
+RUN apt-get update && apt-get install -y --no-install-recommends libkrb5-dev
 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
+RUN git clone --branch release-4.18 https://github.com/openshift/oc.git
+WORKDIR /tmp/oc
+RUN go mod edit -go 1.22.3 &&\
+    go get github.com/moby/buildkit@v0.12.5 &&\
+    go get github.com/containerd/containerd@v1.7.11&&\
+    go get github.com/docker/docker@v25.0.5&&\
+    go mod tidy && go mod vendor
+RUN make GO_REQUIRED_MIN_VERSION:= oc
 
-WORKDIR /root/kraken
+FROM fedora:40
+ARG PR_NUMBER
+ARG TAG
+RUN groupadd -g 1001 krkn && useradd -m -u 1001 -g krkn krkn
+RUN dnf update -y
 
+# krkn version that will be built
+ENV KRKN_VERSION v1.6.2
+
+ENV KUBECONFIG /home/krkn/.kube/config
+
+# install kubectl
+RUN curl -LO "https://dl.k8s.io/release/$(curl -L -s https://dl.k8s.io/release/stable.txt)/bin/linux/amd64/kubectl" &&\
+    cp kubectl /usr/local/bin/kubectl && chmod +x /usr/local/bin/kubectl &&\
+    cp kubectl /usr/bin/kubectl && chmod +x /usr/bin/kubectl
+
+# This overwrites any existing configuration in /etc/yum.repos.d/kubernetes.repo
+RUN dnf update && dnf install -y --setopt=install_weak_deps=False \
+    git python39 jq yq gettext wget which &&\
+    dnf clean all
+
+# copy oc client binary from oc-build image
+COPY --from=oc-build /tmp/oc/oc /usr/bin/oc
+
+# krkn build
+RUN git clone https://github.com/krkn-chaos/krkn.git /home/krkn/kraken && \
+    mkdir -p /home/krkn/.kube
+
+WORKDIR /home/krkn/kraken
+
+# default behaviour will be to build main
+# if it is a PR trigger the PR itself will be checked out
+RUN if [ -n "$PR_NUMBER" ]; then git fetch origin pull/${PR_NUMBER}/head:pr-${PR_NUMBER} && git checkout pr-${PR_NUMBER};fi
+# if it is a TAG trigger checkout the tag
+RUN if [ -n "$TAG" ]; then git checkout "$TAG";fi
+
+RUN python3.9 -m ensurepip
+RUN pip3.9 install -r requirements.txt
+RUN pip3.9 install jsonschema
+
+RUN chown -R krkn:krkn /home/krkn && chmod 755 /home/krkn
+USER krkn
 ENTRYPOINT ["python3.9", "run_kraken.py"]
 CMD ["--config=config/config.yaml"]

containers/Dockerfile-ppc64le

@@ -2,19 +2,14 @@
 
 FROM ppc64le/centos:8
 
-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
 
-# Copy azure client binary from azure-cli image
-COPY --from=azure-cli /usr/local/bin/az /usr/bin/az
-
 # Install dependencies
 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 v1.5.3 /root/kraken && \
+    git clone https://github.com/redhat-chaos/krkn.git --branch v1.5.14 /root/kraken && \
     mkdir -p /root/.kube && cd /root/kraken && \
     pip3.9 install -r requirements.txt && \
     pip3.9 install virtualenv && \
@@ -22,7 +17,7 @@ RUN yum install -y git python39 python3-pip jq gettext wget && \
 
 # 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
+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 oc /usr/bin/oc && cp kubectl /usr/local/bin/kubectl && cp kubectl /usr/bin/kubectl
 
 WORKDIR /root/kraken
 

docker-compose.yml

@@ -1,31 +0,0 @@
-version: "3"
-services:
-  elastic:
-    image: docker.elastic.co/elasticsearch/elasticsearch:7.13.2
-    deploy:
-      replicas: 1
-      restart_policy:
-        condition: on-failure
-    network_mode: host
-    environment:
-      discovery.type: single-node
-  kibana:
-    image: docker.elastic.co/kibana/kibana:7.13.2
-    deploy:
-      replicas: 1
-      restart_policy:
-        condition: on-failure
-    network_mode: host
-    environment:
-      ELASTICSEARCH_HOSTS: "http://0.0.0.0:9200"
-  cerberus:
-    image: quay.io/openshift-scale/cerberus:latest
-    privileged: true
-    deploy:
-      replicas: 1
-      restart_policy:
-        condition: on-failure
-    network_mode: host
-    volumes:
-       - ./config/cerberus.yaml:/root/cerberus/config/config.yaml:Z  # Modify the config in case of the need to monitor additional components
-       - ${HOME}/.kube/config:/root/.kube/config:Z

docs/cloud_setup.md

@@ -27,14 +27,12 @@ After creating the service account you will need to enable the account using the
 
 ## Azure
 
-**NOTE**: For Azure node killing scenarios, make sure [Azure CLI](https://docs.microsoft.com/en-us/cli/azure/install-azure-cli?view=azure-cli-latest) is installed.
-
-You will also need to create a service principal and give it the correct access, see [here](https://docs.openshift.com/container-platform/4.5/installing/installing_azure/installing-azure-account.html) for creating the service principal and setting the proper permissions.
+**NOTE**: You will need to create a service principal and give it the correct access, see [here](https://docs.openshift.com/container-platform/4.5/installing/installing_azure/installing-azure-account.html) for creating the service principal and setting the proper permissions.
 
 To properly run the service principal requires “Azure Active Directory Graph/Application.ReadWrite.OwnedBy” api permission granted and “User Access Administrator”.
 
 Before running you will need to set the following:
-1. Login using ```az login```
+1. ```export AZURE_SUBSCRIPTION_ID=<subscription_id>```
 
 2. ```export AZURE_TENANT_ID=<tenant_id>```
 

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/container_scenarios.md

@@ -4,7 +4,7 @@ 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:
@@ -25,7 +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

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/redhat-chaos/krkn.git
+ git remote add upstream https://github.com/krkn-chaos/krkn.git
 ```
 
 Rebase to upstream master branch.

docs/getting_started.md

@@ -14,11 +14,7 @@ For example, for adding a pod level scenario for a new application, refer to the
     namespace_pattern: ^<namespace>$
     label_selector: <pod label>
     kill: <number of pods to kill>
-- id: wait-for-pods
-  config:
-    namespace_pattern: ^<namespace>$
-    label_selector: <pod label>
-    count: <expected number of pods that match namespace and label>
+    krkn_pod_recovery_time: <expected time for the pod to become ready>
 ```
 
 #### Node Scenario Yaml Template

docs/installation.md

@@ -3,13 +3,13 @@
 The following ways are supported to run Kraken:
 
 - Standalone python program through Git.
-- Containerized version using either Podman or Docker as the runtime via [Krkn-hub](https://github.com/redhat-chaos/krkn-hub)
+- 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 
@@ -19,10 +19,10 @@ 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>
-$ cd kraken
+$ git clone https://github.com/krkn-chaos/krkn.git --branch <release version>
+$ cd krkn
 ```
 
 #### Install the dependencies
@@ -40,13 +40,13 @@ $ python3.9 run_kraken.py --config <config_file_location>
 ```
 
 ### Run containerized version
-[Krkn-hub](https://github.com/redhat-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.
+[Krkn-hub](https://github.com/krkn-chaos/krkn-hub) is a wrapper that allows running Krkn chaos scenarios via podman or docker runtime with scenario parameters/configuration defined as environment variables.
 
-Refer [instructions](https://github.com/redhat-chaos/krkn-hub#supported-chaos-scenarios) to get started.
+Refer [instructions](https://github.com/krkn-chaos/krkn-hub#supported-chaos-scenarios) to get started.
 
 
 ### Run Kraken as a Kubernetes deployment ( unsupported option - standalone or containerized deployers are recommended )
-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.
+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.
 
 
 Refer to the [chaos-kraken chart manpage](https://artifacthub.io/packages/helm/startx/chaos-kraken)

docs/metrics.md

@@ -1,31 +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.
-
-The metrics to capture need to be defined in a metrics profile which Kraken consumes to query prometheus with the start and end timestamp of the run. Each run has a unique identifier ( uuid ). 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:
-    capture_metrics: True
-    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
-```
-

docs/pod_scenarios.md

@@ -17,11 +17,8 @@ You can then create the scenario file with the following contents:
   config:
     namespace_pattern: ^kube-system$
     label_selector: k8s-app=kube-scheduler
-- id: wait-for-pods
-  config:
-    namespace_pattern: ^kube-system$
-    label_selector: k8s-app=kube-scheduler
-    count: 3
+    krkn_pod_recovery_time: 120
+    
 ```
 
 Please adjust the schema reference to point to the [schema file](../scenarios/plugin.schema.json). This file will give you code completion and documentation for the available options in your IDE.

docs/service_disruption_scenarios.md

@@ -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:

docs/service_hijacking_scenarios.md

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

docs/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:

kind-config.yml

@@ -2,6 +2,9 @@ kind: Cluster
 apiVersion: kind.x-k8s.io/v1alpha4
 nodes:
   - role: control-plane
+    extraPortMappings:
+      - containerPort: 30036
+        hostPort: 8888
   - role: control-plane
   - role: control-plane
   - role: worker

kraken/application_outage/actions.py

@@ -4,6 +4,7 @@ import time
 import kraken.cerberus.setup as cerberus
 from jinja2 import Template
 import kraken.invoke.command as runcommand
+from krkn_lib.k8s import KrknKubernetes
 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
@@ -11,14 +12,14 @@ 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, telemetry: KrknTelemetryKubernetes) -> (list[str], list[ScenarioTelemetry]):
+def run(scenarios_list, config, wait_duration,kubecli: KrknKubernetes, 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()
+        scenario_telemetry.start_timestamp = time.time()
         telemetry.set_parameters_base64(scenario_telemetry, app_outage_config)
         if len(app_outage_config) > 1:
             try:
@@ -49,25 +50,22 @@ 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)
+                    yaml_spec = yaml.safe_load(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)
-                    )
 
+                    kubecli.create_net_policy(yaml_spec, namespace)
+                   
                     # 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))
+                    kubecli.delete_net_policy("kraken-deny", namespace)
 
                     logging.info("End of scenario. Waiting for the specified duration: %s" % (wait_duration))
                     time.sleep(wait_duration)
@@ -75,12 +73,12 @@ spec:
                     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
+                scenario_telemetry.exit_status = 1
                 failed_scenarios.append(app_outage_config)
                 log_exception(app_outage_config)
             else:
-                scenario_telemetry.exitStatus = 0
-            scenario_telemetry.endTimeStamp = time.time()
+                scenario_telemetry.exit_status = 0
+            scenario_telemetry.end_timestamp = time.time()
             scenario_telemetries.append(scenario_telemetry)
     return failed_scenarios, scenario_telemetries
 

kraken/arcaflow_plugin/arcaflow_plugin.py

@@ -16,12 +16,12 @@ def run(scenarios_list: List[str], kubeconfig_path: str, telemetry: KrknTelemetr
     for scenario in scenarios_list:
         scenario_telemetry = ScenarioTelemetry()
         scenario_telemetry.scenario = scenario
-        scenario_telemetry.startTimeStamp = time.time()
+        scenario_telemetry.start_timestamp = 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_telemetry.end_timestamp = time.time()
+        scenario_telemetry.exit_status = status_code
         scenario_telemetries.append(scenario_telemetry)
         if status_code != 0:
             failed_post_scenarios.append(scenario)
@@ -36,9 +36,10 @@ def run_workflow(engine_args: arcaflow.EngineArgs, kubeconfig_path: str) -> int:
 
 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)
+    current_path = Path().resolve()
+    context = f"{current_path}/{Path(input_file).parent}"
+    workflow = f"{context}/workflow.yaml"
+    config = f"{context}/config.yaml"
     if not os.path.exists(context):
         raise Exception(
             "context folder for arcaflow workflow not found: {}".format(
@@ -61,7 +62,8 @@ def build_args(input_file: str) -> arcaflow.EngineArgs:
     engine_args = arcaflow.EngineArgs()
     engine_args.context = context
     engine_args.config = config
-    engine_args.input = input_file
+    engine_args.workflow = workflow
+    engine_args.input = f"{current_path}/{input_file}"
     return engine_args
 
 

kraken/chaos_recommender/analysis.py

@@ -4,13 +4,10 @@ import pandas as pd
 import kraken.chaos_recommender.kraken_tests as kraken_tests
 import time
 
-threshold = .7  # Adjust the threshold as needed
-heatmap_cpu_threshold = .5
-heatmap_mem_threshold = .5
-
 KRAKEN_TESTS_PATH = "./kraken_chaos_tests.txt"
 
-#Placeholder, this should be done with topology
+
+# Placeholder, this should be done with topology
 def return_critical_services():
     return ["web", "cart"]
 
@@ -19,15 +16,18 @@ 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["Namespace"] = data["namespace"]
     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):
+
+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()
@@ -47,44 +47,85 @@ def get_services_above_heatmap_threshold(dataframe, cpu_threshold, mem_threshold
     return cpu_services, mem_services
 
 
-def analysis(file_path, chaos_tests_config):
+def analysis(file_path, namespaces, 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)
+    # Dict for saving analysis data -- key is the namespace
+    analysis_data = {}
 
-    # Identify outliers
-    outliers_cpu, outliers_memory, outliers_network = identify_outliers(zscores)
-    cpu_services, mem_services = get_services_above_heatmap_threshold(data, heatmap_cpu_threshold, heatmap_mem_threshold)
+    # Identify outliers for each namespace
+    for namespace in namespaces:
 
-    # Display the identified outliers
-    logging.info("======================== Profiling ==================================")
-    logging.info(f"CPU outliers: {outliers_cpu}")
-    logging.info(f"Memory outliers: {outliers_memory}")
-    logging.info(f"Network outliers: {outliers_network}")
-    logging.info("===================== HeatMap Analysis ==============================")
+        logging.info(f"Identifying outliers for namespace {namespace}...")
+
+        namespace_zscores = zscores.loc[zscores["Namespace"] == namespace]
+        namespace_data = data.loc[data["namespace"] == namespace]
+        outliers_cpu, outliers_memory, outliers_network = identify_outliers(
+            namespace_zscores, threshold)
+        cpu_services, mem_services = get_services_above_heatmap_threshold(
+            namespace_data, heatmap_cpu_threshold, heatmap_mem_threshold)
+
+        analysis_data[namespace] = analysis_json(outliers_cpu, outliers_memory,
+                                                 outliers_network,
+                                                 cpu_services, mem_services,
+                                                 chaos_tests_config)
+
+        if cpu_services:
+            logging.info(f"These services use significant CPU compared to "
+                         f"their assigned limits: {cpu_services}")
+        else:
+            logging.info("There are no services that are using significant "
+                         "CPU compared to their assigned limits "
+                         "(infinite in case no limits are set).")
+        if mem_services:
+            logging.info(f"These services use significant MEMORY compared to "
+                         f"their assigned limits: {mem_services}")
+        else:
+            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:
-        logging.info("Services with CPU_HEATMAP above threshold:", cpu_services)
-    else:
-        logging.info("There are no services that are using siginificant CPU compared to their assigned limits (infinite in case no limits are set).")
+        cpu_recommend = {"services": cpu_services,
+                         "tests": chaos_tests_config['CPU']}
+        recommendations["cpu_services_recommendations"] = cpu_recommend
+
     if mem_services:
-        logging.info("Services with MEM_HEATMAP above threshold:", mem_services)
-    else:
-        logging.info("There are no services that are using siginificant MEMORY compared to their assigned limits (infinite in case no limits are set).")
-    time.sleep(2)
-    logging.info("======================= Recommendations =============================")
-    if cpu_services:
-        logging.info(f"Recommended tests for {str(cpu_services)}  :\n {chaos_tests_config['CPU']}")
-        logging.info("\n")
-    if mem_services:
-        logging.info(f"Recommended tests for {str(mem_services)}  :\n {chaos_tests_config['MEM']}")
-        logging.info("\n")
+        mem_recommend = {"services": mem_services,
+                         "tests": chaos_tests_config['MEM']}
+        recommendations["mem_services_recommendations"] = mem_recommend
 
     if outliers_network:
-        logging.info(f"Recommended tests for  str(outliers_network)  :\n {chaos_tests_config['NETWORK']}")
-        logging.info("\n")
+        outliers_network_recommend = {"outliers_networks": outliers_network,
+                                      "tests": chaos_tests_config['NETWORK']}
+        recommendations["outliers_network_recommendations"] = (
+            outliers_network_recommend)
 
-    logging.info("\n")
-    logging.info("Please check data in utilisation.txt for further analysis")
+    return [profiling, heatmap, recommendations]

kraken/chaos_recommender/prometheus.py

@@ -1,6 +1,5 @@
 import logging
 
-import pandas
 from prometheus_api_client import PrometheusConnect
 import pandas as pd
 import urllib3
@@ -8,6 +7,7 @@ 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]
@@ -17,29 +17,60 @@ def convert_data_to_dataframe(data, label):
 
 
 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)
+    return result.get(service) # for those pods whose limits are not defined they can take as much resources, there assigning a very high value
 
 
+def convert_data_limits(data, node_data, service, prometheus):
+    result = {}
+    for entry in data:
+        pod_name = entry['metric']['pod']
+        value = entry['value'][1]
+        result[pod_name] = value
+    return result.get(service, get_node_capacity(node_data, service, prometheus)) # for those pods whose limits are not defined they can take as much resources, there assigning a very high value
+
+def get_node_capacity(node_data, pod_name, prometheus ):
+
+    # Get the node name on which the pod is running
+    query = f'kube_pod_info{{pod="{pod_name}"}}'
+    result = prometheus.custom_query(query)
+    if not result:
+        return None
+
+    node_name = result[0]['metric']['node']
+
+    for item in node_data:
+        if item['metric']['node'] == node_name:
+            return item['value'][1]
+
+    return '1000000000'
+
+
+def save_utilization_to_file(utilization, filename, prometheus):
+
+    merged_df = pd.DataFrame(columns=['namespace', 'service', 'CPU', 'CPU_LIMITS', 'MEM', 'MEM_LIMITS', 'NETWORK'])
+    for namespace in utilization:
+        # Loading utilization_data[] for namespace
+        # indexes -- 0 CPU, 1 CPU limits, 2 mem, 3 mem limits, 4 network
+        utilization_data = utilization[namespace]
+        df_cpu = convert_data_to_dataframe(utilization_data[0], "CPU")
+        services = df_cpu.service.unique()
+        logging.info(f"Services for namespace {namespace}: {services}")
+
+        for s in services:
+
+            new_row_df = pd.DataFrame({
+                "namespace": namespace, "service": s,
+                "CPU": convert_data(utilization_data[0], s),
+                "CPU_LIMITS": convert_data_limits(utilization_data[1],utilization_data[5], s, prometheus),
+                "MEM": convert_data(utilization_data[2], s),
+                "MEM_LIMITS": convert_data_limits(utilization_data[3], utilization_data[6], s, prometheus),
+                "NETWORK": convert_data(utilization_data[4], 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)
@@ -49,48 +80,65 @@ def save_utilization_to_file(cpu_data, cpu_limits_result, mem_data, mem_limits_r
     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['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):
+
+def fetch_utilization_from_prometheus(prometheus_endpoint, auth_token,
+                                      namespaces, scrape_duration):
     urllib3.disable_warnings()
-    prometheus = PrometheusConnect(url=prometheus_endpoint, headers={'Authorization':'Bearer {}'.format(auth_token)}, disable_ssl=True)
+    prometheus = PrometheusConnect(url=prometheus_endpoint, headers={
+        'Authorization':'Bearer {}'.format(auth_token)}, disable_ssl=True)
 
-    # Fetch CPU utilization
-    cpu_query = 'sum (rate (container_cpu_usage_seconds_total{image!="", namespace="%s"}[%s])) by (pod) *1000' % (namespace,scrape_duration)
-    logging.info(cpu_query)
-    cpu_result = prometheus.custom_query(cpu_query)
-    cpu_data = cpu_result
-
-
-    cpu_limits_query = '(sum by (pod) (kube_pod_container_resource_limits{resource="cpu", namespace="%s"}))*1000' %(namespace)
-    logging.info(cpu_limits_query)
-    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)
-    logging.info(mem_query)
-    mem_result = prometheus.custom_query(mem_query)
-    mem_data = mem_result
-
-    mem_limits_query = 'sum by (pod) (kube_pod_container_resource_limits{resource="memory", namespace="%s"})  ' %(namespace)
-    logging.info(mem_limits_query)
-    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)
-    logging.info(network_query)
-    network_data = network_result
-
-
-    save_utilization_to_file(cpu_data, cpu_limits_result, mem_data, mem_limits_result, network_data, saved_metrics_path)
-    return saved_metrics_path
+    # Dicts for saving utilisation and queries -- key is namespace
+    utilization = {}
+    queries = {}
+
+    logging.info("Fetching utilization...")
+    for namespace in namespaces:
+
+        # Fetch CPU 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)
+
+        node_cpu_limits_query = 'kube_node_status_capacity{resource="cpu", unit="core"}*1000'
+        node_cpu_limits_result = prometheus.custom_query(node_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)
+
+        node_mem_limits_query = 'kube_node_status_capacity{resource="memory", unit="byte"}'
+        node_mem_limits_result = prometheus.custom_query(node_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)
+
+        utilization[namespace] = [cpu_result, cpu_limits_result, mem_result, mem_limits_result, network_result, node_cpu_limits_result, node_mem_limits_result ]
+        queries[namespace] = json_queries(cpu_query, cpu_limits_query, mem_query, mem_limits_query, network_query)
+
+    save_utilization_to_file(utilization, saved_metrics_path, prometheus)
+
+    return saved_metrics_path, queries
 
 
+def json_queries(cpu_query, cpu_limits_query, mem_query, mem_limits_query, network_query):
+    queries = {
+        "cpu_query": cpu_query,
+        "cpu_limit_query": cpu_limits_query,
+        "memory_query": mem_query,
+        "memory_limit_query": mem_limits_query,
+        "network_query": network_query
+    }
+    return queries

kraken/network_chaos/actions.py

@@ -23,7 +23,7 @@ def run(scenarios_list, config, wait_duration, kubecli: KrknKubernetes, telemetr
     for net_config in scenarios_list:
         scenario_telemetry = ScenarioTelemetry()
         scenario_telemetry.scenario = net_config
-        scenario_telemetry.startTimeStamp = time.time()
+        scenario_telemetry.start_timestamp = time.time()
         telemetry.set_parameters_base64(scenario_telemetry, net_config)
         try:
             with open(net_config, "r") as file:
@@ -114,11 +114,11 @@ def run(scenarios_list, config, wait_duration, kubecli: KrknKubernetes, telemetr
                     logging.info("Deleting jobs")
                     delete_job(joblst[:], kubecli)
         except (RuntimeError, Exception):
-            scenario_telemetry.exitStatus = 1
+            scenario_telemetry.exit_status = 1
             failed_scenarios.append(net_config)
             log_exception(net_config)
         else:
-            scenario_telemetry.exitStatus = 0
+            scenario_telemetry.exit_status = 0
         scenario_telemetries.append(scenario_telemetry)
     return failed_scenarios, scenario_telemetries
 

kraken/node_actions/az_node_scenarios.py

@@ -1,6 +1,6 @@
 
 import time
-import yaml
+import os
 import kraken.invoke.command as runcommand
 import logging
 import kraken.node_actions.common_node_functions as nodeaction
@@ -17,9 +17,9 @@ class Azure:
         # Acquire a credential object using CLI-based authentication.
         credentials = DefaultAzureCredential()
         logging.info("credential " + str(credentials))
-        az_account = runcommand.invoke("az account list -o yaml")
-        az_account_yaml = yaml.safe_load(az_account, Loader=yaml.FullLoader)
-        subscription_id = az_account_yaml[0]["id"]
+        # az_account = runcommand.invoke("az account list -o yaml")
+        # az_account_yaml = yaml.safe_load(az_account, Loader=yaml.FullLoader)
+        subscription_id = os.getenv("AZURE_SUBSCRIPTION_ID")
         self.compute_client = ComputeManagementClient(credentials, subscription_id)
 
     # Get the instance ID of the node

kraken/node_actions/gcp_node_scenarios.py

@@ -1,6 +1,8 @@
+import os
 import sys
 import time
 import logging
+import json
 import kraken.node_actions.common_node_functions as nodeaction
 from kraken.node_actions.abstract_node_scenarios import abstract_node_scenarios
 from googleapiclient import discovery
@@ -10,11 +12,19 @@ from krkn_lib.k8s import KrknKubernetes
 
 class GCP:
     def __init__(self):
+        try: 
+            gapp_creds = os.getenv("GOOGLE_APPLICATION_CREDENTIALS")
+            with open(gapp_creds, "r") as f:
+                f_str = f.read()
+                self.project = json.loads(f_str)['project_id']
+            #self.project = runcommand.invoke("gcloud config get-value project").split("/n")[0].strip()
+            logging.info("project " + str(self.project) + "!")
+            credentials = GoogleCredentials.get_application_default()
+            self.client = discovery.build("compute", "v1", credentials=credentials, cache_discovery=False)
 
-        self.project = runcommand.invoke("gcloud config get-value project").split("/n")[0].strip()
-        logging.info("project " + str(self.project) + "!")
-        credentials = GoogleCredentials.get_application_default()
-        self.client = discovery.build("compute", "v1", credentials=credentials, cache_discovery=False)
+        except Exception as e: 
+            logging.error("Error on setting up GCP connection: " + str(e))
+            sys.exit(1)
 
     # Get the instance ID of the node
     def get_instance_id(self, node):

kraken/node_actions/run.py

@@ -15,7 +15,7 @@ import kraken.cerberus.setup as cerberus
 from krkn_lib.k8s import KrknKubernetes
 from krkn_lib.telemetry.k8s import KrknTelemetryKubernetes
 from krkn_lib.models.telemetry import ScenarioTelemetry
-from krkn_lib.utils.functions import get_yaml_item_value
+from krkn_lib.utils.functions import get_yaml_item_value, log_exception
 
 node_general = False
 
@@ -61,7 +61,7 @@ def run(scenarios_list, config, wait_duration, kubecli: KrknKubernetes, telemetr
     for node_scenario_config in scenarios_list:
         scenario_telemetry = ScenarioTelemetry()
         scenario_telemetry.scenario = node_scenario_config
-        scenario_telemetry.startTimeStamp = time.time()
+        scenario_telemetry.start_timestamp = time.time()
         telemetry.set_parameters_base64(scenario_telemetry, node_scenario_config)
         with open(node_scenario_config, "r") as f:
             node_scenario_config = yaml.full_load(f)
@@ -78,13 +78,13 @@ def run(scenarios_list, config, wait_duration, kubecli: KrknKubernetes, telemetr
                             cerberus.get_status(config, start_time, end_time)
                             logging.info("")
                         except (RuntimeError, Exception) as e:
-                            scenario_telemetry.exitStatus = 1
+                            scenario_telemetry.exit_status = 1
                             failed_scenarios.append(node_scenario_config)
                             log_exception(node_scenario_config)
                         else:
-                            scenario_telemetry.exitStatus = 0
+                            scenario_telemetry.exit_status = 0
 
-                        scenario_telemetry.endTimeStamp = time.time()
+                        scenario_telemetry.end_timestamp = time.time()
                         scenario_telemetries.append(scenario_telemetry)
 
     return failed_scenarios, scenario_telemetries

kraken/plugins/__init__.py

@@ -2,11 +2,14 @@ import dataclasses
 import json
 import logging
 from os.path import abspath
-from typing import List, Dict
+from typing import List, Dict, Any
 import time
 
 from arcaflow_plugin_sdk import schema, serialization, jsonschema
 from arcaflow_plugin_kill_pod import kill_pods, wait_for_pods
+from krkn_lib.k8s import KrknKubernetes
+from krkn_lib.k8s.pods_monitor_pool import PodsMonitorPool
+
 import kraken.plugins.node_scenarios.vmware_plugin as vmware_plugin
 import kraken.plugins.node_scenarios.ibmcloud_plugin as ibmcloud_plugin
 from kraken.plugins.run_python_plugin import run_python_file
@@ -47,11 +50,14 @@ class Plugins:
                 )
             self.steps_by_id[step.schema.id] = step
 
-    def run(self, file: str, kubeconfig_path: str, kraken_config: str):
+    def unserialize_scenario(self, file: str) -> Any:
+        return serialization.load_from_file(abspath(file))
+
+    def run(self, file: str, kubeconfig_path: str, kraken_config: str, run_uuid:str):
         """
         Run executes a series of steps
         """
-        data = serialization.load_from_file(abspath(file))
+        data = self.unserialize_scenario(abspath(file))
         if not isinstance(data, list):
             raise Exception(
                 "Invalid scenario configuration file: {} expected list, found {}".format(file, type(data).__name__)
@@ -96,7 +102,8 @@ class Plugins:
                 unserialized_input.kubeconfig_path = kubeconfig_path
             if "kraken_config" in step.schema.input.properties:
                 unserialized_input.kraken_config = kraken_config
-            output_id, output_data = step.schema(unserialized_input)
+            output_id, output_data = step.schema(params=unserialized_input, run_id=run_uuid)
+
             logging.info(step.render_output(output_id, output_data) + "\n")
             if output_id in step.error_output_ids:
                 raise Exception(
@@ -213,6 +220,12 @@ PLUGINS = Plugins(
                 "error"
             ]
         ),
+        PluginStep(
+            network_chaos,
+            [
+                "error"
+            ]
+        ),        
         PluginStep(
             pod_outage,
             [
@@ -235,25 +248,73 @@ PLUGINS = Plugins(
 )
 
 
-def run(scenarios: List[str], kubeconfig_path: str, kraken_config: str, failed_post_scenarios: List[str], wait_duration: int, telemetry: KrknTelemetryKubernetes) -> (List[str], list[ScenarioTelemetry]):
+def run(scenarios: List[str],
+        kubeconfig_path: str,
+        kraken_config: str,
+        failed_post_scenarios: List[str],
+        wait_duration: int,
+        telemetry: KrknTelemetryKubernetes,
+        kubecli: KrknKubernetes,
+        run_uuid: str
+        ) -> (List[str], list[ScenarioTelemetry]):
+
     scenario_telemetries: list[ScenarioTelemetry] = []
     for scenario in scenarios:
         scenario_telemetry = ScenarioTelemetry()
         scenario_telemetry.scenario = scenario
-        scenario_telemetry.startTimeStamp = time.time()
+        scenario_telemetry.start_timestamp = time.time()
         telemetry.set_parameters_base64(scenario_telemetry, scenario)
         logging.info('scenario ' + str(scenario))
+        pool = PodsMonitorPool(kubecli)
+        kill_scenarios = [kill_scenario for kill_scenario in PLUGINS.unserialize_scenario(scenario) if kill_scenario["id"] == "kill-pods"]
+
         try:
-            PLUGINS.run(scenario, kubeconfig_path, kraken_config)
+            start_monitoring(pool, kill_scenarios)
+            PLUGINS.run(scenario, kubeconfig_path, kraken_config, run_uuid)
+            result = pool.join()
+            scenario_telemetry.affected_pods = result
+            if result.error:
+                raise Exception(f"unrecovered pods: {result.error}")
+
         except Exception as e:
-            scenario_telemetry.exitStatus = 1
+            logging.error(f"scenario exception: {str(e)}")
+            scenario_telemetry.exit_status = 1
+            pool.cancel()
             failed_post_scenarios.append(scenario)
             log_exception(scenario)
         else:
-            scenario_telemetry.exitStatus = 0
+            scenario_telemetry.exit_status = 0
             logging.info("Waiting for the specified duration: %s" % (wait_duration))
             time.sleep(wait_duration)
         scenario_telemetries.append(scenario_telemetry)
-        scenario_telemetry.endTimeStamp = time.time()
+        scenario_telemetry.end_timestamp = time.time()
 
     return failed_post_scenarios, scenario_telemetries
+
+
+def start_monitoring(pool: PodsMonitorPool, scenarios: list[Any]):
+    for kill_scenario in scenarios:
+        recovery_time = kill_scenario["config"]["krkn_pod_recovery_time"]
+        if ("namespace_pattern" in kill_scenario["config"] and
+                "label_selector" in kill_scenario["config"]):
+            namespace_pattern = kill_scenario["config"]["namespace_pattern"]
+            label_selector = kill_scenario["config"]["label_selector"]
+            pool.select_and_monitor_by_namespace_pattern_and_label(
+                namespace_pattern=namespace_pattern,
+                label_selector=label_selector,
+                max_timeout=recovery_time)
+            logging.info(
+                f"waiting {recovery_time} seconds for pod recovery, "
+                f"pod label selector: {label_selector} namespace pattern: {namespace_pattern}")
+
+        elif ("namespace_pattern" in kill_scenario["config"] and
+              "name_pattern" in kill_scenario["config"]):
+            namespace_pattern = kill_scenario["config"]["namespace_pattern"]
+            name_pattern = kill_scenario["config"]["name_pattern"]
+            pool.select_and_monitor_by_name_pattern_and_namespace_pattern(pod_name_pattern=name_pattern,
+                                                                          namespace_pattern=namespace_pattern,
+                                                                          max_timeout=recovery_time)
+            logging.info(f"waiting {recovery_time} seconds for pod recovery, "
+                         f"pod name pattern: {name_pattern} namespace pattern: {namespace_pattern}")
+        else:
+            raise Exception(f"impossible to determine monitor parameters, check {kill_scenario} configuration")

kraken/plugins/network/ingress_shaping.py

@@ -62,7 +62,7 @@ class NetworkScenarioConfig:
         typing.Optional[int],
         validation.min(1)
     ] = field(
-        default=300,
+        default=30,
         metadata={
             "name": "Wait Duration",
             "description":
@@ -864,7 +864,7 @@ def network_chaos(cfg: NetworkScenarioConfig) -> typing.Tuple[
                 )
             logging.info("Waiting for parallel job to finish")
             start_time = int(time.time())
-            wait_for_job(batch_cli, job_list[:], cfg.wait_duration)
+            wait_for_job(batch_cli, job_list[:], cfg.test_duration+100)
             end_time = int(time.time())
             if publish:
                 cerberus.publish_kraken_status(
@@ -893,7 +893,7 @@ def network_chaos(cfg: NetworkScenarioConfig) -> typing.Tuple[
                     )
                 logging.info("Waiting for serial job to finish")
                 start_time = int(time.time())
-                wait_for_job(batch_cli, job_list[:], cfg.wait_duration)
+                wait_for_job(batch_cli, job_list[:], cfg.test_duration+100)
                 logging.info("Deleting jobs")
                 delete_jobs(cli, batch_cli, job_list[:])
                 job_list = []

kraken/plugins/node_scenarios/vmware_plugin.py

@@ -119,11 +119,11 @@ class vSphere:
         vm = self.get_vm(instance_id)
         try:
             self.client.vcenter.vm.Power.stop(vm)
-            logging.info("Stopped VM -- '{}-({})'", instance_id, vm)
+            logging.info(f"Stopped VM -- '{instance_id}-({vm})'")
             return True
         except AlreadyInDesiredState:
             logging.info(
-                "VM '{}'-'({})' is already Powered Off", instance_id, vm
+                f"VM '{instance_id}'-'({vm})' is already Powered Off"
             )
             return False
 
@@ -136,11 +136,11 @@ class vSphere:
         vm = self.get_vm(instance_id)
         try:
             self.client.vcenter.vm.Power.start(vm)
-            logging.info("Started VM -- '{}-({})'", instance_id, vm)
+            logging.info(f"Started VM -- '{instance_id}-({vm})'")
             return True
         except AlreadyInDesiredState:
             logging.info(
-                "VM '{}'-'({})' is already Powered On", instance_id, vm
+                f"VM '{instance_id}'-'({vm})' is already Powered On"
             )
             return False
 
@@ -318,12 +318,12 @@ class vSphere:
         try:
             vm = self.get_vm(instance_id)
             state = self.client.vcenter.vm.Power.get(vm).state
-            logging.info("Check instance %s status", instance_id)
+            logging.info(f"Check instance {instance_id} status")
             return state
         except Exception as e:
             logging.error(
-                "Failed to get node instance status %s. Encountered following "
-                "exception: %s.", instance_id, e
+                f"Failed to get node instance status {instance_id}. Encountered following "
+                f"exception: {str(e)}. "
             )
             return None
 
@@ -338,16 +338,14 @@ class vSphere:
         while vm is not None:
             vm = self.get_vm(instance_id)
             logging.info(
-                "VM %s is still being deleted, "
-                "sleeping for 5 seconds",
-                instance_id
+                f"VM {instance_id} is still being deleted, "
+                f"sleeping for 5 seconds"
             )
             time.sleep(5)
             time_counter += 5
             if time_counter >= timeout:
                 logging.info(
-                    "VM %s is still not deleted in allotted time",
-                    instance_id
+                    f"VM {instance_id} is still not deleted in allotted time"
                 )
                 return False
         return True
@@ -371,8 +369,7 @@ class vSphere:
             time_counter += 5
             if time_counter >= timeout:
                 logging.info(
-                    "VM %s is still not ready in allotted time",
-                    instance_id
+                    f"VM {instance_id} is still not ready in allotted time"
                 )
                 return False
         return True
@@ -388,16 +385,14 @@ class vSphere:
         while status != Power.State.POWERED_OFF:
             status = self.get_vm_status(instance_id)
             logging.info(
-                "VM %s is still not running, "
-                "sleeping for 5 seconds",
-                instance_id
+                f"VM {instance_id} is still not running, "
+                f"sleeping for 5 seconds"
             )
             time.sleep(5)
             time_counter += 5
             if time_counter >= timeout:
                 logging.info(
-                    "VM %s is still not ready in allotted time",
-                    instance_id
+                    f"VM {instance_id} is still not ready in allotted time"
                 )
                 return False
         return True
@@ -561,7 +556,7 @@ def node_start(
             try:
                 for _ in range(cfg.runs):
                     logging.info("Starting node_start_scenario injection")
-                    logging.info("Starting the node %s ", name)
+                    logging.info(f"Starting the node {name} ")
                     vm_started = vsphere.start_instances(name)
                     if vm_started:
                         vsphere.wait_until_running(name, cfg.timeout)
@@ -571,7 +566,7 @@ def node_start(
                             )
                         nodes_started[int(time.time_ns())] = Node(name=name)
                     logging.info(
-                        "Node with instance ID: %s is in running state", name
+                        f"Node with instance ID: {name} is in running state"
                     )
                     logging.info(
                         "node_start_scenario has been successfully injected!"
@@ -579,8 +574,8 @@ def node_start(
             except Exception as e:
                 logging.error("Failed to start node instance. Test Failed")
                 logging.error(
-                    "node_start_scenario injection failed! "
-                    "Error was: %s", str(e)
+                    f"node_start_scenario injection failed! "
+                    f"Error was: {str(e)}"
                 )
                 return "error", NodeScenarioErrorOutput(
                     format_exc(), kube_helper.Actions.START
@@ -620,7 +615,7 @@ def node_stop(
             try:
                 for _ in range(cfg.runs):
                     logging.info("Starting node_stop_scenario injection")
-                    logging.info("Stopping the node %s ", name)
+                    logging.info(f"Stopping the node {name} ")
                     vm_stopped = vsphere.stop_instances(name)
                     if vm_stopped:
                         vsphere.wait_until_stopped(name, cfg.timeout)
@@ -630,7 +625,7 @@ def node_stop(
                             )
                         nodes_stopped[int(time.time_ns())] = Node(name=name)
                     logging.info(
-                        "Node with instance ID: %s is in stopped state", name
+                        f"Node with instance ID: {name} is in stopped state"
                     )
                     logging.info(
                         "node_stop_scenario has been successfully injected!"
@@ -638,8 +633,8 @@ def node_stop(
             except Exception as e:
                 logging.error("Failed to stop node instance. Test Failed")
                 logging.error(
-                    "node_stop_scenario injection failed! "
-                    "Error was: %s", str(e)
+                    f"node_stop_scenario injection failed! "
+                    f"Error was: {str(e)}"
                 )
                 return "error", NodeScenarioErrorOutput(
                     format_exc(), kube_helper.Actions.STOP
@@ -679,7 +674,7 @@ def node_reboot(
             try:
                 for _ in range(cfg.runs):
                     logging.info("Starting node_reboot_scenario injection")
-                    logging.info("Rebooting the node %s ", name)
+                    logging.info(f"Rebooting the node {name} ")
                     vsphere.reboot_instances(name)
                     if not cfg.skip_openshift_checks:
                         kube_helper.wait_for_unknown_status(
@@ -690,8 +685,8 @@ def node_reboot(
                         )
                     nodes_rebooted[int(time.time_ns())] = Node(name=name)
                     logging.info(
-                        "Node with instance ID: %s has rebooted "
-                        "successfully", name
+                        f"Node with instance ID: {name} has rebooted "
+                        "successfully"
                     )
                     logging.info(
                         "node_reboot_scenario has been successfully injected!"
@@ -699,8 +694,8 @@ def node_reboot(
             except Exception as e:
                 logging.error("Failed to reboot node instance. Test Failed")
                 logging.error(
-                    "node_reboot_scenario injection failed! "
-                    "Error was: %s", str(e)
+                    f"node_reboot_scenario injection failed! "
+                    f"Error was: {str(e)}"
                 )
                 return "error", NodeScenarioErrorOutput(
                     format_exc(), kube_helper.Actions.REBOOT
@@ -739,13 +734,13 @@ def node_terminate(
                     vsphere.stop_instances(name)
                     vsphere.wait_until_stopped(name, cfg.timeout)
                     logging.info(
-                        "Releasing the node with instance ID: %s ", name
+                        f"Releasing the node with instance ID: {name} "
                     )
                     vsphere.release_instances(name)
                     vsphere.wait_until_released(name, cfg.timeout)
                     nodes_terminated[int(time.time_ns())] = Node(name=name)
                     logging.info(
-                        "Node with instance ID: %s has been released", name
+                        f"Node with instance ID: {name} has been released"
                     )
                     logging.info(
                         "node_terminate_scenario has been "
@@ -754,8 +749,8 @@ def node_terminate(
             except Exception as e:
                 logging.error("Failed to terminate node instance. Test Failed")
                 logging.error(
-                    "node_terminate_scenario injection failed! "
-                    "Error was: %s", str(e)
+                    f"node_terminate_scenario injection failed! "
+                    f"Error was: {str(e)}"
                 )
                 return "error", NodeScenarioErrorOutput(
                     format_exc(), kube_helper.Actions.TERMINATE

kraken/pod_scenarios/setup.py

@@ -1,9 +1,13 @@
 import logging
 import time
+from typing import Any
+
 import yaml
 import sys
 import random
 import arcaflow_plugin_kill_pod
+from krkn_lib.k8s.pods_monitor_pool import PodsMonitorPool
+
 import kraken.cerberus.setup as cerberus
 import kraken.post_actions.actions as post_actions
 from krkn_lib.k8s import KrknKubernetes
@@ -79,11 +83,12 @@ def container_run(kubeconfig_path,
 
     failed_scenarios = []
     scenario_telemetries: list[ScenarioTelemetry] = []
+    pool = PodsMonitorPool(kubecli)
 
     for container_scenario_config in scenarios_list:
         scenario_telemetry = ScenarioTelemetry()
         scenario_telemetry.scenario = container_scenario_config[0]
-        scenario_telemetry.startTimeStamp = time.time()
+        scenario_telemetry.start_timestamp = time.time()
         telemetry.set_parameters_base64(scenario_telemetry, container_scenario_config[0])
         if len(container_scenario_config) > 1:
             pre_action_output = post_actions.run(kubeconfig_path, container_scenario_config[1])
@@ -91,23 +96,17 @@ def container_run(kubeconfig_path,
             pre_action_output = ""
         with open(container_scenario_config[0], "r") as f:
             cont_scenario_config = yaml.full_load(f)
+            start_monitoring(kill_scenarios=cont_scenario_config["scenarios"], pool=pool)
             for cont_scenario in cont_scenario_config["scenarios"]:
                 # capture start time
                 start_time = int(time.time())
                 try:
                     killed_containers = container_killing_in_pod(cont_scenario, kubecli)
-                    if len(container_scenario_config) > 1:
-                        failed_post_scenarios = post_actions.check_recovery(
-                            kubeconfig_path,
-                            container_scenario_config,
-                            failed_post_scenarios,
-                            pre_action_output
-                        )
-                    else:
-                        failed_post_scenarios = check_failed_containers(
-                            killed_containers, cont_scenario.get("retry_wait", 120), kubecli
-                        )
-
+                    logging.info(f"killed containers: {str(killed_containers)}")
+                    result = pool.join()
+                    if result.error:
+                        raise Exception(f"pods failed to recovery: {result.error}")
+                    scenario_telemetry.affected_pods = result
                     logging.info("Waiting for the specified duration: %s" % (wait_duration))
                     time.sleep(wait_duration)
 
@@ -117,18 +116,29 @@ def container_run(kubeconfig_path,
                     # publish cerberus status
                     cerberus.publish_kraken_status(config, failed_post_scenarios, start_time, end_time)
                 except (RuntimeError, Exception):
+                    pool.cancel()
                     failed_scenarios.append(container_scenario_config[0])
                     log_exception(container_scenario_config[0])
-                    scenario_telemetry.exitStatus = 1
+                    scenario_telemetry.exit_status = 1
                     # removed_exit
                     # sys.exit(1)
                 else:
-                    scenario_telemetry.exitStatus = 0
-                scenario_telemetry.endTimeStamp = time.time()
+                    scenario_telemetry.exit_status = 0
+                scenario_telemetry.end_timestamp = time.time()
                 scenario_telemetries.append(scenario_telemetry)
 
     return failed_scenarios, scenario_telemetries
 
+def start_monitoring(kill_scenarios: list[Any], pool: PodsMonitorPool):
+    for kill_scenario in kill_scenarios:
+        namespace_pattern = f"^{kill_scenario['namespace']}$"
+        label_selector = kill_scenario["label_selector"]
+        recovery_time = kill_scenario["expected_recovery_time"]
+        pool.select_and_monitor_by_namespace_pattern_and_label(
+            namespace_pattern=namespace_pattern,
+            label_selector=label_selector,
+            max_timeout=recovery_time)
+
 
 def container_killing_in_pod(cont_scenario, kubecli: KrknKubernetes):
     scenario_name = get_yaml_item_value(cont_scenario, "name", "")

kraken/prometheus/client.py

@@ -1,10 +1,13 @@
 import datetime
 import os.path
+from typing import Optional
+
 import urllib3
 import logging
 import sys
 
 import yaml
+from krkn_lib.models.krkn import ChaosRunAlertSummary, ChaosRunAlert
 from krkn_lib.prometheus.krkn_prometheus import KrknPrometheus
 urllib3.disable_warnings(urllib3.exceptions.InsecureRequestWarning)
 def alerts(prom_cli: KrknPrometheus, start_time, end_time, alert_profile):
@@ -27,4 +30,59 @@ def alerts(prom_cli: KrknPrometheus, start_time, end_time, alert_profile):
 
             prom_cli.process_alert(alert,
                                    datetime.datetime.fromtimestamp(start_time),
-                                   datetime.datetime.fromtimestamp(end_time))
+                                   datetime.datetime.fromtimestamp(end_time))
+
+
+def critical_alerts(prom_cli: KrknPrometheus,
+                    summary: ChaosRunAlertSummary,
+                    run_id,
+                    scenario,
+                    start_time,
+                    end_time):
+    summary.scenario = scenario
+    summary.run_id = run_id
+    query = r"""ALERTS{severity="critical"}"""
+    logging.info("Checking for critical alerts firing post chaos")
+
+    during_critical_alerts = prom_cli.process_prom_query_in_range(
+        query,
+        start_time=datetime.datetime.fromtimestamp(start_time),
+        end_time=end_time
+
+    )
+
+    for alert in during_critical_alerts:
+        if "metric" in alert:
+            alertname = alert["metric"]["alertname"] if "alertname" in alert["metric"] else "none"
+            alertstate = alert["metric"]["alertstate"] if "alertstate" in alert["metric"] else "none"
+            namespace = alert["metric"]["namespace"] if "namespace" in alert["metric"] else "none"
+            severity = alert["metric"]["severity"] if "severity" in alert["metric"] else "none"
+            alert = ChaosRunAlert(alertname, alertstate, namespace, severity)
+            summary.chaos_alerts.append(alert)
+
+
+    post_critical_alerts = prom_cli.process_query(
+        query
+    )
+
+    for alert in post_critical_alerts:
+        if "metric" in alert:
+            alertname = alert["metric"]["alertname"] if "alertname" in alert["metric"] else "none"
+            alertstate = alert["metric"]["alertstate"] if "alertstate" in alert["metric"] else "none"
+            namespace = alert["metric"]["namespace"] if "namespace" in alert["metric"] else "none"
+            severity = alert["metric"]["severity"] if "severity" in alert["metric"] else "none"
+            alert = ChaosRunAlert(alertname, alertstate, namespace, severity)
+            summary.post_chaos_alerts.append(alert)
+
+    during_critical_alerts_count = len(during_critical_alerts)
+    post_critical_alerts_count = len(post_critical_alerts)
+    firing_alerts = False
+
+    if during_critical_alerts_count > 0:
+        firing_alerts = True
+
+    if post_critical_alerts_count > 0:
+        firing_alerts = True
+
+    if not firing_alerts:
+        logging.info("No critical alerts are firing!!")

kraken/pvc/pvc_scenario.py

@@ -11,7 +11,7 @@ from krkn_lib.utils.functions import get_yaml_item_value, log_exception
 
 
 # krkn_lib
-def run(scenarios_list, config, kubecli: KrknKubernetes, telemetry: KrknTelemetryKubernetes) -> (list[str], list[ScenarioTelemetry]):
+def run(scenarios_list, config, wait_duration, kubecli: KrknKubernetes, telemetry: KrknTelemetryKubernetes) -> (list[str], list[ScenarioTelemetry]):
     """
     Reads the scenario config and creates a temp file to fill up the PVC
     """
@@ -21,7 +21,7 @@ def run(scenarios_list, config, kubecli: KrknKubernetes, telemetry: KrknTelemetr
     for app_config in scenarios_list:
         scenario_telemetry = ScenarioTelemetry()
         scenario_telemetry.scenario = app_config
-        scenario_telemetry.startTimeStamp = time.time()
+        scenario_telemetry.start_timestamp = time.time()
         telemetry.set_parameters_base64(scenario_telemetry, app_config)
         try:
             if len(app_config) > 1:
@@ -305,7 +305,9 @@ def run(scenarios_list, config, kubecli: KrknKubernetes, telemetry: KrknTelemetr
                         file_size_kb,
                         kubecli
                     )
-
+                    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,
@@ -314,11 +316,11 @@ def run(scenarios_list, config, kubecli: KrknKubernetes, telemetry: KrknTelemetr
                         end_time
                     )
         except (RuntimeError, Exception):
-            scenario_telemetry.exitStatus = 1
+            scenario_telemetry.exit_status = 1
             failed_scenarios.append(app_config)
             log_exception(app_config)
         else:
-            scenario_telemetry.exitStatus = 0
+            scenario_telemetry.exit_status = 0
         scenario_telemetries.append(scenario_telemetry)
 
     return failed_scenarios, scenario_telemetries

kraken/service_disruption/common_service_disruption_functions.py

@@ -165,7 +165,7 @@ def run(
     for scenario_config in scenarios_list:
         scenario_telemetry = ScenarioTelemetry()
         scenario_telemetry.scenario = scenario_config[0]
-        scenario_telemetry.startTimeStamp = time.time()
+        scenario_telemetry.start_timestamp = time.time()
         telemetry.set_parameters_base64(scenario_telemetry, scenario_config[0])
         try:
             if len(scenario_config) > 1:
@@ -249,12 +249,12 @@ def run(
                     end_time = int(time.time())
                     cerberus.publish_kraken_status(config, failed_post_scenarios, start_time, end_time)
         except (Exception, RuntimeError):
-            scenario_telemetry.exitStatus = 1
+            scenario_telemetry.exit_status = 1
             failed_scenarios.append(scenario_config[0])
             log_exception(scenario_config[0])
         else:
-            scenario_telemetry.exitStatus = 0
-        scenario_telemetry.endTimeStamp = time.time()
+            scenario_telemetry.exit_status = 0
+        scenario_telemetry.end_timestamp = time.time()
         scenario_telemetries.append(scenario_telemetry)
     return failed_scenarios, scenario_telemetries
 

kraken/service_hijacking/service_hijacking.py

@@ -0,0 +1,90 @@
+import logging
+import time
+
+import yaml
+from krkn_lib.k8s import KrknKubernetes
+from krkn_lib.models.telemetry import ScenarioTelemetry
+from krkn_lib.telemetry.k8s import KrknTelemetryKubernetes
+
+
+def run(scenarios_list: list[str],wait_duration: int,  krkn_lib: KrknKubernetes, 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.start_timestamp = time.time()
+        telemetry.set_parameters_base64(scenario_telemetry, scenario)
+        with open(scenario) as stream:
+            scenario_config = yaml.safe_load(stream)
+
+        service_name = scenario_config['service_name']
+        service_namespace = scenario_config['service_namespace']
+        plan = scenario_config["plan"]
+        image = scenario_config["image"]
+        target_port = scenario_config["service_target_port"]
+        chaos_duration = scenario_config["chaos_duration"]
+
+        logging.info(f"checking service {service_name} in namespace: {service_namespace}")
+        if not krkn_lib.service_exists(service_name, service_namespace):
+            logging.error(f"service: {service_name} not found in namespace: {service_namespace}, failed to run scenario.")
+            fail(scenario_telemetry, scenario_telemetries)
+            failed_post_scenarios.append(scenario)
+            break
+        try:
+            logging.info(f"service: {service_name} found in namespace: {service_namespace}")
+            logging.info(f"creating webservice and initializing test plan...")
+            # both named ports and port numbers can be used
+            if isinstance(target_port, int):
+                logging.info(f"webservice will listen on port {target_port}")
+                webservice = krkn_lib.deploy_service_hijacking(service_namespace, plan, image, port_number=target_port)
+            else:
+                logging.info(f"traffic will be redirected to named port: {target_port}")
+                webservice = krkn_lib.deploy_service_hijacking(service_namespace, plan, image, port_name=target_port)
+            logging.info(f"successfully deployed pod: {webservice.pod_name} "
+                         f"in namespace:{service_namespace} with selector {webservice.selector}!"
+                         )
+            logging.info(f"patching service: {service_name} to hijack traffic towards: {webservice.pod_name}")
+            original_service = krkn_lib.replace_service_selector([webservice.selector], service_name, service_namespace)
+            if original_service is None:
+                logging.error(f"failed to patch service: {service_name}, namespace: {service_namespace} with selector {webservice.selector}")
+                fail(scenario_telemetry, scenario_telemetries)
+                failed_post_scenarios.append(scenario)
+                break
+
+            logging.info(f"service: {service_name} successfully patched!")
+            logging.info(f"original service manifest:\n\n{yaml.dump(original_service)}")
+            logging.info(f"waiting {chaos_duration} before restoring the service")
+            time.sleep(chaos_duration)
+            selectors = ["=".join([key, original_service["spec"]["selector"][key]]) for key in original_service["spec"]["selector"].keys()]
+            logging.info(f"restoring the service selectors {selectors}")
+            original_service = krkn_lib.replace_service_selector(selectors, service_name, service_namespace)
+            if original_service is None:
+                logging.error(f"failed to restore original service: {service_name}, namespace: {service_namespace} with selectors: {selectors}")
+                fail(scenario_telemetry, scenario_telemetries)
+                failed_post_scenarios.append(scenario)
+                break
+            logging.info("selectors successfully restored")
+            logging.info("undeploying service-hijacking resources...")
+            krkn_lib.undeploy_service_hijacking(webservice)
+
+            logging.info("End of scenario. Waiting for the specified duration: %s" % (wait_duration))
+            time.sleep(wait_duration)
+            
+            scenario_telemetry.exit_status = 0
+            scenario_telemetry.end_timestamp = time.time()
+            scenario_telemetries.append(scenario_telemetry)
+            logging.info("success")
+        except Exception as e:
+            logging.error(f"scenario {scenario} failed with exception: {e}")
+            fail(scenario_telemetry, scenario_telemetries)
+            failed_post_scenarios.append(scenario)
+
+    return failed_post_scenarios, scenario_telemetries
+
+
+def fail(scenario_telemetry: ScenarioTelemetry,  scenario_telemetries: list[ScenarioTelemetry]):
+    scenario_telemetry.exit_status = 1
+    scenario_telemetry.end_timestamp = time.time()
+    scenario_telemetries.append(scenario_telemetry)
+

kraken/shut_down/common_shut_down_func.py

@@ -147,7 +147,7 @@ def run(scenarios_list, config, wait_duration, kubecli: KrknKubernetes, telemetr
 
         scenario_telemetry = ScenarioTelemetry()
         scenario_telemetry.scenario = config_path
-        scenario_telemetry.startTimeStamp = time.time()
+        scenario_telemetry.start_timestamp = time.time()
         telemetry.set_parameters_base64(scenario_telemetry, config_path)
 
         with open(config_path, "r") as f:
@@ -175,11 +175,11 @@ def run(scenarios_list, config, wait_duration, kubecli: KrknKubernetes, telemetr
             except (RuntimeError, Exception):
                 log_exception(config_path)
                 failed_scenarios.append(config_path)
-                scenario_telemetry.exitStatus = 1
+                scenario_telemetry.exit_status = 1
             else:
-                scenario_telemetry.exitStatus = 0
+                scenario_telemetry.exit_status = 0
 
-            scenario_telemetry.endTimeStamp = time.time()
+            scenario_telemetry.end_timestamp = time.time()
             scenario_telemetries.append(scenario_telemetry)
 
     return failed_scenarios, scenario_telemetries

kraken/time_actions/common_time_functions.py

@@ -2,14 +2,18 @@ import datetime
 import time
 import logging
 import re
+
 import yaml
 import random
+
+from krkn_lib import utils
+from kubernetes.client import ApiException
+
 from ..cerberus import setup as cerberus
-from ..invoke import command as runcommand
 from krkn_lib.k8s import KrknKubernetes
 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
+from krkn_lib.utils.functions import get_yaml_item_value, log_exception, get_random_string
 
 
 # krkn_lib
@@ -35,13 +39,6 @@ def pod_exec(pod_name, command, namespace, container_name, kubecli:KrknKubernete
     return response
 
 
-def node_debug(node_name, command):
-    response = runcommand.invoke(
-        "oc debug node/" + node_name + " -- chroot /host " + command
-    )
-    return response
-
-
 # krkn_lib
 def get_container_name(pod_name, namespace, kubecli:KrknKubernetes, container_name=""):
 
@@ -65,15 +62,46 @@ def get_container_name(pod_name, namespace, kubecli:KrknKubernetes, container_na
         return container_name
 
 
+
+def skew_node(node_name: str, action: str, kubecli: KrknKubernetes):
+    pod_namespace = "default"
+    status_pod_name = f"time-skew-pod-{get_random_string(5)}"
+    skew_pod_name = f"time-skew-pod-{get_random_string(5)}"
+    ntp_enabled = True
+    logging.info(f'Creating pod to skew {"time" if action == "skew_time" else "date"} on node {node_name}')
+    status_command = ["timedatectl"]
+    param = "2001-01-01"
+    skew_command = ["timedatectl", "set-time"]
+    if action == "skew_time":
+        skew_command.append("01:01:01")
+    else:
+        skew_command.append("2001-01-01")
+
+    try:
+        status_response = kubecli.exec_command_on_node(node_name, status_command, status_pod_name, pod_namespace)
+        if "Network time on: no" in status_response:
+            ntp_enabled = False
+
+            logging.warning(f'ntp unactive on node {node_name} skewing {"time" if action == "skew_time" else "date"} to {param}')
+            pod_exec(skew_pod_name, skew_command, pod_namespace, None, kubecli)
+        else:
+            logging.info(f'ntp active in cluster node, {"time" if action == "skew_time" else "date"} skewing will have no effect, skipping')
+    except ApiException:
+        pass
+    except Exception as e:
+        logging.error(f"failed to execute skew command in pod: {e}")
+    finally:
+        kubecli.delete_pod(status_pod_name, pod_namespace)
+        if not ntp_enabled :
+            kubecli.delete_pod(skew_pod_name, pod_namespace)
+
+
+
 # krkn_lib
 def skew_time(scenario, kubecli:KrknKubernetes):
-    skew_command = "date --date "
-    if scenario["action"] == "skew_date":
-        skewed_date = "00-01-01"
-        skew_command += skewed_date
-    elif scenario["action"] == "skew_time":
-        skewed_time = "01:01:01"
-        skew_command += skewed_time
+    if scenario["action"] not in ["skew_date","skew_time"]:
+        raise RuntimeError(f'{scenario["action"]} is not a valid time skew action')
+
     if "node" in scenario["object_type"]:
         node_names = []
         if "object_name" in scenario.keys() and scenario["object_name"]:
@@ -83,13 +111,19 @@ def skew_time(scenario, kubecli:KrknKubernetes):
             scenario["label_selector"]
         ):
             node_names = kubecli.list_nodes(scenario["label_selector"])
-
         for node in node_names:
-            node_debug(node, skew_command)
+            skew_node(node, scenario["action"], kubecli)
             logging.info("Reset date/time on node " + str(node))
         return "node", node_names
 
     elif "pod" in scenario["object_type"]:
+        skew_command = "date --date "
+        if scenario["action"] == "skew_date":
+            skewed_date = "00-01-01"
+            skew_command += skewed_date
+        elif scenario["action"] == "skew_time":
+            skewed_time = "01:01:01"
+            skew_command += skewed_time
         container_name = get_yaml_item_value(scenario, "container_name", "")
         pod_names = []
         if "object_name" in scenario.keys() and scenario["object_name"]:
@@ -241,7 +275,8 @@ def check_date_time(object_type, names, kubecli:KrknKubernetes):
     if object_type == "node":
         for node_name in names:
             first_date_time = datetime.datetime.utcnow()
-            node_datetime_string = node_debug(node_name, skew_command)
+            check_pod_name = f"time-skew-pod-{get_random_string(5)}"
+            node_datetime_string = kubecli.exec_command_on_node(node_name, [skew_command], check_pod_name)
             node_datetime = string_to_date(node_datetime_string)
             counter = 0
             while not (
@@ -252,7 +287,8 @@ def check_date_time(object_type, names, kubecli:KrknKubernetes):
                     "Date/time on node %s still not reset, "
                     "waiting 10 seconds and retrying" % node_name
                 )
-                node_datetime_string = node_debug(node_name, skew_command)
+
+                node_datetime_string = kubecli.exec_cmd_in_pod([skew_command], check_pod_name, "default")
                 node_datetime = string_to_date(node_datetime_string)
                 counter += 1
                 if counter > max_retries:
@@ -266,6 +302,8 @@ def check_date_time(object_type, names, kubecli:KrknKubernetes):
                 logging.info(
                     "Date in node " + str(node_name) + " reset properly"
                 )
+            kubecli.delete_pod(check_pod_name)
+
     elif object_type == "pod":
         for pod_name in names:
             first_date_time = datetime.datetime.utcnow()
@@ -316,7 +354,7 @@ def run(scenarios_list, config, wait_duration, kubecli:KrknKubernetes, telemetry
     for time_scenario_config in scenarios_list:
         scenario_telemetry = ScenarioTelemetry()
         scenario_telemetry.scenario = time_scenario_config
-        scenario_telemetry.startTimeStamp = time.time()
+        scenario_telemetry.start_timestamp = time.time()
         telemetry.set_parameters_base64(scenario_telemetry, time_scenario_config)
         try:
             with open(time_scenario_config, "r") as f:
@@ -339,12 +377,12 @@ def run(scenarios_list, config, wait_duration, kubecli:KrknKubernetes, telemetry
                         end_time
                     )
         except (RuntimeError, Exception):
-            scenario_telemetry.exitStatus = 1
+            scenario_telemetry.exit_status = 1
             log_exception(time_scenario_config)
             failed_scenarios.append(time_scenario_config)
         else:
-            scenario_telemetry.exitStatus = 0
-        scenario_telemetry.endTimeStamp = time.time()
+            scenario_telemetry.exit_status = 0
+        scenario_telemetry.end_timestamp = time.time()
         scenario_telemetries.append(scenario_telemetry)
 
     return failed_scenarios, scenario_telemetries

kraken/zone_outage/actions.py

@@ -19,7 +19,7 @@ def run(scenarios_list, config, wait_duration, telemetry: KrknTelemetryKubernete
     for zone_outage_config in scenarios_list:
         scenario_telemetry = ScenarioTelemetry()
         scenario_telemetry.scenario = zone_outage_config
-        scenario_telemetry.startTimeStamp = time.time()
+        scenario_telemetry.start_timestamp = time.time()
         telemetry.set_parameters_base64(scenario_telemetry, zone_outage_config)
         try:
             if len(zone_outage_config) > 1:
@@ -110,12 +110,12 @@ def run(scenarios_list, config, wait_duration, telemetry: KrknTelemetryKubernete
                         end_time
                     )
         except (RuntimeError, Exception):
-            scenario_telemetry.exitStatus = 1
+            scenario_telemetry.exit_status = 1
             failed_scenarios.append(zone_outage_config)
             log_exception(zone_outage_config)
         else:
-            scenario_telemetry.exitStatus = 0
-        scenario_telemetry.endTimeStamp = time.time()
+            scenario_telemetry.exit_status = 0
+        scenario_telemetry.end_timestamp = time.time()
         scenario_telemetries.append(scenario_telemetry)
     return failed_scenarios, scenario_telemetries
 

requirements.txt

@@ -1,40 +1,40 @@
-PyYAML>=5.1
 aliyun-python-sdk-core==2.13.36
 aliyun-python-sdk-ecs==4.24.25
-arcaflow==0.9.0
-arcaflow-plugin-sdk==0.10.0
-azure-identity
-azure-keyvault
-azure-mgmt-compute
+arcaflow-plugin-sdk==0.14.0
+arcaflow==0.17.2
 boto3==1.28.61
-coverage
-datetime
-docker
-docker-compose
-git+https://github.com/redhat-chaos/arcaflow-plugin-kill-pod.git
-git+https://github.com/vmware/vsphere-automation-sdk-python.git@v8.0.0.0
-gitpython
-google-api-python-client
-ibm_cloud_sdk_core
-ibm_vpc
+azure-identity==1.16.1
+azure-keyvault==4.2.0
+azure-mgmt-compute==30.5.0
 itsdangerous==2.0.1
-jinja2==3.0.3
-krkn-lib >= 1.4.5
-kubernetes
-lxml >= 4.3.0
-oauth2client>=4.1.3
-openshift-client
-paramiko
-podman-compose
-pyVmomi >= 6.7
-pyfiglet
-pytest
-python-ipmi
-python-openstackclient
-requests
-service_identity
+coverage==7.4.1
+datetime==5.4
+docker==7.0.0
+gitpython==3.1.41
+google-api-python-client==2.116.0
+ibm_cloud_sdk_core==3.18.0
+ibm_vpc==0.20.0
+jinja2==3.1.4
+krkn-lib==2.1.6
+lxml==5.1.0
+kubernetes==28.1.0
+oauth2client==4.1.3
+pandas==2.2.0
+openshift-client==1.0.21
+paramiko==3.4.0
+pyVmomi==8.0.2.0.1
+pyfiglet==1.0.2
+pytest==8.0.0
+python-ipmi==0.5.4
+python-openstackclient==6.5.0
+requests==2.32.2
+service_identity==24.1.0
+PyYAML==6.0.1
 setuptools==65.5.1
-werkzeug==3.0.1
-wheel
+werkzeug==3.0.3
+wheel==0.42.0
 zope.interface==5.4.0
-pandas<2.0.0
+
+git+https://github.com/krkn-chaos/arcaflow-plugin-kill-pod.git@v0.1.0
+git+https://github.com/vmware/vsphere-automation-sdk-python.git@v8.0.0.0
+cryptography>=42.0.4 # not directly required, pinned by Snyk to avoid a vulnerability

run_kraken.py

@@ -9,6 +9,8 @@ import optparse
 import pyfiglet
 import uuid
 import time
+
+from krkn_lib.models.krkn import ChaosRunOutput, ChaosRunAlertSummary
 from krkn_lib.prometheus.krkn_prometheus import KrknPrometheus
 import kraken.time_actions.common_time_functions as time_actions
 import kraken.performance_dashboards.setup as performance_dashboards
@@ -23,10 +25,12 @@ import kraken.pvc.pvc_scenario as pvc_scenario
 import kraken.network_chaos.actions as network_chaos
 import kraken.arcaflow_plugin as arcaflow_plugin
 import kraken.prometheus as prometheus_plugin
+import kraken.service_hijacking.service_hijacking as service_hijacking_plugin
 import server as server
 from kraken import plugins
 from krkn_lib.k8s import KrknKubernetes
 from krkn_lib.ocp import KrknOpenshift
+from krkn_lib.telemetry.elastic import KrknElastic
 from krkn_lib.telemetry.k8s import KrknTelemetryKubernetes
 from krkn_lib.telemetry.ocp import KrknTelemetryOpenshift
 from krkn_lib.models.telemetry import ChaosRunTelemetry
@@ -34,7 +38,7 @@ from krkn_lib.utils import SafeLogger
 from krkn_lib.utils.functions import get_yaml_item_value
 
 
-
+report_file = ""
 
 # Main function
 def main(cfg):
@@ -94,6 +98,9 @@ def main(cfg):
             config["performance_monitoring"], "check_critical_alerts", False
         )
         telemetry_api_url = config["telemetry"].get("api_url")
+        elastic_config = get_yaml_item_value(config,"elastic",{})
+        elastic_url = get_yaml_item_value(elastic_config,"elastic_url","")
+        elastic_index = get_yaml_item_value(elastic_config,"elastic_index","")
         
         # Initialize clients
         if (not os.path.isfile(kubeconfig_path) and
@@ -129,8 +136,6 @@ def main(cfg):
         except:
             kubecli.initialize_clients(None)
 
-
-
         # find node kraken might be running on
         kubecli.find_kraken_node()
 
@@ -156,12 +161,22 @@ def main(cfg):
         # Cluster info
         logging.info("Fetching cluster info")
         cv = ""
-        if config["kraken"]["distribution"] == "openshift":
+        if distribution == "openshift":
             cv = ocpcli.get_clusterversion_string()
             if prometheus_url is None:
-                connection_data = ocpcli.get_prometheus_api_connection_data()
-                prometheus_url = connection_data.endpoint
-                prometheus_bearer_token = connection_data.token
+                try:
+                    connection_data = ocpcli.get_prometheus_api_connection_data()
+                    if connection_data:
+                        prometheus_url = connection_data.endpoint
+                        prometheus_bearer_token = connection_data.token
+                    else: 
+                        # If can't make a connection, set alerts to false
+                        enable_alerts = False
+                        critical_alerts = False
+                except Exception:
+                    logging.error("invalid distribution selected, running openshift scenarios against kubernetes cluster."
+                                  "Please set 'kubernetes' in config.yaml krkn.platform and try again")
+                    sys.exit(1)
         if cv != "":
             logging.info(cv)
         else:
@@ -170,7 +185,10 @@ def main(cfg):
         # KrknTelemetry init
         telemetry_k8s = KrknTelemetryKubernetes(safe_logger, kubecli)
         telemetry_ocp = KrknTelemetryOpenshift(safe_logger, ocpcli)
-        prometheus = KrknPrometheus(prometheus_url, prometheus_bearer_token)
+        telemetry_elastic = KrknElastic(safe_logger,elastic_url)
+        summary = ChaosRunAlertSummary()
+        if enable_alerts or check_critical_alerts:
+            prometheus = KrknPrometheus(prometheus_url, prometheus_bearer_token)
 
         logging.info("Server URL: %s" % kubecli.get_host())
 
@@ -200,6 +218,8 @@ def main(cfg):
 
         # Capture the start time
         start_time = int(time.time())
+        post_critical_alerts = 0
+        chaos_output = ChaosRunOutput()
         chaos_telemetry = ChaosRunTelemetry()
         chaos_telemetry.run_uuid = run_uuid
         # Loop to run the chaos starts here
@@ -245,7 +265,9 @@ def main(cfg):
                                 kraken_config,
                                 failed_post_scenarios,
                                 wait_duration,
-                                telemetry_k8s
+                                telemetry_k8s,
+                                kubecli,
+                                run_uuid
                             )
                             chaos_telemetry.scenarios.extend(scenario_telemetries)
                         # krkn_lib
@@ -280,16 +302,9 @@ def main(cfg):
                         # in the config
                         # krkn_lib
                         elif scenario_type == "time_scenarios":
-                            if distribution == "openshift":
                                 logging.info("Running time skew scenarios")
                                 failed_post_scenarios, scenario_telemetries = time_actions.run(scenarios_list, config, wait_duration, kubecli, telemetry_k8s)
                                 chaos_telemetry.scenarios.extend(scenario_telemetries)
-                            else:
-                                logging.error(
-                                    "Litmus scenarios are currently "
-                                    "supported only on openshift"
-                                )
-                                sys.exit(1)
                         # Inject cluster shutdown scenarios
                         # krkn_lib
                         elif scenario_type == "cluster_shut_down_scenarios":
@@ -320,14 +335,14 @@ def main(cfg):
                         elif scenario_type == "application_outages":
                             logging.info("Injecting application outage")
                             failed_post_scenarios, scenario_telemetries = application_outage.run(
-                                scenarios_list, config, wait_duration, telemetry_k8s)
+                                scenarios_list, config, wait_duration, kubecli, telemetry_k8s)
                             chaos_telemetry.scenarios.extend(scenario_telemetries)
 
                         # PVC scenarios
                         # krkn_lib
                         elif scenario_type == "pvc_scenarios":
                             logging.info("Running PVC scenario")
-                            failed_post_scenarios, scenario_telemetries = pvc_scenario.run(scenarios_list, config, kubecli, telemetry_k8s)
+                            failed_post_scenarios, scenario_telemetries = pvc_scenario.run(scenarios_list, config, wait_duration, kubecli, telemetry_k8s)
                             chaos_telemetry.scenarios.extend(scenario_telemetries)
 
                         # Network scenarios
@@ -335,21 +350,27 @@ def main(cfg):
                         elif scenario_type == "network_chaos":
                             logging.info("Running Network Chaos")
                             failed_post_scenarios, scenario_telemetries = network_chaos.run(scenarios_list, config, wait_duration, kubecli, telemetry_k8s)
+                        elif scenario_type == "service_hijacking":
+                            logging.info("Running Service Hijacking Chaos")
+                            failed_post_scenarios, scenario_telemetries = service_hijacking_plugin.run(scenarios_list, wait_duration, kubecli, telemetry_k8s)
+                            chaos_telemetry.scenarios.extend(scenario_telemetries)
 
                         # Check for critical alerts when enabled
+                        post_critical_alerts = 0
                         if check_critical_alerts:
-                            logging.info("Checking for critical alerts firing post choas")
+                            prometheus_plugin.critical_alerts(prometheus,
+                                                              summary,
+                                                              run_uuid,
+                                                              scenario_type,
+                                                              start_time,
+                                                              datetime.datetime.now())
+
+                            chaos_output.critical_alerts = summary
+                            post_critical_alerts = len(summary.post_chaos_alerts)
+                            if post_critical_alerts > 0:
+                                logging.error("Post chaos critical alerts firing please check, exiting")
+                                break
 
-                            ##PROM
-                            query = r"""ALERTS{severity="critical"}"""
-                            critical_alerts = prometheus.process_prom_query_in_range(query, datetime.datetime.fromtimestamp(start_time))
-                            critical_alerts_count = len(critical_alerts)
-                            if critical_alerts_count > 0:
-                                logging.error("Critical alerts are firing: %s", critical_alerts)
-                                logging.error("Please check, exiting")
-                                sys.exit(1)
-                            else:
-                                logging.info("No critical alerts are firing!!")
 
             iteration += 1
             logging.info("")
@@ -363,27 +384,52 @@ def main(cfg):
         # if platform is openshift will be collected
         # Cloud platform and network plugins metadata
         # through OCP specific APIs
-        if config["kraken"]["distribution"] == "openshift":
+        if distribution == "openshift":
             telemetry_ocp.collect_cluster_metadata(chaos_telemetry)
         else:
             telemetry_k8s.collect_cluster_metadata(chaos_telemetry)
 
         decoded_chaos_run_telemetry = ChaosRunTelemetry(json.loads(chaos_telemetry.to_json()))
-        logging.info(f"Telemetry data:\n{decoded_chaos_run_telemetry.to_json()}")
-
+        chaos_output.telemetry = decoded_chaos_run_telemetry
+        logging.info(f"Chaos data:\n{chaos_output.to_json()}")
+        telemetry_elastic.upload_data_to_elasticsearch(decoded_chaos_run_telemetry.to_json(), elastic_index)
         if config["telemetry"]["enabled"]:
-            logging.info(f"telemetry data will be stored on s3 bucket folder: {telemetry_api_url}/download/{telemetry_request_id}")
+            logging.info(f'telemetry data will be stored on s3 bucket folder: {telemetry_api_url}/files/'
+                         f'{(config["telemetry"]["telemetry_group"] if config["telemetry"]["telemetry_group"] else "default")}/'
+                         f'{telemetry_request_id}')
             logging.info(f"telemetry upload log: {safe_logger.log_file_name}")
             try:
                 telemetry_k8s.send_telemetry(config["telemetry"], telemetry_request_id, chaos_telemetry)
                 telemetry_k8s.put_cluster_events(telemetry_request_id, config["telemetry"], start_time, end_time)
+                telemetry_k8s.put_critical_alerts(telemetry_request_id, config["telemetry"], summary)
                 # prometheus data collection is available only on Openshift
-                if config["telemetry"]["prometheus_backup"] and config["kraken"]["distribution"] == "openshift":
-                    safe_logger.info("archives download started:")
-                    prometheus_archive_files = telemetry_ocp.get_ocp_prometheus_data(config["telemetry"], telemetry_request_id)
-                    safe_logger.info("archives upload started:")
-                    telemetry_k8s.put_prometheus_data(config["telemetry"], prometheus_archive_files, telemetry_request_id)
-                if config["telemetry"]["logs_backup"]:
+                if config["telemetry"]["prometheus_backup"]:
+                    prometheus_archive_files = ''
+                    if distribution == "openshift" :
+                        prometheus_archive_files = telemetry_ocp.get_ocp_prometheus_data(config["telemetry"], telemetry_request_id)
+                    else:
+                        if (config["telemetry"]["prometheus_namespace"] and
+                                config["telemetry"]["prometheus_pod_name"] and
+                                config["telemetry"]["prometheus_container_name"]):
+                            try:
+                                prometheus_archive_files = telemetry_k8s.get_prometheus_pod_data(
+                                    config["telemetry"],
+                                    telemetry_request_id,
+                                    config["telemetry"]["prometheus_pod_name"],
+                                    config["telemetry"]["prometheus_container_name"],
+                                    config["telemetry"]["prometheus_namespace"]
+                                )
+                            except Exception as e:
+                                logging.error(f"failed to get prometheus backup with exception {str(e)}")
+                        else:
+                            logging.warning("impossible to backup prometheus,"
+                                            "check if config contains telemetry.prometheus_namespace, "
+                                            "telemetry.prometheus_pod_name and "
+                                            "telemetry.prometheus_container_name")
+                    if prometheus_archive_files:
+                        safe_logger.info("starting prometheus archive upload:")
+                        telemetry_k8s.put_prometheus_data(config["telemetry"], prometheus_archive_files, telemetry_request_id)
+                if config["telemetry"]["logs_backup"] and distribution == "openshift":
                     telemetry_ocp.put_ocp_logs(telemetry_request_id, config["telemetry"], start_time, end_time)
             except Exception as e:
                 logging.error(f"failed to send telemetry data: {str(e)}")
@@ -405,16 +451,19 @@ def main(cfg):
                 logging.error("Alert profile is not defined")
                 sys.exit(1)
 
+        if post_critical_alerts > 0:
+            logging.error("Critical alerts are firing, please check; exiting")
+            sys.exit(2)
+
         if failed_post_scenarios:
             logging.error(
                 "Post scenarios are still failing at the end of all iterations"
             )
-            sys.exit(1)
+            sys.exit(2)
 
-        run_dir = os.getcwd() + "/kraken.report"
         logging.info(
             "Successfully finished running Kraken. UUID for the run: "
-            "%s. Report generated at %s. Exiting" % (run_uuid, run_dir)
+            "%s. Report generated at %s. Exiting" % (run_uuid, report_file)
         )
     else:
         logging.error("Cannot find a config at %s, please check" % (cfg))
@@ -431,12 +480,21 @@ if __name__ == "__main__":
         help="config location",
         default="config/config.yaml",
     )
+    parser.add_option(
+        "-o",
+        "--output",
+        dest="output",
+        help="output report location",
+        default="kraken.report",
+    )
+    
     (options, args) = parser.parse_args()
+    report_file = options.output
     logging.basicConfig(
         level=logging.INFO,
         format="%(asctime)s [%(levelname)s] %(message)s",
         handlers=[
-            logging.FileHandler("kraken.report", mode="w"),
+            logging.FileHandler(report_file, mode="w"),
             logging.StreamHandler(),
         ],
     )

scenarios/arcaflow/cpu-hog/config.yaml

@@ -4,7 +4,7 @@ deployers:
     connection: {}
     deployer_name: kubernetes
 log:
-  level: debug
+  level: error
 logged_outputs:
   error:
     level: error

scenarios/arcaflow/cpu-hog/input.yaml

@@ -1,8 +1,13 @@
 input_list:
-- cpu_count: 1
-  cpu_load_percentage: 80
-  cpu_method: all
-  duration: 1s
-  kubeconfig: ''
-  namespace: default
-  node_selector: {}
+  - cpu_count: 1
+    cpu_load_percentage: 80
+    cpu_method: all
+    duration: 30
+    kubeconfig: ''
+    namespace: default
+    # set the node selector as a key-value pair eg.
+    # node_selector:
+    #  kubernetes.io/hostname: kind-worker2
+    node_selector: {}
+
+

scenarios/arcaflow/cpu-hog/sub-workflow.yaml

@@ -1,9 +1,9 @@
 version: v0.2.0
 input:
-  root: RootObject
+  root: SubRootObject
   objects:
-    RootObject:
-      id: input_item
+    SubRootObject:
+      id: SubRootObject
       properties:
         kubeconfig:
           display:
@@ -35,7 +35,7 @@ input:
             description: stop stress test after T 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
           type:
-            type_id: string
+            type_id: integer
           required: true
         cpu_count:
           display:
@@ -68,18 +68,18 @@ steps:
       kubeconfig: !expr $.input.kubeconfig
   stressng:
     plugin: 
-      src: quay.io/arcalot/arcaflow-plugin-stressng:0.5.0
+      src: quay.io/arcalot/arcaflow-plugin-stressng:0.6.0
       deployment_type: image
     step: workload
     input:
       cleanup: "true"
-      StressNGParams:
-        timeout: !expr $.input.duration
-        stressors:
-          - stressor: cpu
-            cpu_count: !expr $.input.cpu_count
-            cpu_method: !expr $.input.cpu_method
-            cpu_load: !expr $.input.cpu_load_percentage
+
+      timeout: !expr $.input.duration
+      stressors:
+        - stressor: cpu
+          workers: !expr $.input.cpu_count
+          cpu-method: "all"
+          cpu-load: !expr $.input.cpu_load_percentage
     deploy:
       deployer_name: kubernetes
       connection: !expr $.steps.kubeconfig.outputs.success.connection

scenarios/arcaflow/cpu-hog/workflow.yaml

@@ -9,62 +9,10 @@ input:
           type:
             type_id: list
             items:
-              id: input_item
-              type_id: object
-              properties:
-                kubeconfig:
-                  display:
-                    description: The complete kubeconfig file as a string
-                    name: Kubeconfig file contents
-                  type:
-                    type_id: string
-                  required: true
-                namespace:
-                    display:
-                      description: The namespace where the container will be deployed
-                      name: Namespace
-                    type:
-                      type_id: string
-                    required: true
-                node_selector:
-                    display:
-                      description: kubernetes node name where the plugin must be deployed
-                    type:
-                      type_id: map
-                      values:
-                        type_id: string
-                      keys:
-                        type_id: string
-                    required: true
-                duration:
-                  display:
-                    name: duration the scenario expressed in seconds
-                    description: stop stress test after T 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
-                  type:
-                    type_id: string
-                  required: true
-                cpu_count:
-                  display:
-                    description: Number of CPU cores to be used (0 means all)
-                    name: number of CPUs
-                  type:
-                    type_id: integer
-                  required: true
-                cpu_method:
-                  display:
-                    description: CPU stress method
-                    name: fine grained control of which cpu stressors to use (ackermann, cfloat etc.)
-                  type:
-                    type_id: string
-                  required: true
-                cpu_load_percentage:
-                  display:
-                    description: load CPU by percentage
-                    name: CPU load
-                  type:
-                    type_id: integer
-                  required: true
+              id: SubRootObject
+              type_id: ref
+              namespace: $.steps.workload_loop.execute.inputs.items
+
 steps:
   workload_loop:
     kind: foreach

scenarios/arcaflow/io-hog/config.yaml

@@ -3,7 +3,7 @@ deployers:
     connection: {}
     deployer_name: kubernetes
 log:
-  level: debug
+  level: error
 logged_outputs:
   error:
     level: error

scenarios/arcaflow/io-hog/input.yaml

@@ -1,10 +1,13 @@
 input_list:
-- duration: 30s
+- duration: 30
   io_block_size: 1m
   io_workers: 1
   io_write_bytes: 10m
   kubeconfig: ''
   namespace: default
+  # set the node selector as a key-value pair eg.
+  # node_selector:
+  #  kubernetes.io/hostname: kind-worker2
   node_selector: {}
   target_pod_folder: /hog-data
   target_pod_volume:

scenarios/arcaflow/io-hog/sub-workflow.yaml

@@ -1,9 +1,25 @@
 version: v0.2.0
 input:
-  root: RootObject
+  root: SubRootObject
   objects:
-    RootObject:
-      id: input_item
+    hostPath:
+      id: HostPathVolumeSource
+      properties:
+        path:
+          type:
+            type_id: string
+    Volume:
+      id: Volume
+      properties:
+        name:
+          type:
+            type_id: string
+        hostPath:
+          type:
+            id: hostPath
+            type_id: ref
+    SubRootObject:
+      id: SubRootObject
       properties:
         kubeconfig:
           display:
@@ -35,7 +51,7 @@ input:
             description: stop  stress  test  after  T  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
           type:
-            type_id: string
+            type_id: integer
           required: true
         io_workers:
           display:
@@ -73,25 +89,8 @@ input:
             description: the volume that will be attached to the pod. In order to stress
                          the node storage only hosPath mode is currently supported
           type:
-            type_id: object
-            id: k8s_volume
-            properties:
-              name:
-                display:
-                  description: name of the volume (must match the name in pod definition)
-                type:
-                  type_id: string
-                required: true
-              hostPath:
-                  display:
-                    description: hostPath options expressed as string map (key-value)
-                  type:
-                    type_id: map
-                    values:
-                      type_id: string
-                    keys:
-                      type_id: string
-                  required: true
+            type_id: ref
+            id: Volume
           required: true
 
 steps:
@@ -103,19 +102,18 @@ steps:
       kubeconfig: !expr $.input.kubeconfig
   stressng:
     plugin: 
-      src: quay.io/arcalot/arcaflow-plugin-stressng:0.5.0
+      src: quay.io/arcalot/arcaflow-plugin-stressng:0.6.0
       deployment_type: image
     step: workload
     input:
       cleanup: "true"
-      StressNGParams:
-        timeout: !expr $.input.duration
-        workdir: !expr $.input.target_pod_folder
-        stressors:
-          - stressor: hdd
-            hdd: !expr $.input.io_workers
-            hdd_bytes: !expr $.input.io_write_bytes
-            hdd_write_size: !expr $.input.io_block_size
+      timeout: !expr $.input.duration
+      workdir: !expr $.input.target_pod_folder
+      stressors:
+        - stressor: hdd
+          workers: !expr $.input.io_workers
+          hdd-bytes: !expr $.input.io_write_bytes
+          hdd-write-size: !expr $.input.io_block_size
 
     deploy:
       deployer_name: kubernetes

scenarios/arcaflow/io-hog/workflow.yaml

@@ -9,97 +9,9 @@ input:
           type:
             type_id: list
             items:
-              id: input_item
-              type_id: object
-              properties:
-                kubeconfig:
-                  display:
-                    description: The complete kubeconfig file as a string
-                    name: Kubeconfig file contents
-                  type:
-                    type_id: string
-                  required: true
-                namespace:
-                  display:
-                    description: The namespace where the container will be deployed
-                    name: Namespace
-                  type:
-                    type_id: string
-                  required: true
-                node_selector:
-                  display:
-                    description: kubernetes node name where the plugin must be deployed
-                  type:
-                    type_id: map
-                    values:
-                      type_id: string
-                    keys:
-                      type_id: string
-                  required: true
-                duration:
-                  display:
-                    name: duration the scenario expressed in seconds
-                    description: stop  stress  test  after  T  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
-                  type:
-                    type_id: string
-                  required: true
-                io_workers:
-                  display:
-                    description: number of workers
-                    name: start N workers continually writing, reading  and  removing  temporary  files
-                  type:
-                    type_id: integer
-                  required: true
-                io_block_size:
-                  display:
-                    description: single write size
-                    name: specify size of each write in bytes. Size can be from 1 byte to 4MB.
-                  type:
-                    type_id: string
-                  required: true
-                io_write_bytes:
-                  display:
-                    description: Total number of bytes written
-                    name: write  N  bytes for each hdd process, the default is 1 GB. One can specify the size
-                      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
-                  type:
-                    type_id: string
-                  required: true
-                target_pod_folder:
-                  display:
-                    description: Target Folder
-                    name: Folder in the pod where the test will be executed and the test files will be written
-                  type:
-                    type_id: string
-                  required: true
-                target_pod_volume:
-                  display:
-                    name: kubernetes volume definition
-                    description: the volume that will be attached to the pod. In order to stress
-                      the node storage only hosPath mode is currently supported
-                  type:
-                    type_id: object
-                    id: k8s_volume
-                    properties:
-                      name:
-                        display:
-                          description: name of the volume (must match the name in pod definition)
-                        type:
-                          type_id: string
-                        required: true
-                      hostPath:
-                        display:
-                          description: hostPath options expressed as string map (key-value)
-                        type:
-                          type_id: map
-                          values:
-                            type_id: string
-                          keys:
-                            type_id: string
-                        required: true
-                  required: true
+              id: SubRootObject
+              type_id: ref
+              namespace: $.steps.workload_loop.execute.inputs.items
 steps:
   workload_loop:
     kind: foreach

scenarios/arcaflow/memory-hog/config.yaml

@@ -4,7 +4,7 @@ deployers:
     connection: {}
     deployer_name: kubernetes
 log:
-  level: debug
+  level: error
 logged_outputs:
   error:
     level: error

scenarios/arcaflow/memory-hog/input.yaml

@@ -1,11 +1,11 @@
 input_list:
-- duration: 30s
+- duration: 30
   vm_bytes: 10%
   vm_workers: 2
-  node_selector: { }
-  # node selector example
+  # set the node selector as a key-value pair eg.
   # node_selector:
-  #   kubernetes.io/hostname: master
+  #  kubernetes.io/hostname: kind-worker2
+  node_selector: { }
   kubeconfig: ""
   namespace: default
 

scenarios/arcaflow/memory-hog/sub-workflow.yaml

@@ -1,9 +1,9 @@
 version: v0.2.0
 input:
-  root: RootObject
+  root: SubRootObject
   objects:
-    RootObject:
-      id: input_item
+    SubRootObject:
+      id: SubRootObject
       properties:
         kubeconfig:
           display:
@@ -34,7 +34,7 @@ input:
             name: duration the scenario expressed in seconds
             description: stop stress test after T 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
           type:
-            type_id: string
+            type_id: integer
           required: true
         vm_workers:
           display:
@@ -60,17 +60,16 @@ steps:
       kubeconfig: !expr $.input.kubeconfig
   stressng:
     plugin: 
-      src: quay.io/arcalot/arcaflow-plugin-stressng:0.5.0
+      src: quay.io/arcalot/arcaflow-plugin-stressng:0.6.0
       deployment_type: image
     step: workload
     input:
       cleanup: "true"
-      StressNGParams:
-        timeout: !expr $.input.duration
-        stressors:
-          - stressor: vm
-            vm: !expr $.input.vm_workers
-            vm_bytes: !expr $.input.vm_bytes
+      timeout: !expr $.input.duration
+      stressors:
+        - stressor: vm
+          workers: !expr $.input.vm_workers
+          vm-bytes: !expr $.input.vm_bytes
     deploy:
       deployer_name: kubernetes
       connection: !expr $.steps.kubeconfig.outputs.success.connection

scenarios/arcaflow/memory-hog/workflow.yaml

@@ -9,54 +9,10 @@ input:
           type:
             type_id: list
             items:
-              id: input_item
-              type_id: object
-              properties:
-                kubeconfig:
-                  display:
-                    description: The complete kubeconfig file as a string
-                    name: Kubeconfig file contents
-                  type:
-                    type_id: string
-                  required: true
-                namespace:
-                    display:
-                      description: The namespace where the container will be deployed
-                      name: Namespace
-                    type:
-                      type_id: string
-                    required: true
-                node_selector:
-                  display:
-                    description: kubernetes node name where the plugin must be deployed
-                  type:
-                    type_id: map
-                    values:
-                      type_id: string
-                    keys:
-                      type_id: string
-                  required: true
-                duration:
-                  display:
-                    name: duration the scenario expressed in seconds
-                    description: stop stress test after T 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
-                  type:
-                    type_id: string
-                  required: true
-                vm_workers:
-                  display:
-                    description: Number of VM stressors to be run (0 means 1 stressor per CPU)
-                    name: Number of VM stressors
-                  type:
-                    type_id: integer
-                  required: true
-                vm_bytes:
-                  display:
-                    description: N bytes per vm process, the default is 256MB. The size can be expressed in units of Bytes, KBytes, MBytes and GBytes using the suffix b, k, m or g.
-                    name: Kubeconfig file contents
-                  type:
-                    type_id: string
-                  required: true
+              id: SubRootObject
+              type_id: ref
+              namespace: $.steps.workload_loop.execute.inputs.items
+
 steps:
   workload_loop:
     kind: foreach