Dockerfile v1.5.4 (#552)

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

.github/workflows/docker-image.yml

@@ -12,14 +12,25 @@ 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/
+      run:  |
+        docker build --no-cache -t quay.io/krkn-chaos/krkn containers/
+        docker tag quay.io/krkn-chaos/krkn quay.io/redhat-chaos/krkn
     - name: Login in quay
+      if: github.ref == 'refs/heads/main' && github.event_name == 'push'
+      run: docker login quay.io -u ${QUAY_USER} -p ${QUAY_TOKEN}
+      env:
+        QUAY_USER: ${{ secrets.QUAY_USERNAME }}
+        QUAY_TOKEN: ${{ secrets.QUAY_PASSWORD }}
+    - name: Push the KrknChaos Docker images
+      if: github.ref == 'refs/heads/main' && github.event_name == 'push'
+      run: docker push quay.io/krkn-chaos/krkn
+    - name: Login in to redhat-chaos quay
       if: github.ref == 'refs/heads/main' && github.event_name == 'push'
       run: docker login quay.io -u ${QUAY_USER} -p ${QUAY_TOKEN}
       env:
         QUAY_USER: ${{ secrets.QUAY_USER_1 }}
         QUAY_TOKEN: ${{ secrets.QUAY_TOKEN_1 }}
-    - name: Push the Docker images
+    - name: Push the RedHat Chaos Docker images
       if: github.ref == 'refs/heads/main' && github.event_name == 'push'
       run: docker push quay.io/redhat-chaos/krkn
     - name: Rebuild krkn-hub

.github/workflows/functional_tests.yaml

@@ -44,47 +44,65 @@ jobs:
       - name: Install python 3.9
         uses: actions/setup-python@v4
         with:
-          python-version: '3.9' 
+          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:
-          # currently using image coming from tsebastiani quay.io repo
-          # waiting that a fix is merged in the upstream one
-          # post action run cannot (apparently) be properly indented 
-          run: docker run -v "${{ env.WORKDIR_PATH }}:/workdir" -e WORKING_MODE=T -e AWS_ACCESS_KEY_ID=${{ secrets.AWS_ACCESS_KEY_ID }} -e AWS_SECRET_ACCESS_KEY=${{ secrets.AWS_SECRET_ACCESS_KEY }} -e AWS_DEFAULT_REGION=us-west-2 -e TEARDOWN_RUN_ID=crc quay.io/tsebastiani/crc-cloud
-      - name: Run CRC
-          # currently using image coming from tsebastiani quay.io repo
-          # waiting that a fix is merged in the upstream one
+          run: podman run --rm -v "${{ 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: |
-            docker run -v "${{ env.WORKDIR_PATH }}:/workdir" \
-            -e WORKING_MODE=C \
-            -e PULL_SECRET="${{ secrets.PULL_SECRET }}" \
-            -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 \
-            -e CREATE_RUN_ID=crc \
-            -e PASS_KUBEADMIN="${{ secrets.KUBEADMIN_PWD }}" \
-            -e PASS_REDHAT="${{ secrets.REDHAT_PWD }}" \
-            -e PASS_DEVELOPER="${{ secrets.DEVELOPER_PWD }}" \
-            quay.io/tsebastiani/crc-cloud
-      - name: OpenShift login and example deployment, GitHub Action env init 
+          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" > $GITHUB_ENV
+
+      - name: Example deployment, GitHub Action env init
         env:
           NAMESPACE: test-namespace
           DEPLOYMENT_NAME: test-nginx
-          KUBEADMIN_PWD: '${{ secrets.KUBEADMIN_PWD }}'
         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
@@ -106,6 +124,6 @@ jobs:
           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 
+          python -m coverage report --format=markdown >> $GITHUB_STEP_SUMMARY
 
 

CI/CRC/init_github_action.sh

@@ -1,16 +1,11 @@
 #!/bin/bash
 SCRIPT_PATH=./CI/CRC
 DEPLOYMENT_PATH=$SCRIPT_PATH/deployment.yaml
-CLUSTER_INFO=cluster_infos.json
-
-[[ -z $WORKDIR_PATH ]] && echo "[ERROR] please set \$WORKDIR_PATH environment variable" && exit 1
-CLUSTER_INFO_PATH=$WORKDIR_PATH/crc/$CLUSTER_INFO
 
 [[ ! -f $DEPLOYMENT_PATH ]] && echo "[ERROR] please run $0 from GitHub action root directory" && exit 1
-[[ -z $KUBEADMIN_PWD ]] && echo "[ERROR] kubeadmin password not set, please check the repository secrets" && 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
-[[ ! -f $CLUSTER_INFO_PATH ]] && echo  "[ERROR] cluster_info.json not found in $CLUSTER_INFO_PATH" && exit 1 
+
 
 OPENSSL=`which openssl 2>/dev/null`
 [[ $? != 0 ]] && echo "[ERROR]: openssl missing, please install it and try again" && exit 1
@@ -23,20 +18,11 @@ JQ=`which jq 2>/dev/null`
 ENVSUBST=`which envsubst 2>/dev/null`
 [[ $? != 0 ]] && echo "[ERROR]: envsubst missing, please install it and try again" && exit 1
 
-API_ADDRESS="$($JQ -r '.api.address' $CLUSTER_INFO_PATH)"
-API_PORT="$($JQ -r '.api.port' $CLUSTER_INFO_PATH)"
-BASE_HOST=`$JQ -r '.api.address'  $CLUSTER_INFO_PATH | sed -r 's#https:\/\/api\.(.+\.nip\.io)#\1#'`
-FQN=$DEPLOYMENT_NAME.apps.$BASE_HOST
 
-echo "[INF] logging on $API_ADDRESS:$API_PORT"
-COUNTER=1
-until `$OC login  --insecure-skip-tls-verify -u kubeadmin -p $KUBEADMIN_PWD $API_ADDRESS:$API_PORT > /dev/null 2>&1`
-do 
-    echo "[INF] login attempt $COUNTER"
-    [[ $COUNTER == 20 ]] && echo "[ERR] maximum login attempts exceeded, failing" && exit 1
-    ((COUNTER++))
-    sleep 10
-done
+API_PORT="6443"
+API_ADDRESS="https://api.`cat host`.nip.io:${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

CI/config/common_test_config.yaml

@@ -15,15 +15,13 @@ cerberus:
 performance_monitoring:
     deploy_dashboards: False                               # Install a mutable grafana and load the performance dashboards. Enable this only when running on OpenShift.
     repo: "https://github.com/cloud-bulldozer/performance-dashboards.git"
-    kube_burner_binary_url: "https://github.com/cloud-bulldozer/kube-burner/releases/download/v0.9.1/kube-burner-0.9.1-Linux-x86_64.tar.gz"
     capture_metrics: False
-    config_path: config/kube_burner.yaml                   # Define the Elasticsearch url and index name in this config.
     metrics_profile_path: config/metrics-aggregated.yaml
     prometheus_url:                                        # The prometheus url/route is automatically obtained in case of OpenShift, please set it when the distribution is Kubernetes.
     prometheus_bearer_token:                               # The bearer token is automatically obtained in case of OpenShift, please set it when the distribution is Kubernetes. This is needed to authenticate with prometheus.
     uuid:                                                  # uuid for the run is generated by default if not set.
     enable_alerts: False                                   # Runs the queries specified in the alert profile and displays the info or exits 1 when severity=error.
-    alert_profile: config/alerts                           # Path to alert profile with the prometheus queries.
+    alert_profile: config/alerts.yaml                           # Path to alert profile with the prometheus queries.
 
 tunings:
     wait_duration: 6                                       # Duration to wait between each chaos scenario.

CI/scenarios/node_cpu_hog_engine.yaml

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

CI/scenarios/node_cpu_hog_engine_node.yaml

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

CI/scenarios/node_io_engine.yaml

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

CI/scenarios/node_io_engine_node.yaml

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

CI/scenarios/node_mem_engine.yaml

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

CI/scenarios/node_mem_engine_node.yaml

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

CI/tests/test_cpu_hog.sh

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

CI/tests/test_cpu_hog_gh.sh

@@ -1,20 +0,0 @@
-set -xeEo pipefail
-
-source CI/tests/common.sh
-
-trap error ERR
-trap finish EXIT
-
-
-function functional_test_litmus_cpu {
-  [ -z $NODE_NAME ] && echo "[ERR] NODE_NAME variable not set, failing." && exit 1
-  yq -i ' .spec.experiments = [{"name": "node-cpu-hog", "spec":{"components":{"env":[{"name":"TOTAL_CHAOS_DURATION","value":"10"},{"name":"NODE_CPU_CORE","value":"1"},{"name":"NODES_AFFECTED_PERC","value":"30"},{"name":"TARGET_NODES","value":"'$NODE_NAME'"}]}}}]' CI/scenarios/node_cpu_hog_engine_node.yaml
-
-  cp CI/config/common_test_config.yaml CI/config/litmus_config.yaml
-  yq '.kraken.chaos_scenarios = [{"litmus_scenarios":[["scenarios/openshift/templates/litmus-rbac.yaml","CI/scenarios/node_cpu_hog_engine_node.yaml"]]}]' -i CI/config/litmus_config.yaml
-  
-  python3 -m coverage run -a run_kraken.py -c CI/config/litmus_config.yaml
-  echo "Litmus scenario test: Success"
-}
-
-functional_test_litmus_cpu

CI/tests/test_io_hog.sh

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

CI/tests/test_io_hog_gh.sh

@@ -1,19 +0,0 @@
-set -xeEo pipefail
-
-source CI/tests/common.sh
-
-trap error ERR
-trap finish EXIT
-
-
-function functional_test_litmus_io {
-  [ -z $NODE_NAME ] && echo "[ERR] NODE_NAME variable not set, failing." && exit 1
-  yq -i ' .spec.experiments = [{"name": "node-io-stress", "spec":{"components":{"env":[{"name":"TOTAL_CHAOS_DURATION","value":"10"},{"name":"FILESYSTEM_UTILIZATION_PERCENTAGE","value":"100"},{"name":"CPU","value":"1"},{"name":"NUMBER_OF_WORKERS","value":"3"},{"name":"TARGET_NODES","value":"'$NODE_NAME'"}]}}}]' CI/scenarios/node_io_engine_node.yaml
-  cp CI/config/common_test_config.yaml CI/config/litmus_config.yaml
-  yq '.kraken.chaos_scenarios = [{"litmus_scenarios":[["scenarios/openshift/templates/litmus-rbac.yaml","CI/scenarios/node_io_engine_node.yaml"]]}]' -i CI/config/litmus_config.yaml
-  
-  python3 -m coverage run -a run_kraken.py -c CI/config/litmus_config.yaml
-  echo "Litmus scenario test: Success"
-}
-
-functional_test_litmus_io

CI/tests/test_mem_hog.sh

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

CI/tests/test_mem_hog_gh.sh

@@ -1,19 +0,0 @@
-set -xeEo pipefail
-
-source CI/tests/common.sh
-
-trap error ERR
-trap finish EXIT
-
-
-function functional_test_litmus_mem {
-  [ -z $NODE_NAME ] && echo "[ERR] NODE_NAME variable not set, failing." && exit 1
-  yq -i ' .spec.experiments = [{"name": "node-io-stress", "spec":{"components":{"env":[{"name":"TOTAL_CHAOS_DURATION","value":"10"},{"name":"CPU","value":"1"},{"name":"TARGET_NODES","value":"'$NODE_NAME'"}]}}}]' CI/scenarios/node_mem_engine_node.yaml
-  cp CI/config/common_test_config.yaml CI/config/litmus_config.yaml
-  yq '.kraken.chaos_scenarios = [{"litmus_scenarios":[["scenarios/openshift/templates/litmus-rbac.yaml","CI/scenarios/node_mem_engine_node.yaml"]]}]' -i CI/config/litmus_config.yaml
-
-  python3 -m coverage run -a run_kraken.py -c CI/config/litmus_config.yaml
-  echo "Litmus scenario test: Success"
-}
-
-functional_test_litmus_mem

CODE_OF_CONDUCT.md

@@ -1,21 +1,50 @@
-# Contributor Covenant Code of Conduct
+## CNCF Community Code of Conduct v1.3
 
-## Our Pledge
+Other languages available:
+- [Arabic/العربية](code-of-conduct-languages/ar.md)
+- [Bulgarian/Български](code-of-conduct-languages/bg.md)
+- [Chinese/中文](code-of-conduct-languages/zh.md)
+- [Czech/Česky](code-of-conduct-languages/cs.md)
+- [Farsi/فارسی](code-of-conduct-languages/fa.md)
+- [French/Français](code-of-conduct-languages/fr.md)
+- [German/Deutsch](code-of-conduct-languages/de.md)
+- [Hindi/हिन्दी](code-of-conduct-languages/hi.md)
+- [Indonesian/Bahasa Indonesia](code-of-conduct-languages/id.md)
+- [Italian/Italiano](code-of-conduct-languages/it.md)
+- [Japanese/日本語](code-of-conduct-languages/jp.md)
+- [Korean/한국어](code-of-conduct-languages/ko.md)
+- [Polish/Polski](code-of-conduct-languages/pl.md)
+- [Portuguese/Português](code-of-conduct-languages/pt.md)
+- [Russian/Русский](code-of-conduct-languages/ru.md)
+- [Spanish/Español](code-of-conduct-languages/es.md)
+- [Turkish/Türkçe](code-of-conduct-languages/tr.md)
+- [Ukrainian/Українська](code-of-conduct-languages/uk.md)
+- [Vietnamese/Tiếng Việt](code-of-conduct-languages/vi.md)
 
-We as members, contributors, and leaders pledge to make participation in our
-community a harassment-free experience for everyone, regardless of age, body
-size, visible or invisible disability, ethnicity, sex characteristics, gender
-identity and expression, level of experience, education, socio-economic status,
-nationality, personal appearance, race, religion, or sexual identity
-and orientation.
+### Community Code of Conduct
 
-We pledge to act and interact in ways that contribute to an open, welcoming,
-diverse, inclusive, and healthy community.
+As contributors, maintainers, and participants in the CNCF community, and in the interest of fostering
+an open and welcoming community, we pledge to respect all people who participate or contribute
+through reporting issues, posting feature requests, updating documentation,
+submitting pull requests or patches, attending conferences or events, or engaging in other community or project activities.
+
+We are committed to making participation in the CNCF community a harassment-free experience for everyone, regardless of age, body size, caste, disability, ethnicity, level of experience, family status, gender, gender identity and expression, marital status, military or veteran status, nationality, personal appearance, race, religion, sexual orientation, socioeconomic status, tribe, or any other dimension of diversity.
+
+## Scope
+
+This code of conduct applies:
+* within project and community spaces,
+* in other spaces when an individual CNCF community participant's words or actions are directed at or are about a CNCF project, the CNCF community, or another CNCF community participant.
+
+### CNCF Events
+
+CNCF events that are produced by the Linux Foundation with professional events staff are governed by the Linux Foundation [Events Code of Conduct](https://events.linuxfoundation.org/code-of-conduct/) available on the event page. This is designed to be used in conjunction with the CNCF Code of Conduct.
 
 ## Our Standards
 
-Examples of behavior that contributes to a positive environment for our
-community include:
+The CNCF Community is open, inclusive and respectful. Every member of our community has the right to have their identity respected.
+
+Examples of behavior that contributes to a positive environment include but are not limited to:
 
 * Demonstrating empathy and kindness toward other people
 * Being respectful of differing opinions, viewpoints, and experiences
@@ -24,104 +53,52 @@ community include:
   and learning from the experience
 * Focusing on what is best not just for us as individuals, but for the
   overall community
+* Using welcoming and inclusive language
 
-Examples of unacceptable behavior include:
 
-* The use of sexualized language or imagery, and sexual attention or
-  advances of any kind
+Examples of unacceptable behavior include but are not limited to:
+
+* The use of sexualized language or imagery
 * Trolling, insulting or derogatory comments, and personal or political attacks
-* Public or private harassment
+* Public or private harassment in any form
 * Publishing others' private information, such as a physical or email
   address, without their explicit permission
+* Violence, threatening violence, or encouraging others to engage in violent behavior
+* Stalking or following someone without their consent
+* Unwelcome physical contact
+* Unwelcome sexual or romantic attention or advances
 * Other conduct which could reasonably be considered inappropriate in a
   professional setting
 
-## Enforcement Responsibilities
+The following behaviors are also prohibited:
+* Providing knowingly false or misleading information in connection with a Code of Conduct investigation or otherwise intentionally tampering with an investigation.
+* Retaliating against a person because they reported an incident or provided information about an incident as a witness.
 
-Community leaders are responsible for clarifying and enforcing our standards of
-acceptable behavior and will take appropriate and fair corrective action in
-response to any behavior that they deem inappropriate, threatening, offensive,
-or harmful.
+Project maintainers have the right and responsibility to remove, edit, or reject comments, commits, code, wiki edits, issues, and other contributions that are not aligned to this Code of Conduct.
+By adopting this Code of Conduct, project maintainers commit themselves to fairly and consistently applying these principles to every aspect
+of managing a CNCF project.
+Project maintainers who do not follow or enforce the Code of Conduct may be temporarily or permanently removed from the project team.
 
-Community leaders have the right and responsibility to remove, edit, or reject
-comments, commits, code, wiki edits, issues, and other contributions that are
-not aligned to this Code of Conduct, and will communicate reasons for moderation
-decisions when appropriate.
+## Reporting
 
-## Scope
+For incidents occurring in the Kubernetes community, contact the [Kubernetes Code of Conduct Committee](https://git.k8s.io/community/committee-code-of-conduct) via <conduct@kubernetes.io>. You can expect a response within three business days.
 
-This Code of Conduct applies within all community spaces, and also applies when
-an individual is officially representing the community in public spaces.
-Examples of representing our community include using an official e-mail address,
-posting via an official social media account, or acting as an appointed
-representative at an online or offline event.
+For other projects, or for incidents that are project-agnostic or impact multiple CNCF projects, please contact the [CNCF Code of Conduct Committee](https://www.cncf.io/conduct/committee/) via <conduct@cncf.io>.  Alternatively, you can contact any of the individual members of the [CNCF Code of Conduct Committee](https://www.cncf.io/conduct/committee/) to submit your report. For more detailed instructions on how to submit a report, including how to submit a report anonymously, please see our [Incident Resolution Procedures](https://github.com/cncf/foundation/blob/main/code-of-conduct/coc-incident-resolution-procedures.md). You can expect a response within three business days.
+
+For incidents occurring at CNCF event that is produced by the Linux Foundation, please contact <eventconduct@cncf.io>.
 
 ## Enforcement
 
-Instances of abusive, harassing, or otherwise unacceptable behavior may be
-reported to the community leaders responsible for enforcement.
-All complaints will be reviewed and investigated promptly and fairly.
+Upon review and investigation of a reported incident, the CoC response team that has jurisdiction will determine what action is appropriate based on this Code of Conduct and its related documentation.
 
-All community leaders are obligated to respect the privacy and security of the
-reporter of any incident.
+For information about which Code of Conduct incidents are handled by project leadership, which incidents are handled by the CNCF Code of Conduct Committee, and which incidents are handled by the Linux Foundation (including its events team), see our [Jurisdiction Policy](https://github.com/cncf/foundation/blob/main/code-of-conduct/coc-committee-jurisdiction-policy.md).
 
-## Enforcement Guidelines
+## Amendments
 
-Community leaders will follow these Community Impact Guidelines in determining
-the consequences for any action they deem in violation of this Code of Conduct:
+Consistent with the CNCF Charter, any substantive changes to this Code of Conduct must be approved by the Technical Oversight Committee.
 
-### 1. Correction
+## Acknowledgements
 
-**Community Impact**: Use of inappropriate language or other behavior deemed
-unprofessional or unwelcome in the community.
-
-**Consequence**: A private, written warning from community leaders, providing
-clarity around the nature of the violation and an explanation of why the
-behavior was inappropriate. A public apology may be requested.
-
-### 2. Warning
-
-**Community Impact**: A violation through a single incident or series
-of actions.
-
-**Consequence**: A warning with consequences for continued behavior. No
-interaction with the people involved, including unsolicited interaction with
-those enforcing the Code of Conduct, for a specified period of time. This
-includes avoiding interactions in community spaces as well as external channels
-like social media. Violating these terms may lead to a temporary or
-permanent ban.
-
-### 3. Temporary Ban
-
-**Community Impact**: A serious violation of community standards, including
-sustained inappropriate behavior.
-
-**Consequence**: A temporary ban from any sort of interaction or public
-communication with the community for a specified period of time. No public or
-private interaction with the people involved, including unsolicited interaction
-with those enforcing the Code of Conduct, is allowed during this period.
-Violating these terms may lead to a permanent ban.
-
-### 4. Permanent Ban
-
-**Community Impact**: Demonstrating a pattern of violation of community
-standards, including sustained inappropriate behavior,  harassment of an
-individual, or aggression toward or disparagement of classes of individuals.
-
-**Consequence**: A permanent ban from any sort of public interaction within
-the community.
-
-## Attribution
-
-This Code of Conduct is adapted from the [Contributor Covenant][homepage],
-version 2.0, available at
-https://www.contributor-covenant.org/version/2/0/code_of_conduct.html.
-
-Community Impact Guidelines were inspired by [Mozilla's code of conduct
-enforcement ladder](https://github.com/mozilla/diversity).
-
-[homepage]: https://www.contributor-covenant.org
-
-For answers to common questions about this code of conduct, see the FAQ at
-https://www.contributor-covenant.org/faq. Translations are available at
-https://www.contributor-covenant.org/translations.
+This Code of Conduct is adapted from the Contributor Covenant
+(http://contributor-covenant.org), version 2.0 available at
+http://contributor-covenant.org/version/2/0/code_of_conduct/

README.md

@@ -4,8 +4,8 @@
 
 ![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
@@ -18,25 +18,27 @@ Kraken injects deliberate failures into Kubernetes/OpenShift clusters to check i
 ### Chaos Testing Guide
 [Guide](docs/index.md) encapsulates:
 - Test methodology that needs to be embraced.
-- Best practices that an OpenShift cluster, platform and applications running on top of it should take into account for best user experience, performance, resilience and reliability.
+- Best practices that an Kubernetes cluster, platform and applications running on top of it should take into account for best user experience, performance, resilience and reliability.
 - Tooling.
 - Scenarios supported.
 - Test environment recommendations as to how and where to run chaos tests.
 - Chaos testing in practice.
 
-The guide is hosted at https://redhat-chaos.github.io/krkn.
+The guide is hosted at https://krkn-chaos.github.io/krkn.
 
 
 ### How to Get Started
 Instructions on how to setup, configure and run Kraken can be found at [Installation](docs/installation.md).
 
+You may consider utilizing the chaos recommendation tool prior to initiating the chaos runs to profile the application service(s) under test. This tool discovers a list of Krkn scenarios with a high probability of causing failures or disruptions to your application service(s). The tool can be accessed at [Chaos-Recommender](utils/chaos_recommender/README.md).
+
 See the [getting started doc](docs/getting_started.md) on support on how to get started with your own custom scenario or editing current scenarios for your specific usage.
 
 After installation, refer back to the below sections for supported scenarios and how to tweak the kraken config to load them on your cluster.
 
 
 #### Running Kraken with minimal configuration tweaks
-For cases where you want to run Kraken with minimal configuration changes, refer to [Kraken-hub](https://github.com/redhat-chaos/krkn-hub). One use case is CI integration where you do not want to carry around different configuration files for the scenarios.
+For cases where you want to run Kraken with minimal configuration changes, refer to [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:
@@ -55,30 +57,30 @@ This will manage the Cerberus and Elasticsearch containers on the host on which
 Instructions on how to setup the config and the options supported can be found at [Config](docs/config.md).
 
 
-### Kubernetes/OpenShift chaos scenarios supported
+### Kubernetes chaos scenarios supported
 
-Scenario type               | Kubernetes    | OpenShift          
---------------------------- | ------------- |--------------------|  
-[Pod Scenarios](docs/pod_scenarios.md) | :heavy_check_mark: | :heavy_check_mark: |
-[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) | :x: |
+[Hog Scenarios: CPU, Memory](docs/arcaflow_scenarios.md) | :heavy_check_mark: |
+[Cluster Shut Down Scenarios](docs/cluster_shut_down_scenarios.md) | :heavy_check_mark: |
+[Service Disruption Scenarios](docs/service_disruption_scenarios.md.md) | :heavy_check_mark: |
+[Zone Outage Scenarios](docs/zone_outage.md) | :heavy_check_mark: |
+[Application_outages](docs/application_outages.md) | :heavy_check_mark: |
+[PVC scenario](docs/pvc_scenario.md) | :heavy_check_mark: |
+[Network_Chaos](docs/network_chaos.md) | :heavy_check_mark: |
+[ManagedCluster Scenarios](docs/managedcluster_scenarios.md) | :heavy_check_mark: |
 
 
 ### Kraken scenario pass/fail criteria and report
 It is important to make sure to check if the targeted component recovered from the chaos injection and also if the Kubernetes/OpenShift cluster is healthy as failures in one component can have an adverse impact on other components. Kraken does this by:
 - Having built in checks for pod and node based scenarios to ensure the expected number of replicas and nodes are up. It also supports running custom scripts with the checks.
-- Leveraging [Cerberus](https://github.com/openshift-scale/cerberus) to monitor the cluster under test and consuming the aggregated go/no-go signal to determine pass/fail post chaos. It is highly recommended to turn on the Cerberus health check feature available in Kraken. Instructions on installing and setting up Cerberus can be found [here](https://github.com/openshift-scale/cerberus#installation) or can be installed from Kraken using the [instructions](https://github.com/redhat-chaos/krkn#setting-up-infrastructure-dependencies). Once Cerberus is up and running, set cerberus_enabled to True and cerberus_url to the url where Cerberus publishes go/no-go signal in the Kraken config file. Cerberus can monitor [application routes](https://github.com/redhat-chaos/cerberus/blob/main/docs/config.md#watch-routes) during the chaos and fails the run if it encounters downtime as it is a potential downtime in a customers, or users environment as well. It is especially important during the control plane chaos scenarios including the API server, Etcd, Ingress etc. It can be enabled by setting `check_applicaton_routes: True` in the [Kraken config](https://github.com/redhat-chaos/krkn/blob/main/config/config.yaml) provided application routes are being monitored in the [cerberus config](https://github.com/redhat-chaos/krkn/blob/main/config/cerberus.yaml).
-- Leveraging [kube-burner](docs/alerts.md) alerting feature to fail the runs in case of critical alerts.
+- Leveraging [Cerberus](https://github.com/redhat-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/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 built-in alert collection feature to fail the runs in case of critical alerts.
 
 ### Signaling
 In CI runs or any external job it is useful to stop Kraken once a certain test or state gets reached. We created a way to signal to kraken to pause the chaos or stop it completely using a signal posted to a port of your choice.
@@ -92,10 +94,6 @@ 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/cloud-bulldozer/kube-burner) under the hood. The metrics to capture need to be defined in a metrics profile which Kraken consumes to query prometheus ( installed by default in OpenShift ) with the start and end timestamp of the run. Information on enabling and leveraging this feature can be found [here](docs/metrics.md).
-
-
 ### SLOs validation during and post chaos
 - In addition to checking the recovery and health of the cluster and components under test, Kraken takes in a profile with the Prometheus expressions to validate and alerts, exits with a non-zero return code depending on the severity set. This feature can be used to determine pass/fail or alert on abnormalities observed in the cluster based on the metrics. 
 - Kraken also provides ability to check if any critical alerts are firing in the cluster post chaos and pass/fail's. 
@@ -107,12 +105,15 @@ Information on enabling and leveraging this feature can be found [here](docs/SLO
 
 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).
 
+
 ### Blogs and other useful resources
 - Blog post on introduction to Kraken: https://www.openshift.com/blog/introduction-to-kraken-a-chaos-tool-for-openshift/kubernetes
 - Discussion and demo on how Kraken can be leveraged to ensure OpenShift is reliable, performant and scalable: https://www.youtube.com/watch?v=s1PvupI5sD0&ab_channel=OpenShift
 - Blog post emphasizing the importance of making Chaos part of Performance and Scale runs to mimic the production environments: https://www.openshift.com/blog/making-chaos-part-of-kubernetes/openshift-performance-and-scalability-tests
 - Blog post on findings from Chaos test runs: https://cloud.redhat.com/blog/openshift/kubernetes-chaos-stories
-
+- Discussion with CNCF TAG App Delivery on Krkn workflow, features and addition to CNCF sandbox: [Github](https://github.com/cncf/sandbox/issues/44), [Tracker](https://github.com/cncf/tag-app-delivery/issues/465), [recording](https://www.youtube.com/watch?v=nXQkBFK_MWc&t=722s)
+- Blog post on supercharging chaos testing using AI integration in Krkn: https://www.redhat.com/en/blog/supercharging-chaos-testing-using-ai
+- Blog post announcing Krkn joining CNCF Sandbox: https://www.redhat.com/en/blog/krknchaos-joining-cncf-sandbox
 
 ### Roadmap
 Enhancements being planned can be found in the [roadmap](ROADMAP.md).

ROADMAP.md

@@ -5,9 +5,11 @@ Following are a list of enhancements that we are planning to work on adding supp
 - [ ] [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)
-- [ ] [Support for pod level network traffic shaping](https://github.com/redhat-chaos/krkn/issues/393)
+- [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 
+- [ ] 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)
+- [ ] [OCP and Kubernetes functionalities segregation](https://github.com/redhat-chaos/krkn/issues/497)

config/alerts.yaml

@@ -0,0 +1,90 @@
+# etcd
+
+- expr: avg_over_time(histogram_quantile(0.99, rate(etcd_disk_wal_fsync_duration_seconds_bucket[2m]))[10m:]) > 0.01
+  description: 10 minutes avg. 99th etcd fsync latency on {{$labels.pod}} higher than 10ms. {{$value}}s
+  severity: warning
+
+- expr: avg_over_time(histogram_quantile(0.99, rate(etcd_disk_wal_fsync_duration_seconds_bucket[2m]))[10m:]) > 1
+  description: 10 minutes avg. 99th etcd fsync latency on {{$labels.pod}} higher than 1s. {{$value}}s
+  severity: error
+
+- expr: avg_over_time(histogram_quantile(0.99, rate(etcd_disk_backend_commit_duration_seconds_bucket[2m]))[10m:]) > 0.007
+  description: 10 minutes avg. 99th etcd commit latency on {{$labels.pod}} higher than 30ms. {{$value}}s
+  severity: warning
+
+- expr: rate(etcd_server_leader_changes_seen_total[2m]) > 0
+  description: etcd leader changes observed
+  severity: warning
+
+- expr: (last_over_time(etcd_mvcc_db_total_size_in_bytes[5m]) / last_over_time(etcd_server_quota_backend_bytes[5m]))*100 > 95
+  description: etcd cluster database is running full. 
+  severity: critical
+  
+- expr: (last_over_time(etcd_mvcc_db_total_size_in_use_in_bytes[5m]) / last_over_time(etcd_mvcc_db_total_size_in_bytes[5m])) < 0.5
+  description: etcd database size in use is less than 50% of the actual allocated storage.
+  severity: warning  
+
+- expr: rate(etcd_server_proposals_failed_total{job=~".*etcd.*"}[15m]) > 5
+  description: etcd cluster has high number of proposal failures.
+  severity: warning 
+
+- expr: histogram_quantile(0.99, rate(etcd_network_peer_round_trip_time_seconds_bucket{job=~".*etcd.*"}[5m])) > 0.15
+  description: etcd cluster member communication is slow.
+  severity: warning 
+
+- expr: histogram_quantile(0.99, sum(rate(grpc_server_handling_seconds_bucket{job=~".*etcd.*", grpc_method!="Defragment", grpc_type="unary"}[5m])) without(grpc_type)) > 0.15
+  description: etcd grpc requests are slow.
+  severity: critical
+      
+- expr: 100 * sum(rate(grpc_server_handled_total{job=~".*etcd.*", grpc_code=~"Unknown|FailedPrecondition|ResourceExhausted|Internal|Unavailable|DataLoss|DeadlineExceeded"}[5m])) without (grpc_type, grpc_code) / sum(rate(grpc_server_handled_total{job=~".*etcd.*"}[5m])) without (grpc_type, grpc_code) > 5
+  description: etcd cluster has high number of failed grpc requests.
+  severity: critical      
+      
+- expr: etcd_server_has_leader{job=~".*etcd.*"} == 0
+  description: etcd cluster has no leader.
+  severity: warning    
+    
+- expr: sum(up{job=~".*etcd.*"} == bool 1) without (instance) < ((count(up{job=~".*etcd.*"}) without (instance) + 1) / 2)
+  description: etcd cluster has insufficient number of members.
+  severity: warning      
+
+- expr: max without (endpoint) ( sum without (instance) (up{job=~".*etcd.*"} == bool 0) or count without (To) ( sum without (instance) (rate(etcd_network_peer_sent_failures_total{job=~".*etcd.*"}[120s])) > 0.01 )) > 0
+  description: etcd cluster members are down.
+  severity: warning  
+
+# API server
+- expr: avg_over_time(histogram_quantile(0.99, sum(irate(apiserver_request_duration_seconds_bucket{apiserver="kube-apiserver", verb=~"POST|PUT|DELETE|PATCH", subresource!~"log|exec|portforward|attach|proxy"}[2m])) by (le, resource, verb))[10m:]) > 1
+  description: 10 minutes avg. 99th mutating API call latency for {{$labels.verb}}/{{$labels.resource}} higher than 1 second. {{$value}}s
+  severity: error
+
+- expr: avg_over_time(histogram_quantile(0.99, sum(irate(apiserver_request_duration_seconds_bucket{apiserver="kube-apiserver", verb=~"LIST|GET", subresource!~"log|exec|portforward|attach|proxy", scope="resource"}[2m])) by (le, resource, verb, scope))[5m:]) > 1
+  description: 5 minutes avg. 99th read-only API call latency for {{$labels.verb}}/{{$labels.resource}} in scope {{$labels.scope}} higher than 1 second. {{$value}}s
+  severity: error
+
+- expr: avg_over_time(histogram_quantile(0.99, sum(irate(apiserver_request_duration_seconds_bucket{apiserver="kube-apiserver", verb=~"LIST|GET", subresource!~"log|exec|portforward|attach|proxy", scope="namespace"}[2m])) by (le, resource, verb, scope))[5m:]) > 5
+  description: 5 minutes avg. 99th read-only API call latency for {{$labels.verb}}/{{$labels.resource}} in scope {{$labels.scope}} higher than 5 seconds. {{$value}}s
+  severity: error
+
+- expr: avg_over_time(histogram_quantile(0.99, sum(irate(apiserver_request_duration_seconds_bucket{apiserver="kube-apiserver", verb=~"LIST|GET", subresource!~"log|exec|portforward|attach|proxy", scope="cluster"}[2m])) by (le, resource, verb, scope))[5m:]) > 30
+  description: 5 minutes avg. 99th read-only API call latency for {{$labels.verb}}/{{$labels.resource}} in scope {{$labels.scope}} higher than 30 seconds. {{$value}}s
+  severity: error
+
+# Control plane pods
+
+- expr: up{job=~"crio|kubelet"} == 0
+  description: "{{$labels.node}}/{{$labels.job}} down"
+  severity: warning
+
+- expr: up{job="ovnkube-node"} == 0
+  description: "{{$labels.instance}}/{{$labels.pod}} {{$labels.job}} down"
+  severity: warning
+
+# Service sync latency
+- expr: histogram_quantile(0.99, sum(rate(kubeproxy_network_programming_duration_seconds_bucket[2m])) by (le)) > 10
+  description: 99th Kubeproxy network programming latency higher than 10 seconds. {{$value}}s 
+  severity: warning
+
+# Prometheus alerts
+- expr: ALERTS{severity="critical", alertstate="firing"} > 0
+  description: Critical prometheus alert. {{$labels.alertname}}
+  severity: warning

config/config.yaml

@@ -29,13 +29,6 @@ kraken:
             - scenarios/openshift/openshift-kube-apiserver.yml
         - time_scenarios:                                  # List of chaos time scenarios to load
             - scenarios/openshift/time_scenarios_example.yml
-        - litmus_scenarios:                                # List of litmus scenarios to load
-            - - scenarios/openshift/templates/litmus-rbac.yaml
-              - scenarios/openshift/node_cpu_hog_engine.yaml
-            - - scenarios/openshift/templates/litmus-rbac.yaml
-              - scenarios/openshift/node_mem_engine.yaml
-            - - scenarios/openshift/templates/litmus-rbac.yaml
-              - scenarios/openshift/node_io_engine.yaml
         - cluster_shut_down_scenarios:
             - - scenarios/openshift/cluster_shut_down_scenario.yml
               - scenarios/openshift/post_action_shut_down.py
@@ -58,15 +51,11 @@ cerberus:
 performance_monitoring:
     deploy_dashboards: False                              # Install a mutable grafana and load the performance dashboards. Enable this only when running on OpenShift
     repo: "https://github.com/cloud-bulldozer/performance-dashboards.git"
-    kube_burner_binary_url: "https://github.com/cloud-bulldozer/kube-burner/releases/download/v1.7.0/kube-burner-1.7.0-Linux-x86_64.tar.gz"
-    capture_metrics: False
-    config_path: config/kube_burner.yaml                  # Define the Elasticsearch url and index name in this config
-    metrics_profile_path: config/metrics-aggregated.yaml
     prometheus_url:                                       # The prometheus url/route is automatically obtained in case of OpenShift, please set it when the distribution is Kubernetes.
     prometheus_bearer_token:                              # The bearer token is automatically obtained in case of OpenShift, please set it when the distribution is Kubernetes. This is needed to authenticate with prometheus.
     uuid:                                                 # uuid for the run is generated by default if not set
     enable_alerts: False                                  # Runs the queries specified in the alert profile and displays the info or exits 1 when severity=error
-    alert_profile: config/alerts                          # Path or URL to alert profile with the prometheus queries
+    alert_profile: config/alerts.yaml                          # Path or URL to alert profile with the prometheus queries
     check_critical_alerts: False                          # When enabled will check prometheus for critical alerts firing post chaos
 tunings:
     wait_duration: 60                                      # Duration to wait between each chaos scenario
@@ -83,7 +72,7 @@ telemetry:
     archive_path: /tmp                                      # local path where the archive files will be temporarly stored
     max_retries: 0                                          # maximum number of upload retries (if 0 will retry forever)
     run_tag: ''                                             # if set, this will be appended to the run folder in the bucket (useful to group the runs)
-    archive_size: 10000                                     # the size of the prometheus data archive size in KB. The lower the size of archive is
+    archive_size: 500000                                     # the size of the prometheus data archive size in KB. The lower the size of archive is
                                                             # the higher the number of archive files will be produced and uploaded (and processed by backup_threads
                                                             # simultaneously).
                                                             # For unstable/slow connection is better to keep this value low
@@ -95,4 +84,8 @@ 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
+    events_backup: True                                     # enables/disables cluster events collection
+
+
+
 

config/config_kind.yaml

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

config/config_kubernetes.yaml

@@ -5,10 +5,6 @@ kraken:
     port: 8081
     publish_kraken_status: True                            # Can be accessed at http://0.0.0.0:8081
     signal_state: RUN                                      # Will wait for the RUN signal when set to PAUSE before running the scenarios, refer docs/signal.md for more details
-    litmus_install: True                                   # Installs specified version, set to False if it's already setup
-    litmus_version: v1.13.6                                # Litmus version to install
-    litmus_uninstall: False                                # If you want to uninstall litmus if failure
-    litmus_uninstall_before_run: True                      # If you want to uninstall litmus before a new run starts
     chaos_scenarios:                                       # List of policies/chaos scenarios to load
         -   container_scenarios:                                 # List of chaos pod scenarios to load
             - -    scenarios/kube/container_dns.yml
@@ -23,15 +19,11 @@ cerberus:
 performance_monitoring:
     deploy_dashboards: False                              # Install a mutable grafana and load the performance dashboards. Enable this only when running on OpenShift
     repo: "https://github.com/cloud-bulldozer/performance-dashboards.git"
-    kube_burner_binary_url: "https://github.com/cloud-bulldozer/kube-burner/releases/download/v0.9.1/kube-burner-0.9.1-Linux-x86_64.tar.gz"
-    capture_metrics: False
-    config_path: config/kube_burner.yaml                  # Define the Elasticsearch url and index name in this config
-    metrics_profile_path: config/metrics-aggregated.yaml
     prometheus_url:                                       # The prometheus url/route is automatically obtained in case of OpenShift, please set it when the distribution is Kubernetes.
     prometheus_bearer_token:                              # The bearer token is automatically obtained in case of OpenShift, please set it when the distribution is Kubernetes. This is needed to authenticate with prometheus.
     uuid:                                                 # uuid for the run is generated by default if not set
     enable_alerts: False                                  # Runs the queries specified in the alert profile and displays the info or exits 1 when severity=error
-    alert_profile: config/alerts                          # Path to alert profile with the prometheus queries
+    alert_profile: config/alerts.yaml                         # Path to alert profile with the prometheus queries
     check_critical_alerts: False                          # When enabled will check prometheus for critical alerts firing post chaos after soak time for the cluster to settle down
 tunings:
     wait_duration: 60                                      # Duration to wait between each chaos scenario

config/config_performance.yaml

@@ -6,9 +6,6 @@ kraken:
     signal_state: RUN                                      # Will wait for the RUN signal when set to PAUSE before running the scenarios, refer docs/signal.md for more details
     signal_address: 0.0.0.0                                # Signal listening address
     port: 8081                                             # Signal port
-    litmus_version: v1.13.6                                # Litmus version to install
-    litmus_uninstall: False                                # If you want to uninstall litmus if failure
-    litmus_uninstall_before_run: True                      # If you want to uninstall litmus before a new run starts
     chaos_scenarios:                                       # List of policies/chaos scenarios to load
         -   plugin_scenarios:                                 # List of chaos pod scenarios to load
             - scenarios/openshift/etcd.yml
@@ -21,9 +18,6 @@ kraken:
             - scenarios/openshift/openshift-kube-apiserver.yml
         -   time_scenarios:                                # List of chaos time scenarios to load
             - scenarios/openshift/time_scenarios_example.yml
-        -   litmus_scenarios:                              # List of litmus scenarios to load
-            - - https://hub.litmuschaos.io/api/chaos/1.10.0?file=charts/generic/node-cpu-hog/rbac.yaml
-              - scenarios/openshift/node_cpu_hog_engine.yaml
         -   cluster_shut_down_scenarios:
             - - scenarios/openshift/cluster_shut_down_scenario.yml
               - scenarios/openshift/post_action_shut_down.py
@@ -47,17 +41,39 @@ cerberus:
 performance_monitoring:
     deploy_dashboards: True                               # Install a mutable grafana and load the performance dashboards. Enable this only when running on OpenShift
     repo: "https://github.com/cloud-bulldozer/performance-dashboards.git"
-    kube_burner_binary_url: "https://github.com/cloud-bulldozer/kube-burner/releases/download/v0.9.1/kube-burner-0.9.1-Linux-x86_64.tar.gz"
     capture_metrics: True
-    config_path: config/kube_burner.yaml                  # Define the Elasticsearch url and index name in this config
     metrics_profile_path: config/metrics-aggregated.yaml
     prometheus_url:                                       # The prometheus url/route is automatically obtained in case of OpenShift, please set it when the distribution is Kubernetes.
     prometheus_bearer_token:                              # The bearer token is automatically obtained in case of OpenShift, please set it when the distribution is Kubernetes. This is needed to authenticate with prometheus.
     uuid:                                                 # uuid for the run is generated by default if not set
     enable_alerts: True                                   # Runs the queries specified in the alert profile and displays the info or exits 1 when severity=error
-    alert_profile: config/alerts                          # Path to alert profile with the prometheus queries
+    alert_profile: config/alerts.yaml                          # Path to alert profile with the prometheus queries
 
 tunings:
     wait_duration: 60                                      # Duration to wait between each chaos scenario
     iterations: 1                                          # Number of times to execute the scenarios
     daemon_mode: False                                     # Iterations are set to infinity which means that the kraken will cause chaos forever
+
+telemetry:
+    enabled: False                                           # enable/disables the telemetry collection feature
+    api_url: https://ulnmf9xv7j.execute-api.us-west-2.amazonaws.com/production #telemetry service endpoint
+    username: username                                      # telemetry service username
+    password: password                                      # telemetry service password
+    prometheus_backup: True                                 # enables/disables prometheus data collection
+    full_prometheus_backup: False                           # if is set to False only the /prometheus/wal folder will be downloaded.
+    backup_threads: 5                                       # number of telemetry download/upload threads
+    archive_path: /tmp                                      # local path where the archive files will be temporarly stored
+    max_retries: 0                                          # maximum number of upload retries (if 0 will retry forever)
+    run_tag: ''                                             # if set, this will be appended to the run folder in the bucket (useful to group the runs)
+    archive_size: 500000                                     # the size of the prometheus data archive size in KB. The lower the size of archive is
+                                                            # the higher the number of archive files will be produced and uploaded (and processed by backup_threads
+                                                            # simultaneously).
+                                                            # For unstable/slow connection is better to keep this value low
+                                                            # increasing the number of backup_threads, in this way, on upload failure, the retry will happen only on the
+                                                            # failed chunk without affecting the whole upload.
+    logs_backup: True
+    logs_filter_patterns:
+     - "(\\w{3}\\s\\d{1,2}\\s\\d{2}:\\d{2}:\\d{2}\\.\\d+).+"         # Sep 9 11:20:36.123425532
+     - "kinit (\\d+/\\d+/\\d+\\s\\d{2}:\\d{2}:\\d{2})\\s+"          # kinit 2023/09/15 11:20:36 log
+     - "(\\d{4}-\\d{2}-\\d{2}T\\d{2}:\\d{2}:\\d{2}\\.\\d+Z).+"      # 2023-09-15T11:20:36.123425532Z log
+    oc_cli_path: /usr/bin/oc                                # optional, if not specified will be search in $PATH

config/kube_burner.yaml

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

config/recommender_config.yaml

@@ -0,0 +1,29 @@
+application: openshift-etcd
+namespace: openshift-etcd
+labels: app=openshift-etcd
+kubeconfig: ~/.kube/config.yaml
+prometheus_endpoint: <Prometheus_Endpoint>
+auth_token: <Auth_Token>
+scrape_duration: 10m
+chaos_library: "kraken"
+log_level: INFO
+
+# for output purpose only do not change if not needed
+chaos_tests:
+  GENERIC:
+    - pod_failure
+    - container_failure
+    - node_failure
+    - zone_outage
+    - time_skew
+    - namespace_failure
+    - power_outage
+  CPU:
+    - node_cpu_hog
+  NETWORK:
+    - application_outage
+    - node_network_chaos
+    - pod_network_chaos
+  MEM:
+    - node_memory_hog
+    - pvc_disk_fill

containers/Dockerfile

@@ -4,8 +4,6 @@ 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
@@ -14,7 +12,7 @@ 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 v1.4.7 /root/kraken && \
+    git clone https://github.com/krkn-chaos/krkn.git --branch v1.5.4 /root/kraken && \
     mkdir -p /root/.kube && cd /root/kraken && \
     pip3.9 install -r requirements.txt && \
     pip3.9 install virtualenv && \

containers/Dockerfile-ppc64le

@@ -14,7 +14,7 @@ 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 v1.4.7 /root/kraken && \
+    git clone https://github.com/redhat-chaos/krkn.git --branch v1.5.4 /root/kraken && \
     mkdir -p /root/.kube && cd /root/kraken && \
     pip3.9 install -r requirements.txt && \
     pip3.9 install virtualenv && \

containers/README.md

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

containers/build_own_image-README.md

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

docs/SLOs_validation.md

@@ -11,19 +11,18 @@ performance_monitoring:
 ```
 
 ### Validation and alerting based on the queries defined by the user during chaos
-Takes PromQL queries as input and modifies the return code of the run to determine pass/fail. It's especially useful in case of automated runs in CI where user won't be able to monitor the system. It uses [Kube-burner](https://kube-burner.readthedocs.io/en/latest/) under the hood. This feature can be enabled in the [config](https://github.com/redhat-chaos/krkn/blob/main/config/config.yaml) by setting the following:
+Takes PromQL queries as input and modifies the return code of the run to determine pass/fail. It's especially useful in case of automated runs in CI where user won't be able to monitor the system. This feature can be enabled in the [config](https://github.com/redhat-chaos/krkn/blob/main/config/config.yaml) by setting the following:
 
 ```
 performance_monitoring:
-    kube_burner_binary_url: "https://github.com/cloud-bulldozer/kube-burner/releases/download/v0.9.1/kube-burner-0.9.1-Linux-x86_64.tar.gz"
     prometheus_url:                                       # The prometheus url/route is automatically obtained in case of OpenShift, please set it when the distribution is Kubernetes.
     prometheus_bearer_token:                              # The bearer token is automatically obtained in case of OpenShift, please set it when the distribution is Kubernetes. This is needed to authenticate with prometheus.
     enable_alerts: True                                   # Runs the queries specified in the alert profile and displays the info or exits 1 when severity=error.
-    alert_profile: config/alerts                          # Path to alert profile with the prometheus queries.
+    alert_profile: config/alerts.yaml                          # Path to alert profile with the prometheus queries.
 ```
 
 #### Alert profile
-A couple of [alert profiles](https://github.com/redhat-chaos/krkn/tree/main/config) [alerts](https://github.com/redhat-chaos/krkn/blob/main/config/alerts) are shipped by default and can be tweaked to add more queries to alert on. User can provide a URL or path to the file in the [config](https://github.com/redhat-chaos/krkn/blob/main/config/config.yaml). The following are a few alerts examples:
+A couple of [alert profiles](https://github.com/redhat-chaos/krkn/tree/main/config) [alerts](https://github.com/redhat-chaos/krkn/blob/main/config/alerts.yaml) are shipped by default and can be tweaked to add more queries to alert on. User can provide a URL or path to the file in the [config](https://github.com/redhat-chaos/krkn/blob/main/config/config.yaml). The following are a few alerts examples:
 
 ```
 - expr: avg_over_time(histogram_quantile(0.99, rate(etcd_disk_wal_fsync_duration_seconds_bucket[2m]))[5m:]) > 0.01

docs/container_scenarios.md

@@ -8,14 +8,14 @@ The following are the components of Kubernetes/OpenShift for which a basic chaos
 
 ```
 scenarios:
-- name: "<Name of scenario>"
+- name: "<name of scenario>"
   namespace: "<specific namespace>" # can specify "*" if you want to find in all namespaces
   label_selector: "<label of pod(s)>"
   container_name: "<specific container name>"  # This is optional, can take out and will kill all containers in all pods found under namespace and label
   pod_names:  # This is optional, can take out and will select all pods with given namespace and label
   - <pod_name>
   count: <number of containers to disrupt, default=1>
-  action: <Action to run. For example kill 1 ( hang up ) or kill 9. Default is set to kill 1>
+  action: <kill signal to run. For example 1 ( hang up ) or 9. Default is set to 1>
   expected_recovery_time: <number of seconds to wait for container to be running again> (defaults to 120seconds)
 ```
 

docs/contribute.md

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

docs/index.md

@@ -48,7 +48,7 @@ Failures in production are costly. To help mitigate risk to service health, cons
 
 
 ### Best Practices
-Now that we understand the test methodology, let us take a look at the best practices for an OpenShift cluster.  On that platform there are user applications and cluster workloads that need to be designed for stability and to provide the best user experience possible:
+Now that we understand the test methodology, let us take a look at the best practices for an Kubernetes cluster.  On that platform there are user applications and cluster workloads that need to be designed for stability and to provide the best user experience possible:
 
 - Alerts with appropriate severity should get fired.
   - Alerts are key to identify when a component starts degrading, and can help focus the investigation effort on affected system components.
@@ -77,11 +77,11 @@ We want to look at this in terms of CPU, Memory, Disk, Throughput, Network etc.
   - The controller watching the component should recognize a failure as soon as possible. The component needs to have minimal initialization time to avoid extended downtime or overloading the replicas if it is a highly available configuration. The cause of failure can be because of issues with the infrastructure on top of which it is running, application failures, or because of service failures that it depends on.
 
 - High Availability deployment strategy.
-  - There should be multiple replicas ( both OpenShift and application control planes ) running preferably in different availability zones to survive outages while still serving the user/system requests. Avoid single points of failure.
+  - There should be multiple replicas ( both Kubernetes and application control planes ) running preferably in different availability zones to survive outages while still serving the user/system requests. Avoid single points of failure.
 - Backed by persistent storage
   - It is important to have the system/application backed by persistent storage. This is especially important in cases where the application is a database or a stateful application given that a node, pod, or container failure will wipe off the data.
 
-- There should be fallback routes to the backend in case of using CDN, for example, Akamai in case of console.redhat.com - a managed service deployed on top of OpenShift dedicated:
+- There should be fallback routes to the backend in case of using CDN, for example, Akamai in case of console.redhat.com - a managed service deployed on top of Kubernetes dedicated:
   - Content delivery networks (CDNs) are commonly used to host resources such as images, JavaScript files, and CSS. The average web page is nearly 2 MB in size, and offloading heavy resources to third-parties is extremely effective for reducing backend server traffic and latency. However, this makes each CDN an additional point of failure for every site that relies on it. If the CDN fails, its customers could also fail.
   - To test how the application reacts to failures, drop all network traffic between the system and CDN. The application should still serve the content to the user irrespective of the failure.
 
@@ -92,10 +92,10 @@ We want to look at this in terms of CPU, Memory, Disk, Throughput, Network etc.
 
 
 ### Tooling
-Now that we looked at the best practices, In this section, we will go through how [Kraken](https://github.com/redhat-chaos/krkn) - a chaos testing framework can help test the resilience of OpenShift and make sure the applications and services are following the best practices.
+Now that we looked at the best practices, In this section, we will go through how [Kraken](https://github.com/redhat-chaos/krkn) - a chaos testing framework can help test the resilience of Kubernetes and make sure the applications and services are following the best practices.
 
 #### Workflow
-Let us start by understanding the workflow of kraken: the user will start by running kraken by pointing to a specific OpenShift cluster using kubeconfig to be able to talk to the platform on top of which the OpenShift cluster is hosted. This can be done by either the oc/kubectl API or the cloud API. Based on the configuration of kraken, it will inject specific chaos scenarios as shown below, talk to [Cerberus](https://github.com/redhat-chaos/cerberus) to get the go/no-go signal representing the overall health of the cluster ( optional - can be turned off ), scrapes metrics from in-cluster prometheus given a metrics profile with the promql queries and stores them long term in Elasticsearch configured  ( optional - can be turned off ), evaluates the promql expressions specified in the alerts profile ( optional - can be turned off ) and aggregated everything to set the pass/fail i.e. exits 0 or 1. More about the metrics collection, cerberus and metrics evaluation can be found in the next section.
+Let us start by understanding the workflow of kraken: the user will start by running kraken by pointing to a specific Kubernetes cluster using kubeconfig to be able to talk to the platform on top of which the Kubernetes cluster is hosted. This can be done by either the oc/kubectl API or the cloud API. Based on the configuration of kraken, it will inject specific chaos scenarios as shown below, talk to [Cerberus](https://github.com/redhat-chaos/cerberus) to get the go/no-go signal representing the overall health of the cluster ( optional - can be turned off ), scrapes metrics from in-cluster prometheus given a metrics profile with the promql queries and stores them long term in Elasticsearch configured  ( optional - can be turned off ), evaluates the promql expressions specified in the alerts profile ( optional - can be turned off ) and aggregated everything to set the pass/fail i.e. exits 0 or 1. More about the metrics collection, cerberus and metrics evaluation can be found in the next section.
 
 ![Kraken workflow](../media/kraken-workflow.png)
 
@@ -112,15 +112,15 @@ If the monitoring tool, cerberus is enabled it will consume the signal and conti
 
 ### Scenarios
 
-Let us take a look at how to run the chaos scenarios on your OpenShift clusters using Kraken-hub - a lightweight wrapper around Kraken to ease the runs by providing the ability to run them by just running container images using podman with parameters set as environment variables. This eliminates the need to carry around and edit configuration files and makes it easy for any CI framework integration. Here are the scenarios supported:
+Let us take a look at how to run the chaos scenarios on your Kubernetes clusters using Kraken-hub - a lightweight wrapper around Kraken to ease the runs by providing the ability to run them by just running container images using podman with parameters set as environment variables. This eliminates the need to carry around and edit configuration files and makes it easy for any CI framework integration. Here are the scenarios supported:
 
 - Pod Scenarios ([Documentation](https://github.com/redhat-chaos/krkn-hub/blob/main/docs/pod-scenarios.md))
-  - Disrupts OpenShift/Kubernetes and applications deployed as pods:
+  - Disrupts Kubernetes/Kubernetes and applications deployed as pods:
     - Helps understand the availability of the application, the initialization timing and recovery status.
   - [Demo](https://asciinema.org/a/452351?speed=3&theme=solarized-dark)
 
 - Container Scenarios ([Documentation](https://github.com/redhat-chaos/krkn-hub/blob/main/docs/container-scenarios.md))
-  - Disrupts OpenShift/Kubernetes and applications deployed as containers running as part of a pod(s) using a specified kill signal to mimic failures:
+  - Disrupts Kubernetes/Kubernetes and applications deployed as containers running as part of a pod(s) using a specified kill signal to mimic failures:
     - Helps understand the impact and recovery timing when the program/process running in the containers are disrupted - hangs, paused, killed etc., using various kill signals, i.e. SIGHUP, SIGTERM, SIGKILL etc.
   - [Demo](https://asciinema.org/a/BXqs9JSGDSEKcydTIJ5LpPZBM?speed=3&theme=solarized-dark)
 
@@ -134,8 +134,8 @@ Let us take a look at how to run the chaos scenarios on your OpenShift clusters
   - [Demo](https://asciinema.org/a/ANZY7HhPdWTNaWt4xMFanF6Q5)
 
 - Zone Outages ([Documentation](https://github.com/redhat-chaos/krkn-hub/blob/main/docs/zone-outages.md))
-  - Creates outage of availability zone(s) in a targeted region in the public cloud where the OpenShift cluster is running by tweaking the network acl of the zone to simulate the failure, and that in turn will stop both ingress and egress traffic from all nodes in a particular zone for the specified duration and reverts it back to the previous state.
-    - Helps understand the impact on both Kubernetes/OpenShift control plane as well as applications and services running on the worker nodes in that zone.
+  - Creates outage of availability zone(s) in a targeted region in the public cloud where the Kubernetes cluster is running by tweaking the network acl of the zone to simulate the failure, and that in turn will stop both ingress and egress traffic from all nodes in a particular zone for the specified duration and reverts it back to the previous state.
+    - Helps understand the impact on both Kubernetes/Kubernetes control plane as well as applications and services running on the worker nodes in that zone.
     - Currently, only set up for AWS cloud platform: 1 VPC and multiples subnets within the VPC can be specified.
     - [Demo](https://asciinema.org/a/452672?speed=3&theme=solarized-dark)
 
@@ -200,7 +200,7 @@ Let us take a look at few recommendations on how and where to run the chaos test
 - Enable Observability:
   - Chaos Engineering Without Observability ... Is Just Chaos.
   - Make sure to have logging and monitoring installed on the cluster to help with understanding the behaviour as to why it is happening. In case of running the tests in the CI where it is not humanly possible to monitor the cluster all the time, it is recommended to leverage Cerberus to capture the state during the runs and metrics collection in Kraken to store metrics long term even after the cluster is gone.
-  - Kraken ships with dashboards that will help understand API, Etcd and OpenShift cluster level stats and performance metrics.
+  - Kraken ships with dashboards that will help understand API, Etcd and Kubernetes cluster level stats and performance metrics.
   - Pay attention to Prometheus alerts. Check if they are firing as expected.
 
 - Run multiple chaos tests at once to mimic the production outages:

docs/installation.md

@@ -3,8 +3,8 @@
 The following ways are supported to run Kraken:
 
 - Standalone python program through Git.
-- Containerized version using either Podman or Docker as the runtime.
-- Kubernetes or OpenShift deployment.
+- Containerized version using either Podman or Docker as the runtime via [Krkn-hub](https://github.com/redhat-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.
 
@@ -40,26 +40,12 @@ $ python3.9 run_kraken.py --config <config_file_location>
 ```
 
 ### Run containerized version
-Assuming that the latest docker ( 17.05 or greater with multi-build support ) is installed on the host, run:
-```
-$ docker pull quay.io/redhat-chaos/krkn:latest
-$ docker run --name=kraken --net=host -v <path_to_kubeconfig>:/root/.kube/config:Z -v <path_to_kraken_config>:/root/kraken/config/config.yaml:Z -d quay.io/redhat-chaos/krkn:latest
-$ docker run --name=kraken --net=host -v <path_to_kubeconfig>:/root/.kube/config:Z -v <path_to_kraken_config>:/root/kraken/config/config.yaml:Z -v <path_to_scenarios_directory>:/root/kraken/scenarios:Z -d quay.io/redhat-chaos/krkn:latest #custom or tweaked scenario configs
-$ docker logs -f kraken
-```
+[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.
 
-Similarly, podman can be used to achieve the same:
-```
-$ podman pull quay.io/redhat-chaos/krkn
-$ podman run --name=kraken --net=host -v <path_to_kubeconfig>:/root/.kube/config:Z -v <path_to_kraken_config>:/root/kraken/config/config.yaml:Z -d quay.io/redhat-chaos/krkn:latest
-$ podman run --name=kraken --net=host -v <path_to_kubeconfig>:/root/.kube/config:Z -v <path_to_kraken_config>:/root/kraken/config/config.yaml:Z -v <path_to_scenarios_directory>:/root/kraken/scenarios:Z -d quay.io/redhat-chaos/krkn:latest #custom or tweaked scenario configs
-$ podman logs -f kraken
-```
-
-If you want to build your own kraken image see [here](https://github.com/redhat-chaos/krkn/blob/main/containers/build_own_image-README.md)
+Refer [instructions](https://github.com/redhat-chaos/krkn-hub#supported-chaos-scenarios) to get started.
 
 
-### Run Kraken as a Kubernetes deployment
+### 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.
 
 

docs/metrics.md

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

docs/network_chaos.md

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

docs/pod_network_scenarios.md

@@ -27,6 +27,15 @@ Scenario to introduce network latency, packet loss, and bandwidth restriction in
     network_params:
         latency: 500ms             # Add 500ms latency to egress traffic from the pod.
 ```
+##### Sample scenario config for ingress traffic shaping (using plugin)
+```
+- id: pod_ingress_shaping
+  config:
+    namespace: openshift-console   # Required - Namespace of the pod to which filter need to be applied.
+    label_selector: 'component=ui' # Applies traffic shaping to access openshift console.
+    network_params:
+        latency: 500ms             # Add 500ms latency to egress traffic from the pod.
+```
 
 ##### Steps
  - Pick the pods to introduce the network anomaly either from label_selector or pod_name.

kraken/application_outage/actions.py

@@ -4,12 +4,14 @@ import time
 import kraken.cerberus.setup as cerberus
 from jinja2 import Template
 import kraken.invoke.command as runcommand
-from krkn_lib.telemetry import KrknTelemetry
+from krkn_lib.telemetry.k8s import KrknTelemetryKubernetes
 from krkn_lib.models.telemetry import ScenarioTelemetry
+from krkn_lib.utils.functions import get_yaml_item_value, log_exception
+
 
 # Reads the scenario config, applies and deletes a network policy to
 # block the traffic for the specified duration
-def run(scenarios_list, config, wait_duration, telemetry: KrknTelemetry) -> (list[str], list[ScenarioTelemetry]):
+def run(scenarios_list, config, wait_duration, telemetry: KrknTelemetryKubernetes) -> (list[str], list[ScenarioTelemetry]):
     failed_post_scenarios = ""
     scenario_telemetries: list[ScenarioTelemetry] = []
     failed_scenarios = []
@@ -23,10 +25,18 @@ def run(scenarios_list, config, wait_duration, telemetry: KrknTelemetry) -> (lis
                 with open(app_outage_config, "r") as f:
                     app_outage_config_yaml = yaml.full_load(f)
                     scenario_config = app_outage_config_yaml["application_outage"]
-                    pod_selector = scenario_config.get("pod_selector", "{}")
-                    traffic_type = scenario_config.get("block", "[Ingress, Egress]")
-                    namespace = scenario_config.get("namespace", "")
-                    duration = scenario_config.get("duration", 60)
+                    pod_selector = get_yaml_item_value(
+                        scenario_config, "pod_selector", "{}"
+                    )
+                    traffic_type = get_yaml_item_value(
+                        scenario_config, "block", "[Ingress, Egress]"
+                    )
+                    namespace = get_yaml_item_value(
+                        scenario_config, "namespace", ""
+                    )
+                    duration = get_yaml_item_value(
+                        scenario_config, "duration", 60
+                    )
 
                     start_time = int(time.time())
 
@@ -67,7 +77,7 @@ spec:
             except Exception as e :
                 scenario_telemetry.exitStatus = 1
                 failed_scenarios.append(app_outage_config)
-                telemetry.log_exception(app_outage_config)
+                log_exception(app_outage_config)
             else:
                 scenario_telemetry.exitStatus = 0
             scenario_telemetry.endTimeStamp = time.time()

kraken/arcaflow_plugin/arcaflow_plugin.py

@@ -6,11 +6,11 @@ import logging
 from pathlib import Path
 from typing import List
 from .context_auth import ContextAuth
-from krkn_lib.telemetry import KrknTelemetry
+from krkn_lib.telemetry.k8s import KrknTelemetryKubernetes
 from krkn_lib.models.telemetry import ScenarioTelemetry
 
 
-def run(scenarios_list: List[str], kubeconfig_path: str, telemetry: KrknTelemetry) -> (list[str], list[ScenarioTelemetry]):
+def run(scenarios_list: List[str], kubeconfig_path: str, telemetry: KrknTelemetryKubernetes) -> (list[str], list[ScenarioTelemetry]):
     scenario_telemetries: list[ScenarioTelemetry] = []
     failed_post_scenarios = []
     for scenario in scenarios_list:
@@ -96,9 +96,9 @@ def set_arca_kubeconfig(engine_args: arcaflow.EngineArgs, kubeconfig_path: str):
 
     with open(engine_args.config, "r") as stream:
         config_file = yaml.safe_load(stream)
-    if config_file["deployer"]["type"] == "kubernetes":
-        kube_connection = set_kubernetes_deployer_auth(config_file["deployer"]["connection"], context_auth)
-        config_file["deployer"]["connection"]=kube_connection
+    if config_file["deployers"]["image"]["deployer_name"] == "kubernetes":
+        kube_connection = set_kubernetes_deployer_auth(config_file["deployers"]["image"]["connection"], context_auth)
+        config_file["deployers"]["image"]["connection"]=kube_connection
         with open(engine_args.config, "w") as stream:
             yaml.safe_dump(config_file, stream,explicit_start=True, width=4096)
 

kraken/chaos_recommender/__init__.py

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

kraken/chaos_recommender/analysis.py

@@ -0,0 +1,90 @@
+import logging
+
+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
+def return_critical_services():
+    return ["web", "cart"]
+
+
+def load_telemetry_data(file_path):
+    data = pd.read_csv(file_path, delimiter=r"\s+")
+    return data
+
+def calculate_zscores(data):
+    zscores = pd.DataFrame()
+    zscores["Service"] = data["service"]
+    zscores["CPU"] = (data["CPU"] - data["CPU"].mean()) / data["CPU"].std()
+    zscores["Memory"] = (data["MEM"] - data["MEM"].mean()) / data["MEM"].std()
+    zscores["Network"] = (data["NETWORK"] - data["NETWORK"].mean()) / data["NETWORK"].std()
+    return zscores
+
+def identify_outliers(data):
+    outliers_cpu = data[data["CPU"] > threshold]["Service"].tolist()
+    outliers_memory = data[data["Memory"] > threshold]["Service"].tolist()
+    outliers_network = data[data["Network"] > threshold]["Service"].tolist()
+
+    return outliers_cpu, outliers_memory, outliers_network
+
+
+def get_services_above_heatmap_threshold(dataframe, cpu_threshold, mem_threshold):
+    # Filter the DataFrame based on CPU_HEATMAP and MEM_HEATMAP thresholds
+    filtered_df = dataframe[((dataframe['CPU']/dataframe['CPU_LIMITS']) > cpu_threshold)]
+    # Get the lists of services
+    cpu_services = filtered_df['service'].tolist()
+
+    filtered_df = dataframe[((dataframe['MEM']/dataframe['MEM_LIMITS']) > mem_threshold)]
+    mem_services = filtered_df['service'].tolist()
+
+    return cpu_services, mem_services
+
+
+def analysis(file_path, chaos_tests_config):
+    # Load the telemetry data from file
+    data = load_telemetry_data(file_path)
+
+    # Calculate Z-scores for CPU, Memory, and Network columns
+    zscores = calculate_zscores(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)
+
+    # 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 ==============================")
+
+    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).")
+    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")
+
+    if outliers_network:
+        logging.info(f"Recommended tests for  str(outliers_network)  :\n {chaos_tests_config['NETWORK']}")
+        logging.info("\n")
+
+    logging.info("\n")
+    logging.info("Please check data in utilisation.txt for further analysis")

kraken/chaos_recommender/kraken_tests.py

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

kraken/chaos_recommender/prometheus.py

@@ -0,0 +1,96 @@
+import logging
+
+import pandas
+from prometheus_api_client import PrometheusConnect
+import pandas as pd
+import urllib3
+
+
+saved_metrics_path = "./utilisation.txt"
+
+def convert_data_to_dataframe(data, label):
+    df = pd.DataFrame()
+    df['service'] = [item['metric']['pod'] for item in data]
+    df[label] = [item['value'][1] for item in data]
+
+    return df
+
+
+def convert_data(data, service):
+
+    result = {}
+    for entry in data:
+        pod_name = entry['metric']['pod']
+        value = entry['value'][1]
+        result[pod_name] = value
+    return result.get(service, '100000000000') # for those pods whose limits are not defined they can take as much resources, there assigning a very high value
+
+def save_utilization_to_file(cpu_data, cpu_limits_result, mem_data, mem_limits_result, network_data, filename):
+    df_cpu = convert_data_to_dataframe(cpu_data, "CPU")
+    merged_df = pd.DataFrame(columns=['service','CPU','CPU_LIMITS','MEM','MEM_LIMITS','NETWORK'])
+    services = df_cpu.service.unique()
+    logging.info(services)
+
+    for s in services:
+
+        new_row_df = pd.DataFrame( {"service": s, "CPU" : convert_data(cpu_data, s),
+                    "CPU_LIMITS" : convert_data(cpu_limits_result, s),
+                    "MEM" : convert_data(mem_data, s), "MEM_LIMITS" : convert_data(mem_limits_result, s),
+                    "NETWORK" : convert_data(network_data, s)}, index=[0])
+        merged_df = pd.concat([merged_df, new_row_df], ignore_index=True)
+
+
+
+    # Convert columns to string
+    merged_df['CPU'] = merged_df['CPU'].astype(str)
+    merged_df['MEM'] = merged_df['MEM'].astype(str)
+    merged_df['CPU_LIMITS'] = merged_df['CPU_LIMITS'].astype(str)
+    merged_df['MEM_LIMITS'] = merged_df['MEM_LIMITS'].astype(str)
+    merged_df['NETWORK'] = merged_df['NETWORK'].astype(str)
+
+    # Extract integer part before the decimal point
+    merged_df['CPU'] = merged_df['CPU'].str.split('.').str[0]
+    merged_df['MEM'] = merged_df['MEM'].str.split('.').str[0]
+    merged_df['CPU_LIMITS'] = merged_df['CPU_LIMITS'].str.split('.').str[0]
+    merged_df['MEM_LIMITS'] = merged_df['MEM_LIMITS'].str.split('.').str[0]
+    merged_df['NETWORK'] = merged_df['NETWORK'].str.split('.').str[0]
+
+    merged_df.to_csv(filename, sep='\t', index=False)
+
+def fetch_utilization_from_prometheus(prometheus_endpoint, auth_token, namespace, scrape_duration):
+    urllib3.disable_warnings()
+    prometheus = PrometheusConnect(url=prometheus_endpoint, headers={'Authorization':'Bearer {}'.format(auth_token)}, disable_ssl=True)
+
+    # Fetch CPU utilization
+    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
+
+

kraken/kube_burner/client.py

@@ -1,116 +0,0 @@
-import subprocess
-import logging
-import urllib.request
-import shutil
-import sys
-import requests
-import tempfile
-import kraken.prometheus.client as prometheus
-from urllib.parse import urlparse
-
-
-def setup(url):
-    """
-    Downloads and unpacks kube-burner binary
-    """
-
-    filename = "kube_burner.tar"
-    try:
-        logging.info("Fetching kube-burner binary")
-        urllib.request.urlretrieve(url, filename)
-    except Exception as e:
-        logging.error("Failed to download kube-burner binary located at %s" % url, e)
-        sys.exit(1)
-    try:
-        logging.info("Unpacking kube-burner tar ball")
-        shutil.unpack_archive(filename)
-    except Exception as e:
-        logging.error("Failed to unpack the kube-burner binary tarball: %s" % e)
-        sys.exit(1)
-
-
-def scrape_metrics(
-    distribution, uuid, prometheus_url, prometheus_bearer_token, start_time, end_time, config_path, metrics_profile
-):
-    """
-    Scrapes metrics defined in the profile from Prometheus and indexes them into Elasticsearch
-    """
-
-    if not prometheus_url:
-        if distribution == "openshift":
-            logging.info("Looks like prometheus_url is not defined, trying to use the default instance on the cluster")
-            prometheus_url, prometheus_bearer_token = prometheus.instance(
-                distribution, prometheus_url, prometheus_bearer_token
-            )
-        else:
-            logging.error("Looks like prometheus url is not defined, exiting")
-            sys.exit(1)
-    command = (
-        "./kube-burner index --uuid "
-        + str(uuid)
-        + " -u "
-        + str(prometheus_url)
-        + " -t "
-        + str(prometheus_bearer_token)
-        + " -m "
-        + str(metrics_profile)
-        + " --start "
-        + str(start_time)
-        + " --end "
-        + str(end_time)
-        + " -c "
-        + str(config_path)
-    )
-    try:
-        logging.info("Running kube-burner to capture the metrics: %s" % command)
-        logging.info("UUID for the run: %s" % uuid)
-        subprocess.run(command, shell=True, universal_newlines=True)
-    except Exception as e:
-        logging.error("Failed to run kube-burner, error: %s" % (e))
-        sys.exit(1)
-
-
-def alerts(distribution, prometheus_url, prometheus_bearer_token, start_time, end_time, alert_profile):
-    """
-    Scrapes metrics defined in the profile from Prometheus and alerts based on the severity defined
-    """
-
-    is_url = urlparse(alert_profile)
-    if is_url.scheme and is_url.netloc:
-        response = requests.get(alert_profile)
-        temp_alerts = tempfile.NamedTemporaryFile()
-        temp_alerts.write(response.content)
-        temp_alerts.flush()
-        alert_profile = temp_alerts.name
-
-    if not prometheus_url:
-        if distribution == "openshift":
-            logging.info("Looks like prometheus_url is not defined, trying to use the default instance on the cluster")
-            prometheus_url, prometheus_bearer_token = prometheus.instance(
-                distribution, prometheus_url, prometheus_bearer_token
-            )
-        else:
-            logging.error("Looks like prometheus url is not defined, exiting")
-            sys.exit(1)
-    command = (
-        "./kube-burner check-alerts "
-        + " -u "
-        + str(prometheus_url)
-        + " -t "
-        + str(prometheus_bearer_token)
-        + " -a "
-        + str(alert_profile)
-        + " --start "
-        + str(start_time)
-        + " --end "
-        + str(end_time)
-    )
-    try:
-        logging.info("Running kube-burner to capture the metrics: %s" % command)
-        output = subprocess.run(command, shell=True, universal_newlines=True)
-        if output.returncode != 0:
-            logging.error("command exited with a non-zero rc, please check the logs for errors or critical alerts")
-            sys.exit(output.returncode)
-    except Exception as e:
-        logging.error("Failed to run kube-burner, error: %s" % (e))
-        sys.exit(1)

kraken/litmus/common_litmus.py

@@ -1,221 +0,0 @@
-import kraken.invoke.command as runcommand
-import logging
-import time
-import sys
-import requests
-import yaml
-import kraken.cerberus.setup as cerberus
-from krkn_lib.k8s import KrknKubernetes
-
-# krkn_lib
-# Inject litmus scenarios defined in the config
-def run(
-        scenarios_list,
-        config,
-        litmus_uninstall,
-        wait_duration,
-        litmus_namespace,
-        kubecli: KrknKubernetes
-):
-    # Loop to run the scenarios starts here
-    for l_scenario in scenarios_list:
-        start_time = int(time.time())
-        try:
-            for item in l_scenario:
-                runcommand.invoke("kubectl apply -f %s -n %s" % (item, litmus_namespace))
-                if "http" in item:
-                    f = requests.get(item)
-                    yaml_item = list(yaml.safe_load_all(f.content))[0]
-                else:
-                    with open(item, "r") as f:
-                        yaml_item = list(yaml.safe_load_all(f))[0]
-
-                if yaml_item["kind"] == "ChaosEngine":
-                    engine_name = yaml_item["metadata"]["name"]
-                    experiment_names = yaml_item["spec"]["experiments"]
-                    experiment_namespace = yaml_item["metadata"]["namespace"]
-                    if experiment_namespace != "litmus":
-                        logging.error(
-                            "Specified namespace: %s in the scenario: %s is not supported, please switch it to litmus"
-                            % (experiment_namespace, l_scenario)
-                        )
-                        sys.exit(1)
-                    for expr in experiment_names:
-                        expr_name = expr["name"]
-                        experiment_result = check_experiment(engine_name, expr_name, litmus_namespace, kubecli)
-                        if experiment_result:
-                            logging.info("Scenario: %s has been successfully injected!" % item)
-                        else:
-                            logging.info("Scenario: %s was not successfully injected, please check" % item)
-                            if litmus_uninstall:
-                                delete_chaos(litmus_namespace, kubecli)
-                            sys.exit(1)
-            if litmus_uninstall:
-                delete_chaos(litmus_namespace, kubecli)
-            logging.info("Waiting for the specified duration: %s" % wait_duration)
-            time.sleep(wait_duration)
-            end_time = int(time.time())
-            cerberus.get_status(config, start_time, end_time)
-        except Exception as e:
-            logging.error("Failed to run litmus scenario: %s. Encountered " "the following exception: %s" % (item, e))
-            sys.exit(1)
-
-
-# Install litmus and wait until pod is running
-def install_litmus(version, namespace):
-    logging.info("Installing version %s of litmus in namespace %s" % (version, namespace))
-    litmus_install = runcommand.invoke(
-        "kubectl -n %s apply -f " "https://litmuschaos.github.io/litmus/litmus-operator-%s.yaml" % (namespace, version)
-    )
-    if "unable" in litmus_install:
-        logging.info("Unable to install litmus because " + str(litmus_install))
-        sys.exit(1)
-
-    runcommand.invoke(
-        "oc patch -n %s deployment.apps/chaos-operator-ce --type=json --patch ' "
-        '[ { "op": "add", "path": "/spec/template/spec/containers/0/env/-", '
-        '"value": { "name": "ANALYTICS", "value": "FALSE" } } ]\'' % namespace
-    )
-    logging.info("Waiting for litmus operator to become available")
-    runcommand.invoke("oc wait deploy -n %s chaos-operator-ce --for=condition=Available" % namespace)
-
-
-def deploy_all_experiments(version_string, namespace):
-
-    if not version_string.startswith("v"):
-        logging.error("Incorrect version string for litmus, needs to start with 'v' " "followed by a number")
-        sys.exit(1)
-    version = version_string[1:]
-    logging.info("Installing all litmus experiments")
-    runcommand.invoke(
-        "kubectl -n %s apply -f "
-        "https://hub.litmuschaos.io/api/chaos/%s?file=charts/generic/experiments.yaml" % (namespace, version)
-    )
-
-
-# krkn_lib
-def wait_for_initialized(engine_name, experiment_name, namespace, kubecli: KrknKubernetes):
-
-    chaos_engine = kubecli.get_litmus_chaos_object(kind='chaosengine', name=engine_name,
-                                                   namespace=namespace).engineStatus
-    engine_status = chaos_engine.strip()
-    max_tries = 30
-    engine_counter = 0
-    while engine_status.lower() != "initialized":
-        time.sleep(10)
-        logging.info("Waiting for " + experiment_name + " to be initialized")
-        chaos_engine = kubecli.get_litmus_chaos_object(kind='chaosengine', name=engine_name,
-                                                       namespace=namespace).engineStatus
-        engine_status = chaos_engine.strip()
-        if engine_counter >= max_tries:
-            logging.error("Chaos engine " + experiment_name + " took longer than 5 minutes to be initialized")
-            return False
-        engine_counter += 1
-        # need to see if error in run
-        if "notfound" in engine_status.lower():
-            logging.info("Chaos engine was not found")
-            return False
-    return True
-
-
-# krkn_lib
-def wait_for_status(
-        engine_name,
-        expected_status,
-        experiment_name,
-        namespace,
-        kubecli: KrknKubernetes
-):
-
-    if expected_status == "running":
-        response = wait_for_initialized(engine_name, experiment_name, namespace, kubecli)
-        if not response:
-            logging.info("Chaos engine never initialized, exiting")
-            return False
-    chaos_engine = kubecli.get_litmus_chaos_object(kind='chaosengine', name=engine_name,
-                                                   namespace=namespace).expStatus
-    engine_status = chaos_engine.strip()
-    max_tries = 30
-    engine_counter = 0
-    while engine_status.lower() != expected_status:
-        time.sleep(10)
-        logging.info("Waiting for " + experiment_name + " to be " + expected_status)
-        chaos_engine = kubecli.get_litmus_chaos_object(kind='chaosengine', name=engine_name,
-                                                       namespace=namespace).expStatus
-        engine_status = chaos_engine.strip()
-        if engine_counter >= max_tries:
-            logging.error("Chaos engine " + experiment_name + " took longer than 5 minutes to be " + expected_status)
-            return False
-        engine_counter += 1
-        # need to see if error in run
-        if "notfound" in engine_status.lower():
-            logging.info("Chaos engine was not found")
-            return False
-    return True
-
-
-# Check status of experiment
-# krkn_lib
-def check_experiment(engine_name, experiment_name, namespace, kubecli: KrknKubernetes):
-
-    wait_response = wait_for_status(engine_name, "running", experiment_name, namespace, kubecli)
-
-    if wait_response:
-        wait_for_status(engine_name, "completed", experiment_name, namespace, kubecli)
-    else:
-        sys.exit(1)
-
-    chaos_result = kubecli.get_litmus_chaos_object(kind='chaosresult', name=engine_name+'-'+experiment_name,
-                                                   namespace=namespace).verdict
-    if chaos_result == "Pass":
-        logging.info("Engine " + str(engine_name) + " finished with status " + str(chaos_result))
-        return True
-    else:
-        chaos_result = kubecli.get_litmus_chaos_object(kind='chaosresult', name=engine_name+'-'+experiment_name,
-                                                       namespace=namespace).failStep
-        logging.info("Chaos scenario:" + engine_name + " failed with error: " + str(chaos_result))
-        logging.info(
-            "See 'kubectl get chaosresult %s"
-            "-%s -n %s -o yaml' for full results" % (engine_name, experiment_name, namespace)
-        )
-        return False
-
-
-# Delete all chaos engines in a given namespace
-# krkn_lib
-def delete_chaos_experiments(namespace, kubecli: KrknKubernetes):
-
-    if kubecli.check_if_namespace_exists(namespace):
-        chaos_exp_exists = runcommand.invoke_no_exit("kubectl get chaosexperiment")
-        if "returned non-zero exit status 1" not in chaos_exp_exists:
-            logging.info("Deleting all litmus experiments")
-            runcommand.invoke("kubectl delete chaosexperiment --all -n " + str(namespace))
-
-
-# Delete all chaos engines in a given namespace
-# krkn_lib
-def delete_chaos(namespace, kubecli:KrknKubernetes):
-
-    if kubecli.check_if_namespace_exists(namespace):
-        logging.info("Deleting all litmus run objects")
-        chaos_engine_exists = runcommand.invoke_no_exit("kubectl get chaosengine")
-        if "returned non-zero exit status 1" not in chaos_engine_exists:
-            runcommand.invoke("kubectl delete chaosengine --all -n " + str(namespace))
-        chaos_result_exists = runcommand.invoke_no_exit("kubectl get chaosresult")
-        if "returned non-zero exit status 1" not in chaos_result_exists:
-            runcommand.invoke("kubectl delete chaosresult --all -n " + str(namespace))
-    else:
-        logging.info(namespace + " namespace doesn't exist")
-
-
-# krkn_lib
-def uninstall_litmus(version, litmus_namespace, kubecli: KrknKubernetes):
-
-    if kubecli.check_if_namespace_exists(litmus_namespace):
-        logging.info("Uninstalling Litmus operator")
-        runcommand.invoke_no_exit(
-            "kubectl delete -n %s -f "
-            "https://litmuschaos.github.io/litmus/litmus-operator-%s.yaml" % (litmus_namespace, version)
-        )
-        logging.info("Deleting litmus crd")
-        runcommand.invoke_no_exit("kubectl get crds | grep litmus | awk '{print $1}' | xargs -I {} oc delete crd/{}")

kraken/managedcluster_scenarios/run.py

@@ -5,6 +5,7 @@ from kraken.managedcluster_scenarios.managedcluster_scenarios import managedclus
 import kraken.managedcluster_scenarios.common_managedcluster_functions as common_managedcluster_functions
 import kraken.cerberus.setup as cerberus
 from krkn_lib.k8s import KrknKubernetes
+from krkn_lib.utils.functions import get_yaml_item_value
 
 # Get the managedcluster scenarios object of specfied cloud type
 # krkn_lib
@@ -34,11 +35,19 @@ def run(scenarios_list, config, wait_duration, kubecli: KrknKubernetes):
 # krkn_lib
 def inject_managedcluster_scenario(action, managedcluster_scenario, managedcluster_scenario_object, kubecli: KrknKubernetes):
     # Get the managedcluster scenario configurations
-    run_kill_count = managedcluster_scenario.get("runs", 1)
-    instance_kill_count = managedcluster_scenario.get("instance_count", 1)
-    managedcluster_name = managedcluster_scenario.get("managedcluster_name", "")
-    label_selector = managedcluster_scenario.get("label_selector", "")
-    timeout = managedcluster_scenario.get("timeout", 120)
+    run_kill_count = get_yaml_item_value(
+        managedcluster_scenario, "runs", 1
+    )
+    instance_kill_count = get_yaml_item_value(
+        managedcluster_scenario, "instance_count", 1
+    )
+    managedcluster_name = get_yaml_item_value(
+        managedcluster_scenario, "managedcluster_name", ""
+    )
+    label_selector = get_yaml_item_value(
+        managedcluster_scenario, "label_selector", ""
+    )
+    timeout = get_yaml_item_value(managedcluster_scenario, "timeout", 120)
     # Get the managedcluster to apply the scenario
     if managedcluster_name:
         managedcluster_name_list = managedcluster_name.split(",")

kraken/network_chaos/actions.py

@@ -7,13 +7,14 @@ import kraken.cerberus.setup as cerberus
 import kraken.node_actions.common_node_functions as common_node_functions
 from jinja2 import Environment, FileSystemLoader
 from krkn_lib.k8s import KrknKubernetes
-from krkn_lib.telemetry import KrknTelemetry
+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
 
 
 # krkn_lib
 # Reads the scenario config and introduces traffic variations in Node's host network interface.
-def run(scenarios_list, config, wait_duration, kubecli: KrknKubernetes, telemetry: KrknTelemetry) -> (list[str], list[ScenarioTelemetry]):
+def run(scenarios_list, config, wait_duration, kubecli: KrknKubernetes, telemetry: KrknTelemetryKubernetes) -> (list[str], list[ScenarioTelemetry]):
     failed_post_scenarios = ""
     logging.info("Runing the Network Chaos tests")
     failed_post_scenarios = ""
@@ -29,13 +30,26 @@ def run(scenarios_list, config, wait_duration, kubecli: KrknKubernetes, telemetr
                 param_lst = ["latency", "loss", "bandwidth"]
                 test_config = yaml.safe_load(file)
                 test_dict = test_config["network_chaos"]
-                test_duration = int(test_dict.get("duration", 300))
-                test_interface = test_dict.get("interfaces", [])
-                test_node = test_dict.get("node_name", "")
-                test_node_label = test_dict.get("label_selector", "node-role.kubernetes.io/master")
-                test_execution = test_dict.get("execution", "serial")
-                test_instance_count = test_dict.get("instance_count", 1)
-                test_egress = test_dict.get("egress", {"bandwidth": "100mbit"})
+                test_duration = int(
+                    get_yaml_item_value(test_dict, "duration", 300)
+                )
+                test_interface = get_yaml_item_value(
+                    test_dict, "interfaces", []
+                )
+                test_node = get_yaml_item_value(test_dict, "node_name", "")
+                test_node_label = get_yaml_item_value(
+                    test_dict, "label_selector",
+                    "node-role.kubernetes.io/master"
+                )
+                test_execution = get_yaml_item_value(
+                    test_dict, "execution", "serial"
+                )
+                test_instance_count = get_yaml_item_value(
+                    test_dict, "instance_count", 1
+                )
+                test_egress = get_yaml_item_value(
+                    test_dict, "egress", {"bandwidth": "100mbit"}
+                )
                 if test_node:
                     node_name_list = test_node.split(",")
                 else:
@@ -102,7 +116,7 @@ def run(scenarios_list, config, wait_duration, kubecli: KrknKubernetes, telemetr
         except (RuntimeError, Exception):
             scenario_telemetry.exitStatus = 1
             failed_scenarios.append(net_config)
-            telemetry.log_exception(net_config)
+            log_exception(net_config)
         else:
             scenario_telemetry.exitStatus = 0
         scenario_telemetries.append(scenario_telemetry)

kraken/node_actions/run.py

@@ -13,7 +13,9 @@ from kraken.node_actions.docker_node_scenarios import docker_node_scenarios
 import kraken.node_actions.common_node_functions as common_node_functions
 import kraken.cerberus.setup as cerberus
 from krkn_lib.k8s import KrknKubernetes
-from krkn_lib.telemetry import KrknTelemetry, ScenarioTelemetry
+from krkn_lib.telemetry.k8s import KrknTelemetryKubernetes
+from krkn_lib.models.telemetry import ScenarioTelemetry
+from krkn_lib.utils.functions import get_yaml_item_value
 
 node_general = False
 
@@ -53,7 +55,7 @@ def get_node_scenario_object(node_scenario, kubecli: KrknKubernetes):
 
 # Run defined scenarios
 # krkn_lib
-def run(scenarios_list, config, wait_duration, kubecli: KrknKubernetes, telemetry: KrknTelemetry) -> (list[str], list[ScenarioTelemetry]):
+def run(scenarios_list, config, wait_duration, kubecli: KrknKubernetes, telemetry: KrknTelemetryKubernetes) -> (list[str], list[ScenarioTelemetry]):
     scenario_telemetries: list[ScenarioTelemetry] = []
     failed_scenarios = []
     for node_scenario_config in scenarios_list:
@@ -78,7 +80,7 @@ def run(scenarios_list, config, wait_duration, kubecli: KrknKubernetes, telemetr
                         except (RuntimeError, Exception) as e:
                             scenario_telemetry.exitStatus = 1
                             failed_scenarios.append(node_scenario_config)
-                            telemetry.log_exception(node_scenario_config)
+                            log_exception(node_scenario_config)
                         else:
                             scenario_telemetry.exitStatus = 0
 
@@ -92,13 +94,17 @@ def run(scenarios_list, config, wait_duration, kubecli: KrknKubernetes, telemetr
 def inject_node_scenario(action, node_scenario, node_scenario_object, kubecli: KrknKubernetes):
     generic_cloud_scenarios = ("stop_kubelet_scenario", "node_crash_scenario")
     # Get the node scenario configurations
-    run_kill_count = node_scenario.get("runs", 1)
-    instance_kill_count = node_scenario.get("instance_count", 1)
-    node_name = node_scenario.get("node_name", "")
-    label_selector = node_scenario.get("label_selector", "")
-    timeout = node_scenario.get("timeout", 120)
-    service = node_scenario.get("service", "")
-    ssh_private_key = node_scenario.get("ssh_private_key", "~/.ssh/id_rsa")
+    run_kill_count = get_yaml_item_value(node_scenario, "runs", 1)
+    instance_kill_count = get_yaml_item_value(
+        node_scenario, "instance_count", 1
+    )
+    node_name = get_yaml_item_value(node_scenario, "node_name", "")
+    label_selector = get_yaml_item_value(node_scenario, "label_selector", "")
+    timeout = get_yaml_item_value(node_scenario, "timeout", 120)
+    service = get_yaml_item_value(node_scenario, "service", "")
+    ssh_private_key = get_yaml_item_value(
+        node_scenario, "ssh_private_key", "~/.ssh/id_rsa"
+    )
     # Get the node to apply the scenario
     if node_name:
         node_name_list = node_name.split(",")

kraken/plugins/__init__.py

@@ -13,9 +13,10 @@ from kraken.plugins.run_python_plugin import run_python_file
 from kraken.plugins.network.ingress_shaping import network_chaos
 from kraken.plugins.pod_network_outage.pod_network_outage_plugin import pod_outage
 from kraken.plugins.pod_network_outage.pod_network_outage_plugin import pod_egress_shaping
-from krkn_lib.telemetry import KrknTelemetry
+from krkn_lib.telemetry.k8s import KrknTelemetryKubernetes
+from kraken.plugins.pod_network_outage.pod_network_outage_plugin import pod_ingress_shaping
 from krkn_lib.models.telemetry import ScenarioTelemetry
-
+from krkn_lib.utils.functions import log_exception
 
 
 @dataclasses.dataclass
@@ -223,25 +224,31 @@ PLUGINS = Plugins(
             [
                 "error"
             ]
-        )       
+        ),
+         PluginStep(
+            pod_ingress_shaping,
+            [
+                "error"
+            ]
+        )                  
     ]
 )
 
 
-def run(scenarios: List[str], kubeconfig_path: str, kraken_config: str, failed_post_scenarios: List[str], wait_duration: int, telemetry: KrknTelemetry) -> (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) -> (List[str], list[ScenarioTelemetry]):
     scenario_telemetries: list[ScenarioTelemetry] = []
     for scenario in scenarios:
         scenario_telemetry = ScenarioTelemetry()
         scenario_telemetry.scenario = scenario
         scenario_telemetry.startTimeStamp = time.time()
         telemetry.set_parameters_base64(scenario_telemetry, scenario)
-        logging.info('scenario '+ str(scenario))
+        logging.info('scenario ' + str(scenario))
         try:
             PLUGINS.run(scenario, kubeconfig_path, kraken_config)
         except Exception as e:
             scenario_telemetry.exitStatus = 1
             failed_post_scenarios.append(scenario)
-            telemetry.log_exception(scenario)
+            log_exception(scenario)
         else:
             scenario_telemetry.exitStatus = 0
             logging.info("Waiting for the specified duration: %s" % (wait_duration))

kraken/plugins/pod_network_outage/pod_network_outage_plugin.py

@@ -269,6 +269,85 @@ def apply_outage_policy(
     return job_list
 
 
+def apply_ingress_policy(
+    mod: str,
+    node: str,
+    ips: typing.List[str],
+    job_template,
+    pod_template,
+    network_params: typing.Dict[str, str],
+    duration: str,
+    bridge_name: str,
+    kubecli: KrknKubernetes,
+    test_execution: str,
+) -> typing.List[str]:
+    """
+    Function that applies ingress traffic shaping to pod interface.
+
+    Args:
+
+        mod (String)
+            - Traffic shaping filter to apply
+
+        node (String)
+            - node associated with the pod
+
+        ips (List)
+            - IPs of pods found in the node
+
+        job_template (jinja2.environment.Template)
+            - The YAML template used to instantiate a job to apply and remove
+              the filters on the interfaces
+
+        pod_template (jinja2.environment.Template)
+            - The YAML template used to instantiate a pod to query
+              the node's interface
+
+        network_params (Dictionary with key and value as string)
+            - Loss/Delay/Bandwidth and their corresponding value
+
+        duration (string)
+            - Duration for which the traffic control is to be done
+
+        bridge_name (string):
+            - bridge to which  filter rules need to be applied
+
+        kubecli (KrknKubernetes)
+            - Object to interact with Kubernetes Python client
+
+        test_execution (String)
+            - The order in which the filters are applied
+
+    Returns:
+        The name of the job created that executes the traffic shaping
+        filter
+    """
+
+    job_list = []
+
+    create_virtual_interfaces(kubecli, len(ips), node, pod_template)
+
+    for count, pod_ip in enumerate(set(ips)):
+        pod_inf = get_pod_interface(
+            node, pod_ip, pod_template, bridge_name, kubecli)
+        exec_cmd = get_ingress_cmd(
+            test_execution, pod_inf, mod, count, network_params, duration
+        )
+        logging.info("Executing %s on pod %s in node %s" %
+                     (exec_cmd, pod_ip, node))
+        job_body = yaml.safe_load(
+            job_template.render(jobname=mod + str(pod_ip),
+                                nodename=node, cmd=exec_cmd)
+        )
+        job_list.append(job_body["metadata"]["name"])
+        api_response = kubecli.create_job(job_body)
+        if api_response is None:
+            raise Exception("Error creating job")
+        if pod_ip == node:
+            break
+    return job_list
+
+
 def apply_net_policy(
     mod: str,
     node: str,
@@ -325,7 +404,7 @@ def apply_net_policy(
 
     job_list = []
 
-    for pod_ip in ips:
+    for pod_ip in set(ips):
         pod_inf = get_pod_interface(
             node, pod_ip, pod_template, bridge_name, kubecli)
         exec_cmd = get_egress_cmd(
@@ -344,6 +423,64 @@ def apply_net_policy(
     return job_list
 
 
+def get_ingress_cmd(
+    execution: str,
+    test_interface: str,
+    mod: str,
+    count: int,
+    vallst: typing.List[str],
+    duration: str,
+) -> str:
+    """
+    Function generates ingress filter to apply on pod
+
+    Args:
+        execution (str):
+            - The order in which the filters are applied
+
+        test_interface (str):
+            - Pod interface
+
+        mod (str):
+            - Filter to apply
+
+        count (int):
+            - IFB device number
+
+        vallst (typing.List[str]):
+            - List of filters to apply
+
+        duration (str):
+            - Duration for which the traffic control is to be done
+
+    Returns:
+        str: ingress filter
+    """
+    ifb_dev = 'ifb{0}'.format(count)
+    tc_set = tc_unset = tc_ls = ""
+    param_map = {"latency": "delay", "loss": "loss", "bandwidth": "rate"}
+    tc_set = "tc qdisc add dev {0} ingress ;".format(test_interface)
+    tc_set = "{0} tc filter add dev {1} ingress matchall action mirred egress redirect dev {2} ;".format(
+        tc_set, test_interface, ifb_dev)
+    tc_set = "{0} tc qdisc replace dev {1} root netem".format(
+        tc_set, ifb_dev)
+    tc_unset = "{0} tc qdisc del dev {1} root ;".format(
+        tc_unset, ifb_dev)
+    tc_unset = "{0} tc qdisc del dev {1} ingress".format(
+        tc_unset, test_interface)
+    tc_ls = "{0} tc qdisc ls dev {1} ;".format(tc_ls, ifb_dev)
+    if execution == "parallel":
+        for val in vallst.keys():
+            tc_set += " {0} {1} ".format(param_map[val], vallst[val])
+        tc_set += ";"
+    else:
+        tc_set += " {0} {1} ;".format(param_map[mod], vallst[mod])
+    exec_cmd = "{0} {1} sleep {2};{3}".format(
+        tc_set, tc_ls, duration, tc_unset)
+
+    return exec_cmd
+
+
 def get_egress_cmd(
     execution: str,
     test_interface: str,
@@ -392,6 +529,124 @@ def get_egress_cmd(
     return exec_cmd
 
 
+def create_virtual_interfaces(
+    kubecli: KrknKubernetes,
+    nummber: int,
+    node: str,
+    pod_template
+) -> None:
+    """
+    Function that creates a privileged pod and uses it to create
+    virtual interfaces on the node
+
+    Args:
+        cli (CoreV1Api)
+            - Object to interact with Kubernetes Python client's CoreV1 API
+
+        interface_list (List of strings)
+            - The list of interfaces on the node for which virtual interfaces
+              are to be created
+
+        node (string)
+            - The node on which the virtual interfaces are created
+
+        pod_template (jinja2.environment.Template))
+            - The YAML template used to instantiate a pod to create
+              virtual interfaces on the node
+    """
+    pod_body = yaml.safe_load(
+        pod_template.render(nodename=node)
+    )
+    kubecli.create_pod(pod_body, "default", 300)
+    logging.info(
+        "Creating {0} virtual interfaces on node {1} using a pod".format(
+            nummber,
+            node
+        )
+    )
+    create_ifb(kubecli, nummber, 'modtools')
+    logging.info("Deleting pod used to create virtual interfaces")
+    kubecli.delete_pod("modtools", "default")
+
+
+def delete_virtual_interfaces(
+    kubecli: KrknKubernetes,
+    node_list: typing.List[str],
+    pod_template
+):
+    """
+    Function that creates a privileged pod and uses it to delete all
+    virtual interfaces on the specified nodes
+
+    Args:
+        cli (CoreV1Api)
+            - Object to interact with Kubernetes Python client's CoreV1 API
+
+        node_list (List of strings)
+            - The list of nodes on which the list of virtual interfaces are
+              to be deleted
+
+        node (string)
+            - The node on which the virtual interfaces are created
+
+        pod_template (jinja2.environment.Template))
+            - The YAML template used to instantiate a pod to delete
+              virtual interfaces on the node
+    """
+
+    for node in node_list:
+        pod_body = yaml.safe_load(
+            pod_template.render(nodename=node)
+        )
+        kubecli.create_pod(pod_body, "default", 300)
+        logging.info(
+            "Deleting all virtual interfaces on node {0}".format(node)
+        )
+        delete_ifb(kubecli, 'modtools')
+        kubecli.delete_pod("modtools", "default")
+
+
+def create_ifb(kubecli: KrknKubernetes, number: int, pod_name: str):
+    """
+    Function that creates virtual interfaces in a pod.
+    Makes use of modprobe commands
+    """
+
+    exec_command = [
+        '/host',
+        'modprobe', 'ifb', 'numifbs=' + str(number)
+    ]
+    kubecli.exec_cmd_in_pod(
+        exec_command,
+        pod_name,
+        'default',
+        base_command="chroot")
+
+    for i in range(0, number):
+        exec_command = ['/host', 'ip', 'link', 'set', 'dev']
+        exec_command += ['ifb' + str(i), 'up']
+        kubecli.exec_cmd_in_pod(
+            exec_command,
+            pod_name,
+            'default',
+            base_command="chroot"
+        )
+
+
+def delete_ifb(kubecli: KrknKubernetes, pod_name: str):
+    """
+    Function that deletes all virtual interfaces in a pod.
+    Makes use of modprobe command
+    """
+
+    exec_command = ['/host', 'modprobe', '-r', 'ifb']
+    kubecli.exec_cmd_in_pod(
+        exec_command,
+        pod_name,
+        'default',
+        base_command="chroot")
+
+
 def list_bridges(
     node: str, pod_template, kubecli: KrknKubernetes
 ) -> typing.List[str]:
@@ -424,7 +679,7 @@ def list_bridges(
         )
 
         if not output:
-            logging.error("Exception occurred while executing command in pod")
+            logging.error(f"Exception occurred while executing command {cmd} in pod")
             sys.exit(1)
 
         bridges = output.split("\n")
@@ -483,7 +738,7 @@ def check_cookie(
         )
 
         if not output:
-            logging.error("Exception occurred while executing command in pod")
+            logging.error(f"Exception occurred while executing command {cmd} in pod")
             sys.exit(1)
 
         flow_list = output.split("\n")
@@ -525,50 +780,41 @@ def get_pod_interface(
     pod_body = yaml.safe_load(pod_template.render(nodename=node))
     logging.info("Creating pod to query pod interface on node %s" % node)
     kubecli.create_pod(pod_body, "default", 300)
+    inf = ""
 
     try:
+        if br_name == "br-int":
+            find_ip = f"external-ids:ip_addresses={ip}/23"
+        else:
+            find_ip = f"external-ids:ip={ip}"
+                       
         cmd = [
             "/host",
-            "ovs-ofctl",
-            "-O",
-            "OpenFlow13",
-            "dump-flows",
-            br_name,
-            f"ip,nw_src={ip}",
+            "ovs-vsctl",
+            "--bare",
+            "--columns=name",
+            "find",
+            "interface",
+            find_ip,
         ]
+      
         output = kubecli.exec_cmd_in_pod(
             cmd, "modtools", "default", base_command="chroot"
         )
         if not output:
-            logging.error("Exception occurred while executing command in pod")
-            sys.exit(1)
-
-        flow_lists = output.split("\n")
-        port = ""
-        inf = ""
-        for flow in flow_lists:
-            match = re.search(r".*in_port=(.*),nw_src=.*", flow)
-            if match is not None:
-                port = match.group(1)
-                exit
-        if not re.findall("\\D", port):
-            cmd = ["/host", "ovs-ofctl", "-O",
-                   "OpenFlow13", "dump-ports-desc", br_name]
+            cmd= [
+                "/host",
+                "ip",
+                "addr",
+                "show"
+            ]
             output = kubecli.exec_cmd_in_pod(
-                cmd, "modtools", "default", base_command="chroot"
-            )
-            if not output:
-                logging.error(
-                    "Exception occurred while executing command in pod")
-                sys.exit(1)
-            ports_desc = output.split("\n")
-            for desc in ports_desc:
-                match = re.search(rf".*{port}\((.*)\):.*", desc)
-                if match is not None:
-                    inf = match.group(1)
-                    exit
+                cmd, "modtools", "default", base_command="chroot")
+            for if_str in output.split("\n"):
+                if re.search(ip,if_str):
+                    inf = if_str.split(' ')[-1]
         else:
-            inf = port
+            inf = output       
     finally:
         logging.info("Deleting pod to query interface on node")
         kubecli.delete_pod("modtools", "default")
@@ -1098,7 +1344,7 @@ def pod_egress_shaping(
 
         for mod in mod_lst:
             for node, ips in node_dict.items():
-                job_list = apply_net_policy(
+                job_list.extend( apply_net_policy(
                     mod,
                     node,
                     ips,
@@ -1109,20 +1355,20 @@ def pod_egress_shaping(
                     br_name,
                     kubecli,
                     params.execution_type,
-                )
-                if params.execution_type == "serial":
-                    logging.info("Waiting for serial job to finish")
-                    start_time = int(time.time())
-                    wait_for_job(job_list[:], kubecli,
-                                 params.test_duration + 20)
-                    logging.info("Waiting for wait_duration %s" %
-                                 params.test_duration)
-                    time.sleep(params.test_duration)
-                    end_time = int(time.time())
-                    if publish:
-                        cerberus.publish_kraken_status(
-                            config, failed_post_scenarios, start_time, end_time
-                        )
+                ))
+            if params.execution_type == "serial":
+                logging.info("Waiting for serial job to finish")
+                start_time = int(time.time())
+                wait_for_job(job_list[:], kubecli,
+                                params.test_duration + 20)
+                logging.info("Waiting for wait_duration %s" %
+                                params.test_duration)
+                time.sleep(params.test_duration)
+                end_time = int(time.time())
+                if publish:
+                    cerberus.publish_kraken_status(
+                        config, failed_post_scenarios, start_time, end_time
+                    )
             if params.execution_type == "parallel":
                 break
         if params.execution_type == "parallel":
@@ -1149,3 +1395,281 @@ def pod_egress_shaping(
     finally:
         logging.info("Deleting jobs(if any)")
         delete_jobs(kubecli, job_list[:])
+
+
+@dataclass
+class IngressParams:
+    """
+    This is the data structure for the input parameters of the step defined below.
+    """
+
+    namespace: typing.Annotated[str, validation.min(1)] = field(
+        metadata={
+            "name": "Namespace",
+            "description": "Namespace of the pod to which filter need to be applied"
+            "for details.",
+        }
+    )
+
+    network_params: typing.Dict[str, str] = field(
+        metadata={
+            "name": "Network Parameters",
+            "description": "The network filters that are applied on the interface. "
+            "The currently supported filters are latency, "
+            "loss and bandwidth",
+        },
+    )
+
+    kubeconfig_path: typing.Optional[str] = field(
+        default=None,
+        metadata={
+            "name": "Kubeconfig path",
+            "description": "Kubeconfig file as string\n"
+            "See https://kubernetes.io/docs/concepts/configuration/organize-cluster-access-kubeconfig/ for "
+            "details.",
+        },
+    )
+    pod_name: typing.Annotated[
+        typing.Optional[str],
+        validation.required_if_not("label_selector"),
+    ] = field(
+        default=None,
+        metadata={
+            "name": "Pod name",
+            "description": "When label_selector is not specified, pod matching the name will be"
+            "selected for the chaos scenario",
+        },
+    )
+
+    label_selector: typing.Annotated[
+        typing.Optional[str], validation.required_if_not("pod_name")
+    ] = field(
+        default=None,
+        metadata={
+            "name": "Label selector",
+            "description": "Kubernetes label selector for the target pod. "
+            "When pod_name is not specified, pod with matching label_selector is selected for chaos scenario",
+        },
+    )
+
+    kraken_config: typing.Optional[str] = field(
+        default=None,
+        metadata={
+            "name": "Kraken Config",
+            "description": "Path to the config file of Kraken. "
+            "Set this field if you wish to publish status onto Cerberus",
+        },
+    )
+
+    test_duration: typing.Annotated[typing.Optional[int], validation.min(1)] = field(
+        default=90,
+        metadata={
+            "name": "Test duration",
+            "description": "Duration for which each step of the ingress chaos testing "
+            "is to be performed.",
+        },
+    )
+
+    wait_duration: typing.Annotated[typing.Optional[int], validation.min(1)] = field(
+        default=300,
+        metadata={
+            "name": "Wait Duration",
+            "description": "Wait duration for finishing a test and its cleanup."
+            "Ensure that it is significantly greater than wait_duration",
+        },
+    )
+
+    instance_count: typing.Annotated[typing.Optional[int], validation.min(1)] = field(
+        default=1,
+        metadata={
+            "name": "Instance Count",
+            "description": "Number of pods to perform action/select that match "
+            "the label selector.",
+        },
+    )
+
+    execution_type: typing.Optional[str] = field(
+        default="parallel",
+        metadata={
+            "name": "Execution Type",
+            "description": "The order in which the ingress filters are applied. "
+            "Execution type can be 'serial' or 'parallel'",
+        },
+    )
+
+
+@dataclass
+class PodIngressNetShapingSuccessOutput:
+    """
+    This is the output data structure for the success case.
+    """
+
+    test_pods: typing.List[str] = field(
+        metadata={
+            "name": "Test pods",
+            "description": "List of test pods where the selected for chaos scenario",
+        }
+    )
+
+    network_parameters: typing.Dict[str, str] = field(
+        metadata={
+            "name": "Network Parameters",
+            "description": "The network filters that are applied on the interfaces",
+        }
+    )
+
+    execution_type: str = field(
+        metadata={
+            "name": "Execution Type",
+            "description": "The order in which the filters are applied",
+        }
+    )
+
+
+@dataclass
+class PodIngressNetShapingErrorOutput:
+    error: str = field(
+        metadata={
+            "name": "Error",
+            "description": "Error message when there is a run-time error during "
+            "the execution of the scenario",
+        }
+    )
+
+
+@plugin.step(
+    id="pod_ingress_shaping",
+    name="Pod ingress network Shaping",
+    description="Does ingress network traffic shaping at pod level",
+    outputs={
+        "success": PodIngressNetShapingSuccessOutput,
+        "error": PodIngressNetShapingErrorOutput,
+    },
+)
+def pod_ingress_shaping(
+    params: IngressParams,
+) -> typing.Tuple[
+    str, typing.Union[PodIngressNetShapingSuccessOutput,
+                      PodIngressNetShapingErrorOutput]
+]:
+    """
+    Function that performs ingress pod traffic shaping based
+    on the provided configuration
+
+    Args:
+        params (IngressParams,)
+            - The object containing the configuration for the scenario
+
+    Returns
+        A 'success' or 'error' message along with their details
+    """
+
+    file_loader = FileSystemLoader(os.path.abspath(os.path.dirname(__file__)))
+    env = Environment(loader=file_loader)
+    job_template = env.get_template("job.j2")
+    pod_module_template = env.get_template("pod_module.j2")
+    test_namespace = params.namespace
+    test_label_selector = params.label_selector
+    test_pod_name = params.pod_name
+    job_list = []
+    publish = False
+
+    if params.kraken_config:
+        failed_post_scenarios = ""
+        try:
+            with open(params.kraken_config, "r") as f:
+                config = yaml.full_load(f)
+        except Exception:
+            logging.error("Error reading Kraken config from %s" %
+                          params.kraken_config)
+            return "error", PodIngressNetShapingErrorOutput(format_exc())
+        publish = True
+
+    try:
+        ip_set = set()
+        node_dict = {}
+        label_set = set()
+        param_lst = ["latency", "loss", "bandwidth"]
+        mod_lst = [i for i in param_lst if i in params.network_params]
+
+        kubecli = KrknKubernetes(kubeconfig_path=params.kubeconfig_path)
+        api_ext = client.ApiextensionsV1Api(kubecli.api_client)
+        custom_obj = client.CustomObjectsApi(kubecli.api_client)
+
+        br_name = get_bridge_name(api_ext, custom_obj)
+        pods_list = get_test_pods(
+            test_pod_name, test_label_selector, test_namespace, kubecli
+        )
+
+        while not len(pods_list) <= params.instance_count:
+            pods_list.pop(random.randint(0, len(pods_list) - 1))
+        for pod_name in pods_list:
+            pod_stat = kubecli.read_pod(pod_name, test_namespace)
+            ip_set.add(pod_stat.status.pod_ip)
+            node_dict.setdefault(pod_stat.spec.node_name, [])
+            node_dict[pod_stat.spec.node_name].append(pod_stat.status.pod_ip)
+            for key, value in pod_stat.metadata.labels.items():
+                label_set.add("%s=%s" % (key, value))
+
+        check_bridge_interface(
+            list(node_dict.keys())[0], pod_module_template, br_name, kubecli
+        )
+
+        for mod in mod_lst:
+            for node, ips in node_dict.items():
+                job_list.extend(apply_ingress_policy(
+                    mod,
+                    node,
+                    ips,
+                    job_template,
+                    pod_module_template,
+                    params.network_params,
+                    params.test_duration,
+                    br_name,
+                    kubecli,
+                    params.execution_type,
+                ))
+            if params.execution_type == "serial":
+                logging.info("Waiting for serial job to finish")
+                start_time = int(time.time())
+                wait_for_job(job_list[:], kubecli,
+                             params.test_duration + 20)
+                logging.info("Waiting for wait_duration %s" %
+                             params.test_duration)
+                time.sleep(params.test_duration)
+                end_time = int(time.time())
+                if publish:
+                    cerberus.publish_kraken_status(
+                        config, failed_post_scenarios, start_time, end_time
+                    )
+            if params.execution_type == "parallel":
+                break
+        if params.execution_type == "parallel":
+            logging.info("Waiting for parallel job to finish")
+            start_time = int(time.time())
+            wait_for_job(job_list[:], kubecli, params.test_duration + 300)
+            logging.info("Waiting for wait_duration %s" % params.test_duration)
+            time.sleep(params.test_duration)
+            end_time = int(time.time())
+            if publish:
+                cerberus.publish_kraken_status(
+                    config, failed_post_scenarios, start_time, end_time
+                )
+
+        return "success", PodIngressNetShapingSuccessOutput(
+            test_pods=pods_list,
+            network_parameters=params.network_params,
+            execution_type=params.execution_type,
+        )
+    except Exception as e:
+        logging.error(
+            "Pod network Shaping scenario exiting due to Exception - %s" % e)
+        return "error", PodIngressNetShapingErrorOutput(format_exc())
+    finally:
+        delete_virtual_interfaces(
+            kubecli,
+            node_dict.keys(),
+            pod_module_template
+        )
+        logging.info("Deleting jobs(if any)")
+        delete_jobs(kubecli, job_list[:])

kraken/pod_scenarios/setup.py

@@ -7,9 +7,11 @@ import arcaflow_plugin_kill_pod
 import kraken.cerberus.setup as cerberus
 import kraken.post_actions.actions as post_actions
 from krkn_lib.k8s import KrknKubernetes
-from krkn_lib.telemetry import KrknTelemetry
+from krkn_lib.telemetry.k8s import KrknTelemetryKubernetes
 from krkn_lib.models.telemetry import ScenarioTelemetry
 from arcaflow_plugin_sdk import serialization
+from krkn_lib.utils.functions import get_yaml_item_value, log_exception
+
 
 # Run pod based scenarios
 def run(kubeconfig_path, scenarios_list, config, failed_post_scenarios, wait_duration):
@@ -65,6 +67,7 @@ def run(kubeconfig_path, scenarios_list, config, failed_post_scenarios, wait_dur
         cerberus.publish_kraken_status(config, failed_post_scenarios, start_time, end_time)
     return failed_post_scenarios
 
+
 # krkn_lib
 def container_run(kubeconfig_path,
                   scenarios_list,
@@ -72,7 +75,7 @@ def container_run(kubeconfig_path,
                   failed_post_scenarios,
                   wait_duration,
                   kubecli: KrknKubernetes,
-                  telemetry: KrknTelemetry) -> (list[str], list[ScenarioTelemetry]):
+                  telemetry: KrknTelemetryKubernetes) -> (list[str], list[ScenarioTelemetry]):
 
     failed_scenarios = []
     scenario_telemetries: list[ScenarioTelemetry] = []
@@ -115,7 +118,7 @@ def container_run(kubeconfig_path,
                     cerberus.publish_kraken_status(config, failed_post_scenarios, start_time, end_time)
                 except (RuntimeError, Exception):
                     failed_scenarios.append(container_scenario_config[0])
-                    telemetry.log_exception(container_scenario_config[0])
+                    log_exception(container_scenario_config[0])
                     scenario_telemetry.exitStatus = 1
                     # removed_exit
                     # sys.exit(1)
@@ -127,15 +130,22 @@ def container_run(kubeconfig_path,
     return failed_scenarios, scenario_telemetries
 
 
-
 def container_killing_in_pod(cont_scenario, kubecli: KrknKubernetes):
-    scenario_name = cont_scenario.get("name", "")
-    namespace = cont_scenario.get("namespace", "*")
-    label_selector = cont_scenario.get("label_selector", None)
-    pod_names = cont_scenario.get("pod_names", [])
-    container_name = cont_scenario.get("container_name", "")
-    kill_action = cont_scenario.get("action", "kill 1")
-    kill_count = cont_scenario.get("count", 1)
+    scenario_name = get_yaml_item_value(cont_scenario, "name", "")
+    namespace = get_yaml_item_value(cont_scenario, "namespace", "*")
+    label_selector = get_yaml_item_value(cont_scenario, "label_selector", None)
+    pod_names = get_yaml_item_value(cont_scenario, "pod_names", [])
+    container_name = get_yaml_item_value(cont_scenario, "container_name", "")
+    kill_action = get_yaml_item_value(cont_scenario, "action", 1)
+    kill_count = get_yaml_item_value(cont_scenario, "count", 1)
+    if not isinstance(kill_action, int):
+        logging.error("Please make sure the action parameter defined in the "
+                      "config is an integer")
+        raise RuntimeError()
+    if (kill_action < 1) or (kill_action > 15):
+        logging.error("Only 1-15 kill signals are supported.")
+        raise RuntimeError()
+    kill_action = "kill " + str(kill_action)
     if type(pod_names) != list:
         logging.error("Please make sure your pod_names are in a list format")
         # removed_exit

kraken/prometheus/__init__.py

@@ -0,0 +1 @@
+from .client import *

kraken/prometheus/client.py

@@ -1,49 +1,30 @@
+import datetime
+import os.path
 import urllib3
 import logging
-import prometheus_api_client
 import sys
-import kraken.invoke.command as runcommand
 
+import yaml
+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):
 
-# Initialize the client
-def initialize_prom_client(distribution, prometheus_url, prometheus_bearer_token):
-    global prom_cli
-    prometheus_url, prometheus_bearer_token = instance(distribution, prometheus_url, prometheus_bearer_token)
-    if prometheus_url and prometheus_bearer_token:
-        bearer = "Bearer " + prometheus_bearer_token
-        headers = {"Authorization": bearer}
-        try:
-            prom_cli = prometheus_api_client.PrometheusConnect(url=prometheus_url, headers=headers, disable_ssl=True)
-        except Exception as e:
-            logging.error("Not able to initialize the client %s" % e)
+    if alert_profile is None or os.path.exists(alert_profile) is False:
+        logging.error(f"{alert_profile} alert profile does not exist")
+        sys.exit(1)
+
+    with open(alert_profile) as profile:
+        profile_yaml = yaml.safe_load(profile)
+        if not isinstance(profile_yaml, list):
+            logging.error(f"{alert_profile} wrong file format, alert profile must be "
+                          f"a valid yaml file containing a list of items with 3 properties: "
+                          f"expr, description, severity" )
             sys.exit(1)
-    else:
-        prom_cli = None
 
+        for alert in profile_yaml:
+            if list(alert.keys()).sort() != ["expr", "description", "severity"].sort():
+                logging.error(f"wrong alert {alert}, skipping")
 
-# Process custom prometheus query
-def process_prom_query(query):
-    if prom_cli:
-        try:
-            return prom_cli.custom_query(query=query, params=None)
-        except Exception as e:
-            logging.error("Failed to get the metrics: %s" % e)
-            sys.exit(1)
-    else:
-        logging.info("Skipping the prometheus query as the prometheus client couldn't " "be initialized\n")
-
-# Get prometheus details
-def instance(distribution, prometheus_url, prometheus_bearer_token):
-    if distribution == "openshift" and not prometheus_url:
-        url = runcommand.invoke(
-            r"""oc get routes -n openshift-monitoring -o=jsonpath='{.items[?(@.metadata.name=="prometheus-k8s")].spec.host}'"""  # noqa
-        )
-        prometheus_url = "https://" + url
-    if distribution == "openshift" and not prometheus_bearer_token:
-        prometheus_bearer_token = runcommand.invoke(
-            "oc create token -n openshift-monitoring prometheus-k8s  --duration=12h "
-            "|| oc -n openshift-monitoring sa get-token prometheus-k8s "
-            "|| oc sa new-token -n openshift-monitoring prometheus-k8s"
-        )
-    return prometheus_url, prometheus_bearer_token
+            prom_cli.process_alert(alert,
+                                   datetime.datetime.fromtimestamp(start_time),
+                                   datetime.datetime.fromtimestamp(end_time))

kraken/pvc/pvc_scenario.py

@@ -5,12 +5,13 @@ import time
 import yaml
 from ..cerberus import setup as cerberus
 from krkn_lib.k8s import KrknKubernetes
-from krkn_lib.telemetry import KrknTelemetry
+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
 
 
 # krkn_lib
-def run(scenarios_list, config, kubecli: KrknKubernetes, telemetry: KrknTelemetry) -> (list[str], list[ScenarioTelemetry]):
+def run(scenarios_list, config, kubecli: KrknKubernetes, telemetry: KrknTelemetryKubernetes) -> (list[str], list[ScenarioTelemetry]):
     """
     Reads the scenario config and creates a temp file to fill up the PVC
     """
@@ -27,13 +28,21 @@ def run(scenarios_list, config, kubecli: KrknKubernetes, telemetry: KrknTelemetr
                 with open(app_config, "r") as f:
                     config_yaml = yaml.full_load(f)
                     scenario_config = config_yaml["pvc_scenario"]
-                    pvc_name = scenario_config.get("pvc_name", "")
-                    pod_name = scenario_config.get("pod_name", "")
-                    namespace = scenario_config.get("namespace", "")
-                    target_fill_percentage = scenario_config.get(
-                        "fill_percentage", "50"
+                    pvc_name = get_yaml_item_value(
+                        scenario_config, "pvc_name", ""
+                    )
+                    pod_name = get_yaml_item_value(
+                        scenario_config, "pod_name", ""
+                    )
+                    namespace = get_yaml_item_value(
+                        scenario_config, "namespace", ""
+                    )
+                    target_fill_percentage = get_yaml_item_value(
+                        scenario_config, "fill_percentage", "50"
+                    )
+                    duration = get_yaml_item_value(
+                        scenario_config, "duration", 60
                     )
-                    duration = scenario_config.get("duration", 60)
 
                     logging.info(
                         "Input params:\n"
@@ -307,7 +316,7 @@ def run(scenarios_list, config, kubecli: KrknKubernetes, telemetry: KrknTelemetr
         except (RuntimeError, Exception):
             scenario_telemetry.exitStatus = 1
             failed_scenarios.append(app_config)
-            telemetry.log_exception(app_config)
+            log_exception(app_config)
         else:
             scenario_telemetry.exitStatus = 0
         scenario_telemetries.append(scenario_telemetry)

kraken/service_disruption/common_service_disruption_functions.py

@@ -5,12 +5,13 @@ import kraken.cerberus.setup as cerberus
 import kraken.post_actions.actions as post_actions
 import yaml
 from krkn_lib.k8s import KrknKubernetes
-from krkn_lib.telemetry import KrknTelemetry
+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
 
 
-def delete_objects(kubecli, namespace): 
-    
+def delete_objects(kubecli, namespace):
+
     services = delete_all_services_namespace(kubecli, namespace)
     daemonsets = delete_all_daemonset_namespace(kubecli, namespace)
     statefulsets = delete_all_statefulsets_namespace(kubecli, namespace)
@@ -20,12 +21,13 @@ def delete_objects(kubecli, namespace):
     objects = { "daemonsets": daemonsets,
                 "deployments": deployments,
                 "replicasets": replicasets,
-                "statefulsets": statefulsets, 
+                "statefulsets": statefulsets,
                 "services": services
                 }
 
     return objects
 
+
 def get_list_running_pods(kubecli: KrknKubernetes, namespace: str):
     running_pods = []
     pods = kubecli.list_pods(namespace)
@@ -36,6 +38,7 @@ def get_list_running_pods(kubecli: KrknKubernetes, namespace: str):
     logging.info('all running pods ' + str(running_pods))
     return running_pods
 
+
 def delete_all_deployment_namespace(kubecli: KrknKubernetes, namespace: str):
     """
     Delete all the deployments in the specified namespace
@@ -43,20 +46,21 @@ def delete_all_deployment_namespace(kubecli: KrknKubernetes, namespace: str):
     :param kubecli: krkn kubernetes python package
     :param namespace: namespace
     """
-    try: 
+    try:
         deployments = kubecli.get_deployment_ns(namespace)
         for deployment in deployments:
             logging.info("Deleting deployment" + deployment)
-            kubecli.delete_deployment(deployment,namespace)
+            kubecli.delete_deployment(deployment, namespace)
     except Exception as e:
         logging.error(
             "Exception when calling delete_all_deployment_namespace: %s\n",
             str(e),
         )
         raise e
-    
+
     return deployments
 
+
 def delete_all_daemonset_namespace(kubecli: KrknKubernetes, namespace: str):
     """
     Delete all the daemonset in the specified namespace
@@ -64,42 +68,44 @@ def delete_all_daemonset_namespace(kubecli: KrknKubernetes, namespace: str):
     :param kubecli: krkn kubernetes python package
     :param namespace: namespace
     """
-    try: 
+    try:
         daemonsets = kubecli.get_daemonset(namespace)
         for daemonset in daemonsets:
             logging.info("Deleting daemonset" + daemonset)
-            kubecli.delete_daemonset(daemonset,namespace)
+            kubecli.delete_daemonset(daemonset, namespace)
     except Exception as e:
         logging.error(
             "Exception when calling delete_all_daemonset_namespace: %s\n",
             str(e),
         )
         raise e
-    
+
     return daemonsets
 
+
 def delete_all_statefulsets_namespace(kubecli: KrknKubernetes, namespace: str):
     """
     Delete all the statefulsets in the specified namespace
 
-    
+
     :param kubecli: krkn kubernetes python package
     :param namespace: namespace
     """
-    try: 
+    try:
         statefulsets = kubecli.get_all_statefulset(namespace)
         for statefulset in statefulsets:
             logging.info("Deleting statefulsets" + statefulsets)
-            kubecli.delete_statefulset(statefulset,namespace)
+            kubecli.delete_statefulset(statefulset, namespace)
     except Exception as e:
         logging.error(
             "Exception when calling delete_all_statefulsets_namespace: %s\n",
             str(e),
         )
         raise e
-    
+
     return statefulsets
 
+
 def delete_all_replicaset_namespace(kubecli: KrknKubernetes, namespace: str):
     """
     Delete all the replicasets in the specified namespace
@@ -107,42 +113,43 @@ def delete_all_replicaset_namespace(kubecli: KrknKubernetes, namespace: str):
     :param kubecli: krkn kubernetes python package
     :param namespace: namespace
     """
-    try: 
+    try:
         replicasets = kubecli.get_all_replicasets(namespace)
         for replicaset in replicasets:
             logging.info("Deleting replicaset" + replicaset)
-            kubecli.delete_replicaset(replicaset,namespace)
+            kubecli.delete_replicaset(replicaset, namespace)
     except Exception as e:
         logging.error(
             "Exception when calling delete_all_replicaset_namespace: %s\n",
             str(e),
         )
         raise e
-    
+
     return replicasets
 
 def delete_all_services_namespace(kubecli: KrknKubernetes, namespace: str):
     """
     Delete all the services in the specified namespace
 
-    
+
     :param kubecli: krkn kubernetes python package
     :param namespace: namespace
     """
-    try: 
+    try:
         services = kubecli.get_all_services(namespace)
         for service in services:
             logging.info("Deleting services" + service)
-            kubecli.delete_services(service,namespace)
+            kubecli.delete_services(service, namespace)
     except Exception as e:
         logging.error(
             "Exception when calling delete_all_services_namespace: %s\n",
             str(e),
         )
         raise e
-    
+
     return services
 
+
 # krkn_lib
 def run(
         scenarios_list,
@@ -151,7 +158,7 @@ def run(
         failed_post_scenarios,
         kubeconfig_path,
         kubecli: KrknKubernetes,
-        telemetry: KrknTelemetry
+        telemetry: KrknTelemetryKubernetes
 ) -> (list[str], list[ScenarioTelemetry]):
     scenario_telemetries: list[ScenarioTelemetry] = []
     failed_scenarios = []
@@ -168,8 +175,12 @@ def run(
             with open(scenario_config[0], "r") as f:
                 scenario_config_yaml = yaml.full_load(f)
                 for scenario in scenario_config_yaml["scenarios"]:
-                    scenario_namespace = scenario.get("namespace", "")
-                    scenario_label = scenario.get("label_selector", "")
+                    scenario_namespace = get_yaml_item_value(
+                        scenario, "namespace", ""
+                    )
+                    scenario_label = get_yaml_item_value(
+                        scenario, "label_selector", ""
+                    )
                     if scenario_namespace is not None and scenario_namespace.strip() != "":
                         if scenario_label is not None and scenario_label.strip() != "":
                             logging.error("You can only have namespace or label set in your namespace scenario")
@@ -183,11 +194,15 @@ def run(
                             # removed_exit
                             # sys.exit(1)
                             raise RuntimeError()
-                    delete_count = scenario.get("delete_count", 1)
-                    run_count = scenario.get("runs", 1)
-                    run_sleep = scenario.get("sleep", 10)
-                    wait_time = scenario.get("wait_time", 30)
-                    
+                    delete_count = get_yaml_item_value(
+                        scenario, "delete_count", 1
+                    )
+                    run_count = get_yaml_item_value(scenario, "runs", 1)
+                    run_sleep = get_yaml_item_value(scenario, "sleep", 10)
+                    wait_time = get_yaml_item_value(scenario, "wait_time", 30)
+
+                    logging.info(str(scenario_namespace) + str(scenario_label) + str(delete_count) + str(run_count) + str(run_sleep) + str(wait_time))
+                    logging.info("done")
                     start_time = int(time.time())
                     for i in range(run_count):
                         killed_namespaces = {}
@@ -230,13 +245,13 @@ def run(
                                 raise RuntimeError()
                         else:
                             failed_post_scenarios = check_all_running_deployment(killed_namespaces, wait_time, kubecli)
-                        
+
                     end_time = int(time.time())
                     cerberus.publish_kraken_status(config, failed_post_scenarios, start_time, end_time)
         except (Exception, RuntimeError):
             scenario_telemetry.exitStatus = 1
             failed_scenarios.append(scenario_config[0])
-            telemetry.log_exception(scenario_config[0])
+            log_exception(scenario_config[0])
         else:
             scenario_telemetry.exitStatus = 0
         scenario_telemetry.endTimeStamp = time.time()
@@ -244,19 +259,19 @@ def run(
     return failed_scenarios, scenario_telemetries
 
 
-def check_all_running_pods(kubecli: KrknKubernetes, namespace_name, wait_time): 
+def check_all_running_pods(kubecli: KrknKubernetes, namespace_name, wait_time):
 
     timer = 0
-    while timer < wait_time: 
+    while timer < wait_time:
         pod_list = kubecli.list_pods(namespace_name)
         pods_running = 0
-        for pod in pod_list: 
-            pod_info = kubecli.get_pod_info(pod,namespace_name)
+        for pod in pod_list:
+            pod_info = kubecli.get_pod_info(pod, namespace_name)
             if pod_info.status != "Running" and pod_info.status != "Succeeded":
                 logging.info("Pods %s still not running or completed" % pod_info.name)
                 break
-            pods_running +=1 
-        if len(pod_list) == pods_running: 
+            pods_running += 1
+        if len(pod_list) == pods_running:
             break
         timer += 5
         time.sleep(5)
@@ -264,36 +279,36 @@ def check_all_running_pods(kubecli: KrknKubernetes, namespace_name, wait_time):
 
 # krkn_lib
 def check_all_running_deployment(killed_namespaces, wait_time, kubecli: KrknKubernetes):
-    
+
     timer = 0
     while timer < wait_time and killed_namespaces:
         still_missing_ns = killed_namespaces.copy()
         for namespace_name, objects in killed_namespaces.items():
             still_missing_obj = objects.copy()
-            for obj_name, obj_list in objects.items(): 
-                if "deployments" == obj_name: 
+            for obj_name, obj_list in objects.items():
+                if "deployments" == obj_name:
                     deployments = kubecli.get_deployment_ns(namespace_name)
                     if len(obj_list) == len(deployments):
                         still_missing_obj.pop(obj_name)
                 elif "replicasets" == obj_name:
                     replicasets = kubecli.get_all_replicasets(namespace_name)
-                    if len(obj_list) == len(replicasets): 
+                    if len(obj_list) == len(replicasets):
                         still_missing_obj.pop(obj_name)
-                elif "statefulsets" == obj_name: 
+                elif "statefulsets" == obj_name:
                     statefulsets = kubecli.get_all_statefulset(namespace_name)
-                    if len(obj_list) == len(statefulsets): 
+                    if len(obj_list) == len(statefulsets):
                         still_missing_obj.pop(obj_name)
-                elif "services" == obj_name: 
+                elif "services" == obj_name:
                     services = kubecli.get_all_services(namespace_name)
-                    if len(obj_list) == len(services): 
+                    if len(obj_list) == len(services):
                         still_missing_obj.pop(obj_name)
-                elif "daemonsets" == obj_name: 
+                elif "daemonsets" == obj_name:
                     daemonsets = kubecli.get_daemonset(namespace_name)
-                    if len(obj_list) == len(daemonsets): 
+                    if len(obj_list) == len(daemonsets):
                         still_missing_obj.pop(obj_name)
             logging.info("Still missing objects " + str(still_missing_obj))
             killed_namespaces[namespace_name] = still_missing_obj.copy()
-            if len(killed_namespaces[namespace_name].keys()) == 0: 
+            if len(killed_namespaces[namespace_name].keys()) == 0:
                 logging.info("Wait for pods to become running for namespace: " + namespace_name)
                 check_all_running_pods(kubecli, namespace_name, wait_time)
                 still_missing_ns.pop(namespace_name)

kraken/shut_down/common_shut_down_func.py

@@ -10,8 +10,9 @@ from ..node_actions.openstack_node_scenarios import OPENSTACKCLOUD
 from ..node_actions.az_node_scenarios import Azure
 from ..node_actions.gcp_node_scenarios import GCP
 from krkn_lib.k8s import KrknKubernetes
-from krkn_lib.telemetry import KrknTelemetry
+from krkn_lib.telemetry.k8s import KrknTelemetryKubernetes
 from krkn_lib.models.telemetry import ScenarioTelemetry
+from krkn_lib.utils.functions import log_exception
 
 def multiprocess_nodes(cloud_object_function, nodes):
     try:
@@ -128,21 +129,28 @@ def cluster_shut_down(shut_down_config, kubecli: KrknKubernetes):
 
 # krkn_lib
 
-def run(scenarios_list, config, wait_duration, kubecli: KrknKubernetes, telemetry: KrknTelemetry) -> (list[str], list[ScenarioTelemetry]):
+def run(scenarios_list, config, wait_duration, kubecli: KrknKubernetes, telemetry: KrknTelemetryKubernetes) -> (list[str], list[ScenarioTelemetry]):
     failed_post_scenarios = []
     failed_scenarios = []
     scenario_telemetries: list[ScenarioTelemetry] = []
 
     for shut_down_config in scenarios_list:
+        config_path = shut_down_config
+        pre_action_output = ""
+        if isinstance(shut_down_config, list) :
+            if len(shut_down_config) == 0:
+                raise Exception("bad config file format for shutdown scenario")
+
+            config_path = shut_down_config[0]
+            if len(shut_down_config) > 1:
+                pre_action_output = post_actions.run("", shut_down_config[1])
+
         scenario_telemetry = ScenarioTelemetry()
-        scenario_telemetry.scenario = shut_down_config
+        scenario_telemetry.scenario = config_path
         scenario_telemetry.startTimeStamp = time.time()
-        telemetry.set_parameters_base64(scenario_telemetry, shut_down_config[0])
-        if len(shut_down_config) > 1:
-            pre_action_output = post_actions.run("", shut_down_config[1])
-        else:
-            pre_action_output = ""
-        with open(shut_down_config[0], "r") as f:
+        telemetry.set_parameters_base64(scenario_telemetry, config_path)
+
+        with open(config_path, "r") as f:
             shut_down_config_yaml = yaml.full_load(f)
             shut_down_config_scenario = \
                 shut_down_config_yaml["cluster_shut_down_scenario"]
@@ -165,8 +173,8 @@ def run(scenarios_list, config, wait_duration, kubecli: KrknKubernetes, telemetr
                 )
 
             except (RuntimeError, Exception):
-                telemetry.log_exception(shut_down_config[0])
-                failed_scenarios.append(shut_down_config[0])
+                log_exception(config_path)
+                failed_scenarios.append(config_path)
                 scenario_telemetry.exitStatus = 1
             else:
                 scenario_telemetry.exitStatus = 0

kraken/time_actions/common_time_functions.py

@@ -2,13 +2,19 @@ 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 import KrknTelemetry
+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, get_random_string
+
 
 # krkn_lib
 def pod_exec(pod_name, command, namespace, container_name, kubecli:KrknKubernetes):
@@ -33,13 +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=""):
 
@@ -63,15 +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"]:
@@ -81,14 +111,20 @@ 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"]:
-        container_name = scenario.get("container_name", "")
+        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"]:
             for name in scenario["object_name"]:
@@ -239,7 +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 (
@@ -250,7 +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:
@@ -264,6 +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()
@@ -308,7 +348,7 @@ def check_date_time(object_type, names, kubecli:KrknKubernetes):
 
 
 # krkn_lib
-def run(scenarios_list, config, wait_duration, kubecli:KrknKubernetes, telemetry: KrknTelemetry) -> (list[str], list[ScenarioTelemetry]):
+def run(scenarios_list, config, wait_duration, kubecli:KrknKubernetes, telemetry: KrknTelemetryKubernetes) -> (list[str], list[ScenarioTelemetry]):
     failed_scenarios = []
     scenario_telemetries: list[ScenarioTelemetry] = []
     for time_scenario_config in scenarios_list:
@@ -338,7 +378,7 @@ def run(scenarios_list, config, wait_duration, kubecli:KrknKubernetes, telemetry
                     )
         except (RuntimeError, Exception):
             scenario_telemetry.exitStatus = 1
-            telemetry.log_exception(time_scenario_config)
+            log_exception(time_scenario_config)
             failed_scenarios.append(time_scenario_config)
         else:
             scenario_telemetry.exitStatus = 0

kraken/zone_outage/actions.py

@@ -3,11 +3,11 @@ import logging
 import time
 from ..node_actions.aws_node_scenarios import AWS
 from ..cerberus import setup as cerberus
-from krkn_lib.telemetry import KrknTelemetry
+from krkn_lib.telemetry.k8s import KrknTelemetryKubernetes
 from krkn_lib.models.telemetry import ScenarioTelemetry
+from krkn_lib.utils.functions import log_exception
 
-
-def run(scenarios_list, config, wait_duration, telemetry: KrknTelemetry) -> (list[str], list[ScenarioTelemetry]) :
+def run(scenarios_list, config, wait_duration, telemetry: KrknTelemetryKubernetes) -> (list[str], list[ScenarioTelemetry]) :
     """
     filters the subnet of interest and applies the network acl
     to create zone outage
@@ -112,7 +112,7 @@ def run(scenarios_list, config, wait_duration, telemetry: KrknTelemetry) -> (lis
         except (RuntimeError, Exception):
             scenario_telemetry.exitStatus = 1
             failed_scenarios.append(zone_outage_config)
-            telemetry.log_exception(zone_outage_config)
+            log_exception(zone_outage_config)
         else:
             scenario_telemetry.exitStatus = 0
         scenario_telemetry.endTimeStamp = time.time()

requirements.txt

@@ -1,8 +1,8 @@
 PyYAML>=5.1
 aliyun-python-sdk-core==2.13.36
 aliyun-python-sdk-ecs==4.24.25
-arcaflow >= 0.6.1
-arcaflow-plugin-sdk >= 0.10.0
+arcaflow==0.9.0
+arcaflow-plugin-sdk==0.10.0
 azure-identity
 azure-keyvault
 azure-mgmt-compute
@@ -18,15 +18,14 @@ google-api-python-client
 ibm_cloud_sdk_core
 ibm_vpc
 itsdangerous==2.0.1
-jinja2==3.0.3
-krkn-lib == 1.3.2
+jinja2==3.1.3
+krkn-lib >= 1.4.6
 kubernetes
 lxml >= 4.3.0
 oauth2client>=4.1.3
 openshift-client
 paramiko
 podman-compose
-prometheus_api_client
 pyVmomi >= 6.7
 pyfiglet
 pytest
@@ -35,6 +34,7 @@ python-openstackclient
 requests
 service_identity
 setuptools==65.5.1
-werkzeug==2.2.3
+werkzeug==3.0.1
 wheel
-zope.interface==5.4.0
+zope.interface==5.4.0
+pandas<2.0.0

run_kraken.py

@@ -1,4 +1,5 @@
 #!/usr/bin/env python
+import datetime
 import json
 import os
 import sys
@@ -8,7 +9,7 @@ import optparse
 import pyfiglet
 import uuid
 import time
-import kraken.litmus.common_litmus as common_litmus
+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
 import kraken.pod_scenarios.setup as pod_scenarios
@@ -16,26 +17,23 @@ import kraken.service_disruption.common_service_disruption_functions as service_
 import kraken.shut_down.common_shut_down_func as shut_down
 import kraken.node_actions.run as nodeaction
 import kraken.managedcluster_scenarios.run as managedcluster_scenarios
-import kraken.kube_burner.client as kube_burner
 import kraken.zone_outage.actions as zone_outages
 import kraken.application_outage.actions as application_outage
 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 server as server
-import kraken.prometheus.client as promcli
 from kraken import plugins
-
 from krkn_lib.k8s import KrknKubernetes
-from krkn_lib.telemetry import KrknTelemetry
+from krkn_lib.ocp import KrknOpenshift
+from krkn_lib.telemetry.k8s import KrknTelemetryKubernetes
+from krkn_lib.telemetry.ocp import KrknTelemetryOpenshift
 from krkn_lib.models.telemetry import ChaosRunTelemetry
 from krkn_lib.utils import SafeLogger
+from krkn_lib.utils.functions import get_yaml_item_value
+
 
-KUBE_BURNER_URL = (
-    "https://github.com/cloud-bulldozer/kube-burner/"
-    "releases/download/v{version}/kube-burner-{version}-Linux-x86_64.tar.gz"
-)
-KUBE_BURNER_VERSION = "1.7.0"
 
 
 # Main function
@@ -49,51 +47,54 @@ def main(cfg):
         with open(cfg, "r") as f:
             config = yaml.full_load(f)
         global kubeconfig_path, wait_duration, kraken_config
-        distribution = config["kraken"].get("distribution", "openshift")
+        distribution = get_yaml_item_value(
+            config["kraken"], "distribution", "openshift"
+        )
         kubeconfig_path = os.path.expanduser(
-            config["kraken"].get("kubeconfig_path", "")
+            get_yaml_item_value(config["kraken"], "kubeconfig_path", "")
         )
         kraken_config = cfg
-        chaos_scenarios = config["kraken"].get("chaos_scenarios", [])
-        publish_running_status = config["kraken"].get("publish_kraken_status", False)
-        port = config["kraken"].get("port")
-        signal_address = config["kraken"].get("signal_address")
-        run_signal = config["kraken"].get("signal_state", "RUN")
-        litmus_install = config["kraken"].get("litmus_install", True)
-        litmus_version = config["kraken"].get("litmus_version", "v1.9.1")
-        litmus_uninstall = config["kraken"].get("litmus_uninstall", False)
-        litmus_uninstall_before_run = config["kraken"].get(
-            "litmus_uninstall_before_run", True
+        chaos_scenarios = get_yaml_item_value(
+            config["kraken"], "chaos_scenarios", []
         )
-        wait_duration = config["tunings"].get("wait_duration", 60)
-        iterations = config["tunings"].get("iterations", 1)
-        daemon_mode = config["tunings"].get("daemon_mode", False)
-        deploy_performance_dashboards = config["performance_monitoring"].get(
-            "deploy_dashboards", False
+        publish_running_status = get_yaml_item_value(
+            config["kraken"], "publish_kraken_status", False
         )
-        dashboard_repo = config["performance_monitoring"].get(
-            "repo", "https://github.com/cloud-bulldozer/performance-dashboards.git"
+        port = get_yaml_item_value(config["kraken"], "port", 8081)
+        signal_address = get_yaml_item_value(
+            config["kraken"], "signal_address", "0.0.0.0")
+        run_signal = get_yaml_item_value(
+            config["kraken"], "signal_state", "RUN"
         )
-        capture_metrics = config["performance_monitoring"].get("capture_metrics", False)
-        kube_burner_url = config["performance_monitoring"].get(
-            "kube_burner_binary_url",
-            KUBE_BURNER_URL.format(version=KUBE_BURNER_VERSION),
+        wait_duration = get_yaml_item_value(
+            config["tunings"], "wait_duration", 60
         )
-        config_path = config["performance_monitoring"].get(
-            "config_path", "config/kube_burner.yaml"
+        iterations = get_yaml_item_value(config["tunings"], "iterations", 1)
+        daemon_mode = get_yaml_item_value(
+            config["tunings"], "daemon_mode", False
         )
-        metrics_profile = config["performance_monitoring"].get(
-            "metrics_profile_path", "config/metrics-aggregated.yaml"
+        deploy_performance_dashboards = get_yaml_item_value(
+            config["performance_monitoring"], "deploy_dashboards", False
         )
-        prometheus_url = config["performance_monitoring"].get("prometheus_url", "")
-        prometheus_bearer_token = config["performance_monitoring"].get(
-            "prometheus_bearer_token", ""
+        dashboard_repo = get_yaml_item_value(
+            config["performance_monitoring"], "repo",
+            "https://github.com/cloud-bulldozer/performance-dashboards.git"
         )
-        run_uuid = config["performance_monitoring"].get("uuid", "")
-        enable_alerts = config["performance_monitoring"].get("enable_alerts", False)
-        alert_profile = config["performance_monitoring"].get("alert_profile", "")
-        check_critical_alerts = config["performance_monitoring"].get("check_critical_alerts", False)
 
+        prometheus_url = config["performance_monitoring"].get("prometheus_url")
+        prometheus_bearer_token = config["performance_monitoring"].get(
+            "prometheus_bearer_token"
+        )
+        run_uuid = config["performance_monitoring"].get("uuid")
+        enable_alerts = get_yaml_item_value(
+            config["performance_monitoring"], "enable_alerts", False
+        )
+        alert_profile = config["performance_monitoring"].get("alert_profile")
+        check_critical_alerts = get_yaml_item_value(
+            config["performance_monitoring"], "check_critical_alerts", False
+        )
+        telemetry_api_url = config["telemetry"].get("api_url")
+        
         # Initialize clients
         if (not os.path.isfile(kubeconfig_path) and
             not os.path.isfile("/var/run/secrets/kubernetes.io/serviceaccount/token")):
@@ -124,11 +125,11 @@ def main(cfg):
             os.environ["KUBECONFIG"] = str(kubeconfig_path)
             # krkn-lib-kubernetes init
             kubecli = KrknKubernetes(kubeconfig_path=kubeconfig_path)
+            ocpcli = KrknOpenshift(kubeconfig_path=kubeconfig_path)
         except:
             kubecli.initialize_clients(None)
 
-        # KrknTelemetry init
-        telemetry = KrknTelemetry(safe_logger, kubecli)
+
 
         # find node kraken might be running on
         kubecli.find_kraken_node()
@@ -154,12 +155,26 @@ def main(cfg):
 
         # Cluster info
         logging.info("Fetching cluster info")
-        cv = kubecli.get_clusterversion_string()
+        cv = ""
+        if config["kraken"]["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
         if cv != "":
             logging.info(cv)
         else:
             logging.info("Cluster version CRD not detected, skipping")
 
+        # KrknTelemetry init
+        telemetry_k8s = KrknTelemetryKubernetes(safe_logger, kubecli)
+        telemetry_ocp = KrknTelemetryOpenshift(safe_logger, ocpcli)
+
+
+        if enable_alerts:
+            prometheus = KrknPrometheus(prometheus_url, prometheus_bearer_token)
+
         logging.info("Server URL: %s" % kubecli.get_host())
 
         # Deploy performance dashboards
@@ -188,7 +203,7 @@ def main(cfg):
 
         # Capture the start time
         start_time = int(time.time())
-        litmus_installed = False
+
         chaos_telemetry = ChaosRunTelemetry()
         chaos_telemetry.run_uuid = run_uuid
         # Loop to run the chaos starts here
@@ -223,7 +238,7 @@ def main(cfg):
                             sys.exit(1)
                         elif scenario_type == "arcaflow_scenarios":
                             failed_post_scenarios, scenario_telemetries = arcaflow_plugin.run(
-                                scenarios_list, kubeconfig_path, telemetry
+                                scenarios_list, kubeconfig_path, telemetry_k8s
                             )
                             chaos_telemetry.scenarios.extend(scenario_telemetries)
 
@@ -234,7 +249,7 @@ def main(cfg):
                                 kraken_config,
                                 failed_post_scenarios,
                                 wait_duration,
-                                telemetry
+                                telemetry_k8s
                             )
                             chaos_telemetry.scenarios.extend(scenario_telemetries)
                         # krkn_lib
@@ -247,7 +262,7 @@ def main(cfg):
                                 failed_post_scenarios,
                                 wait_duration,
                                 kubecli,
-                                telemetry
+                                telemetry_k8s
                             )
                             chaos_telemetry.scenarios.extend(scenario_telemetries)
 
@@ -255,7 +270,7 @@ def main(cfg):
                         # krkn_lib
                         elif scenario_type == "node_scenarios":
                             logging.info("Running node scenarios")
-                            failed_post_scenarios, scenario_telemetries = nodeaction.run(scenarios_list, config, wait_duration, kubecli, telemetry)
+                            failed_post_scenarios, scenario_telemetries = nodeaction.run(scenarios_list, config, wait_duration, kubecli, telemetry_k8s)
                             chaos_telemetry.scenarios.extend(scenario_telemetries)
                         # Inject managedcluster chaos scenarios specified in the config
                         # krkn_lib
@@ -269,60 +284,13 @@ 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)
+                                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 litmus based chaos scenarios
-                        elif scenario_type == "litmus_scenarios":
-                            if distribution == "openshift":
-                                logging.info("Running litmus scenarios")
-                                litmus_namespace = "litmus"
-                                if litmus_install:
-                                    # Remove Litmus resources
-                                    # before running the scenarios
-                                    common_litmus.delete_chaos(litmus_namespace, kubecli)
-                                    common_litmus.delete_chaos_experiments(
-                                        litmus_namespace,
-                                        kubecli
-                                    )
-                                    if litmus_uninstall_before_run:
-                                        common_litmus.uninstall_litmus(
-                                            litmus_version, litmus_namespace, kubecli
-                                        )
-                                    common_litmus.install_litmus(
-                                        litmus_version, litmus_namespace
-                                    )
-                                    common_litmus.deploy_all_experiments(
-                                        litmus_version, litmus_namespace
-                                    )
-                                litmus_installed = True
-                                common_litmus.run(
-                                    scenarios_list,
-                                    config,
-                                    litmus_uninstall,
-                                    wait_duration,
-                                    litmus_namespace,
-                                    kubecli
-                                )
-                            else:
-                                logging.error(
-                                    "Litmus scenarios are currently "
-                                    "only supported on openshift"
-                                )
-                                sys.exit(1)
-
                         # Inject cluster shutdown scenarios
                         # krkn_lib
                         elif scenario_type == "cluster_shut_down_scenarios":
-                            failed_post_scenarios, scenario_telemetries = shut_down.run(scenarios_list, config, wait_duration, kubecli, telemetry)
+                            failed_post_scenarios, scenario_telemetries = shut_down.run(scenarios_list, config, wait_duration, kubecli, telemetry_k8s)
                             chaos_telemetry.scenarios.extend(scenario_telemetries)
 
                         # Inject namespace chaos scenarios
@@ -336,41 +304,48 @@ def main(cfg):
                                 failed_post_scenarios,
                                 kubeconfig_path,
                                 kubecli,
-                                telemetry
+                                telemetry_k8s
                             )
                             chaos_telemetry.scenarios.extend(scenario_telemetries)
 
                         # Inject zone failures
                         elif scenario_type == "zone_outages":
                             logging.info("Inject zone outages")
-                            failed_post_scenarios, scenario_telemetries = zone_outages.run(scenarios_list, config, wait_duration, telemetry)
+                            failed_post_scenarios, scenario_telemetries = zone_outages.run(scenarios_list, config, wait_duration, telemetry_k8s)
                             chaos_telemetry.scenarios.extend(scenario_telemetries)
                         # Application outages
                         elif scenario_type == "application_outages":
                             logging.info("Injecting application outage")
                             failed_post_scenarios, scenario_telemetries = application_outage.run(
-                                scenarios_list, config, wait_duration, telemetry)
+                                scenarios_list, config, wait_duration, 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)
+                            failed_post_scenarios, scenario_telemetries = pvc_scenario.run(scenarios_list, config, kubecli, telemetry_k8s)
                             chaos_telemetry.scenarios.extend(scenario_telemetries)
 
                         # Network scenarios
                         # krkn_lib
                         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)
+                            failed_post_scenarios, scenario_telemetries = network_chaos.run(scenarios_list, config, wait_duration, kubecli, telemetry_k8s)
 
                         # Check for critical alerts when enabled
-                        if check_critical_alerts:
+                        if enable_alerts and check_critical_alerts :
                             logging.info("Checking for critical alerts firing post choas")
-                            promcli.initialize_prom_client(distribution, prometheus_url, prometheus_bearer_token)
+
+                            ##PROM
                             query = r"""ALERTS{severity="critical"}"""
-                            critical_alerts = promcli.process_prom_query(query)
+                            end_time = datetime.datetime.now()
+                            critical_alerts = prometheus.process_prom_query_in_range(
+                                query,
+                                start_time = datetime.datetime.fromtimestamp(start_time),
+                                end_time = end_time
+
+                            )
                             critical_alerts_count = len(critical_alerts)
                             if critical_alerts_count > 0:
                                 logging.error("Critical alerts are firing: %s", critical_alerts)
@@ -387,53 +362,44 @@ def main(cfg):
         # is disabled, it's necessary to serialize the ChaosRunTelemetry object
         # to json, and recreate a new object from it.
         end_time = int(time.time())
-        telemetry.collect_cluster_metadata(chaos_telemetry)
+
+        # if platform is openshift will be collected
+        # Cloud platform and network plugins metadata
+        # through OCP specific APIs
+        if config["kraken"]["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()}")
+
         if config["telemetry"]["enabled"]:
-            logging.info(f"telemetry data will be stored on s3 bucket folder: {telemetry_request_id}")
+            logging.info(f"telemetry data will be stored on s3 bucket folder: {telemetry_api_url}/download/{telemetry_request_id}")
             logging.info(f"telemetry upload log: {safe_logger.log_file_name}")
             try:
-                telemetry.send_telemetry(config["telemetry"], telemetry_request_id, chaos_telemetry)
-                if config["telemetry"]["prometheus_backup"]:
+                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)
+                # 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.get_ocp_prometheus_data(config["telemetry"], telemetry_request_id)
+                    prometheus_archive_files = telemetry_ocp.get_ocp_prometheus_data(config["telemetry"], telemetry_request_id)
                     safe_logger.info("archives upload started:")
-                    telemetry.put_ocp_prometheus_data(config["telemetry"], prometheus_archive_files, telemetry_request_id)
+                    telemetry_k8s.put_prometheus_data(config["telemetry"], prometheus_archive_files, telemetry_request_id)
                 if config["telemetry"]["logs_backup"]:
-                    telemetry.put_ocp_logs(telemetry_request_id, config["telemetry"], start_time, end_time)
+                    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)}")
         else:
             logging.info("telemetry collection disabled, skipping.")
 
-        # Capture the end time
-
-
-        # Capture metrics for the run
-        if capture_metrics:
-            logging.info("Capturing metrics")
-            kube_burner.setup(kube_burner_url)
-            kube_burner.scrape_metrics(
-                distribution,
-                run_uuid,
-                prometheus_url,
-                prometheus_bearer_token,
-                start_time,
-                end_time,
-                config_path,
-                metrics_profile,
-            )
 
         # Check for the alerts specified
         if enable_alerts:
             logging.info("Alerts checking is enabled")
-            kube_burner.setup(kube_burner_url)
             if alert_profile:
-                kube_burner.alerts(
-                    distribution,
-                    prometheus_url,
-                    prometheus_bearer_token,
+                prometheus_plugin.alerts(
+                    prometheus,
                     start_time,
                     end_time,
                     alert_profile,
@@ -442,11 +408,6 @@ def main(cfg):
                 logging.error("Alert profile is not defined")
                 sys.exit(1)
 
-        if litmus_uninstall and litmus_installed:
-            common_litmus.delete_chaos(litmus_namespace, kubecli)
-            common_litmus.delete_chaos_experiments(litmus_namespace, kubecli)
-            common_litmus.uninstall_litmus(litmus_version, litmus_namespace, kubecli)
-
         if failed_post_scenarios:
             logging.error(
                 "Post scenarios are still failing at the end of all iterations"

scenarios/arcaflow/cpu-hog/config.yaml

@@ -1,7 +1,8 @@
 ---
-deployer:
-  connection: {}
-  type: kubernetes
+deployers:
+  image:
+    connection: {}
+    deployer_name: kubernetes
 log:
   level: debug
 logged_outputs:

scenarios/arcaflow/cpu-hog/input.yaml

@@ -2,13 +2,7 @@ input_list:
 - cpu_count: 1
   cpu_load_percentage: 80
   cpu_method: all
-  duration: 30s
-  node_selector: {}
-  # node selector example
-  # node_selector:
-  #   kubernetes.io/hostname: master
-  kubeconfig: ""
+  duration: 1s
+  kubeconfig: ''
   namespace: default
-
-# duplicate this section to run simultaneous stressors in the same run
-
+  node_selector: {}

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

@@ -1,8 +1,9 @@
+version: v0.2.0
 input:
   root: RootObject
   objects:
     RootObject:
-      id: RootObject
+      id: input_item
       properties:
         kubeconfig:
           display:
@@ -60,11 +61,15 @@ input:
 
 steps:
   kubeconfig:
-    plugin: quay.io/arcalot/arcaflow-plugin-kubeconfig:0.2.0
+    plugin: 
+      src: quay.io/arcalot/arcaflow-plugin-kubeconfig:0.2.0
+      deployment_type: image
     input:
       kubeconfig: !expr $.input.kubeconfig
   stressng:
-    plugin: quay.io/arcalot/arcaflow-plugin-stressng:0.3.1
+    plugin: 
+      src: quay.io/arcalot/arcaflow-plugin-stressng:0.5.0
+      deployment_type: image
     step: workload
     input:
       cleanup: "true"
@@ -76,7 +81,7 @@ steps:
             cpu_method: !expr $.input.cpu_method
             cpu_load: !expr $.input.cpu_load_percentage
     deploy:
-      type: kubernetes
+      deployer_name: kubernetes
       connection: !expr $.steps.kubeconfig.outputs.success.connection
       pod:
         metadata:

scenarios/arcaflow/cpu-hog/workflow.yaml

@@ -1,3 +1,4 @@
+version: v0.2.0
 input:
   root: RootObject
   objects:

scenarios/arcaflow/io-hog/config.yaml

@@ -1,6 +1,7 @@
-deployer:
-  connection: {}
-  type: kubernetes
+deployers:
+  image:
+    connection: {}
+    deployer_name: kubernetes
 log:
   level: debug
 logged_outputs:

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

@@ -1,8 +1,9 @@
+version: v0.2.0
 input:
   root: RootObject
   objects:
     RootObject:
-      id: RootObject
+      id: input_item
       properties:
         kubeconfig:
           display:
@@ -95,11 +96,15 @@ input:
 
 steps:
   kubeconfig:
-    plugin: quay.io/arcalot/arcaflow-plugin-kubeconfig:0.2.0
+    plugin: 
+      src: quay.io/arcalot/arcaflow-plugin-kubeconfig:0.2.0
+      deployment_type: image
     input:
       kubeconfig: !expr $.input.kubeconfig
   stressng:
-    plugin: quay.io/arcalot/arcaflow-plugin-stressng:0.3.1
+    plugin: 
+      src: quay.io/arcalot/arcaflow-plugin-stressng:0.5.0
+      deployment_type: image
     step: workload
     input:
       cleanup: "true"
@@ -113,7 +118,7 @@ steps:
             hdd_write_size: !expr $.input.io_block_size
 
     deploy:
-      type: kubernetes
+      deployer_name: kubernetes
       connection: !expr $.steps.kubeconfig.outputs.success.connection
       pod:
         metadata:

scenarios/arcaflow/io-hog/workflow.yaml

@@ -1,3 +1,4 @@
+version: v0.2.0
 input:
   root: RootObject
   objects:

scenarios/arcaflow/memory-hog/config.yaml

@@ -1,7 +1,8 @@
 ---
-deployer:
-  connection: {}
-  type: kubernetes
+deployers:
+  image:
+    connection: {}
+    deployer_name: kubernetes
 log:
   level: debug
 logged_outputs:

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

@@ -1,8 +1,9 @@
+version: v0.2.0
 input:
   root: RootObject
   objects:
     RootObject:
-      id: RootObject
+      id: input_item
       properties:
         kubeconfig:
           display:
@@ -52,11 +53,15 @@ input:
 
 steps:
   kubeconfig:
-    plugin: quay.io/arcalot/arcaflow-plugin-kubeconfig:0.2.0
+    plugin: 
+      src: quay.io/arcalot/arcaflow-plugin-kubeconfig:0.2.0
+      deployment_type: image
     input:
       kubeconfig: !expr $.input.kubeconfig
   stressng:
-    plugin: quay.io/arcalot/arcaflow-plugin-stressng:0.3.1
+    plugin: 
+      src: quay.io/arcalot/arcaflow-plugin-stressng:0.5.0
+      deployment_type: image
     step: workload
     input:
       cleanup: "true"
@@ -67,7 +72,7 @@ steps:
             vm: !expr $.input.vm_workers
             vm_bytes: !expr $.input.vm_bytes
     deploy:
-      type: kubernetes
+      deployer_name: kubernetes
       connection: !expr $.steps.kubeconfig.outputs.success.connection
       pod:
         metadata:

scenarios/arcaflow/memory-hog/workflow.yaml

@@ -1,3 +1,4 @@
+version: v0.2.0
 input:
   root: RootObject
   objects:

scenarios/openshift/container_etcd.yml

@@ -3,6 +3,6 @@ scenarios:
   namespace: "openshift-etcd"
   label_selector: "k8s-app=etcd"
   container_name: "etcd"
-  action: "kill 1"
+  action: 1
   count: 1
   expected_recovery_time: 60

scenarios/openshift/node_cpu_hog_engine.yaml

@@ -1,34 +0,0 @@
-apiVersion: litmuschaos.io/v1alpha1
-kind: ChaosEngine
-metadata:
-  name: nginx-chaos
-  namespace: litmus
-spec:
-  # It can be true/false
-  annotationCheck: 'false'
-  # It can be active/stop
-  engineState: 'active'
-  chaosServiceAccount: litmus-sa
-  monitoring: false
-  # It can be delete/retain
-  jobCleanUpPolicy: 'delete'
-  experiments:
-    - name: node-cpu-hog
-      spec:
-        components:
-          env:
-            # set chaos duration (in sec) as desired
-            - name: TOTAL_CHAOS_DURATION
-              value: '60'
-
-            # Number of cores of node CPU to be consumed
-            - name: NODE_CPU_CORE
-              value: '1'
-
-            # percentage of total nodes to target
-            - name: NODES_AFFECTED_PERC
-              value: ''
-
-            # ENTER THE COMMA SEPARATED TARGET NODES NAME
-            - name: TARGET_NODES
-              value: '<node_name>'

scenarios/openshift/node_io_engine.yaml

@@ -1,35 +0,0 @@
-apiVersion: litmuschaos.io/v1alpha1
-kind: ChaosEngine
-metadata:
-  name: nginx-chaos
-  namespace: litmus
-spec:
-  # It can be delete/retain
-  jobCleanUpPolicy: 'retain'
-  # It can be active/stop
-  engineState: 'active'
-  chaosServiceAccount: litmus-sa
-  experiments:
-    - name: node-io-stress
-      spec:
-        components:
-          env:
-            # set chaos duration (in sec) as desired
-            - name: TOTAL_CHAOS_DURATION
-              value: '40'
-
-            ## specify the size as percentage of free space on the file system
-            - name: FILESYSTEM_UTILIZATION_PERCENTAGE
-              value: '100'
-
-            ## Number of core of CPU
-            - name: CPU
-              value: '1'
-
-            ## Total number of workers default value is 4
-            - name: NUMBER_OF_WORKERS
-              value: '3'
-
-             ## enter the comma separated target nodes name
-            - name: TARGET_NODES
-              value: '<node_name>'

scenarios/openshift/node_mem_engine.yaml

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

scenarios/openshift/pod_ingress_shaping.yml

@@ -0,0 +1,14 @@
+# yaml-language-server: $schema=../plugin.schema.json
+- id: pod_ingress_shaping
+  config:
+    namespace: <namespace>              # Required - Namespace of the pod to which traffic shaping need to be applied
+    label_selector: <label_selector>    # When pod_name is not specified, pod with matching label_selector is selected for chaos scenario
+    pod_name: <pod name>                # When label_selector is not specified, pod matching the name will be selected for the chaos scenario
+    network_params:                     # latency, loss and bandwidth are the three supported network parameters to alter for the chaos test
+        latency: <time>                 # Value is a string. For example : 50ms
+        loss: <fraction>                # Loss is a fraction between 0 and 1. It has to be enclosed in quotes to treat it as a string. For example, '0.02%' (not 0.02%)       
+        bandwidth: <rate>               # Value is a string. For example: 100mbit
+    execution_type: <serial/parallel>   # Used to specify whether you want to apply filters on interfaces one at a time or all at once. Default is 'parallel'
+    instance_count: <number>            # Number of pods to perform action/select that match the label selector
+    wait_duration: <time_duration>      # Default is 300. Ensure that it is at least about twice of test_duration
+    test_duration: <time_duration>      # Default is 120 

scenarios/plugin.schema.json

@@ -2413,7 +2413,168 @@
 					"id",
 					"config"
 				]
+			},
+			{
+				"type": "object",
+				"title": "pod_ingress_shaping Arcaflow scenarios",
+				"properties": {
+					"id": {
+						"type": "string",
+						"const": "pod_ingress_shaping"
+					},
+					"config": {
+						"$defs": {
+							"IngressParams": {
+								"type": "object",
+								"properties": {
+									"namespace": {
+										"type": "string",
+										"minLength": 1,
+										"title": "Namespace",
+										"description": "Namespace of the pod to which filter need to be appliedfor details."
+									},
+									"network_params": {
+										"type": "object",
+										"propertyNames": {},
+										"additionalProperties": {
+											"type": "string"
+										},
+										"title": "Network Parameters",
+										"description": "The network filters that are applied on the interface. The currently supported filters are latency, loss and bandwidth"
+									},
+									"kubeconfig_path": {
+										"type": "string",
+										"title": "Kubeconfig path",
+										"description": "Kubeconfig file as string\nSee https://kubernetes.io/docs/concepts/configuration/organize-cluster-access-kubeconfig/ for details."
+									},
+									"pod_name": {
+										"type": "string",
+										"title": "Pod name",
+										"description": "When label_selector is not specified, pod matching the name will beselected for the chaos scenario"
+									},
+									"label_selector": {
+										"type": "string",
+										"title": "Label selector",
+										"description": "Kubernetes label selector for the target pod. When pod_name is not specified, pod with matching label_selector is selected for chaos scenario"
+									},
+									"kraken_config": {
+										"type": "string",
+										"title": "Kraken Config",
+										"description": "Path to the config file of Kraken. Set this field if you wish to publish status onto Cerberus"
+									},
+									"test_duration": {
+										"type": "integer",
+										"minimum": 1,
+										"default": 90,
+										"title": "Test duration",
+										"description": "Duration for which each step of the ingress chaos testing is to be performed."
+									},
+									"wait_duration": {
+										"type": "integer",
+										"minimum": 1,
+										"default": 300,
+										"title": "Wait Duration",
+										"description": "Wait duration for finishing a test and its cleanup.Ensure that it is significantly greater than wait_duration"
+									},
+									"instance_count": {
+										"type": "integer",
+										"minimum": 1,
+										"default": 1,
+										"title": "Instance Count",
+										"description": "Number of pods to perform action/select that match the label selector."
+									},
+									"execution_type": {
+										"type": "string",
+										"default": "parallel",
+										"title": "Execution Type",
+										"description": "The order in which the ingress filters are applied. Execution type can be 'serial' or 'parallel'"
+									}
+								},
+								"required": [
+									"namespace"
+								],
+								"additionalProperties": false,
+								"dependentRequired": {}
+							}
+						},
+						"type": "object",
+						"properties": {
+							"namespace": {
+								"type": "string",
+								"minLength": 1,
+								"title": "Namespace",
+								"description": "Namespace of the pod to which filter need to be appliedfor details."
+							},
+							"network_params": {
+								"type": "object",
+								"propertyNames": {},
+								"additionalProperties": {
+									"type": "string"
+								},
+								"title": "Network Parameters",
+								"description": "The network filters that are applied on the interface. The currently supported filters are latency, loss and bandwidth"
+							},
+							"kubeconfig_path": {
+								"type": "string",
+								"title": "Kubeconfig path",
+								"description": "Kubeconfig file as string\nSee https://kubernetes.io/docs/concepts/configuration/organize-cluster-access-kubeconfig/ for details."
+							},
+							"pod_name": {
+								"type": "string",
+								"title": "Pod name",
+								"description": "When label_selector is not specified, pod matching the name will beselected for the chaos scenario"
+							},
+							"label_selector": {
+								"type": "string",
+								"title": "Label selector",
+								"description": "Kubernetes label selector for the target pod. When pod_name is not specified, pod with matching label_selector is selected for chaos scenario"
+							},
+							"kraken_config": {
+								"type": "string",
+								"title": "Kraken Config",
+								"description": "Path to the config file of Kraken. Set this field if you wish to publish status onto Cerberus"
+							},
+							"test_duration": {
+								"type": "integer",
+								"minimum": 1,
+								"default": 90,
+								"title": "Test duration",
+								"description": "Duration for which each step of the ingress chaos testing is to be performed."
+							},
+							"wait_duration": {
+								"type": "integer",
+								"minimum": 1,
+								"default": 300,
+								"title": "Wait Duration",
+								"description": "Wait duration for finishing a test and its cleanup.Ensure that it is significantly greater than wait_duration"
+							},
+							"instance_count": {
+								"type": "integer",
+								"minimum": 1,
+								"default": 1,
+								"title": "Instance Count",
+								"description": "Number of pods to perform action/select that match the label selector."
+							},
+							"execution_type": {
+								"type": "string",
+								"default": "parallel",
+								"title": "Execution Type",
+								"description": "The order in which the ingress filters are applied. Execution type can be 'serial' or 'parallel'"
+							}
+						},
+						"required": [
+							"namespace"
+						],
+						"additionalProperties": false,
+						"dependentRequired": {}
+					}
+				},
+				"required": [
+					"id",
+					"config"
+				]
 			}
+
 		]
 	}
 }

utils/chaos_recommender/README.md

@@ -0,0 +1,106 @@
+# Chaos Recommendation Tool
+
+This tool, designed for Redhat Kraken, operates through the command line and offers recommendations for chaos testing. It suggests probable chaos test cases that can disrupt application services by analyzing their behavior and assessing their susceptibility to specific fault types.
+
+This tool profiles an application and gathers telemetry data such as CPU, Memory, and Network usage, analyzing it to suggest probable chaos scenarios. For optimal results, it is recommended to activate the utility while the application is under load.
+
+## Pre-requisites
+
+- Openshift Or Kubernetes Environment where the application is hosted
+- Access to the telemetry data via the exposed Prometheus endpoint
+- Python3
+
+## Usage
+
+1. To run
+
+    ```
+    $ python3.9 -m venv chaos
+    $ source chaos/bin/activate
+    $ git clone https://github.com/redhat-chaos/krkn.git 
+    $ cd krkn
+    $ pip3 install -r requirements.txt
+    $ python3.9 utils/chaos_recommender/chaos_recommender.py
+    ```
+
+2. Follow the prompts to provide the required information.
+
+## Configuration
+To run the recommender with a config file specify the config file path with the `-c` argument.
+You can customize the default values by editing the `krkn/config/recommender_config.yaml` file. The configuration file contains the following options:
+
+  - `application`: Specify the application name.
+  - `namespace`: Specify the namespace name. If you want to profile
+  - `labels`: Specify the labels (not used).
+  - `kubeconfig`: Specify the location of the kubeconfig file (not used).
+  - `prometheus_endpoint`: Specify the prometheus endpoint (must).
+  - `auth_token`: Auth token to connect to prometheus endpoint (must).
+  - `scrape_duration`: For how long data should be fetched, e.g., '1m' (must).
+  - `chaos_library`: "kraken" (currently it only supports kraken).
+  - `chaos_tests`: (for output purpose only do not change if not needed)
+    - `GENERAL`: list of general purpose tests available in Krkn
+    - `MEM`: list of memory related tests available in Krkn
+    - `NETWORK`: list of network related tests available in Krkn
+    - `CPU`: list of memory related tests available in Krkn
+
+*TIP:* to collect prometheus endpoint and token from your OpenShift cluster you can run the following commands:
+        ```
+         prometheus_url=$(kubectl get routes -n openshift-monitoring prometheus-k8s --no-headers | awk '{print $2}')
+         #TO USE YOUR CURRENT SESSION TOKEN
+         token=$(oc whoami -t)
+         #TO CREATE A NEW TOKEN
+         token=$(kubectl create token -n openshift-monitoring prometheus-k8s --duration=6h || oc sa new-token -n openshift-monitoring prometheus-k8s)
+        ```
+
+You can also provide the input values through command-line arguments launching the recommender with `-o` option:
+
+```
+  -o, --options         Evaluate command line options
+  -a APPLICATION, --application APPLICATION
+                        Kubernetes application name
+  -n NAMESPACE, --namespace NAMESPACE
+                        Kubernetes application namespace
+  -l LABELS, --labels LABELS
+                        Kubernetes application labels
+  -p PROMETHEUS_ENDPOINT, --prometheus-endpoint PROMETHEUS_ENDPOINT
+                        Prometheus endpoint URI
+  -k KUBECONFIG, --kubeconfig KUBECONFIG
+                        Kubeconfig path
+  -t TOKEN, --token TOKEN
+                        Kubernetes authentication token
+  -s SCRAPE_DURATION, --scrape-duration SCRAPE_DURATION
+                        Prometheus scrape duration
+  -i LIBRARY, --library LIBRARY
+                        Chaos library
+  -L LOG_LEVEL, --log-level LOG_LEVEL
+                        log level (DEBUG, INFO, WARNING, ERROR, CRITICAL
+  -M MEM [MEM ...], --MEM MEM [MEM ...]
+                        Memory related chaos tests (space separated list)
+  -C CPU [CPU ...], --CPU CPU [CPU ...]
+                        CPU related chaos tests (space separated list)
+  -N NETWORK [NETWORK ...], --NETWORK NETWORK [NETWORK ...]
+                        Network related chaos tests (space separated list)
+  -G GENERIC [GENERIC ...], --GENERIC GENERIC [GENERIC ...]
+                        Memory related chaos tests (space separated list)
+
+```
+
+If you provide the input values through command-line arguments, the corresponding config file inputs would be ignored.
+
+## Podman & Docker image
+
+To run the recommender image please visit the [krkn-hub](https://github.com/redhat-chaos/krkn-hub for further infos.
+
+## How it works
+
+After obtaining telemetry data, sourced either locally or from Prometheus, the tool conducts a comprehensive data analysis to detect anomalies. Employing the Z-score method and heatmaps, it identifies outliers by evaluating CPU, memory, and network usage against established limits. Services with Z-scores surpassing a specified threshold are categorized as outliers. This categorization classifies services as network, CPU, or memory-sensitive, consequently leading to the recommendation of relevant test cases.
+
+## Customizing Thresholds and Options
+
+You can customize the thresholds and options used for data analysis by modifying the `krkn/kraken/chaos_recommender/analysis.py` file. For example, you can adjust the threshold for identifying outliers by changing the value of the `threshold` variable in the `identify_outliers` function.
+
+## Additional Files
+
+- `config/recommender_config.yaml`: The configuration file containing default values for application, namespace, labels, and kubeconfig.
+
+Happy Chaos!

utils/chaos_recommender/chaos_recommender.py

@@ -0,0 +1,117 @@
+import argparse
+import logging
+import os.path
+import sys
+import yaml
+# kraken module import for running the recommender
+# both from the root directory and the recommender
+# folder
+sys.path.insert(0, './')
+sys.path.insert(0, '../../')
+
+import kraken.chaos_recommender.analysis as analysis
+import kraken.chaos_recommender.prometheus as prometheus
+from kubernetes import config as kube_config
+
+
+
+def parse_arguments(parser):
+
+    # command line options
+    parser.add_argument("-c", "--config-file", action="store", help="Config file path")
+    parser.add_argument("-o", "--options", action="store_true", help="Evaluate command line options")
+    parser.add_argument("-n", "--namespace", action="store", default="", help="Kubernetes application namespace")
+    parser.add_argument("-p", "--prometheus-endpoint", action="store", default="", help="Prometheus endpoint URI")
+    parser.add_argument("-k", "--kubeconfig", action="store", default=kube_config.KUBE_CONFIG_DEFAULT_LOCATION, help="Kubeconfig path")
+    parser.add_argument("-t", "--token", action="store", default="", help="Kubernetes authentication token")
+    parser.add_argument("-s", "--scrape-duration", action="store", default="10m", help="Prometheus scrape duration")
+    parser.add_argument("-L", "--log-level", action="store", default="INFO", help="log level (DEBUG, INFO, WARNING, ERROR, CRITICAL")
+
+    parser.add_argument("-M", "--MEM", nargs='+', action="store", default=[],
+                        help="Memory related chaos tests (space separated list)")
+    parser.add_argument("-C", "--CPU", nargs='+', action="store", default=[],
+                        help="CPU related chaos tests (space separated list)")
+    parser.add_argument("-N", "--NETWORK", nargs='+', action="store", default=[],
+                        help="Network related chaos tests (space separated list)")
+    parser.add_argument("-G", "--GENERIC", nargs='+', action="store", default=[],
+                        help="Memory related chaos tests (space separated list)")
+
+
+    return parser.parse_args()
+
+def read_configuration(config_file_path):
+    if not os.path.exists(config_file_path):
+        logging.error(f"Config file not found: {config_file_path}")
+        sys.exit(1)
+
+    with open(config_file_path, mode="r") as config_file:
+        config = yaml.safe_load(config_file)
+
+    log_level = config.get("log level", "INFO")
+    namespace = config.get("namespace", "")
+    kubeconfig = config.get("kubeconfig", kube_config.KUBE_CONFIG_DEFAULT_LOCATION)
+
+    prometheus_endpoint = config.get("prometheus_endpoint", "")
+    auth_token = config.get("auth_token", "")
+    scrape_duration = config.get("scrape_duration", "10m")
+    chaos_tests = config.get("chaos_tests" , {})
+    return (namespace, kubeconfig, prometheus_endpoint, auth_token, scrape_duration,
+            chaos_tests, log_level)
+
+def prompt_input(prompt, default_value):
+    user_input = input(f"{prompt} [{default_value}]: ")
+    if user_input.strip():
+        return user_input
+    return default_value
+
+def main():
+    parser = argparse.ArgumentParser(description="Krkn Chaos Recommender Command-Line tool")
+    args = parse_arguments(parser)
+
+    if args.config_file is None and not args.options:
+        logging.error("You have to either specify a config file path or pass recommender options as command line arguments")
+        parser.print_help()
+        sys.exit(1)
+
+    if args.config_file is not None:
+        (
+         namespace,
+         kubeconfig,
+         prometheus_endpoint,
+         auth_token,
+         scrape_duration,
+         chaos_tests,
+         log_level
+         ) = read_configuration(args.config_file)
+
+    if args.options:
+        namespace = args.namespace
+        kubeconfig = args.kubeconfig
+        auth_token = args.token
+        scrape_duration = args.scrape_duration
+        log_level = args.log_level
+        prometheus_endpoint = args.prometheus_endpoint
+        chaos_tests = {"MEM": args.MEM, "GENERIC": args.GENERIC, "CPU": args.CPU, "NETWORK": args.NETWORK}
+
+    if log_level not in ["DEBUG","INFO", "WARNING", "ERROR","CRITICAL"]:
+        logging.error(f"{log_level} not a valid log level")
+        sys.exit(1)
+
+    logging.basicConfig(level=log_level)
+
+    logging.info("============================INPUTS===================================")
+    logging.info(f"Namespace: {namespace}")
+    logging.info(f"Kubeconfig: {kubeconfig}")
+    logging.info(f"Prometheus endpoint: {prometheus_endpoint}")
+    logging.info(f"Scrape duration: {scrape_duration}")
+    for test in chaos_tests.keys():
+        logging.info(f"Chaos tests {test}: {chaos_tests[test]}")
+    logging.info("=====================================================================")
+    logging.info("Starting Analysis ...")
+    logging.info("Fetching the Telemetry data")
+
+    file_path = prometheus.fetch_utilization_from_prometheus(prometheus_endpoint, auth_token, namespace, scrape_duration)
+    analysis(file_path, chaos_tests)
+
+if __name__ == "__main__":
+    main()