apiVersion: argoproj.io/v1alpha1 kind: Workflow metadata: name: argowf-chaos-bank-of-anthos-resiliency namespace: litmus labels: subject: "bank-of-anthos" spec: entrypoint: argowf-chaos serviceAccountName: argo-chaos securityContext: runAsUser: 1000 runAsNonRoot: true arguments: parameters: - name: adminModeNamespace value: "litmus" - name: appNamespace value: "bank" templates: - name: argowf-chaos steps: - - name: install-application template: install-application - - name: install-chaos-faults template: install-chaos-faults - - name: pod-network-loss template: pod-network-loss - - 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=bank","-typeName=resilient","-operation=apply","-timeout=400", "-app=bank-of-anthos","-scope=cluster"] #for weak provide type flagName as resilient(-typeName=weak) - name: install-chaos-faults inputs: artifacts: - name: pod-network-loss-x1w path: /tmp/pod-network-loss-x1w.yaml raw: data: | apiVersion: litmuschaos.io/v1alpha1 description: message: | Injects network packet loss on pods belonging to an app deployment kind: ChaosExperiment metadata: name: pod-network-loss labels: name: pod-network-loss 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/go-runner:latest" imagePullPolicy: Always args: - -c - ./experiments -name pod-network-loss command: - /bin/bash env: - name: TARGET_CONTAINER value: "" # provide lib image - name: LIB_IMAGE value: "litmuschaos/go-runner:latest" - name: NETWORK_INTERFACE value: "eth0" - name: TC_IMAGE value: "gaiadocker/iproute2" - name: NETWORK_PACKET_LOSS_PERCENTAGE value: "100" #in PERCENTAGE - name: TOTAL_CHAOS_DURATION value: "60" # in seconds # time period to wait before and after injection of chaos in sec - name: RAMP_TIME value: "" ## percentage of total pods to target - name: PODS_AFFECTED_PERC value: "" - name: DEFAULT_HEALTH_CHECK value: "false" - name: TARGET_PODS value: "" # To select pods on specific node(s) - name: NODE_LABEL value: "" # provide the name of container runtime # for litmus LIB, it supports docker, containerd, crio # for pumba LIB, it supports docker only - name: CONTAINER_RUNTIME value: "containerd" # provide the destination ips # chaos injection will be triggered for these destination ips - name: DESTINATION_IPS value: "" # provide the destination hosts # chaos injection will be triggered for these destination hosts - name: DESTINATION_HOSTS value: "" # provide the socket file path - name: SOCKET_PATH value: "/run/containerd/containerd.sock" ## it defines the sequence of chaos execution for multiple target pods ## supported values: serial, parallel - name: SEQUENCE value: "parallel" labels: name: pod-network-loss app.kubernetes.io/part-of: litmus app.kubernetes.io/component: experiment-job app.kubernetes.io/runtime-api-usage: "true" app.kubernetes.io/version: latest outputs: {} metadata: {} container: name: "" image: litmuschaos/k8s:latest command: - sh - "-c" args: - kubectl apply -f /tmp/pod-network-loss-x1w.yaml -n {{workflow.parameters.adminModeNamespace}} && sleep 30 resources: {} - name: pod-network-loss inputs: artifacts: - name: pod-network-loss path: /tmp/chaosengine.yaml raw: data: | apiVersion: litmuschaos.io/v1alpha1 kind: ChaosEngine metadata: name: pod-network-loss-chaos namespace: "{{workflow.parameters.adminModeNamespace}}" labels: context: "{{workflow.parameters.appNamespace}}_bank-of-anthos" annotations: {} spec: appinfo: appns: 'bank' applabel: 'name=balancereader' appkind: 'deployment' jobCleanUpPolicy: retain engineState: 'active' chaosServiceAccount: litmus-admin components: runner: imagePullPolicy: Always experiments: - name: pod-network-loss spec: probe: - name: "check-frontend-access-url" type: "httpProbe" httpProbe/inputs: url: "http://frontend.bank.svc.cluster.local:80" responseTimeout: 100 method: get: criteria: "==" responseCode: "200" mode: "Continuous" runProperties: probeTimeout: 1s interval: 100ms attempt: 2 components: env: - name: TOTAL_CHAOS_DURATION value: '90' - name: NETWORK_INTERFACE value: 'eth0' - name: NETWORK_PACKET_LOSS_PERCENTAGE value: '100' - name: CONTAINER_RUNTIME value: 'containerd' - name: SOCKET_PATH value: '/run/containerd/containerd.sock' 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=bank","-typeName=resilient","-operation=delete", "-app=bank-of-anthos"] - name: cleanup-chaos-resources container: image: litmuschaos/k8s:latest command: [sh, -c] args: [ "kubectl delete chaosengine pod-network-loss-chaos -n {{workflow.parameters.adminModeNamespace}}", ]