apiVersion: argoproj.io/v1alpha1 kind: Workflow metadata: name: argowf-podtato-head-chaos namespace: litmus labels: subject : "podtato-main" spec: entrypoint: argowf-chaos serviceAccountName: argo-chaos securityContext: runAsUser: 1000 runAsNonRoot: true arguments: parameters: - name: adminModeNamespace value: "litmus" templates: - name: argowf-chaos steps: - - name: install-application template: install-application - - name: install-chaos-faults template: install-chaos-faults - - name: pod-delete template: pod-delete - - name: cleanup-chaos-resources template: cleanup-chaos-resources - name: delete-application template: delete-application - name: install-application container: image: litmuschaos/litmus-app-deployer:latest args: ["-namespace={{workflow.parameters.adminModeNamespace}}","-typeName=resilient","-operation=apply","-timeout=400", "-app=podtato-head","-scope=namespace"] - name: install-chaos-faults inputs: artifacts: - name: pod-delete-rm5 path: /tmp/pod-delete-rm5.yaml raw: data: | apiVersion: litmuschaos.io/v1alpha1 description: message: | Deletes a pod belonging to a deployment/statefulset/daemonset kind: ChaosExperiment metadata: name: pod-delete labels: name: pod-delete app.kubernetes.io/part-of: litmus app.kubernetes.io/component: chaosexperiment app.kubernetes.io/version: latest spec: definition: scope: Namespaced permissions: # Create and monitor the experiment & helper pods - apiGroups: [""] resources: ["pods"] verbs: [ "create", "delete", "get", "list", "patch", "update", "deletecollection", ] # Performs CRUD operations on the events inside chaosengine and chaosresult - apiGroups: [""] resources: ["events"] verbs: ["create", "get", "list", "patch", "update"] # Fetch configmaps details and mount it to the experiment pod (if specified) - apiGroups: [""] resources: ["configmaps"] verbs: ["get", "list"] # Track and get the runner, experiment, and helper pods log - apiGroups: [""] resources: ["pods/log"] verbs: ["get", "list", "watch"] # for creating and managing to execute commands inside target container - apiGroups: [""] resources: ["pods/exec"] verbs: ["get", "list", "create"] # deriving the parent/owner details of the pod(if parent is anyof {deployment, statefulset, daemonsets}) - apiGroups: ["apps"] resources: ["deployments", "statefulsets", "replicasets", "daemonsets"] verbs: ["list", "get"] # deriving the parent/owner details of the pod(if parent is deploymentConfig) - apiGroups: ["apps.openshift.io"] resources: ["deploymentconfigs"] verbs: ["list", "get"] # deriving the parent/owner details of the pod(if parent is deploymentConfig) - apiGroups: [""] resources: ["replicationcontrollers"] verbs: ["get", "list"] # deriving the parent/owner details of the pod(if parent is argo-rollouts) - apiGroups: ["argoproj.io"] resources: ["rollouts"] verbs: ["list", "get"] # for configuring and monitor the experiment job by the chaos-runner pod - apiGroups: ["batch"] resources: ["jobs"] verbs: ["create", "list", "get", "delete", "deletecollection"] # for creation, status polling and deletion of litmus chaos resources used within a chaos workflow - apiGroups: ["litmuschaos.io"] resources: ["chaosengines", "chaosexperiments", "chaosresults"] verbs: ["create", "list", "get", "patch", "update", "delete"] image: "litmuschaos.docker.scarf.sh/litmuschaos/go-runner:latest" imagePullPolicy: Always args: - -c - ./experiments -name pod-delete command: - /bin/bash env: - name: TOTAL_CHAOS_DURATION value: "15" # Period to wait before and after injection of chaos in sec - name: RAMP_TIME value: "" - name: FORCE value: "true" - name: CHAOS_INTERVAL value: "5" ## percentage of total pods to target - name: PODS_AFFECTED_PERC value: "" - name: TARGET_CONTAINER value: "" - name: TARGET_PODS value: "" - name: DEFAULT_HEALTH_CHECK value: "false" # To select pods on specific node(s) - name: NODE_LABEL value: "" ## it defines the sequence of chaos execution for multiple target pods ## supported values: serial, parallel - name: SEQUENCE value: "parallel" labels: name: pod-delete app.kubernetes.io/part-of: litmus app.kubernetes.io/component: experiment-job app.kubernetes.io/version: latest outputs: {} metadata: {} container: name: "" image: litmuschaos/k8s:latest command: - sh - "-c" args: - kubectl apply -f /tmp/pod-delete-rm5.yaml -n {{workflow.parameters.adminModeNamespace}} && sleep 30 resources: {} - name: pod-delete inputs: artifacts: - name: pod-delete path: /tmp/chaosengine.yaml raw: data: | apiVersion: litmuschaos.io/v1alpha1 kind: ChaosEngine metadata: name: podtato-main-pod-delete-chaos namespace: "{{workflow.parameters.adminModeNamespace}}" labels: context: "{{workflow.parameters.adminModeNamespace}}_podtato-main" annotations: {} spec: appinfo: appns: "{{workflow.parameters.adminModeNamespace}}" applabel: 'name=podtato-main' appkind: 'deployment' engineState: 'active' chaosServiceAccount: litmus-admin jobCleanUpPolicy: 'retain' components: runner: imagePullPolicy: Always experiments: - name: pod-delete spec: probe: - name: "check-podtato-main-access-url" type: "httpProbe" httpProbe/inputs: url: "http://podtato-main.{{workflow.parameters.adminModeNamespace}}.svc.cluster.local:9000" insecureSkipVerify: false method: get: criteria: "==" responseCode: "200" mode: "Continuous" runProperties: probeTimeout: 1s interval: 100ms attempt: 1 components: env: - name: TOTAL_CHAOS_DURATION value: '30' # set chaos interval (in sec) as desired - name: CHAOS_INTERVAL value: '10' # pod failures without '--force' & default terminationGracePeriodSeconds - name: FORCE value: 'false' container: image: litmuschaos/litmus-checker:latest args: ["-file=/tmp/chaosengine.yaml","-saveName=/tmp/engine-name"] - name: delete-application container: image: litmuschaos/litmus-app-deployer:latest args: ["-namespace={{workflow.parameters.adminModeNamespace}}","-typeName=resilient","-operation=delete","-app=podtato-head"] - name: cleanup-chaos-resources container: image: litmuschaos/k8s:latest command: [sh, -c] args: [ "kubectl delete chaosengine podtato-main-pod-delete-chaos -n {{workflow.parameters.adminModeNamespace}}", ]