diff --git a/charts/generic/experiments.yaml b/charts/generic/experiments.yaml index 814356c..43a1104 100644 --- a/charts/generic/experiments.yaml +++ b/charts/generic/experiments.yaml @@ -1,12 +1,12 @@ apiVersion: litmuschaos.io/v1alpha1 description: message: | - Injects network packet duplication on pods belonging to an app deployment + Deletes a pod belonging to a deployment/statefulset/daemonset kind: ChaosExperiment metadata: - name: pod-network-duplication + name: k8-service-kill labels: - name: pod-network-duplication + name: k8-service-kill app.kubernetes.io/part-of: litmus app.kubernetes.io/component: chaosexperiment app.kubernetes.io/version: latest @@ -14,69 +14,346 @@ spec: definition: scope: Namespaced permissions: - - apiGroups: - - "" - - "batch" - - "apps" - - "apps.openshift.io" - - "argoproj.io" - - "litmuschaos.io" - resources: - - "jobs" - - "pods" - - "pods/log" - - "replicationcontrollers" - - "deployments" - - "statefulsets" - - "daemonsets" - - "replicasets" - - "deploymentconfigs" - - "rollouts" - - "pods/exec" - - "events" - - "chaosengines" - - "chaosexperiments" - - "chaosresults" - verbs: - - "get" - - "list" - - "patch" - - "create" - - "update" - - "delete" - - "deletecollection" + - apiGroups: + - "" + - "apps" + - "batch" + - "litmuschaos.io" + resources: + - "deployments" + - "jobs" + - "pods" + - "configmaps" + - "chaosengines" + - "chaosexperiments" + - "chaosresults" + verbs: + - "create" + - "list" + - "get" + - "patch" + - "update" + - "delete" + - apiGroups: + - "" + resources: + - "nodes" + verbs : + - "get" + - "list" + labels: + name: k8-service-kill + app.kubernetes.io/part-of: litmus + image: "litmuschaos/chaostoolkit:latest" + args: + - -c + - python /app/chaos/chaostest/kubernetes/k8_wrapper.py; exit 0 + command: + - /bin/bash + env: + - name: CHAOSTOOLKIT_IN_POD + value: 'true' + + - name: FILE + value: 'service-app-kill-health.json' + + - name: NAME_SPACE + value: '' + + - name: LABEL_NAME + value: '' + + - name: APP_ENDPOINT + value: '' + + - name: PERCENTAGE + value: '50' + + - name: REPORT + value: 'true' + + - name: REPORT_ENDPOINT + value: 'none' + + - name: TEST_NAMESPACE + value: 'default' + + +--- +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: + - apiGroups: + - "" + - "apps" + - "apps.openshift.io" + - "argoproj.io" + - "batch" + - "litmuschaos.io" + resources: + - "deployments" + - "jobs" + - "pods" + - "pods/log" + - "replicationcontrollers" + - "deployments" + - "statefulsets" + - "daemonsets" + - "replicasets" + - "deploymentconfigs" + - "rollouts" + - "pods/exec" + - "events" + - "chaosengines" + - "chaosexperiments" + - "chaosresults" + verbs: + - "create" + - "list" + - "get" + - "patch" + - "update" + - "delete" + - "deletecollection" image: "litmuschaos/go-runner:latest" imagePullPolicy: Always args: - -c - - ./experiments -name pod-network-duplication + - ./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: LIB + value: 'litmus' + + - name: TARGET_PODS + 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 + +--- +apiVersion: litmuschaos.io/v1alpha1 +description: + message: | + Injects cpu consumption on pods belonging to an app deployment +kind: ChaosExperiment +metadata: + name: pod-cpu-hog + labels: + name: pod-cpu-hog + app.kubernetes.io/part-of: litmus + app.kubernetes.io/component: chaosexperiment + app.kubernetes.io/version: latest +spec: + definition: + scope: Namespaced + permissions: + - apiGroups: + - "" + - "batch" + - "apps" + - "apps.openshift.io" + - "argoproj.io" + - "litmuschaos.io" + resources: + - "jobs" + - "pods" + - "pods/log" + - "events" + - "replicationcontrollers" + - "deployments" + - "statefulsets" + - "daemonsets" + - "replicasets" + - "deploymentconfigs" + - "rollouts" + - "pods/exec" + - "chaosengines" + - "chaosexperiments" + - "chaosresults" + verbs: + - "create" + - "list" + - "get" + - "patch" + - "update" + - "delete" + - "deletecollection" + image: "litmuschaos/go-runner:latest" + imagePullPolicy: Always + args: + - -c + - ./experiments -name pod-cpu-hog command: - /bin/bash env: - name: TOTAL_CHAOS_DURATION value: '60' + ## Number of CPU cores to stress + - name: CPU_CORES + value: '1' + + ## Percentage of total pods to target + - name: PODS_AFFECTED_PERC + value: '' + + ## Period to wait before and after injection of chaos in sec - name: RAMP_TIME value: '' - - name: TARGET_CONTAINER - value: '' - - - name: TC_IMAGE - value: 'gaiadocker/iproute2' - - - name: NETWORK_INTERFACE - value: 'eth0' - - - name: NETWORK_PACKET_DUPLICATION_PERCENTAGE - value: '100' # in percentage - - # lib can be litmus or pumba + ## env var that describes the library used to execute the chaos + ## default: litmus. Supported values: litmus, pumba - name: LIB - value: 'litmus' + value: 'litmus' + + ## It is used in pumba lib only + - name: LIB_IMAGE + value: 'litmuschaos/go-runner:latest' + + ## It is used in pumba lib only + - name: STRESS_IMAGE + value: 'alexeiled/stress-ng:latest-ubuntu' + + # provide the socket file path + # it is used in pumba lib + - name: SOCKET_PATH + value: '/var/run/docker.sock' - name: TARGET_PODS - value: '' + value: '' + + ## it defines the sequence of chaos execution for multiple target pods + ## supported values: serial, parallel + - name: SEQUENCE + value: 'parallel' + + labels: + name: pod-cpu-hog + app.kubernetes.io/part-of: litmus + app.kubernetes.io/component: experiment-job + app.kubernetes.io/version: latest + +--- +apiVersion: litmuschaos.io/v1alpha1 +description: + message: | + Fillup Ephemeral Storage of a Resource +kind: ChaosExperiment +metadata: + name: disk-fill + labels: + name: disk-fill + app.kubernetes.io/part-of: litmus + app.kubernetes.io/component: chaosexperiment + app.kubernetes.io/version: latest +spec: + definition: + scope: Namespaced + permissions: + - apiGroups: + - "" + - "apps" + - "batch" + - "apps.openshift.io" + - "argoproj.io" + - "litmuschaos.io" + resources: + - "jobs" + - "pods" + - "pods/exec" + - "pods/log" + - "replicationcontrollers" + - "deployments" + - "statefulsets" + - "daemonsets" + - "replicasets" + - "deploymentconfigs" + - "rollouts" + - "events" + - "chaosengines" + - "chaosexperiments" + - "chaosresults" + verbs: + - "create" + - "list" + - "get" + - "patch" + - "update" + - "delete" + - "deletecollection" + image: "litmuschaos/go-runner:latest" + imagePullPolicy: Always + args: + - -c + - ./experiments -name disk-fill + command: + - /bin/bash + env: + + - name: TARGET_CONTAINER + value: '' + + - name: FILL_PERCENTAGE + value: '80' + + - name: TOTAL_CHAOS_DURATION + value: '60' + + # Period to wait before and after injection of chaos in sec + - name: RAMP_TIME + value: '' + + # Provide the LIB here + # Only litmus supported + - name: LIB + value: 'litmus' + + - name: TARGET_PODS + value: '' + + - name: EPHEMERAL_STORAGE_MEBIBYTES + value: '' ## percentage of total pods to target - name: PODS_AFFECTED_PERC @@ -85,25 +362,10 @@ spec: - name: LIB_IMAGE value: 'litmuschaos/go-runner:latest' - # 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: 'docker' - - # 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: '/var/run/docker.sock' + # Provide the container runtime path + # Default set to docker container path + - name: CONTAINER_PATH + value: '/var/lib/docker/containers' ## it defines the sequence of chaos execution for multiple target pods ## supported values: serial, parallel @@ -111,420 +373,7 @@ spec: value: 'parallel' labels: - name: pod-network-duplication - app.kubernetes.io/part-of: litmus - app.kubernetes.io/component: experiment-job - app.kubernetes.io/version: latest - ---- -apiVersion: litmuschaos.io/v1alpha1 -description: - message: | - Give a cpu spike on a node belonging to a deployment -kind: ChaosExperiment -metadata: - name: node-cpu-hog - labels: - name: node-cpu-hog - app.kubernetes.io/part-of: litmus - app.kubernetes.io/component: chaosexperiment - app.kubernetes.io/version: latest -spec: - definition: - scope: Cluster - permissions: - - apiGroups: - - "" - - "batch" - - "litmuschaos.io" - resources: - - "jobs" - - "pods" - - "pods/log" - - "pods/exec" - - "events" - - "chaosengines" - - "chaosexperiments" - - "chaosresults" - verbs: - - "create" - - "list" - - "get" - - "patch" - - "update" - - "delete" - - "deletecollection" - - apiGroups: - - "" - resources: - - "nodes" - verbs: - - "get" - - "list" - image: "litmuschaos/go-runner:latest" - imagePullPolicy: Always - args: - - -c - - ./experiments -name node-cpu-hog - command: - - /bin/bash - env: - - - name: TOTAL_CHAOS_DURATION - value: '60' - - # Period to wait before and after injection of chaos in sec - - name: RAMP_TIME - value: '' - - ## ENTER THE NUMBER OF CORES OF CPU FOR CPU HOGGING - ## OPTIONAL VALUE IN CASE OF EMPTY VALUE IT WILL TAKE NODE CPU CAPACITY - - name: NODE_CPU_CORE - value: '' - - # ENTER THE COMMA SEPARATED TARGET NODES NAME - - name: TARGET_NODES - value: '' - - # PROVIDE THE LIB HERE - # ONLY LITMUS SUPPORTED - - name: LIB - value: 'litmus' - - # provide lib image - - name: LIB_IMAGE - value: 'litmuschaos/go-runner:latest' - - ## percentage of total nodes to target - - name: NODES_AFFECTED_PERC - value: '' - - ## it defines the sequence of chaos execution for multiple target nodes - ## supported values: serial, parallel - - name: SEQUENCE - value: 'parallel' - - labels: - name: node-cpu-hog - app.kubernetes.io/part-of: litmus - app.kubernetes.io/component: experiment-job - app.kubernetes.io/version: latest - ---- ---- -apiVersion: litmuschaos.io/v1alpha1 -description: - message: | - Drain the node where application pod is scheduled -kind: ChaosExperiment -metadata: - name: node-drain - labels: - name: node-drain - app.kubernetes.io/part-of: litmus - app.kubernetes.io/component: chaosexperiment - app.kubernetes.io/version: latest -spec: - definition: - scope: Cluster - permissions: - - apiGroups: - - "" - - "batch" - - "litmuschaos.io" - - "apps" - resources: - - "jobs" - - "pods" - - "events" - - "pods/log" - - "pods/exec" - - "daemonsets" - - "pods/eviction" - - "chaosengines" - - "chaosexperiments" - - "chaosresults" - verbs: - - "create" - - "list" - - "get" - - "patch" - - "update" - - "delete" - - "deletecollection" - - apiGroups: - - "" - resources: - - "nodes" - verbs: - - "get" - - "list" - - "patch" - image: "litmuschaos/go-runner:latest" - imagePullPolicy: Always - args: - - -c - - ./experiments -name node-drain - command: - - /bin/bash - env: - - - name: TARGET_NODE - value: '' - - - name: TOTAL_CHAOS_DURATION - value: '60' - - # Provide the LIB here - # Only litmus supported - - name: LIB - value: 'litmus' - - # Period to wait before and after injection of chaos in sec - - name: RAMP_TIME - value: '' - - labels: - name: node-drain - app.kubernetes.io/part-of: litmus - app.kubernetes.io/component: experiment-job - app.kubernetes.io/version: latest - ---- -apiVersion: litmuschaos.io/v1alpha1 -description: - message: | - Kills the docker service on the application node to check the resiliency. -kind: ChaosExperiment -metadata: - name: docker-service-kill - labels: - name: docker-service-kill - app.kubernetes.io/part-of: litmus - app.kubernetes.io/component: chaosexperiment - app.kubernetes.io/version: latest -spec: - definition: - scope: Cluster - permissions: - - apiGroups: - - "" - - "batch" - - "apps" - - "litmuschaos.io" - resources: - - "jobs" - - "pods" - - "pods/log" - - "events" - - "chaosengines" - - "chaosexperiments" - - "chaosresults" - verbs: - - "create" - - "list" - - "get" - - "patch" - - "update" - - "delete" - - apiGroups: - - "" - resources: - - "nodes" - verbs: - - "get" - - "list" - image: "litmuschaos/ansible-runner:ci" - imagePullPolicy: Always - args: - - -c - - ansible-playbook ./experiments/generic/docker_service_kill/docker_service_kill_ansible_logic.yml -i /etc/ansible/hosts -vv; exit 0 - command: - - /bin/bash - env: - - name: ANSIBLE_STDOUT_CALLBACK - value: 'default' - - - name: TOTAL_CHAOS_DURATION - value: '90' # in seconds - - # Period to wait before injection of chaos in sec - - name: RAMP_TIME - value: '' - - - name: LIB - value: 'litmus' - labels: - name: docker-service-kill - app.kubernetes.io/part-of: litmus - app.kubernetes.io/component: experiment-job - app.kubernetes.io/version: latest - - ---- ---- -apiVersion: litmuschaos.io/v1alpha1 -description: - message: | - Taint the node where application pod is scheduled -kind: ChaosExperiment -metadata: - name: node-taint - labels: - name: node-taint - app.kubernetes.io/part-of: litmus - app.kubernetes.io/component: chaosexperiment - app.kubernetes.io/version: latest -spec: - definition: - scope: Cluster - permissions: - - apiGroups: - - "" - - "batch" - - "apps" - - "litmuschaos.io" - resources: - - "jobs" - - "pods" - - "events" - - "pods/log" - - "pods/exec" - - "daemonsets" - - "pods/eviction" - - "chaosengines" - - "chaosexperiments" - - "chaosresults" - verbs: - - "create" - - "list" - - "get" - - "patch" - - "update" - - "delete" - - "deletecollection" - - apiGroups: - - "" - resources: - - "nodes" - verbs: - - "get" - - "list" - - "patch" - - "update" - image: "litmuschaos/go-runner:latest" - imagePullPolicy: Always - args: - - -c - - ./experiments -name node-taint - command: - - /bin/bash - env: - - - name: TARGET_NODE - value: '' - - - name: TOTAL_CHAOS_DURATION - value: '60' - - # Provide the LIB here - # Only litmus supported - - name: LIB - value: 'litmus' - - # Period to wait before and after injection of chaos in sec - - name: RAMP_TIME - value: '' - - # set taint label & effect - # key=value:effect or key:effect - - name: TAINTS - value: '' - - labels: - name: node-taint - app.kubernetes.io/part-of: litmus - app.kubernetes.io/component: experiment-job - app.kubernetes.io/version: latest - ---- -apiVersion: litmuschaos.io/v1alpha1 -description: - message: | - Scale the application replicas and test the node autoscaling on cluster -kind: ChaosExperiment -metadata: - name: pod-autoscaler - labels: - name: pod-autoscaler - app.kubernetes.io/part-of: litmus - app.kubernetes.io/component: chaosexperiment - app.kubernetes.io/version: latest -spec: - definition: - scope: Cluster - permissions: - - apiGroups: - - "" - - "batch" - - "apps" - - "litmuschaos.io" - resources: - - "jobs" - - "pods" - - "pods/log" - - "pods/exec" - - "deployments" - - "statefulsets" - - "events" - - "chaosengines" - - "chaosexperiments" - - "chaosresults" - verbs: - - "create" - - "list" - - "get" - - "patch" - - "update" - - "delete" - - "deletecollection" - - apiGroups: - - "" - resources: - - "nodes" - verbs: - - "get" - - "list" - - "create" - - "patch" - - "update" - image: "litmuschaos/go-runner:latest" - imagePullPolicy: Always - args: - - -c - - ./experiments -name pod-autoscaler - command: - - /bin/bash - env: - - - name: TOTAL_CHAOS_DURATION - value: '60' - - # Period to wait before and after injection of chaos in sec - - name: RAMP_TIME - value: '' - - # Number of replicas to scale - - name: REPLICA_COUNT - value: '5' - - # PROVIDE THE LIB HERE - # ONLY LITMUS SUPPORTED - - name: LIB - value: 'litmus' - - labels: - name: pod-autoscaler + name: disk-fill app.kubernetes.io/part-of: litmus app.kubernetes.io/component: experiment-job app.kubernetes.io/version: latest @@ -655,12 +504,12 @@ spec: apiVersion: litmuschaos.io/v1alpha1 description: message: | - Give a memory hog on a node belonging to a deployment + Give a cpu spike on a node belonging to a deployment kind: ChaosExperiment metadata: - name: node-memory-hog + name: node-cpu-hog labels: - name: node-memory-hog + name: node-cpu-hog app.kubernetes.io/part-of: litmus app.kubernetes.io/component: chaosexperiment app.kubernetes.io/version: latest @@ -700,7 +549,721 @@ spec: imagePullPolicy: Always args: - -c - - ./experiments -name node-memory-hog + - ./experiments -name node-cpu-hog + command: + - /bin/bash + env: + + - name: TOTAL_CHAOS_DURATION + value: '60' + + # Period to wait before and after injection of chaos in sec + - name: RAMP_TIME + value: '' + + ## ENTER THE NUMBER OF CORES OF CPU FOR CPU HOGGING + ## OPTIONAL VALUE IN CASE OF EMPTY VALUE IT WILL TAKE NODE CPU CAPACITY + - name: NODE_CPU_CORE + value: '' + + # ENTER THE COMMA SEPARATED TARGET NODES NAME + - name: TARGET_NODES + value: '' + + # PROVIDE THE LIB HERE + # ONLY LITMUS SUPPORTED + - name: LIB + value: 'litmus' + + # provide lib image + - name: LIB_IMAGE + value: 'litmuschaos/go-runner:latest' + + ## percentage of total nodes to target + - name: NODES_AFFECTED_PERC + value: '' + + ## it defines the sequence of chaos execution for multiple target nodes + ## supported values: serial, parallel + - name: SEQUENCE + value: 'parallel' + + labels: + name: node-cpu-hog + app.kubernetes.io/part-of: litmus + app.kubernetes.io/component: experiment-job + app.kubernetes.io/version: latest + +--- +apiVersion: litmuschaos.io/v1alpha1 +description: + message: | + Deletes a pod belonging to a deployment/statefulset/daemonset +kind: ChaosExperiment +metadata: + name: k8-pod-delete + labels: + name: k8-pod-delete + app.kubernetes.io/part-of: litmus + app.kubernetes.io/component: chaosexperiment + app.kubernetes.io/version: latest +spec: + definition: + scope: Namespaced + permissions: + - apiGroups: + - "" + - "apps" + - "batch" + - "litmuschaos.io" + resources: + - "deployments" + - "jobs" + - "pods" + - "configmaps" + - "chaosengines" + - "chaosexperiments" + - "chaosresults" + verbs: + - "create" + - "list" + - "get" + - "patch" + - "update" + - "delete" + - apiGroups: + - "" + resources: + - "nodes" + verbs : + - "get" + - "list" + image: "litmuschaos/chaostoolkit:latest" + args: + - -c + - python /app/chaos/chaostest/kubernetes/k8_wrapper.py; exit 0 + command: + - /bin/bash + env: + - name: CHAOSTOOLKIT_IN_POD + value: 'true' + + - name: FILE + value: 'pod-app-kill-count.json' + + - name: NAME_SPACE + value: '' + + - name: LABEL_NAME + value: '' + + - name: APP_ENDPOINT + value: '' + + - name: PERCENTAGE + value: '50' + + - name: REPORT + value: 'true' + + - name: REPORT_ENDPOINT + value: 'none' + + - name: TEST_NAMESPACE + value: 'default' + + + labels: + name: k8-pod-delete + app.kubernetes.io/part-of: litmus + app.kubernetes.io/component: experiment-job + app.kubernetes.io/version: latest + +--- +--- +apiVersion: litmuschaos.io/v1alpha1 +description: + message: | + Drain the node where application pod is scheduled +kind: ChaosExperiment +metadata: + name: node-drain + labels: + name: node-drain + app.kubernetes.io/part-of: litmus + app.kubernetes.io/component: chaosexperiment + app.kubernetes.io/version: latest +spec: + definition: + scope: Cluster + permissions: + - apiGroups: + - "" + - "batch" + - "litmuschaos.io" + - "apps" + resources: + - "jobs" + - "pods" + - "events" + - "pods/log" + - "pods/exec" + - "daemonsets" + - "pods/eviction" + - "chaosengines" + - "chaosexperiments" + - "chaosresults" + verbs: + - "create" + - "list" + - "get" + - "patch" + - "update" + - "delete" + - "deletecollection" + - apiGroups: + - "" + resources: + - "nodes" + verbs: + - "get" + - "list" + - "patch" + image: "litmuschaos/go-runner:latest" + imagePullPolicy: Always + args: + - -c + - ./experiments -name node-drain + command: + - /bin/bash + env: + + - name: TARGET_NODE + value: '' + + - name: TOTAL_CHAOS_DURATION + value: '60' + + # Provide the LIB here + # Only litmus supported + - name: LIB + value: 'litmus' + + # Period to wait before and after injection of chaos in sec + - name: RAMP_TIME + value: '' + + labels: + name: node-drain + app.kubernetes.io/part-of: litmus + app.kubernetes.io/component: experiment-job + app.kubernetes.io/version: latest + +--- +apiVersion: litmuschaos.io/v1alpha1 +description: + message: | + Kills the kubelet service on the application node to check the resiliency. +kind: ChaosExperiment +metadata: + name: kubelet-service-kill + labels: + name: kubelet-service-kill + app.kubernetes.io/part-of: litmus + app.kubernetes.io/component: chaosexperiment + app.kubernetes.io/version: latest +spec: + definition: + scope: Cluster + permissions: + - apiGroups: + - "" + - "batch" + - "litmuschaos.io" + resources: + - "jobs" + - "pods" + - "pods/log" + - "pods/exec" + - "events" + - "chaosengines" + - "chaosexperiments" + - "chaosresults" + verbs: + - "create" + - "list" + - "get" + - "patch" + - "update" + - "delete" + - "deletecollection" + - apiGroups: + - "" + resources: + - "nodes" + verbs: + - "get" + - "list" + image: "litmuschaos/go-runner:latest" + imagePullPolicy: Always + args: + - -c + - ./experiments -name kubelet-service-kill + command: + - /bin/bash + env: + + - name: TOTAL_CHAOS_DURATION + value: '90' # in seconds + + # Period to wait before and after injection of chaos in sec + - name: RAMP_TIME + value: '' + + - name: LIB + value: 'litmus' + + # provide lib image + - name: LIB_IMAGE + value: 'ubuntu:16.04' + + # provide the target node name + - name: TARGET_NODE + value: '' + + labels: + name: kubelet-service-kill + app.kubernetes.io/part-of: litmus + app.kubernetes.io/component: experiment-job + app.kubernetes.io/version: latest + +--- +apiVersion: litmuschaos.io/v1alpha1 +description: + message: | + Restart node +kind: ChaosExperiment +metadata: + name: node-restart + labels: + name: node-restart + app.kubernetes.io/part-of: litmus + app.kubernetes.io/component: chaosexperiment + app.kubernetes.io/version: latest +spec: + definition: + scope: Cluster + permissions: + - apiGroups: + - "" + - "batch" + - "litmuschaos.io" + resources: + - "jobs" + - "pods" + - "pods/log" + - "pods/exec" + - "events" + - "chaosengines" + - "chaosexperiments" + - "chaosresults" + - "secrets" + verbs: + - "create" + - "list" + - "get" + - "patch" + - "update" + - "delete" + - "deletecollection" + - apiGroups: + - "" + resources: + - "nodes" + verbs: + - "get" + - "list" + image: "litmuschaos/go-runner:latest" + imagePullPolicy: Always + args: + - -c + - ./experiments -name node-restart + command: + - /bin/bash + env: + - name: SSH_USER + value: 'root' + + - name: TOTAL_CHAOS_DURATION + value: '60' + + # Period to wait before and after injection of chaos in sec + - name: RAMP_TIME + value: '' + + # PROVIDE THE LIB HERE + # ONLY LITMUS SUPPORTED + - name: LIB + value: 'litmus' + + # provide lib image + - name: LIB_IMAGE + value: "litmuschaos/go-runner:latest" + + # ENTER THE TARGET NODE NAME + - name: TARGET_NODE + value: '' + + # ENTER THE TARGET NODE IP + - name: TARGET_NODE_IP + value: '' + + labels: + name: node-restart + app.kubernetes.io/part-of: litmus + app.kubernetes.io/component: experiment-job + app.kubernetes.io/version: latest + secrets: + - name: id-rsa + mountPath: /mnt/ + +--- +apiVersion: litmuschaos.io/v1alpha1 +description: + message: | + injects dns failure in target pod container +kind: ChaosExperiment +metadata: + name: pod-dns-chaos + labels: + name: pod-dns-chaos + app.kubernetes.io/part-of: litmus + app.kubernetes.io/component: chaosexperiment + app.kubernetes.io/version: latest +spec: + definition: + scope: Namespaced + permissions: + - apiGroups: + - "" + - "batch" + - "apps" + - "apps.openshift.io" + - "argoproj.io" + - "litmuschaos.io" + resources: + - "jobs" + - "pods" + - "pods/log" + - "replicationcontrollers" + - "deployments" + - "statefulsets" + - "daemonsets" + - "replicasets" + - "deploymentconfigs" + - "rollouts" + - "pods/exec" + - "events" + - "chaosengines" + - "chaosexperiments" + - "chaosresults" + verbs: + - "create" + - "list" + - "get" + - "patch" + - "update" + - "delete" + - "deletecollection" + image: "litmuschaos/go-runner:latest" + args: + - -c + - ./experiments -name pod-dns-chaos + command: + - /bin/bash + env: + + - name: TARGET_CONTAINER + value: '' + + # provide lib image + - name: LIB_IMAGE + value: 'litmuschaos/go-runner:latest' + + - 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: TARGET_PODS + value: '' + + # provide the name of container runtime, it supports docker, containerd, crio + - name: CONTAINER_RUNTIME + value: 'docker' + + # provide the socket file path + - name: SOCKET_PATH + value: '/var/run/docker.sock' + + ## it defines the sequence of chaos execution for multiple target pods + ## supported values: serial, parallel + - name: SEQUENCE + value: 'parallel' + + # list of the target hostnames or kewywords eg. '["litmuschaos","chaosnative.io"]' . If empty all hostnames are targets + - name: TARGET_HOSTNAMES + value: '' + + # can be either exact or substring, determines whether the dns query has to match exactly with one of the targets or can have any of the targets as substring + - name: MATCH_SCHEME + value: 'exact' + + # currently only error chaos is supported + - name: CHAOS_TYPE + value: 'error' + + labels: + experiment: pod-dns-chaos + app.kubernetes.io/part-of: litmus + app.kubernetes.io/component: experiment-job + app.kubernetes.io/version: latest + + +--- +apiVersion: litmuschaos.io/v1alpha1 +description: + message: | + Scale the application replicas and test the node autoscaling on cluster +kind: ChaosExperiment +metadata: + name: pod-autoscaler + labels: + name: pod-autoscaler + app.kubernetes.io/part-of: litmus + app.kubernetes.io/component: chaosexperiment + app.kubernetes.io/version: latest +spec: + definition: + scope: Cluster + permissions: + - apiGroups: + - "" + - "batch" + - "apps" + - "litmuschaos.io" + resources: + - "jobs" + - "pods" + - "pods/log" + - "pods/exec" + - "deployments" + - "statefulsets" + - "events" + - "chaosengines" + - "chaosexperiments" + - "chaosresults" + verbs: + - "create" + - "list" + - "get" + - "patch" + - "update" + - "delete" + - "deletecollection" + - apiGroups: + - "" + resources: + - "nodes" + verbs: + - "get" + - "list" + - "create" + - "patch" + - "update" + image: "litmuschaos/go-runner:latest" + imagePullPolicy: Always + args: + - -c + - ./experiments -name pod-autoscaler + command: + - /bin/bash + env: + + - name: TOTAL_CHAOS_DURATION + value: '60' + + # Period to wait before and after injection of chaos in sec + - name: RAMP_TIME + value: '' + + # Number of replicas to scale + - name: REPLICA_COUNT + value: '5' + + # PROVIDE THE LIB HERE + # ONLY LITMUS SUPPORTED + - name: LIB + value: 'litmus' + + labels: + name: pod-autoscaler + app.kubernetes.io/part-of: litmus + app.kubernetes.io/component: experiment-job + app.kubernetes.io/version: latest + +--- +apiVersion: litmuschaos.io/v1alpha1 +description: + message: | + poweroff node +kind: ChaosExperiment +metadata: + name: node-poweroff + labels: + name: node-poweroff + app.kubernetes.io/part-of: litmus + app.kubernetes.io/component: chaosexperiment + app.kubernetes.io/version: latest +spec: + definition: + scope: Cluster + permissions: + - apiGroups: + - "" + - "batch" + - "litmuschaos.io" + resources: + - "jobs" + - "pods" + - "pods/log" + - "pods/exec" + - "events" + - "chaosengines" + - "chaosexperiments" + - "chaosresults" + - "secrets" + verbs: + - "create" + - "list" + - "get" + - "patch" + - "update" + - "delete" + - "deletecollection" + - apiGroups: + - "" + resources: + - "nodes" + verbs: + - "get" + - "list" + image: "litmuschaos/go-runner:latest" + imagePullPolicy: Always + args: + - -c + - ./experiments -name node-restart + command: + - /bin/bash + env: + - name: SSH_USER + value: 'root' + + - name: TOTAL_CHAOS_DURATION + value: '360' + + - name: EXPERIMENT_NAME + value: 'node-poweroff' + + - name: REBOOT_COMMAND + value: '-o ServerAliveInterval=1 -o ServerAliveCountMax=1 "sudo systemctl poweroff --force --force" ; true' + + # Period to wait before and after injection of chaos in sec + - name: RAMP_TIME + value: '' + + # PROVIDE THE LIB HERE + # ONLY LITMUS SUPPORTED + - name: LIB + value: 'litmus' + + # provide lib image + - name: LIB_IMAGE + value: "litmuschaos/go-runner:latest" + + # ENTER THE TARGET NODE NAME + - name: TARGET_NODE + value: '' + + # ENTER THE TARGET NODE IP + - name: TARGET_NODE_IP + value: '' + + labels: + name: node-poweroff + app.kubernetes.io/part-of: litmus + app.kubernetes.io/component: experiment-job + app.kubernetes.io/version: latest + secrets: + - name: id-rsa + mountPath: /mnt/ + +--- +apiVersion: litmuschaos.io/v1alpha1 +description: + message: | + Give IO disk stress on a node belonging to a deployment +kind: ChaosExperiment +metadata: + name: node-io-stress + labels: + name: node-io-stress + app.kubernetes.io/part-of: litmus + app.kubernetes.io/component: chaosexperiment + app.kubernetes.io/version: latest +spec: + definition: + scope: Cluster + permissions: + - apiGroups: + - "" + - "batch" + - "litmuschaos.io" + resources: + - "jobs" + - "pods" + - "pods/log" + - "pods/exec" + - "events" + - "chaosengines" + - "chaosexperiments" + - "chaosresults" + verbs: + - "create" + - "list" + - "get" + - "patch" + - "update" + - "delete" + - "deletecollection" + - apiGroups: + - "" + resources: + - "nodes" + verbs: + - "get" + - "list" + image: "litmuschaos/go-runner:latest" + imagePullPolicy: Always + args: + - -c + - ./experiments -name node-io-stress command: - /bin/bash env: @@ -708,20 +1271,29 @@ spec: - name: TOTAL_CHAOS_DURATION value: '120' - ## Specify the size as percent of total node capacity Ex: '30' - ## NOTE: for selecting this option keep MEMORY_CONSUMPTION_MEBIBYTES empty - - name: MEMORY_CONSUMPTION_PERCENTAGE - value: '' - - ## Specify the amount of memory to be consumed in mebibytes - ## NOTE: for selecting this option keep MEMORY_CONSUMPTION_PERCENTAGE empty - - name: MEMORY_CONSUMPTION_MEBIBYTES + ## specify the size as percentage of free space on the file system + ## default value 90 (in percentage) + - name: FILESYSTEM_UTILIZATION_PERCENTAGE + value: '10' + + ## we can specify the size in Gigabyte (Gb) also in place of percentage of free space + ## NOTE: for selecting this option FILESYSTEM_UTILIZATION_PERCENTAGE should be empty + - name: FILESYSTEM_UTILIZATION_BYTES value: '' + ## Number of core of CPU + - name: CPU + value: '1' + + ## Total number of workers default value is 4 - name: NUMBER_OF_WORKERS + value: '4' + + ## Total number of vm workers + - name: VM_WORKERS value: '1' - # ENTER THE COMMA SEPARATED TARGET NODES NAME + ## enter the comma separated target nodes name - name: TARGET_NODES value: '' @@ -748,113 +1320,22 @@ spec: value: 'parallel' labels: - name: node-memory-hog + name: node-io-stress app.kubernetes.io/part-of: litmus app.kubernetes.io/component: experiment-job app.kubernetes.io/version: latest ---- -apiVersion: litmuschaos.io/v1alpha1 -description: - message: | - Detaching a persistent disk from a node/instance. Supports only for AWS and GCP -kind: ChaosExperiment -metadata: - name: disk-loss - labels: - name: disk-loss - app.kubernetes.io/part-of: litmus - app.kubernetes.io/component: chaosexperiment - app.kubernetes.io/version: latest -spec: - definition: - scope: Cluster - permissions: - - apiGroups: - - "" - - "batch" - - "litmuschaos.io" - resources: - - "jobs" - - "pods" - - "events" - - "pods/log" - - "secrets" - - "chaosengines" - - "chaosexperiments" - - "chaosresults" - verbs: - - "create" - - "list" - - "get" - - "patch" - - "update" - - "delete" - image: "litmuschaos/ansible-runner:latest" - imagePullPolicy: Always - args: - - -c - - ansible-playbook ./experiments/generic/disk_loss/disk_loss_ansible_logic.yml -i /etc/ansible/hosts -vv; exit 0 - command: - - /bin/bash - env: - - name: ANSIBLE_STDOUT_CALLBACK - value: 'default' - - - name: TOTAL_CHAOS_DURATION - value: '15' - - # Period to wait before and after injection of chaos in sec - - name: RAMP_TIME - value: '' - - - name: APP_CHECK - value: 'true' - - # GKE and AWS supported - - name: CLOUD_PLATFORM - value: 'GKE' - - - name: PROJECT_ID - value: '' - - - name: NODE_NAME - value: '' - - - name: DISK_NAME - value: '' - - # provide the LIB - # only litmus supported - - name: LIB - value: 'litmus' - - - name: ZONE_NAME - value: '' - - - name: DEVICE_NAME - value: '' - - labels: - name: disk-loss - app.kubernetes.io/part-of: litmus - app.kubernetes.io/component: experiment-job - app.kubernetes.io/version: latest - secrets: - - name: cloud-secret - mountPath: /tmp/ - --- --- apiVersion: litmuschaos.io/v1alpha1 description: message: | - IO stress on a app pods belonging to an app deployment + Injects memory consumption on pods belonging to an app deployment kind: ChaosExperiment metadata: - name: pod-io-stress + name: pod-memory-hog labels: - name: pod-io-stress + name: pod-memory-hog app.kubernetes.io/part-of: litmus app.kubernetes.io/component: chaosexperiment app.kubernetes.io/version: latest @@ -897,64 +1378,248 @@ spec: imagePullPolicy: Always args: - -c - - ./experiments -name pod-io-stress + - ./experiments -name pod-memory-hog command: - /bin/bash env: - name: TOTAL_CHAOS_DURATION - value: '120' + value: '60' - ## specify the size as percentage of free space on the file system - ## default value 90 (in percentage) - - name: FILESYSTEM_UTILIZATION_PERCENTAGE - value: '10' + ## enter the amount of memory in megabytes to be consumed by the application pod + - name: MEMORY_CONSUMPTION + value: '500' - ## we can specify the size in Gigabyte (Gb) also in place of percentage of free space - ## NOTE: for selecting this option FILESYSTEM_UTILIZATION_PERCENTAGE should be empty - - name: FILESYSTEM_UTILIZATION_BYTES - value: '' - - ## Total number of workers default value is 4 - - name: NUMBER_OF_WORKERS - value: '4' - - ## Percentage of total pods to target + ## percentage of total pods to target - name: PODS_AFFECTED_PERC - value: '' - - # provide volume mount path - - name: VOLUME_MOUNT_PATH value: '' - ## specify the comma separated target pods - - name: TARGET_PODS - value: '' - - # Period to wait before and after injection of chaos in sec + ## Period to wait before and after injection of chaos in sec - name: RAMP_TIME - value: '' + value: '' - # Provide the LIB here - # Only pumba supported + ## env var that describes the library used to execute the chaos + ## default: litmus. Supported values: litmus, pumba - name: LIB - value: 'pumba' + value: 'litmus' - # provide lib image + ## It is used in pumba lib only - name: LIB_IMAGE value: 'litmuschaos/go-runner:latest' + ## It is used in pumba lib only + - name: STRESS_IMAGE + value: 'alexeiled/stress-ng:latest-ubuntu' + # provide the socket file path # it is used in pumba lib - name: SOCKET_PATH - value: '/var/run/docker.sock' - + value: '/var/run/docker.sock' + ## it defines the sequence of chaos execution for multiple target pods ## supported values: serial, parallel - name: SEQUENCE value: 'parallel' + - name: TARGET_PODS + value: '' + labels: - name: pod-io-stress + name: pod-memory-hog + app.kubernetes.io/part-of: litmus + app.kubernetes.io/component: experiment-job + app.kubernetes.io/version: latest + +--- +--- +apiVersion: litmuschaos.io/v1alpha1 +description: + message: | + Taint the node where application pod is scheduled +kind: ChaosExperiment +metadata: + name: node-taint + labels: + name: node-taint + app.kubernetes.io/part-of: litmus + app.kubernetes.io/component: chaosexperiment + app.kubernetes.io/version: latest +spec: + definition: + scope: Cluster + permissions: + - apiGroups: + - "" + - "batch" + - "apps" + - "litmuschaos.io" + resources: + - "jobs" + - "pods" + - "events" + - "pods/log" + - "pods/exec" + - "daemonsets" + - "pods/eviction" + - "chaosengines" + - "chaosexperiments" + - "chaosresults" + verbs: + - "create" + - "list" + - "get" + - "patch" + - "update" + - "delete" + - "deletecollection" + - apiGroups: + - "" + resources: + - "nodes" + verbs: + - "get" + - "list" + - "patch" + - "update" + image: "litmuschaos/go-runner:latest" + imagePullPolicy: Always + args: + - -c + - ./experiments -name node-taint + command: + - /bin/bash + env: + + - name: TARGET_NODE + value: '' + + - name: TOTAL_CHAOS_DURATION + value: '60' + + # Provide the LIB here + # Only litmus supported + - name: LIB + value: 'litmus' + + # Period to wait before and after injection of chaos in sec + - name: RAMP_TIME + value: '' + + # set taint label & effect + # key=value:effect or key:effect + - name: TAINTS + value: '' + + labels: + name: node-taint + app.kubernetes.io/part-of: litmus + app.kubernetes.io/component: experiment-job + app.kubernetes.io/version: latest + +--- +apiVersion: litmuschaos.io/v1alpha1 +description: + message: "Kills a container belonging to an application pod \n" +kind: ChaosExperiment +metadata: + name: container-kill + labels: + name: container-kill + app.kubernetes.io/part-of: litmus + app.kubernetes.io/component: chaosexperiment + app.kubernetes.io/version: latest +spec: + definition: + scope: Namespaced + permissions: + - apiGroups: + - "" + - "apps" + - "batch" + - "apps.openshift.io" + - "argoproj.io" + - "litmuschaos.io" + resources: + - "jobs" + - "pods" + - "pods/log" + - "events" + - "replicationcontrollers" + - "deployments" + - "statefulsets" + - "daemonsets" + - "replicasets" + - "deploymentconfigs" + - "rollouts" + - "pods/exec" + - "chaosengines" + - "chaosexperiments" + - "chaosresults" + verbs: + - "create" + - "list" + - "get" + - "update" + - "patch" + - "delete" + - "deletecollection" + image: "litmuschaos/go-runner:latest" + imagePullPolicy: Always + args: + - -c + - ./experiments -name container-kill + command: + - /bin/bash + env: + + - name: TARGET_CONTAINER + value: '' + + # Period to wait before and after injection of chaos in sec + - name: RAMP_TIME + value: '' + + # lib can be litmus or pumba + - name: LIB + value: 'litmus' + + - name: TARGET_PODS + value: '' + + # provide the chaos interval + - name: CHAOS_INTERVAL + value: '10' + + - name: SIGNAL + value: 'SIGKILL' + + # provide the socket file path + - name: SOCKET_PATH + value: '/var/run/docker.sock' + + # 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: 'docker' + + # provide the total chaos duration + - name: TOTAL_CHAOS_DURATION + value: '20' + + ## percentage of total pods to target + - name: PODS_AFFECTED_PERC + value: '' + + - name: LIB_IMAGE + value: 'litmuschaos/go-runner:latest' + + ## it defines the sequence of chaos execution for multiple target pods + ## supported values: serial, parallel + - name: SEQUENCE + value: 'parallel' + + labels: + name: container-kill app.kubernetes.io/part-of: litmus app.kubernetes.io/component: experiment-job app.kubernetes.io/version: latest @@ -1084,12 +1749,85 @@ spec: --- apiVersion: litmuschaos.io/v1alpha1 description: - message: "Kills a container belonging to an application pod \n" + message: | + Kills the docker service on the application node to check the resiliency. kind: ChaosExperiment metadata: - name: container-kill + name: docker-service-kill labels: - name: container-kill + name: docker-service-kill + app.kubernetes.io/part-of: litmus + app.kubernetes.io/component: chaosexperiment + app.kubernetes.io/version: latest +spec: + definition: + scope: Cluster + permissions: + - apiGroups: + - "" + - "batch" + - "apps" + - "litmuschaos.io" + resources: + - "jobs" + - "pods" + - "pods/log" + - "events" + - "chaosengines" + - "chaosexperiments" + - "chaosresults" + verbs: + - "create" + - "list" + - "get" + - "patch" + - "update" + - "delete" + - apiGroups: + - "" + resources: + - "nodes" + verbs: + - "get" + - "list" + image: "litmuschaos/ansible-runner:ci" + imagePullPolicy: Always + args: + - -c + - ansible-playbook ./experiments/generic/docker_service_kill/docker_service_kill_ansible_logic.yml -i /etc/ansible/hosts -vv; exit 0 + command: + - /bin/bash + env: + - name: ANSIBLE_STDOUT_CALLBACK + value: 'default' + + - name: TOTAL_CHAOS_DURATION + value: '90' # in seconds + + # Period to wait before injection of chaos in sec + - name: RAMP_TIME + value: '' + + - name: LIB + value: 'litmus' + labels: + name: docker-service-kill + app.kubernetes.io/part-of: litmus + app.kubernetes.io/component: experiment-job + app.kubernetes.io/version: latest + + +--- +--- +apiVersion: litmuschaos.io/v1alpha1 +description: + message: | + IO stress on a app pods belonging to an app deployment +kind: ChaosExperiment +metadata: + name: pod-io-stress + labels: + name: pod-io-stress app.kubernetes.io/part-of: litmus app.kubernetes.io/component: chaosexperiment app.kubernetes.io/version: latest @@ -1099,8 +1837,8 @@ spec: permissions: - apiGroups: - "" - - "apps" - "batch" + - "apps" - "apps.openshift.io" - "argoproj.io" - "litmuschaos.io" @@ -1108,7 +1846,6 @@ spec: - "jobs" - "pods" - "pods/log" - - "events" - "replicationcontrollers" - "deployments" - "statefulsets" @@ -1117,6 +1854,7 @@ spec: - "deploymentconfigs" - "rollouts" - "pods/exec" + - "events" - "chaosengines" - "chaosexperiments" - "chaosresults" @@ -1124,68 +1862,72 @@ spec: - "create" - "list" - "get" - - "update" - "patch" + - "update" - "delete" - "deletecollection" image: "litmuschaos/go-runner:latest" imagePullPolicy: Always args: - -c - - ./experiments -name container-kill + - ./experiments -name pod-io-stress command: - /bin/bash env: + - name: TOTAL_CHAOS_DURATION + value: '120' - - name: TARGET_CONTAINER - value: '' + ## specify the size as percentage of free space on the file system + ## default value 90 (in percentage) + - name: FILESYSTEM_UTILIZATION_PERCENTAGE + value: '10' - # Period to wait before and after injection of chaos in sec - - name: RAMP_TIME - value: '' + ## we can specify the size in Gigabyte (Gb) also in place of percentage of free space + ## NOTE: for selecting this option FILESYSTEM_UTILIZATION_PERCENTAGE should be empty + - name: FILESYSTEM_UTILIZATION_BYTES + value: '' - # lib can be litmus or pumba - - name: LIB - value: 'litmus' - - - name: TARGET_PODS - value: '' + ## Total number of workers default value is 4 + - name: NUMBER_OF_WORKERS + value: '4' - # provide the chaos interval - - name: CHAOS_INTERVAL - value: '10' + ## Percentage of total pods to target + - name: PODS_AFFECTED_PERC + value: '' - - name: SIGNAL - value: 'SIGKILL' + # provide volume mount path + - name: VOLUME_MOUNT_PATH + value: '' - # provide the socket file path - - name: SOCKET_PATH - value: '/var/run/docker.sock' + ## specify the comma separated target pods + - name: TARGET_PODS + 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: 'docker' + # Period to wait before and after injection of chaos in sec + - name: RAMP_TIME + value: '' - # provide the total chaos duration - - name: TOTAL_CHAOS_DURATION - value: '20' - - ## percentage of total pods to target - - name: PODS_AFFECTED_PERC - value: '' + # Provide the LIB here + # Only pumba supported + - name: LIB + value: 'pumba' - - name: LIB_IMAGE - value: 'litmuschaos/go-runner:latest' + # provide lib image + - name: LIB_IMAGE + value: 'litmuschaos/go-runner:latest' - ## it defines the sequence of chaos execution for multiple target pods - ## supported values: serial, parallel - - name: SEQUENCE - value: 'parallel' + # provide the socket file path + # it is used in pumba lib + - name: SOCKET_PATH + value: '/var/run/docker.sock' + + ## it defines the sequence of chaos execution for multiple target pods + ## supported values: serial, parallel + - name: SEQUENCE + value: 'parallel' labels: - name: container-kill + name: pod-io-stress app.kubernetes.io/part-of: litmus app.kubernetes.io/component: experiment-job app.kubernetes.io/version: latest @@ -1194,12 +1936,12 @@ spec: apiVersion: litmuschaos.io/v1alpha1 description: message: | - Restart node + Detaching a persistent disk from a node/instance. Supports only for AWS and GCP kind: ChaosExperiment metadata: - name: node-restart + name: disk-loss labels: - name: node-restart + name: disk-loss app.kubernetes.io/part-of: litmus app.kubernetes.io/component: chaosexperiment app.kubernetes.io/version: latest @@ -1214,13 +1956,12 @@ spec: resources: - "jobs" - "pods" - - "pods/log" - - "pods/exec" - "events" + - "pods/log" + - "secrets" - "chaosengines" - "chaosexperiments" - "chaosresults" - - "secrets" verbs: - "create" - "list" @@ -1228,375 +1969,59 @@ spec: - "patch" - "update" - "delete" - - "deletecollection" - - apiGroups: - - "" - resources: - - "nodes" - verbs: - - "get" - - "list" - image: "litmuschaos/go-runner:latest" + image: "litmuschaos/ansible-runner:latest" imagePullPolicy: Always args: - -c - - ./experiments -name node-restart + - ansible-playbook ./experiments/generic/disk_loss/disk_loss_ansible_logic.yml -i /etc/ansible/hosts -vv; exit 0 command: - /bin/bash env: - - name: SSH_USER - value: 'root' + - name: ANSIBLE_STDOUT_CALLBACK + value: 'default' - name: TOTAL_CHAOS_DURATION - value: '60' + value: '15' # Period to wait before and after injection of chaos in sec - name: RAMP_TIME value: '' - # PROVIDE THE LIB HERE - # ONLY LITMUS SUPPORTED + - name: APP_CHECK + value: 'true' + + # GKE and AWS supported + - name: CLOUD_PLATFORM + value: 'GKE' + + - name: PROJECT_ID + value: '' + + - name: NODE_NAME + value: '' + + - name: DISK_NAME + value: '' + + # provide the LIB + # only litmus supported - name: LIB - value: 'litmus' - - # provide lib image - - name: LIB_IMAGE - value: "litmuschaos/go-runner:latest" - - # ENTER THE TARGET NODE NAME - - name: TARGET_NODE - value: '' - - # ENTER THE TARGET NODE IP - - name: TARGET_NODE_IP - value: '' + value: 'litmus' + + - name: ZONE_NAME + value: '' + - name: DEVICE_NAME + value: '' + labels: - name: node-restart + name: disk-loss app.kubernetes.io/part-of: litmus app.kubernetes.io/component: experiment-job app.kubernetes.io/version: latest secrets: - - name: id-rsa - mountPath: /mnt/ - ---- -apiVersion: litmuschaos.io/v1alpha1 -description: - message: | - Give IO disk stress on a node belonging to a deployment -kind: ChaosExperiment -metadata: - name: node-io-stress - labels: - name: node-io-stress - app.kubernetes.io/part-of: litmus - app.kubernetes.io/component: chaosexperiment - app.kubernetes.io/version: latest -spec: - definition: - scope: Cluster - permissions: - - apiGroups: - - "" - - "batch" - - "litmuschaos.io" - resources: - - "jobs" - - "pods" - - "pods/log" - - "pods/exec" - - "events" - - "chaosengines" - - "chaosexperiments" - - "chaosresults" - verbs: - - "create" - - "list" - - "get" - - "patch" - - "update" - - "delete" - - "deletecollection" - - apiGroups: - - "" - resources: - - "nodes" - verbs: - - "get" - - "list" - image: "litmuschaos/go-runner:latest" - imagePullPolicy: Always - args: - - -c - - ./experiments -name node-io-stress - command: - - /bin/bash - env: - - - name: TOTAL_CHAOS_DURATION - value: '120' - - ## specify the size as percentage of free space on the file system - ## default value 90 (in percentage) - - name: FILESYSTEM_UTILIZATION_PERCENTAGE - value: '10' - - ## we can specify the size in Gigabyte (Gb) also in place of percentage of free space - ## NOTE: for selecting this option FILESYSTEM_UTILIZATION_PERCENTAGE should be empty - - name: FILESYSTEM_UTILIZATION_BYTES - value: '' - - ## Number of core of CPU - - name: CPU - value: '1' - - ## Total number of workers default value is 4 - - name: NUMBER_OF_WORKERS - value: '4' - - ## Total number of vm workers - - name: VM_WORKERS - value: '1' - - ## enter the comma separated target nodes name - - name: TARGET_NODES - value: '' - - # Period to wait before and after injection of chaos in sec - - name: RAMP_TIME - value: '' - - # Provide the LIB here - # Only litmus supported - - name: LIB - value: 'litmus' - - # provide lib image - - name: LIB_IMAGE - value: 'litmuschaos/go-runner:latest' - - ## percentage of total nodes to target - - name: NODES_AFFECTED_PERC - value: '' - - ## it defines the sequence of chaos execution for multiple target nodes - ## supported values: serial, parallel - - name: SEQUENCE - value: 'parallel' - - labels: - name: node-io-stress - app.kubernetes.io/part-of: litmus - app.kubernetes.io/component: experiment-job - app.kubernetes.io/version: latest - ---- -apiVersion: litmuschaos.io/v1alpha1 -description: - message: | - Fillup Ephemeral Storage of a Resource -kind: ChaosExperiment -metadata: - name: disk-fill - labels: - name: disk-fill - app.kubernetes.io/part-of: litmus - app.kubernetes.io/component: chaosexperiment - app.kubernetes.io/version: latest -spec: - definition: - scope: Namespaced - permissions: - - apiGroups: - - "" - - "apps" - - "batch" - - "apps.openshift.io" - - "argoproj.io" - - "litmuschaos.io" - resources: - - "jobs" - - "pods" - - "pods/exec" - - "pods/log" - - "replicationcontrollers" - - "deployments" - - "statefulsets" - - "daemonsets" - - "replicasets" - - "deploymentconfigs" - - "rollouts" - - "events" - - "chaosengines" - - "chaosexperiments" - - "chaosresults" - verbs: - - "create" - - "list" - - "get" - - "patch" - - "update" - - "delete" - - "deletecollection" - image: "litmuschaos/go-runner:latest" - imagePullPolicy: Always - args: - - -c - - ./experiments -name disk-fill - command: - - /bin/bash - env: - - - name: TARGET_CONTAINER - value: '' - - - name: FILL_PERCENTAGE - value: '80' - - - name: TOTAL_CHAOS_DURATION - value: '60' - - # Period to wait before and after injection of chaos in sec - - name: RAMP_TIME - value: '' - - # Provide the LIB here - # Only litmus supported - - name: LIB - value: 'litmus' - - - name: TARGET_PODS - value: '' - - - name: EPHEMERAL_STORAGE_MEBIBYTES - value: '' - - ## percentage of total pods to target - - name: PODS_AFFECTED_PERC - value: '' - - - name: LIB_IMAGE - value: 'litmuschaos/go-runner:latest' - - # Provide the container runtime path - # Default set to docker container path - - name: CONTAINER_PATH - value: '/var/lib/docker/containers' - - ## it defines the sequence of chaos execution for multiple target pods - ## supported values: serial, parallel - - name: SEQUENCE - value: 'parallel' - - labels: - name: disk-fill - app.kubernetes.io/part-of: litmus - app.kubernetes.io/component: experiment-job - app.kubernetes.io/version: latest - ---- -apiVersion: litmuschaos.io/v1alpha1 -description: - message: | - Injects cpu consumption on pods belonging to an app deployment -kind: ChaosExperiment -metadata: - name: pod-cpu-hog - labels: - name: pod-cpu-hog - app.kubernetes.io/part-of: litmus - app.kubernetes.io/component: chaosexperiment - app.kubernetes.io/version: latest -spec: - definition: - scope: Namespaced - permissions: - - apiGroups: - - "" - - "batch" - - "apps" - - "apps.openshift.io" - - "argoproj.io" - - "litmuschaos.io" - resources: - - "jobs" - - "pods" - - "pods/log" - - "events" - - "replicationcontrollers" - - "deployments" - - "statefulsets" - - "daemonsets" - - "replicasets" - - "deploymentconfigs" - - "rollouts" - - "pods/exec" - - "chaosengines" - - "chaosexperiments" - - "chaosresults" - verbs: - - "create" - - "list" - - "get" - - "patch" - - "update" - - "delete" - - "deletecollection" - image: "litmuschaos/go-runner:latest" - imagePullPolicy: Always - args: - - -c - - ./experiments -name pod-cpu-hog - command: - - /bin/bash - env: - - name: TOTAL_CHAOS_DURATION - value: '60' - - ## Number of CPU cores to stress - - name: CPU_CORES - value: '1' - - ## Percentage of total pods to target - - name: PODS_AFFECTED_PERC - value: '' - - ## Period to wait before and after injection of chaos in sec - - name: RAMP_TIME - value: '' - - ## env var that describes the library used to execute the chaos - ## default: litmus. Supported values: litmus, pumba - - name: LIB - value: 'litmus' - - ## It is used in pumba lib only - - name: LIB_IMAGE - value: 'litmuschaos/go-runner:latest' - - ## It is used in pumba lib only - - name: STRESS_IMAGE - value: 'alexeiled/stress-ng:latest-ubuntu' - - # provide the socket file path - # it is used in pumba lib - - name: SOCKET_PATH - value: '/var/run/docker.sock' - - - name: TARGET_PODS - value: '' - - ## it defines the sequence of chaos execution for multiple target pods - ## supported values: serial, parallel - - name: SEQUENCE - value: 'parallel' - - labels: - name: pod-cpu-hog - app.kubernetes.io/part-of: litmus - app.kubernetes.io/component: experiment-job - app.kubernetes.io/version: latest + - name: cloud-secret + mountPath: /tmp/ --- apiVersion: litmuschaos.io/v1alpha1 @@ -1724,12 +2149,12 @@ spec: apiVersion: litmuschaos.io/v1alpha1 description: message: | - Kills the kubelet service on the application node to check the resiliency. + Give a memory hog on a node belonging to a deployment kind: ChaosExperiment metadata: - name: kubelet-service-kill + name: node-memory-hog labels: - name: kubelet-service-kill + name: node-memory-hog app.kubernetes.io/part-of: litmus app.kubernetes.io/component: chaosexperiment app.kubernetes.io/version: latest @@ -1769,208 +2194,55 @@ spec: imagePullPolicy: Always args: - -c - - ./experiments -name kubelet-service-kill + - ./experiments -name node-memory-hog command: - /bin/bash env: - + - name: TOTAL_CHAOS_DURATION - value: '90' # in seconds + value: '120' + + ## Specify the size as percent of total node capacity Ex: '30' + ## NOTE: for selecting this option keep MEMORY_CONSUMPTION_MEBIBYTES empty + - name: MEMORY_CONSUMPTION_PERCENTAGE + value: '' + + ## Specify the amount of memory to be consumed in mebibytes + ## NOTE: for selecting this option keep MEMORY_CONSUMPTION_PERCENTAGE empty + - name: MEMORY_CONSUMPTION_MEBIBYTES + value: '' + + - name: NUMBER_OF_WORKERS + value: '1' + + # ENTER THE COMMA SEPARATED TARGET NODES NAME + - name: TARGET_NODES + value: '' # Period to wait before and after injection of chaos in sec - name: RAMP_TIME value: '' + # Provide the LIB here + # Only litmus supported - name: LIB value: 'litmus' # provide lib image - name: LIB_IMAGE - value: 'ubuntu:16.04' - - # provide the target node name - - name: TARGET_NODE + value: 'litmuschaos/go-runner:latest' + + ## percentage of total nodes to target + - name: NODES_AFFECTED_PERC value: '' - labels: - name: kubelet-service-kill - app.kubernetes.io/part-of: litmus - app.kubernetes.io/component: experiment-job - app.kubernetes.io/version: latest - ---- -apiVersion: litmuschaos.io/v1alpha1 -description: - message: | - Deletes a pod belonging to a deployment/statefulset/daemonset -kind: ChaosExperiment -metadata: - name: k8-pod-delete - labels: - name: k8-pod-delete - app.kubernetes.io/part-of: litmus - app.kubernetes.io/component: chaosexperiment - app.kubernetes.io/version: latest -spec: - definition: - scope: Namespaced - permissions: - - apiGroups: - - "" - - "apps" - - "batch" - - "litmuschaos.io" - resources: - - "deployments" - - "jobs" - - "pods" - - "configmaps" - - "chaosengines" - - "chaosexperiments" - - "chaosresults" - verbs: - - "create" - - "list" - - "get" - - "patch" - - "update" - - "delete" - - apiGroups: - - "" - resources: - - "nodes" - verbs : - - "get" - - "list" - image: "litmuschaos/chaostoolkit:latest" - args: - - -c - - python /app/chaos/chaostest/kubernetes/k8_wrapper.py; exit 0 - command: - - /bin/bash - env: - - name: CHAOSTOOLKIT_IN_POD - value: 'true' - - - name: FILE - value: 'pod-app-kill-count.json' - - - name: NAME_SPACE - value: '' - - - name: LABEL_NAME - value: '' - - - name: APP_ENDPOINT - value: '' - - - name: PERCENTAGE - value: '50' - - - name: REPORT - value: 'true' - - - name: REPORT_ENDPOINT - value: 'none' - - - name: TEST_NAMESPACE - value: 'default' - - - labels: - name: k8-pod-delete - app.kubernetes.io/part-of: litmus - app.kubernetes.io/component: experiment-job - app.kubernetes.io/version: latest - ---- -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: - - apiGroups: - - "" - - "apps" - - "apps.openshift.io" - - "argoproj.io" - - "batch" - - "litmuschaos.io" - resources: - - "deployments" - - "jobs" - - "pods" - - "pods/log" - - "replicationcontrollers" - - "deployments" - - "statefulsets" - - "daemonsets" - - "replicasets" - - "deploymentconfigs" - - "rollouts" - - "pods/exec" - - "events" - - "chaosengines" - - "chaosexperiments" - - "chaosresults" - verbs: - - "create" - - "list" - - "get" - - "patch" - - "update" - - "delete" - - "deletecollection" - image: "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: LIB - value: 'litmus' - - - name: TARGET_PODS - value: '' - - ## it defines the sequence of chaos execution for multiple target pods + ## it defines the sequence of chaos execution for multiple target nodes ## supported values: serial, parallel - name: SEQUENCE value: 'parallel' labels: - name: pod-delete + name: node-memory-hog app.kubernetes.io/part-of: litmus app.kubernetes.io/component: experiment-job app.kubernetes.io/version: latest @@ -1979,389 +2251,117 @@ spec: apiVersion: litmuschaos.io/v1alpha1 description: message: | - poweroff node + Injects network packet duplication on pods belonging to an app deployment kind: ChaosExperiment metadata: - name: node-poweroff + name: pod-network-duplication labels: - name: node-poweroff + name: pod-network-duplication app.kubernetes.io/part-of: litmus app.kubernetes.io/component: chaosexperiment app.kubernetes.io/version: latest spec: definition: - scope: Cluster + scope: Namespaced permissions: - - apiGroups: - - "" - - "batch" - - "litmuschaos.io" - resources: - - "jobs" - - "pods" - - "pods/log" - - "pods/exec" - - "events" - - "chaosengines" - - "chaosexperiments" - - "chaosresults" - - "secrets" - verbs: - - "create" - - "list" - - "get" - - "patch" - - "update" - - "delete" - - "deletecollection" - - apiGroups: - - "" - resources: - - "nodes" - verbs: - - "get" - - "list" + - apiGroups: + - "" + - "batch" + - "apps" + - "apps.openshift.io" + - "argoproj.io" + - "litmuschaos.io" + resources: + - "jobs" + - "pods" + - "pods/log" + - "replicationcontrollers" + - "deployments" + - "statefulsets" + - "daemonsets" + - "replicasets" + - "deploymentconfigs" + - "rollouts" + - "pods/exec" + - "events" + - "chaosengines" + - "chaosexperiments" + - "chaosresults" + verbs: + - "get" + - "list" + - "patch" + - "create" + - "update" + - "delete" + - "deletecollection" image: "litmuschaos/go-runner:latest" imagePullPolicy: Always args: - -c - - ./experiments -name node-restart + - ./experiments -name pod-network-duplication command: - /bin/bash env: - - name: SSH_USER - value: 'root' - - name: TOTAL_CHAOS_DURATION - value: '360' + value: '60' - - name: EXPERIMENT_NAME - value: 'node-poweroff' - - - name: REBOOT_COMMAND - value: '-o ServerAliveInterval=1 -o ServerAliveCountMax=1 "sudo systemctl poweroff --force --force" ; true' - - # Period to wait before and after injection of chaos in sec - name: RAMP_TIME value: '' - # PROVIDE THE LIB HERE - # ONLY LITMUS SUPPORTED + - name: TARGET_CONTAINER + value: '' + + - name: TC_IMAGE + value: 'gaiadocker/iproute2' + + - name: NETWORK_INTERFACE + value: 'eth0' + + - name: NETWORK_PACKET_DUPLICATION_PERCENTAGE + value: '100' # in percentage + + # lib can be litmus or pumba - name: LIB - value: 'litmus' + value: 'litmus' + + - name: TARGET_PODS + value: '' + + ## percentage of total pods to target + - name: PODS_AFFECTED_PERC + value: '' - # provide lib image - name: LIB_IMAGE - value: "litmuschaos/go-runner:latest" + value: 'litmuschaos/go-runner:latest' - # ENTER THE TARGET NODE NAME - - name: TARGET_NODE + # 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: 'docker' + + # provide the destination ips + # chaos injection will be triggered for these destination ips + - name: DESTINATION_IPS value: '' - # ENTER THE TARGET NODE IP - - name: TARGET_NODE_IP + # 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: '/var/run/docker.sock' + + ## it defines the sequence of chaos execution for multiple target pods + ## supported values: serial, parallel + - name: SEQUENCE + value: 'parallel' + labels: - name: node-poweroff - app.kubernetes.io/part-of: litmus - app.kubernetes.io/component: experiment-job - app.kubernetes.io/version: latest - secrets: - - name: id-rsa - mountPath: /mnt/ - ---- -apiVersion: litmuschaos.io/v1alpha1 -description: - message: | - injects dns failure in target pod container -kind: ChaosExperiment -metadata: - name: pod-dns-chaos - labels: - name: pod-dns-chaos - app.kubernetes.io/part-of: litmus - app.kubernetes.io/component: chaosexperiment - app.kubernetes.io/version: latest -spec: - definition: - scope: Namespaced - permissions: - - apiGroups: - - "" - - "batch" - - "apps" - - "apps.openshift.io" - - "argoproj.io" - - "litmuschaos.io" - resources: - - "jobs" - - "pods" - - "pods/log" - - "replicationcontrollers" - - "deployments" - - "statefulsets" - - "daemonsets" - - "replicasets" - - "deploymentconfigs" - - "rollouts" - - "pods/exec" - - "events" - - "chaosengines" - - "chaosexperiments" - - "chaosresults" - verbs: - - "create" - - "list" - - "get" - - "patch" - - "update" - - "delete" - - "deletecollection" - image: "litmuschaos/go-runner:latest" - args: - - -c - - ./experiments -name pod-dns-chaos - command: - - /bin/bash - env: - - - name: TARGET_CONTAINER - value: '' - - # provide lib image - - name: LIB_IMAGE - value: 'litmuschaos/go-runner:latest' - - - 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: TARGET_PODS - value: '' - - # provide the name of container runtime, it supports docker, containerd, crio - - name: CONTAINER_RUNTIME - value: 'docker' - - # provide the socket file path - - name: SOCKET_PATH - value: '/var/run/docker.sock' - - ## it defines the sequence of chaos execution for multiple target pods - ## supported values: serial, parallel - - name: SEQUENCE - value: 'parallel' - - # list of the target hostnames or kewywords eg. '["litmuschaos","chaosnative.io"]' . If empty all hostnames are targets - - name: TARGET_HOSTNAMES - value: '' - - # can be either exact or substring, determines whether the dns query has to match exactly with one of the targets or can have any of the targets as substring - - name: MATCH_SCHEME - value: 'exact' - - # currently only error chaos is supported - - name: CHAOS_TYPE - value: 'error' - - labels: - experiment: pod-dns-chaos - app.kubernetes.io/part-of: litmus - app.kubernetes.io/component: experiment-job - app.kubernetes.io/version: latest - - ---- -apiVersion: litmuschaos.io/v1alpha1 -description: - message: | - Deletes a pod belonging to a deployment/statefulset/daemonset -kind: ChaosExperiment -metadata: - name: k8-service-kill - labels: - name: k8-service-kill - app.kubernetes.io/part-of: litmus - app.kubernetes.io/component: chaosexperiment - app.kubernetes.io/version: latest -spec: - definition: - scope: Namespaced - permissions: - - apiGroups: - - "" - - "apps" - - "batch" - - "litmuschaos.io" - resources: - - "deployments" - - "jobs" - - "pods" - - "configmaps" - - "chaosengines" - - "chaosexperiments" - - "chaosresults" - verbs: - - "create" - - "list" - - "get" - - "patch" - - "update" - - "delete" - - apiGroups: - - "" - resources: - - "nodes" - verbs : - - "get" - - "list" - labels: - name: k8-service-kill - app.kubernetes.io/part-of: litmus - image: "litmuschaos/chaostoolkit:latest" - args: - - -c - - python /app/chaos/chaostest/kubernetes/k8_wrapper.py; exit 0 - command: - - /bin/bash - env: - - name: CHAOSTOOLKIT_IN_POD - value: 'true' - - - name: FILE - value: 'service-app-kill-health.json' - - - name: NAME_SPACE - value: '' - - - name: LABEL_NAME - value: '' - - - name: APP_ENDPOINT - value: '' - - - name: PERCENTAGE - value: '50' - - - name: REPORT - value: 'true' - - - name: REPORT_ENDPOINT - value: 'none' - - - name: TEST_NAMESPACE - value: 'default' - - ---- ---- -apiVersion: litmuschaos.io/v1alpha1 -description: - message: | - Injects memory consumption on pods belonging to an app deployment -kind: ChaosExperiment -metadata: - name: pod-memory-hog - labels: - name: pod-memory-hog - app.kubernetes.io/part-of: litmus - app.kubernetes.io/component: chaosexperiment - app.kubernetes.io/version: latest -spec: - definition: - scope: Namespaced - permissions: - - apiGroups: - - "" - - "batch" - - "apps" - - "apps.openshift.io" - - "argoproj.io" - - "litmuschaos.io" - resources: - - "jobs" - - "pods" - - "pods/log" - - "replicationcontrollers" - - "deployments" - - "statefulsets" - - "daemonsets" - - "replicasets" - - "deploymentconfigs" - - "rollouts" - - "pods/exec" - - "events" - - "chaosengines" - - "chaosexperiments" - - "chaosresults" - verbs: - - "create" - - "list" - - "get" - - "patch" - - "update" - - "delete" - - "deletecollection" - image: "litmuschaos/go-runner:latest" - imagePullPolicy: Always - args: - - -c - - ./experiments -name pod-memory-hog - command: - - /bin/bash - env: - - name: TOTAL_CHAOS_DURATION - value: '60' - - ## enter the amount of memory in megabytes to be consumed by the application pod - - name: MEMORY_CONSUMPTION - value: '500' - - ## percentage of total pods to target - - name: PODS_AFFECTED_PERC - value: '' - - ## Period to wait before and after injection of chaos in sec - - name: RAMP_TIME - value: '' - - ## env var that describes the library used to execute the chaos - ## default: litmus. Supported values: litmus, pumba - - name: LIB - value: 'litmus' - - ## It is used in pumba lib only - - name: LIB_IMAGE - value: 'litmuschaos/go-runner:latest' - - ## It is used in pumba lib only - - name: STRESS_IMAGE - value: 'alexeiled/stress-ng:latest-ubuntu' - - # provide the socket file path - # it is used in pumba lib - - name: SOCKET_PATH - value: '/var/run/docker.sock' - - ## it defines the sequence of chaos execution for multiple target pods - ## supported values: serial, parallel - - name: SEQUENCE - value: 'parallel' - - - name: TARGET_PODS - value: '' - - labels: - name: pod-memory-hog + name: pod-network-duplication app.kubernetes.io/part-of: litmus app.kubernetes.io/component: experiment-job app.kubernetes.io/version: latest diff --git a/charts/kafka/experiments.yaml b/charts/kafka/experiments.yaml index 48f53e2..08b2017 100644 --- a/charts/kafka/experiments.yaml +++ b/charts/kafka/experiments.yaml @@ -1,4 +1,124 @@ apiVersion: litmuschaos.io/v1alpha1 +description: + message: | + Detaching a persistent disk from a node/instance for kafka. +kind: ChaosExperiment +metadata: + name: kafka-broker-disk-failure + labels: + name: kafka-broker-disk-failure + app.kubernetes.io/part-of: litmus + app.kubernetes.io/component: chaosexperiment + app.kubernetes.io/version: latest +spec: + definition: + scope: Cluster + permissions: + - apiGroups: + - "" + - "apps" + - "batch" + - "litmuschaos.io" + resources: + - "statefulsets" + - "secrets" + - "jobs" + - "pods/log" + - "events" + - "pods" + - "pods/exec" + - "chaosengines" + - "chaosexperiments" + - "chaosresults" + verbs: + - "create" + - "delete" + - "get" + - "list" + - "patch" + image: "litmuschaos/ansible-runner:latest" + imagePullPolicy: Always + args: + - -c + - ansible-playbook ./experiments/kafka/kafka-broker-disk-failure/kafka-broker-disk-failure-ansible-logic.yml -i /etc/ansible/hosts -vv; exit 0 + command: + - /bin/bash + env: + - name: ANSIBLE_STDOUT_CALLBACK + value: 'default' + + - name: KAFKA_KIND + value: 'statefulset' + + - name: KAFKA_LIVENESS_STREAM + value: 'enabled' + + - name: KAFKA_LIVENESS_IMAGE + value: 'litmuschaos/kafka-client:ci' + + - name: KAFKA_CONSUMER_TIMEOUT + value: '30000' + + - name: TOTAL_CHAOS_DURATION + value: '15' + + - name: PROJECT_ID + value: '' + + - name: DISK_NAME + value: '' + + - name: ZONE_NAME + value: '' + + # GKE and AWS supported + - name: CLOUD_PLATFORM + value: 'GKE' + + - name: KAFKA_NAMESPACE + value: '' + + - name: KAFKA_LABEL + value: '' + + - name: KAFKA_BROKER + value: '' + + - name: KAFKA_INSTANCE_NAME + value: '' + + - name: KAFKA_REPLICATION_FACTOR + value: '' + + - name: KAFKA_SERVICE + value: '' + + - name: KAFKA_PORT + value: '' + + - name: ZOOKEEPER_NAMESPACE + value: '' + + - name: ZOOKEEPER_LABEL + value: '' + + - name: ZOOKEEPER_SERVICE + value: '' + + - name: ZOOKEEPER_PORT + value: '' + labels: + name: kafka-broker-disk-failure + app.kubernetes.io/part-of: litmus + app.kubernetes.io/component: experiment-job + app.kubernetes.io/version: latest + secrets: + - name: kafka-broker-disk-failure + mountPath: /tmp/ + + +--- +apiVersion: litmuschaos.io/v1alpha1 description: message: | Deleting a kafka broker pod @@ -131,123 +251,3 @@ spec: app.kubernetes.io/version: latest --- -apiVersion: litmuschaos.io/v1alpha1 -description: - message: | - Detaching a persistent disk from a node/instance for kafka. -kind: ChaosExperiment -metadata: - name: kafka-broker-disk-failure - labels: - name: kafka-broker-disk-failure - app.kubernetes.io/part-of: litmus - app.kubernetes.io/component: chaosexperiment - app.kubernetes.io/version: latest -spec: - definition: - scope: Cluster - permissions: - - apiGroups: - - "" - - "apps" - - "batch" - - "litmuschaos.io" - resources: - - "statefulsets" - - "secrets" - - "jobs" - - "pods/log" - - "events" - - "pods" - - "pods/exec" - - "chaosengines" - - "chaosexperiments" - - "chaosresults" - verbs: - - "create" - - "delete" - - "get" - - "list" - - "patch" - image: "litmuschaos/ansible-runner:latest" - imagePullPolicy: Always - args: - - -c - - ansible-playbook ./experiments/kafka/kafka-broker-disk-failure/kafka-broker-disk-failure-ansible-logic.yml -i /etc/ansible/hosts -vv; exit 0 - command: - - /bin/bash - env: - - name: ANSIBLE_STDOUT_CALLBACK - value: 'default' - - - name: KAFKA_KIND - value: 'statefulset' - - - name: KAFKA_LIVENESS_STREAM - value: 'enabled' - - - name: KAFKA_LIVENESS_IMAGE - value: 'litmuschaos/kafka-client:ci' - - - name: KAFKA_CONSUMER_TIMEOUT - value: '30000' - - - name: TOTAL_CHAOS_DURATION - value: '15' - - - name: PROJECT_ID - value: '' - - - name: DISK_NAME - value: '' - - - name: ZONE_NAME - value: '' - - # GKE and AWS supported - - name: CLOUD_PLATFORM - value: 'GKE' - - - name: KAFKA_NAMESPACE - value: '' - - - name: KAFKA_LABEL - value: '' - - - name: KAFKA_BROKER - value: '' - - - name: KAFKA_INSTANCE_NAME - value: '' - - - name: KAFKA_REPLICATION_FACTOR - value: '' - - - name: KAFKA_SERVICE - value: '' - - - name: KAFKA_PORT - value: '' - - - name: ZOOKEEPER_NAMESPACE - value: '' - - - name: ZOOKEEPER_LABEL - value: '' - - - name: ZOOKEEPER_SERVICE - value: '' - - - name: ZOOKEEPER_PORT - value: '' - labels: - name: kafka-broker-disk-failure - app.kubernetes.io/part-of: litmus - app.kubernetes.io/component: experiment-job - app.kubernetes.io/version: latest - secrets: - - name: kafka-broker-disk-failure - mountPath: /tmp/ - - ---- diff --git a/charts/kube-aws/experiments.yaml b/charts/kube-aws/experiments.yaml index a56eb7c..0ee3f47 100644 --- a/charts/kube-aws/experiments.yaml +++ b/charts/kube-aws/experiments.yaml @@ -3,94 +3,6 @@ description: message: | Detaching an ebs volume from ec2 instance. kind: ChaosExperiment -metadata: - name: ec2-terminate-by-tag - labels: - name: ec2-terminate-by-tag - app.kubernetes.io/part-of: litmus - app.kubernetes.io/component: chaosexperiment - app.kubernetes.io/version: latest -spec: - definition: - scope: Cluster - permissions: - - apiGroups: - - "" - - "batch" - - "litmuschaos.io" - resources: - - "jobs" - - "pods" - - "events" - - "pods/log" - - "pods/exec" - - "secrets" - - "chaosengines" - - "chaosexperiments" - - "chaosresults" - verbs: - - "create" - - "list" - - "get" - - "patch" - - "update" - - "delete" - image: "litmuschaos/go-runner:latest" - imagePullPolicy: Always - args: - - -c - - ./experiments -name ec2-terminate-by-tag - command: - - /bin/bash - env: - - name: TOTAL_CHAOS_DURATION - value: '30' - - - name: CHAOS_INTERVAL - value: '30' - - # Period to wait before and after injection of chaos in sec - - name: RAMP_TIME - value: '' - - # enable it if the target instance is a part of self-managed nodegroup. - - name: MANAGED_NODEGROUP - value: 'disable' - - - name: REGION - value: '' - - # Target the percentage of instance filtered from tag - - name: INSTANCE_AFFECTED_PERC - value: '' - - - name: SEQUENCE - value: 'parallel' - - # Provide the path of aws credentials mounted from secret - - name: AWS_SHARED_CREDENTIALS_FILE - value: '/tmp/cloud_config.yml' - - # provide the LIB - # only litmus supported - - name: LIB - value: 'litmus' - - labels: - name: ec2-terminate-by-tag - app.kubernetes.io/part-of: litmus - app.kubernetes.io/component: experiment-job - app.kubernetes.io/version: latest - secrets: - - name: cloud-secret - mountPath: /tmp/ - ---- -apiVersion: litmuschaos.io/v1alpha1 -description: - message: | - Detaching an ebs volume from ec2 instance. -kind: ChaosExperiment metadata: name: ec2-terminate-by-id labels: @@ -372,3 +284,91 @@ spec: mountPath: /tmp/ --- +apiVersion: litmuschaos.io/v1alpha1 +description: + message: | + Detaching an ebs volume from ec2 instance. +kind: ChaosExperiment +metadata: + name: ec2-terminate-by-tag + labels: + name: ec2-terminate-by-tag + app.kubernetes.io/part-of: litmus + app.kubernetes.io/component: chaosexperiment + app.kubernetes.io/version: latest +spec: + definition: + scope: Cluster + permissions: + - apiGroups: + - "" + - "batch" + - "litmuschaos.io" + resources: + - "jobs" + - "pods" + - "events" + - "pods/log" + - "pods/exec" + - "secrets" + - "chaosengines" + - "chaosexperiments" + - "chaosresults" + verbs: + - "create" + - "list" + - "get" + - "patch" + - "update" + - "delete" + image: "litmuschaos/go-runner:latest" + imagePullPolicy: Always + args: + - -c + - ./experiments -name ec2-terminate-by-tag + command: + - /bin/bash + env: + - name: TOTAL_CHAOS_DURATION + value: '30' + + - name: CHAOS_INTERVAL + value: '30' + + # Period to wait before and after injection of chaos in sec + - name: RAMP_TIME + value: '' + + # enable it if the target instance is a part of self-managed nodegroup. + - name: MANAGED_NODEGROUP + value: 'disable' + + - name: REGION + value: '' + + # Target the percentage of instance filtered from tag + - name: INSTANCE_AFFECTED_PERC + value: '' + + - name: SEQUENCE + value: 'parallel' + + # Provide the path of aws credentials mounted from secret + - name: AWS_SHARED_CREDENTIALS_FILE + value: '/tmp/cloud_config.yml' + + # provide the LIB + # only litmus supported + - name: LIB + value: 'litmus' + + labels: + name: ec2-terminate-by-tag + app.kubernetes.io/part-of: litmus + app.kubernetes.io/component: experiment-job + app.kubernetes.io/version: latest + secrets: + - name: cloud-secret + mountPath: /tmp/ + +--- diff --git a/charts/openebs/experiments.yaml b/charts/openebs/experiments.yaml index 8b54ca0..684c5ce 100644 --- a/charts/openebs/experiments.yaml +++ b/charts/openebs/experiments.yaml @@ -1,98 +1,3 @@ -apiVersion: litmuschaos.io/v1alpha1 -description: - message: | - Network delay to pool pod belonging to a OpenEBS PVC - This experiment is using pumba lib for network chaos -kind: ChaosExperiment -metadata: - labels: - litmuschaos.io/name: openebs - name: openebs-pool-network-delay - app.kubernetes.io/part-of: litmus - app.kubernetes.io/component: chaosexperiment - app.kubernetes.io/version: latest - name: openebs-pool-network-delay -spec: - definition: - scope: Cluster - permissions: - - apiGroups: - - "" - - "apps" - - "litmuschaos.io" - - "batch" - - "extensions" - - "storage.k8s.io" - - "openebs.io" - resources: - - "pods" - - "pods/exec" - - "jobs" - - "pods/log" - - "events" - - "configmaps" - - "services" - - "persistentvolumeclaims" - - "storageclasses" - - "persistentvolumes" - - "chaosengines" - - "chaosexperiments" - - "chaosresults" - - "cstorpools" - - "cstorvolumereplicas" - - "replicasets" - verbs: - - "create" - - "get" - - "list" - - "patch" - - "update" - - "delete" - image: "litmuschaos/ansible-runner:latest" - imagePullPolicy: Always - args: - - -c - - ansible-playbook ./experiments/openebs/openebs-pool-network-delay/openebs_pool_network_delay_ansible_logic.yml -i /etc/ansible/hosts -vv; exit 0 - command: - - /bin/bash - env: - - name: ANSIBLE_STDOUT_CALLBACK - value: 'default' - - - name: OPENEBS_NAMESPACE - value: 'openebs' - - # only pumba supported - # For pumba image use : gaiaadm/pumba:0.6.5 - - name: LIB_IMAGE - value: 'gaiaadm/pumba:0.6.5' - - # in milliseconds - - name: NETWORK_DELAY - value: '60000' - - - name: TC_IMAGE - value: 'gaiadocker/iproute2' - - - name: TOTAL_CHAOS_DURATION - value: '60' # in seconds - - - name: LIVENESS_APP_LABEL - value: '' - - - name: LIVENESS_APP_NAMESPACE - value: '' - - - name: DATA_PERSISTENCE - value: '' - - labels: - name: openebs-pool-network-delay - app.kubernetes.io/part-of: litmus - app.kubernetes.io/component: experiment-job - app.kubernetes.io/version: latest - ---- --- apiVersion: litmuschaos.io/v1alpha1 description: @@ -207,6 +112,102 @@ spec: #- name: openebs-target-container-failure # mountPath: /mnt +--- +apiVersion: litmuschaos.io/v1alpha1 +description: + message: | + Network loss to target pod belonging to a OpenEBS PVC +kind: ChaosExperiment +metadata: + labels: + litmuschaos.io/name: openebs + name: openebs-target-network-loss + app.kubernetes.io/part-of: litmus + app.kubernetes.io/component: chaosexperiment + app.kubernetes.io/version: latest + name: openebs-target-network-loss +spec: + definition: + scope: Cluster + permissions: + - apiGroups: + - "" + - "extensions" + - "apps" + - "batch" + - "litmuschaos.io" + - "storage.k8s.io" + resources: + - "jobs" + - "pods" + - "events" + - "services" + - "pods/log" + - "pods/exec" + - "configmaps" + - "secrets" + - "persistentvolumeclaims" + - "storageclasses" + - "persistentvolumes" + - "chaosengines" + - "chaosexperiments" + - "chaosresults" + verbs: + - "create" + - "get" + - "delete" + - "list" + - "patch" + - "update" + image: "litmuschaos/ansible-runner:latest" + imagePullPolicy: Always + args: + - -c + - ansible-playbook ./experiments/openebs/openebs-target-network-loss/openebs_target_network_loss_ansible_logic.yml -i /etc/ansible/hosts -vv; exit 0 + command: + - /bin/bash + env: + - name: ANSIBLE_STDOUT_CALLBACK + value: 'default' + + - name: OPENEBS_NAMESPACE + value: 'openebs' + + - name: APP_PVC + value: '' + + - name: TC_IMAGE + value: 'gaiadocker/iproute2' + + # only pumba supported + # For pumba image use : gaiaadm/pumba:0.6.5 + - name: LIB_IMAGE + value: 'gaiaadm/pumba:0.6.5' + + - name: NETWORK_PACKET_LOSS_PERCENTAGE + value: '100' # in percentage + + - name: TOTAL_CHAOS_DURATION + value: '120' # in seconds + + - name: LIVENESS_APP_LABEL + value: '' + + - name: LIVENESS_APP_NAMESPACE + value: '' + + - name: DATA_PERSISTENCE + value: '' + + labels: + name: openebs-target-network-loss + app.kubernetes.io/part-of: litmus + app.kubernetes.io/component: experiment-job + app.kubernetes.io/version: latest + #configmaps: + #- name: openebs-target-network-loss + # mountPath: /mnt + --- --- apiVersion: litmuschaos.io/v1alpha1 @@ -309,6 +310,282 @@ spec: - name: openebs-nfs-provisioner-kill mountPath: /mnt/ +--- +--- +apiVersion: litmuschaos.io/v1alpha1 +description: + message: | + Kill all openebs control plane pod and check if gets scheduled again +kind: ChaosExperiment +metadata: + labels: + litmuschaos.io/name: openebs + name: openebs-control-plane-chaos + app.kubernetes.io/part-of: litmus + app.kubernetes.io/component: chaosexperiment + app.kubernetes.io/version: latest + name: openebs-control-plane-chaos +spec: + definition: + scope: Namespaced + permissions: + - apiGroups: + - "" + - "litmuschaos.io" + - "batch" + - "apps" + resources: + - "pods" + - "pods/log" + - "deployments" + - "events" + - "jobs" + - "configmaps" + - "chaosengines" + - "chaosexperiments" + - "chaosresults" + verbs: + - "create" + - "list" + - "get" + - "patch" + - "update" + - "delete" + - apiGroups: + - "" + resources: + - "nodes" + verbs: + - "get" + - "list" + + image: "litmuschaos/ansible-runner:latest" + imagePullPolicy: Always + args: + - -c + - ansible-playbook ./experiments/openebs/openebs-control-plane-chaos/openebs_control_plane_chaos_ansible_logic.yml -i /etc/ansible/hosts -vv; exit 0 + command: + - /bin/bash + env: + - name: ANSIBLE_STDOUT_CALLBACK + value: 'default' + + - name: OPENEBS_NAMESPACE + value: 'openebs' + + ## Period to wait before injection of chaos + - name: RAMP_TIME + value: '' + + - name: FORCE + value: '' + + ## env var that describes the library used to execute the chaos + ## default: litmus. Supported values: litmus, powerfulseal + - name: LIB + value: '' + + labels: + name: openebs-control-plane-chaos + app.kubernetes.io/part-of: litmus + app.kubernetes.io/component: experiment-job + app.kubernetes.io/version: latest + +--- +--- +apiVersion: litmuschaos.io/v1alpha1 +description: + message: | + Kill the pool pod and check if gets scheduled again +kind: ChaosExperiment +metadata: + labels: + litmuschaos.io/name: openebs + name: openebs-pool-pod-failure + app.kubernetes.io/part-of: litmus + app.kubernetes.io/component: chaosexperiment + app.kubernetes.io/version: latest + name: openebs-pool-pod-failure +spec: + definition: + scope: Cluster + permissions: + - apiGroups: + - "" + - "extensions" + - "apps" + - "batch" + - "litmuschaos.io" + - "openebs.io" + - "storage.k8s.io" + resources: + - "deployments" + - "replicasets" + - "jobs" + - "pods/log" + - "events" + - "pods" + - "configmaps" + - "secrets" + - "storageclasses" + - "persistentvolumeclaims" + - "cstorvolumereplicas" + - "chaosengines" + - "chaosexperiments" + - "chaosresults" + verbs: + - "create" + - "get" + - "delete" + - "list" + - "patch" + - "update" + - apiGroups: + - "" + resources: + - "nodes" + verbs: + - "get" + - "list" + image: "litmuschaos/ansible-runner:latest" + imagePullPolicy: Always + args: + - -c + - ansible-playbook ./experiments/openebs/openebs-pool-pod-failure/openebs_pool_pod_failure_ansible_logic.yml -i /etc/ansible/hosts -vv; exit 0 + command: + - /bin/bash + env: + - name: ANSIBLE_STDOUT_CALLBACK + value: default + + - name: OPENEBS_NS + value: 'openebs' + + - name: APP_PVC + value: '' + + - name: LIVENESS_APP_LABEL + value: '' + + - name: LIVENESS_APP_NAMESPACE + value: '' + + - name: CHAOS_ITERATIONS + value: '2' + + # provide the kill count + - name: KILL_COUNT + value: '' + + - name: DATA_PERSISTENCE + value: '' + + labels: + name: openebs-pool-pod-failure + app.kubernetes.io/part-of: litmus + app.kubernetes.io/component: experiment-job + app.kubernetes.io/version: latest + #configmaps: + #- name: openebs-pool-pod-failure + # mountPath: /mnt + + +--- +apiVersion: litmuschaos.io/v1alpha1 +description: + message: | + Network delay to target pod belonging to a deployment/statefulset/daemonset +kind: ChaosExperiment +metadata: + labels: + litmuschaos.io/name: openebs + name: openebs-target-network-delay + app.kubernetes.io/part-of: litmus + app.kubernetes.io/component: chaosexperiment + app.kubernetes.io/version: latest + name: openebs-target-network-delay +spec: + definition: + scope: Cluster + permissions: + - apiGroups: + - "" + - "extensions" + - "apps" + - "batch" + - "litmuschaos.io" + - "storage.k8s.io" + resources: + - "jobs" + - "pods" + - "services" + - "events" + - "pods/exec" + - "pods/log" + - "configmaps" + - "secrets" + - "persistentvolumeclaims" + - "storageclasses" + - "persistentvolumes" + - "chaosengines" + - "chaosexperiments" + - "chaosresults" + verbs: + - "create" + - "get" + - "delete" + - "list" + - "patch" + - "update" + image: "litmuschaos/ansible-runner:latest" + imagePullPolicy: Always + args: + - -c + - ansible-playbook ./experiments/openebs/openebs-target-network-delay/openebs_target_network_delay_ansible_logic.yml -i /etc/ansible/hosts -vv; exit 0 + command: + - /bin/bash + env: + - name: ANSIBLE_STDOUT_CALLBACK + value: 'default' + + - name: OPENEBS_NAMESPACE + value: 'openebs' + + - name: APP_PVC + value: '' + + - name: TC_IMAGE + value: 'gaiadocker/iproute2' + + # only pumba supported + # For pumba image use : gaiaadm/pumba:0.6.5 + - name: LIB_IMAGE + value: 'gaiaadm/pumba:0.6.5' + + - name: NETWORK_DELAY + value: '60000' # in milliseconds + + - name: TOTAL_CHAOS_DURATION + value: '60' # in seconds + + - name: LIVENESS_APP_LABEL + value: '' + + - name: LIVENESS_APP_NAMESPACE + value: '' + + - name: DATA_PERSISTENCE + value: '' + + labels: + name: openebs-target-network-delay + app.kubernetes.io/part-of: litmus + app.kubernetes.io/component: experiment-job + app.kubernetes.io/version: latest + #configmaps: + #- name: openebs-target-network-delay + # mountPath: /mnt + --- --- apiVersion: litmuschaos.io/v1alpha1 @@ -427,42 +704,50 @@ spec: apiVersion: litmuschaos.io/v1alpha1 description: message: | - Kill all openebs control plane pod and check if gets scheduled again + Kill the cstor target/Jiva controller pod and check if gets created again kind: ChaosExperiment metadata: labels: litmuschaos.io/name: openebs - name: openebs-control-plane-chaos + name: openebs-target-pod-failure app.kubernetes.io/part-of: litmus app.kubernetes.io/component: chaosexperiment app.kubernetes.io/version: latest - name: openebs-control-plane-chaos + name: openebs-target-pod-failure spec: definition: - scope: Namespaced + scope: Cluster permissions: - apiGroups: - "" - - "litmuschaos.io" - - "batch" + - "extensions" - "apps" + - "batch" + - "litmuschaos.io" + - "storage.k8s.io" resources: + - "deployments" + - "jobs" + - "events" - "pods" - "pods/log" - - "deployments" - - "events" - - "jobs" + - "pods/exec" - "configmaps" + - "secrets" + - "services" - "chaosengines" - "chaosexperiments" - "chaosresults" + - "persistentvolumeclaims" + - "storageclasses" + - "persistentvolumes" verbs: - "create" - - "list" - "get" + - "delete" + - "list" - "patch" - "update" - - "delete" - apiGroups: - "" resources: @@ -470,12 +755,11 @@ spec: verbs: - "get" - "list" - image: "litmuschaos/ansible-runner:latest" imagePullPolicy: Always args: - -c - - ansible-playbook ./experiments/openebs/openebs-control-plane-chaos/openebs_control_plane_chaos_ansible_logic.yml -i /etc/ansible/hosts -vv; exit 0 + - ansible-playbook ./experiments/openebs/openebs-target-pod-failure/openebs_target_pod_failure_ansible_logic.yml -i /etc/ansible/hosts -vv; exit 0 command: - /bin/bash env: @@ -484,24 +768,43 @@ spec: - name: OPENEBS_NAMESPACE value: 'openebs' - - ## Period to wait before injection of chaos - - name: RAMP_TIME + + - name: APP_PVC value: '' - + - name: FORCE + value: 'true' + + - name: LIVENESS_APP_LABEL value: '' - ## env var that describes the library used to execute the chaos - ## default: litmus. Supported values: litmus, powerfulseal - - name: LIB + - name: LIVENESS_APP_NAMESPACE value: '' + - name: DATA_PERSISTENCE + value: '' + + - name: TOTAL_CHAOS_DURATION + value: '60' + + # provide the kill count + - name: KILL_COUNT + value: '' + + - name: CHAOS_INTERVAL + value: '15' + + - name: DEPLOY_TYPE + value: 'deployment' + labels: - name: openebs-control-plane-chaos + name: openebs-target-pod-failure app.kubernetes.io/part-of: litmus app.kubernetes.io/component: experiment-job app.kubernetes.io/version: latest + #configmaps: + #- name: openebs-target-pod-failure + # mountPath: /mnt --- --- @@ -602,201 +905,6 @@ spec: #- name: openebs-pool-container-failure # mountPath: /mnt ---- -apiVersion: litmuschaos.io/v1alpha1 -description: - message: | - Network delay to target pod belonging to a deployment/statefulset/daemonset -kind: ChaosExperiment -metadata: - labels: - litmuschaos.io/name: openebs - name: openebs-target-network-delay - app.kubernetes.io/part-of: litmus - app.kubernetes.io/component: chaosexperiment - app.kubernetes.io/version: latest - name: openebs-target-network-delay -spec: - definition: - scope: Cluster - permissions: - - apiGroups: - - "" - - "extensions" - - "apps" - - "batch" - - "litmuschaos.io" - - "storage.k8s.io" - resources: - - "jobs" - - "pods" - - "services" - - "events" - - "pods/exec" - - "pods/log" - - "configmaps" - - "secrets" - - "persistentvolumeclaims" - - "storageclasses" - - "persistentvolumes" - - "chaosengines" - - "chaosexperiments" - - "chaosresults" - verbs: - - "create" - - "get" - - "delete" - - "list" - - "patch" - - "update" - image: "litmuschaos/ansible-runner:latest" - imagePullPolicy: Always - args: - - -c - - ansible-playbook ./experiments/openebs/openebs-target-network-delay/openebs_target_network_delay_ansible_logic.yml -i /etc/ansible/hosts -vv; exit 0 - command: - - /bin/bash - env: - - name: ANSIBLE_STDOUT_CALLBACK - value: 'default' - - - name: OPENEBS_NAMESPACE - value: 'openebs' - - - name: APP_PVC - value: '' - - - name: TC_IMAGE - value: 'gaiadocker/iproute2' - - # only pumba supported - # For pumba image use : gaiaadm/pumba:0.6.5 - - name: LIB_IMAGE - value: 'gaiaadm/pumba:0.6.5' - - - name: NETWORK_DELAY - value: '60000' # in milliseconds - - - name: TOTAL_CHAOS_DURATION - value: '60' # in seconds - - - name: LIVENESS_APP_LABEL - value: '' - - - name: LIVENESS_APP_NAMESPACE - value: '' - - - name: DATA_PERSISTENCE - value: '' - - labels: - name: openebs-target-network-delay - app.kubernetes.io/part-of: litmus - app.kubernetes.io/component: experiment-job - app.kubernetes.io/version: latest - #configmaps: - #- name: openebs-target-network-delay - # mountPath: /mnt - ---- ---- -apiVersion: litmuschaos.io/v1alpha1 -description: - message: | - Kill the pool pod and check if gets scheduled again -kind: ChaosExperiment -metadata: - labels: - litmuschaos.io/name: openebs - name: openebs-pool-pod-failure - app.kubernetes.io/part-of: litmus - app.kubernetes.io/component: chaosexperiment - app.kubernetes.io/version: latest - name: openebs-pool-pod-failure -spec: - definition: - scope: Cluster - permissions: - - apiGroups: - - "" - - "extensions" - - "apps" - - "batch" - - "litmuschaos.io" - - "openebs.io" - - "storage.k8s.io" - resources: - - "deployments" - - "replicasets" - - "jobs" - - "pods/log" - - "events" - - "pods" - - "configmaps" - - "secrets" - - "storageclasses" - - "persistentvolumeclaims" - - "cstorvolumereplicas" - - "chaosengines" - - "chaosexperiments" - - "chaosresults" - verbs: - - "create" - - "get" - - "delete" - - "list" - - "patch" - - "update" - - apiGroups: - - "" - resources: - - "nodes" - verbs: - - "get" - - "list" - image: "litmuschaos/ansible-runner:latest" - imagePullPolicy: Always - args: - - -c - - ansible-playbook ./experiments/openebs/openebs-pool-pod-failure/openebs_pool_pod_failure_ansible_logic.yml -i /etc/ansible/hosts -vv; exit 0 - command: - - /bin/bash - env: - - name: ANSIBLE_STDOUT_CALLBACK - value: default - - - name: OPENEBS_NS - value: 'openebs' - - - name: APP_PVC - value: '' - - - name: LIVENESS_APP_LABEL - value: '' - - - name: LIVENESS_APP_NAMESPACE - value: '' - - - name: CHAOS_ITERATIONS - value: '2' - - # provide the kill count - - name: KILL_COUNT - value: '' - - - name: DATA_PERSISTENCE - value: '' - - labels: - name: openebs-pool-pod-failure - app.kubernetes.io/part-of: litmus - app.kubernetes.io/component: experiment-job - app.kubernetes.io/version: latest - #configmaps: - #- name: openebs-pool-pod-failure - # mountPath: /mnt - - --- apiVersion: litmuschaos.io/v1alpha1 description: @@ -891,67 +999,62 @@ spec: app.kubernetes.io/component: experiment-job app.kubernetes.io/version: latest ---- --- apiVersion: litmuschaos.io/v1alpha1 description: message: | - Kill the cstor target/Jiva controller pod and check if gets created again + Network delay to pool pod belonging to a OpenEBS PVC + This experiment is using pumba lib for network chaos kind: ChaosExperiment metadata: labels: litmuschaos.io/name: openebs - name: openebs-target-pod-failure + name: openebs-pool-network-delay app.kubernetes.io/part-of: litmus app.kubernetes.io/component: chaosexperiment app.kubernetes.io/version: latest - name: openebs-target-pod-failure + name: openebs-pool-network-delay spec: definition: scope: Cluster permissions: - apiGroups: - "" - - "extensions" - "apps" - - "batch" - "litmuschaos.io" + - "batch" + - "extensions" - "storage.k8s.io" + - "openebs.io" resources: - - "deployments" - - "jobs" - - "events" - "pods" - - "pods/log" - "pods/exec" + - "jobs" + - "pods/log" + - "events" - "configmaps" - - "secrets" - "services" - - "chaosengines" - - "chaosexperiments" - - "chaosresults" - "persistentvolumeclaims" - "storageclasses" - "persistentvolumes" + - "chaosengines" + - "chaosexperiments" + - "chaosresults" + - "cstorpools" + - "cstorvolumereplicas" + - "replicasets" verbs: - "create" - "get" - - "delete" - "list" - "patch" - "update" - - apiGroups: - - "" - resources: - - "nodes" - verbs: - - "get" - - "list" + - "delete" image: "litmuschaos/ansible-runner:latest" imagePullPolicy: Always args: - -c - - ansible-playbook ./experiments/openebs/openebs-target-pod-failure/openebs_target_pod_failure_ansible_logic.yml -i /etc/ansible/hosts -vv; exit 0 + - ansible-playbook ./experiments/openebs/openebs-pool-network-delay/openebs_pool_network_delay_ansible_logic.yml -i /etc/ansible/hosts -vv; exit 0 command: - /bin/bash env: @@ -960,121 +1063,21 @@ spec: - name: OPENEBS_NAMESPACE value: 'openebs' - - - name: APP_PVC - value: '' - - - name: FORCE - value: 'true' - - - name: LIVENESS_APP_LABEL - value: '' - - - name: LIVENESS_APP_NAMESPACE - value: '' - - - name: DATA_PERSISTENCE - value: '' - - - name: TOTAL_CHAOS_DURATION - value: '60' - - # provide the kill count - - name: KILL_COUNT - value: '' - - - name: CHAOS_INTERVAL - value: '15' - - - name: DEPLOY_TYPE - value: 'deployment' - - labels: - name: openebs-target-pod-failure - app.kubernetes.io/part-of: litmus - app.kubernetes.io/component: experiment-job - app.kubernetes.io/version: latest - #configmaps: - #- name: openebs-target-pod-failure - # mountPath: /mnt - ---- -apiVersion: litmuschaos.io/v1alpha1 -description: - message: | - Network loss to target pod belonging to a OpenEBS PVC -kind: ChaosExperiment -metadata: - labels: - litmuschaos.io/name: openebs - name: openebs-target-network-loss - app.kubernetes.io/part-of: litmus - app.kubernetes.io/component: chaosexperiment - app.kubernetes.io/version: latest - name: openebs-target-network-loss -spec: - definition: - scope: Cluster - permissions: - - apiGroups: - - "" - - "extensions" - - "apps" - - "batch" - - "litmuschaos.io" - - "storage.k8s.io" - resources: - - "jobs" - - "pods" - - "events" - - "services" - - "pods/log" - - "pods/exec" - - "configmaps" - - "secrets" - - "persistentvolumeclaims" - - "storageclasses" - - "persistentvolumes" - - "chaosengines" - - "chaosexperiments" - - "chaosresults" - verbs: - - "create" - - "get" - - "delete" - - "list" - - "patch" - - "update" - image: "litmuschaos/ansible-runner:latest" - imagePullPolicy: Always - args: - - -c - - ansible-playbook ./experiments/openebs/openebs-target-network-loss/openebs_target_network_loss_ansible_logic.yml -i /etc/ansible/hosts -vv; exit 0 - command: - - /bin/bash - env: - - name: ANSIBLE_STDOUT_CALLBACK - value: 'default' - - - name: OPENEBS_NAMESPACE - value: 'openebs' - - - name: APP_PVC - value: '' - - - name: TC_IMAGE - value: 'gaiadocker/iproute2' # only pumba supported # For pumba image use : gaiaadm/pumba:0.6.5 - name: LIB_IMAGE value: 'gaiaadm/pumba:0.6.5' - - name: NETWORK_PACKET_LOSS_PERCENTAGE - value: '100' # in percentage + # in milliseconds + - name: NETWORK_DELAY + value: '60000' + + - name: TC_IMAGE + value: 'gaiadocker/iproute2' - name: TOTAL_CHAOS_DURATION - value: '120' # in seconds + value: '60' # in seconds - name: LIVENESS_APP_LABEL value: '' @@ -1086,12 +1089,9 @@ spec: value: '' labels: - name: openebs-target-network-loss - app.kubernetes.io/part-of: litmus + name: openebs-pool-network-delay + app.kubernetes.io/part-of: litmus app.kubernetes.io/component: experiment-job app.kubernetes.io/version: latest - #configmaps: - #- name: openebs-target-network-loss - # mountPath: /mnt --- diff --git a/charts/vmware/experiments.yaml b/charts/vmware/experiments.yaml new file mode 100644 index 0000000..208fd8d --- /dev/null +++ b/charts/vmware/experiments.yaml @@ -0,0 +1,84 @@ +apiVersion: litmuschaos.io/v1alpha1 +description: + message: | + stops a vm for a certain chaos duration +kind: ChaosExperiment +metadata: + name: vm-poweroff + labels: + name: vm-poweroff + app.kubernetes.io/part-of: litmus + app.kubernetes.io/component: chaosexperiment + app.kubernetes.io/version: latest +spec: + definition: + scope: Cluster + permissions: + - apiGroups: + - "" + - "batch" + - "litmuschaos.io" + resources: + - "jobs" + - "events" + - "pods/log" + - "pods/exec" + - "secrets" + - "pods" + - "chaosengines" + - "chaosexperiments" + - "chaosresults" + verbs: + - "create" + - "list" + - "get" + - "update" + - "patch" + - "delete" + image: "litmuschaos/go-runner:latest" + args: + - -c + - ./experiments -name vm-poweroff + command: + - /bin/bash + env: + + - name: VCENTERSERVER + valueFrom: + secretKeyRef: + name: vcenter-secret + key: VCENTERSERVER + + - name: VCENTERUSER + valueFrom: + secretKeyRef: + name: vcenter-secret + key: VCENTERUSER + + - name: VCENTERPASS + valueFrom: + secretKeyRef: + name: vcenter-secret + key: VCENTERPASS + + # provide the vm moid + - name: APP_VM_MOID + value: '' + + - name: TOTAL_CHAOS_DURATION + value: '30' + + + - name: LIB + value: 'litmus' + + - name: RAMP_TIME + value: '' + + labels: + experiment: vm-poweroff + app.kubernetes.io/part-of: litmus + app.kubernetes.io/component: experiment-job + app.kubernetes.io/version: latest + +---