From 1ba09eb4b7a1bf2ca399995b3d0caf683649083b Mon Sep 17 00:00:00 2001 From: litmusbot Date: Fri, 7 May 2021 11:44:36 +0000 Subject: [PATCH] 820134881: version upgraded for chaos-charts --- charts/generic/experiments.yaml | 2248 +++++++++++++++--------------- charts/kafka/experiments.yaml | 240 ++-- charts/kube-aws/experiments.yaml | 198 +-- charts/openebs/experiments.yaml | 1012 +++++++------- 4 files changed, 1849 insertions(+), 1849 deletions(-) diff --git a/charts/generic/experiments.yaml b/charts/generic/experiments.yaml index ddd73b8..d74f1b1 100644 --- a/charts/generic/experiments.yaml +++ b/charts/generic/experiments.yaml @@ -1,32 +1,33 @@ apiVersion: litmuschaos.io/v1alpha1 description: message: | - Deletes a pod belonging to a deployment/statefulset/daemonset + Restart node kind: ChaosExperiment metadata: - name: k8-service-kill + name: node-restart labels: - name: k8-service-kill + name: node-restart app.kubernetes.io/part-of: litmus app.kubernetes.io/component: chaosexperiment app.kubernetes.io/version: latest spec: definition: - scope: Namespaced + scope: Cluster permissions: - apiGroups: - "" - - "apps" - "batch" - "litmuschaos.io" resources: - - "deployments" - "jobs" - "pods" - - "configmaps" + - "pods/log" + - "pods/exec" + - "events" - "chaosengines" - "chaosexperiments" - "chaosresults" + - "secrets" verbs: - "create" - "list" @@ -34,283 +35,92 @@ spec: - "patch" - "update" - "delete" + - "deletecollection" - 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" + - "list" image: "litmuschaos/go-runner:latest" imagePullPolicy: Always args: - -c - - ./experiments -name pod-delete + - ./experiments -name node-restart command: - /bin/bash env: + - name: SSH_USER + value: 'root' - name: TOTAL_CHAOS_DURATION - value: '15' + value: '60' # 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: '' - - ## env var that describes the library used to execute the chaos - ## default: litmus. Supported values: litmus, pumba + # PROVIDE THE LIB HERE + # ONLY LITMUS SUPPORTED - name: LIB value: 'litmus' - ## It is used in pumba lib only + # provide lib image - name: LIB_IMAGE - value: 'litmuschaos/go-runner:latest' + 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 + # ENTER THE TARGET NODE NAME + - name: TARGET_NODE + value: '' + + - name: NODE_LABEL + value: '' + + # ENTER THE TARGET NODE IP + - name: TARGET_NODE_IP 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 + 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: | - Fillup Ephemeral Storage of a Resource + Drain the node where application pod is scheduled kind: ChaosExperiment metadata: - name: disk-fill + name: node-drain labels: - name: disk-fill + name: node-drain app.kubernetes.io/part-of: litmus app.kubernetes.io/component: chaosexperiment app.kubernetes.io/version: latest spec: definition: - scope: Namespaced - permissions: + scope: Cluster + permissions: - apiGroups: - "" - - "apps" - "batch" - - "apps.openshift.io" - - "argoproj.io" - "litmuschaos.io" + - "apps" resources: - "jobs" - "pods" - - "pods/exec" - - "pods/log" - - "replicationcontrollers" - - "deployments" - - "statefulsets" - - "daemonsets" - - "replicasets" - - "deploymentconfigs" - - "rollouts" - "events" + - "pods/log" + - "pods/exec" + - "daemonsets" + - "pods/eviction" - "chaosengines" - "chaosexperiments" - "chaosresults" @@ -322,63 +132,43 @@ spec: - "update" - "delete" - "deletecollection" + - apiGroups: + - "" + resources: + - "nodes" + verbs: + - "get" + - "list" + - "patch" image: "litmuschaos/go-runner:latest" imagePullPolicy: Always args: - -c - - ./experiments -name disk-fill + - ./experiments -name node-drain command: - /bin/bash env: - - - name: TARGET_CONTAINER - value: '' - - name: FILL_PERCENTAGE - value: '80' + - name: TARGET_NODE + value: '' + + - name: NODE_LABEL + value: '' - 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 the data block size - # supported unit is KB - - name: DATA_BLOCK_SIZE - value: '256' - - - name: TARGET_PODS + # Period to wait before and after injection of chaos in sec + - name: RAMP_TIME 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 + name: node-drain app.kubernetes.io/part-of: litmus app.kubernetes.io/component: experiment-job app.kubernetes.io/version: latest @@ -509,95 +299,117 @@ spec: apiVersion: litmuschaos.io/v1alpha1 description: message: | - Give a cpu spike on a node belonging to a deployment + Injects network packet duplication on pods belonging to an app deployment kind: ChaosExperiment metadata: - name: node-cpu-hog + name: pod-network-duplication labels: - name: node-cpu-hog + 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" - 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-cpu-hog + - ./experiments -name pod-network-duplication 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 + - name: TARGET_CONTAINER value: '' - # ENTER THE COMMA SEPARATED TARGET NODES NAME - - name: TARGET_NODES - value: '' + - name: TC_IMAGE + value: 'gaiadocker/iproute2' - - name: NODE_LABEL - value: '' + - name: NETWORK_INTERFACE + value: 'eth0' - # PROVIDE THE LIB HERE - # ONLY LITMUS SUPPORTED + - name: NETWORK_PACKET_DUPLICATION_PERCENTAGE + value: '100' # in percentage + + # lib can be litmus or pumba - name: LIB - value: 'litmus' + value: 'litmus' - # provide lib image - - name: LIB_IMAGE - value: 'litmuschaos/go-runner:latest' + - name: TARGET_PODS + value: '' - ## percentage of total nodes to target - - name: NODES_AFFECTED_PERC + ## percentage of total pods to target + - name: PODS_AFFECTED_PERC value: '' - ## it defines the sequence of chaos execution for multiple target nodes + - 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' + + ## it defines the sequence of chaos execution for multiple target pods ## supported values: serial, parallel - name: SEQUENCE value: 'parallel' - + labels: - name: node-cpu-hog + name: pod-network-duplication app.kubernetes.io/part-of: litmus app.kubernetes.io/component: experiment-job app.kubernetes.io/version: latest @@ -605,13 +417,12 @@ spec: --- apiVersion: litmuschaos.io/v1alpha1 description: - message: | - Deletes a pod belonging to a deployment/statefulset/daemonset + message: "Kills a container belonging to an application pod \n" kind: ChaosExperiment metadata: - name: k8-pod-delete + name: container-kill labels: - name: k8-pod-delete + name: container-kill app.kubernetes.io/part-of: litmus app.kubernetes.io/component: chaosexperiment app.kubernetes.io/version: latest @@ -623,101 +434,22 @@ spec: - "" - "apps" - "batch" + - "apps.openshift.io" + - "argoproj.io" - "litmuschaos.io" resources: + - "jobs" + - "pods" + - "pods/log" + - "events" + - "replicationcontrollers" - "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" + - "statefulsets" - "daemonsets" - - "pods/eviction" + - "replicasets" + - "deploymentconfigs" + - "rollouts" + - "pods/exec" - "chaosengines" - "chaosexperiments" - "chaosresults" @@ -725,225 +457,72 @@ spec: - "create" - "list" - "get" - - "patch" - "update" + - "patch" - "delete" - "deletecollection" - - apiGroups: - - "" - resources: - - "nodes" - verbs: - - "get" - - "list" - - "patch" image: "litmuschaos/go-runner:latest" imagePullPolicy: Always args: - -c - - ./experiments -name node-drain + - ./experiments -name container-kill command: - /bin/bash env: - - - name: TARGET_NODE + + - name: TARGET_CONTAINER value: '' - - name: NODE_LABEL - 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: '' + + # lib can be litmus or pumba + - name: LIB + value: 'litmus' - labels: - name: node-drain - app.kubernetes.io/part-of: litmus - app.kubernetes.io/component: experiment-job - app.kubernetes.io/version: latest + - name: TARGET_PODS + value: '' ---- -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: - + # 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: '90' # in seconds - - # Period to wait before and after injection of chaos in sec - - name: RAMP_TIME + value: '20' + + ## percentage of total pods to target + - name: PODS_AFFECTED_PERC value: '' - - name: LIB - value: 'litmus' + - name: LIB_IMAGE + value: 'litmuschaos/go-runner:latest' - - name: NODE_LABEL - value: '' - - # provide lib image - - name: LIB_IMAGE - value: 'ubuntu:16.04' - - # provide the target node name - - name: TARGET_NODE - value: '' + ## it defines the sequence of chaos execution for multiple target pods + ## supported values: serial, parallel + - name: SEQUENCE + value: 'parallel' labels: - name: kubelet-service-kill + name: container-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: '' - - - name: NODE_LABEL - 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: @@ -1053,35 +632,43 @@ spec: app.kubernetes.io/version: latest +--- --- apiVersion: litmuschaos.io/v1alpha1 description: message: | - Scale the application replicas and test the node autoscaling on cluster + Injects memory consumption on pods belonging to an app deployment kind: ChaosExperiment metadata: - name: pod-autoscaler + name: pod-memory-hog labels: - name: pod-autoscaler + name: pod-memory-hog 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" - "apps" + - "apps.openshift.io" + - "argoproj.io" - "litmuschaos.io" resources: - "jobs" - "pods" - "pods/log" - - "pods/exec" + - "replicationcontrollers" - "deployments" - "statefulsets" + - "daemonsets" + - "replicasets" + - "deploymentconfigs" + - "rollouts" + - "pods/exec" - "events" - "chaosengines" - "chaosexperiments" @@ -1094,43 +681,57 @@ spec: - "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 + - ./experiments -name pod-memory-hog command: - /bin/bash env: + - name: TOTAL_CHAOS_DURATION + value: '60' - - 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' - # 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: '' - # Number of replicas to scale - - name: REPLICA_COUNT - value: '5' + ## 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: '' - # PROVIDE THE LIB HERE - # ONLY LITMUS SUPPORTED - - name: LIB - value: 'litmus' - labels: - name: pod-autoscaler + name: pod-memory-hog app.kubernetes.io/part-of: litmus app.kubernetes.io/component: experiment-job app.kubernetes.io/version: latest @@ -1139,33 +740,42 @@ spec: apiVersion: litmuschaos.io/v1alpha1 description: message: | - poweroff node + Fillup Ephemeral Storage of a Resource kind: ChaosExperiment metadata: - name: node-poweroff + name: disk-fill labels: - name: node-poweroff + name: disk-fill app.kubernetes.io/part-of: litmus app.kubernetes.io/component: chaosexperiment app.kubernetes.io/version: latest spec: definition: - scope: Cluster - permissions: + scope: Namespaced + permissions: - apiGroups: - "" + - "apps" - "batch" + - "apps.openshift.io" + - "argoproj.io" - "litmuschaos.io" resources: - "jobs" - "pods" - - "pods/log" - "pods/exec" + - "pods/log" + - "replicationcontrollers" + - "deployments" + - "statefulsets" + - "daemonsets" + - "replicasets" + - "deploymentconfigs" + - "rollouts" - "events" - "chaosengines" - "chaosexperiments" - "chaosresults" - - "secrets" verbs: - "create" - "list" @@ -1174,65 +784,169 @@ spec: - "update" - "delete" - "deletecollection" - - apiGroups: - - "" - resources: - - "nodes" - verbs: - - "get" - - "list" image: "litmuschaos/go-runner:latest" imagePullPolicy: Always args: - -c - - ./experiments -name node-restart + - ./experiments -name disk-fill command: - /bin/bash env: - - name: SSH_USER - value: 'root' + + - name: TARGET_CONTAINER + value: '' + + - name: FILL_PERCENTAGE + value: '80' - 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' + value: '60' # Period to wait before and after injection of chaos in sec - name: RAMP_TIME value: '' - # PROVIDE THE LIB HERE - # ONLY LITMUS SUPPORTED + # Provide the LIB here + # Only litmus supported - name: LIB value: 'litmus' - # provide lib image + # provide the data block size + # supported unit is KB + - name: DATA_BLOCK_SIZE + value: '256' + + - 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" + value: 'litmuschaos/go-runner:latest' - # ENTER THE TARGET NODE NAME - - name: TARGET_NODE - value: '' + # Provide the container runtime path + # Default set to docker container path + - name: CONTAINER_PATH + value: '/var/lib/docker/containers' - - name: NODE_LABEL - value: '' - - # ENTER THE TARGET NODE IP - - name: TARGET_NODE_IP - value: '' + ## it defines the sequence of chaos execution for multiple target pods + ## supported values: serial, parallel + - name: SEQUENCE + value: 'parallel' labels: - name: node-poweroff + 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 - secrets: - - name: id-rsa - mountPath: /mnt/ --- apiVersion: litmuschaos.io/v1alpha1 @@ -1348,121 +1062,16 @@ spec: app.kubernetes.io/component: experiment-job app.kubernetes.io/version: latest ---- --- apiVersion: litmuschaos.io/v1alpha1 description: message: | - Injects memory consumption on pods belonging to an app deployment + Kills the kubelet service on the application node to check the resiliency. kind: ChaosExperiment metadata: - name: pod-memory-hog + name: kubelet-service-kill 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 - 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 + name: kubelet-service-kill app.kubernetes.io/part-of: litmus app.kubernetes.io/component: chaosexperiment app.kubernetes.io/version: latest @@ -1473,16 +1082,13 @@ spec: - apiGroups: - "" - "batch" - - "apps" - "litmuschaos.io" resources: - "jobs" - "pods" - - "events" - "pods/log" - "pods/exec" - - "daemonsets" - - "pods/eviction" + - "events" - "chaosengines" - "chaosexperiments" - "chaosresults" @@ -1501,42 +1107,38 @@ spec: verbs: - "get" - "list" - - "patch" - - "update" image: "litmuschaos/go-runner:latest" imagePullPolicy: Always args: - -c - - ./experiments -name node-taint + - ./experiments -name kubelet-service-kill command: - /bin/bash env: - - - name: TARGET_NODE - value: '' - - - name: NODE_LABEL - value: '' - + - name: TOTAL_CHAOS_DURATION - value: '60' - - # Provide the LIB here - # Only litmus supported - - name: LIB - value: 'litmus' + value: '90' # in seconds # 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: '' + - name: LIB + value: 'litmus' + + - name: NODE_LABEL + value: '' + + # provide lib image + - name: LIB_IMAGE + value: 'ubuntu:16.04' + + # provide the target node name + - name: TARGET_NODE + value: '' labels: - name: node-taint + name: kubelet-service-kill app.kubernetes.io/part-of: litmus app.kubernetes.io/component: experiment-job app.kubernetes.io/version: latest @@ -1544,12 +1146,13 @@ spec: --- apiVersion: litmuschaos.io/v1alpha1 description: - message: "Kills a container belonging to an application pod \n" + message: | + Deletes a pod belonging to a deployment/statefulset/daemonset kind: ChaosExperiment metadata: - name: container-kill + name: k8-pod-delete labels: - name: container-kill + name: k8-pod-delete app.kubernetes.io/part-of: litmus app.kubernetes.io/component: chaosexperiment app.kubernetes.io/version: latest @@ -1561,6 +1164,425 @@ spec: - "" - "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: 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: | + 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: '' + + - name: NODE_LABEL + 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: | + 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: | + 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: | + Injects network latency on pods belonging to an app deployment +kind: ChaosExperiment +metadata: + name: pod-network-latency + labels: + name: pod-network-latency + 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" @@ -1568,7 +1590,6 @@ spec: - "jobs" - "pods" - "pods/log" - - "events" - "replicationcontrollers" - "deployments" - "statefulsets" @@ -1577,6 +1598,7 @@ spec: - "deploymentconfigs" - "rollouts" - "pods/exec" + - "events" - "chaosengines" - "chaosexperiments" - "chaosresults" @@ -1584,43 +1606,52 @@ 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-network-latency command: - /bin/bash env: - + - name: TARGET_CONTAINER value: '' - # Period to wait before and after injection of chaos in sec + - name: NETWORK_INTERFACE + value: 'eth0' + + # provide lib image + - name: LIB_IMAGE + value: 'litmuschaos/go-runner:latest' + + - name: TC_IMAGE + value: 'gaiadocker/iproute2' + + - name: NETWORK_LATENCY + value: '2000' #in ms + + - name: TOTAL_CHAOS_DURATION + value: '60' # in seconds + + # Time 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 + + ## percentage of total pods to target + - name: PODS_AFFECTED_PERC 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' + - name: TARGET_PODS + value: '' # provide the name of container runtime # for litmus LIB, it supports docker, containerd, crio @@ -1628,16 +1659,19 @@ spec: - 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 + # provide the destination ips + # chaos injection will be triggered for these destination ips + - name: DESTINATION_IPS value: '' - - name: LIB_IMAGE - value: 'litmuschaos/go-runner:latest' + # 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 @@ -1645,7 +1679,196 @@ spec: value: 'parallel' labels: - name: container-kill + name: pod-network-latency + 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 + ## 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: | + 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: '' + + - name: NODE_LABEL + 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 @@ -1772,77 +1995,6 @@ spec: 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 @@ -2049,128 +2201,6 @@ spec: - name: cloud-secret mountPath: /tmp/ ---- -apiVersion: litmuschaos.io/v1alpha1 -description: - message: | - Injects network latency on pods belonging to an app deployment -kind: ChaosExperiment -metadata: - name: pod-network-latency - labels: - name: pod-network-latency - 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-network-latency - command: - - /bin/bash - env: - - - name: TARGET_CONTAINER - value: '' - - - name: NETWORK_INTERFACE - value: 'eth0' - - # provide lib image - - name: LIB_IMAGE - value: 'litmuschaos/go-runner:latest' - - - name: TC_IMAGE - value: 'gaiadocker/iproute2' - - - name: NETWORK_LATENCY - value: '2000' #in ms - - - name: TOTAL_CHAOS_DURATION - value: '60' # in seconds - - # Time 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' - - ## percentage of total pods to target - - name: PODS_AFFECTED_PERC - value: '' - - - 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' - - # 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' - - ## it defines the sequence of chaos execution for multiple target pods - ## supported values: serial, parallel - - name: SEQUENCE - value: 'parallel' - - labels: - name: pod-network-latency - app.kubernetes.io/part-of: litmus - app.kubernetes.io/component: experiment-job - app.kubernetes.io/version: latest - --- apiVersion: litmuschaos.io/v1alpha1 description: @@ -2276,121 +2306,91 @@ spec: app.kubernetes.io/component: experiment-job app.kubernetes.io/version: latest +--- --- apiVersion: litmuschaos.io/v1alpha1 description: message: | - Injects network packet duplication on pods belonging to an app deployment + Taint the node where application pod is scheduled kind: ChaosExperiment metadata: - name: pod-network-duplication + name: node-taint labels: - name: pod-network-duplication + name: node-taint app.kubernetes.io/part-of: litmus app.kubernetes.io/component: chaosexperiment app.kubernetes.io/version: latest spec: definition: - scope: Namespaced + scope: Cluster 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: + - "" + - "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 pod-network-duplication + - ./experiments -name node-taint command: - /bin/bash env: + + - name: TARGET_NODE + value: '' + + - name: NODE_LABEL + 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: '' - - 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' - - - name: TARGET_PODS - value: '' - - ## percentage of total pods to target - - name: PODS_AFFECTED_PERC - value: '' - - - 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' - - ## it defines the sequence of chaos execution for multiple target pods - ## supported values: serial, parallel - - name: SEQUENCE - value: 'parallel' + # set taint label & effect + # key=value:effect or key:effect + - name: TAINTS + value: '' labels: - name: pod-network-duplication + name: node-taint 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 08b2017..48f53e2 100644 --- a/charts/kafka/experiments.yaml +++ b/charts/kafka/experiments.yaml @@ -1,124 +1,4 @@ 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 @@ -251,3 +131,123 @@ 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 bd6ff61..8ddccaa 100644 --- a/charts/kube-aws/experiments.yaml +++ b/charts/kube-aws/experiments.yaml @@ -1,93 +1,4 @@ apiVersion: litmuschaos.io/v1alpha1 -description: - message: | - Detaching an ebs volume from ec2 instance. -kind: ChaosExperiment -metadata: - name: ec2-terminate-by-id - labels: - name: ec2-terminate-by-id - 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-id - 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' - - # Instance ID of the target ec2 instance - # Multiple IDs can also be provided as comma separated values ex: id1,id2 - - name: EC2_INSTANCE_ID - value: '' - - - name: REGION - 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-id - 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: | Deletes an aws instance belonging to a deployment/statefulset/daemonset @@ -200,6 +111,94 @@ spec: app.kubernetes.io/version: latest +--- +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/ + --- apiVersion: litmuschaos.io/v1alpha1 description: @@ -290,9 +289,9 @@ description: Detaching an ebs volume from ec2 instance. kind: ChaosExperiment metadata: - name: ec2-terminate-by-tag + name: ec2-terminate-by-id labels: - name: ec2-terminate-by-tag + name: ec2-terminate-by-id app.kubernetes.io/part-of: litmus app.kubernetes.io/component: chaosexperiment app.kubernetes.io/version: latest @@ -325,7 +324,7 @@ spec: imagePullPolicy: Always args: - -c - - ./experiments -name ec2-terminate-by-tag + - ./experiments -name ec2-terminate-by-id command: - /bin/bash env: @@ -341,17 +340,18 @@ spec: # enable it if the target instance is a part of self-managed nodegroup. - name: MANAGED_NODEGROUP - value: 'disable' + value: 'disable' + + # Instance ID of the target ec2 instance + # Multiple IDs can also be provided as comma separated values ex: id1,id2 + - name: EC2_INSTANCE_ID + value: '' - name: REGION value: '' - # Target the percentage of instance filtered from tag - - name: INSTANCE_AFFECTED_PERC - value: '' - - name: SEQUENCE - value: 'parallel' + value: 'parallel' # Provide the path of aws credentials mounted from secret - name: AWS_SHARED_CREDENTIALS_FILE @@ -363,7 +363,7 @@ spec: value: 'litmus' labels: - name: ec2-terminate-by-tag + name: ec2-terminate-by-id app.kubernetes.io/part-of: litmus app.kubernetes.io/component: experiment-job app.kubernetes.io/version: latest diff --git a/charts/openebs/experiments.yaml b/charts/openebs/experiments.yaml index 684c5ce..282ebd9 100644 --- a/charts/openebs/experiments.yaml +++ b/charts/openebs/experiments.yaml @@ -1,5 +1,275 @@ --- 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: | + Network loss to pool pod belonging to a OpenEBS PVC +kind: ChaosExperiment +metadata: + labels: + litmuschaos.io/name: openebs + name: openebs-pool-network-loss + app.kubernetes.io/part-of: litmus + app.kubernetes.io/component: chaosexperiment + app.kubernetes.io/version: latest + name: openebs-pool-network-loss +spec: + definition: + scope: Cluster + permissions: + - apiGroups: + - "" + - "apps" + - "litmuschaos.io" + - "batch" + - "extensions" + - "storage.k8s.io" + - "openebs.io" + resources: + - "pods" + - "pods/log" + - "pods/exec" + - "events" + - "jobs" + - "configmaps" + - "services" + - "persistentvolumeclaims" + - "storageclasses" + - "persistentvolumeclaims" + - "persistentvolumes" + - "chaosengines" + - "chaosexperiments" + - "chaosresults" + - "cstorpools" + - "cstorvolumereplicas" + - "replicasets" + verbs: + - "create" + - "get" + - "delete" + - "list" + - "patch" + - "update" + image: "litmuschaos/ansible-runner:latest" + imagePullPolicy: Always + args: + - -c + - ansible-playbook ./experiments/openebs/openebs-pool-network-loss/openebs_pool_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' + + # only pumba supported + # For pumba image use : gaiaadm/pumba:0.6.5 + - name: LIB_IMAGE + value: 'gaiaadm/pumba:0.6.5' + + - name: TC_IMAGE + value: 'gaiadocker/iproute2' + + - 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-pool-network-loss + app.kubernetes.io/part-of: litmus + app.kubernetes.io/component: experiment-job + app.kubernetes.io/version: latest + +--- +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: message: | Kill the cstor target/Jiva controller container and check if gets created again @@ -112,6 +382,218 @@ spec: #- name: openebs-target-container-failure # mountPath: /mnt +--- +--- +apiVersion: litmuschaos.io/v1alpha1 +description: + message: | + OpenEBS Pool Disk Loss contains chaos to disrupt state of infra resources. Experiments can inject disk loss against openEBS pool. +kind: ChaosExperiment +metadata: + labels: + litmuschaos.io/name: openebs + name: openebs-pool-disk-loss + app.kubernetes.io/part-of: litmus + app.kubernetes.io/component: chaosexperiment + app.kubernetes.io/version: latest + name: openebs-pool-disk-loss +spec: + definition: + scope: Cluster + permissions: + - apiGroups: + - "" + - "apps" + - "litmuschaos.io" + - "batch" + - "extensions" + - "storage.k8s.io" + - "openebs.io" + resources: + - "pods" + - "jobs" + - "pods/log" + - "events" + - "pods/exec" + - "cstorpools" + - "configmaps" + - "secrets" + - "storageclasses" + - "persistentvolumes" + - "persistentvolumeclaims" + - "cstorvolumereplicas" + - "chaosexperiments" + - "chaosresults" + - "chaosengines" + verbs: + - "create" + - "list" + - "get" + - "patch" + - "update" + - "delete" + image: "litmuschaos/ansible-runner:latest" + imagePullPolicy: Always + args: + - -c + - ansible-playbook ./experiments/openebs/openebs-pool-disk-loss/openebs_pool_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: '60' + + # Period to wait before injection of chaos in sec + - name: RAMP_TIME + value: '' + + # GKE and AWS supported + - name: CLOUD_PLATFORM + value: 'GKE' + + - name: PROJECT_ID + value: '' + + - name: NODE_NAME + value: '' + + - name: DISK_NAME + value: '' + + - name: ZONE_NAME + value: '' + + - name: DEVICE_NAME + value: '' + + - name: LIVENESS_APP_LABEL + value: '' + + - name: LIVENESS_APP_NAMESPACE + value: '' + + - name: DATA_PERSISTENCE + value: '' + + - name: OPENEBS_NAMESPACE + value: 'openebs' + + labels: + name: openebs-pool-disk-loss + app.kubernetes.io/part-of: litmus + app.kubernetes.io/component: experiment-job + app.kubernetes.io/version: latest + + configmaps: + - name: openebs-pool-disk-loss + mountPath: /mnt/ + + secrets: + - name: cloud-secret + mountPath: /tmp/ + +--- +--- +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: @@ -315,97 +797,16 @@ spec: apiVersion: litmuschaos.io/v1alpha1 description: message: | - Kill all openebs control plane pod and check if gets scheduled again + Kill the pool container and check if gets scheduled again kind: ChaosExperiment metadata: labels: litmuschaos.io/name: openebs - name: openebs-control-plane-chaos + name: openebs-pool-container-failure 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 + name: openebs-pool-container-failure spec: definition: scope: Cluster @@ -419,15 +820,14 @@ spec: - "openebs.io" - "storage.k8s.io" resources: - - "deployments" - "replicasets" - - "jobs" - - "pods/log" - "events" + - "jobs" - "pods" + - "pods/log" + - "pods/exec" - "configmaps" - "secrets" - - "storageclasses" - "persistentvolumeclaims" - "cstorvolumereplicas" - "chaosengines" @@ -440,23 +840,16 @@ spec: - "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 + - ansible-playbook ./experiments/openebs/openebs-pool-container-failure/openebs_pool_container_failure_ansible_logic.yml -i /etc/ansible/hosts -vv; exit 0 command: - /bin/bash env: - name: ANSIBLE_STDOUT_CALLBACK - value: default + value: 'default' - name: OPENEBS_NS value: 'openebs' @@ -467,28 +860,36 @@ spec: - name: LIVENESS_APP_LABEL value: '' + # only pumba supported + # For pumba image use : gaiaadm/pumba:0.6.5 + - name: LIB_IMAGE + value: 'gaiaadm/pumba:0.6.5' + - name: LIVENESS_APP_NAMESPACE value: '' - - name: CHAOS_ITERATIONS - value: '2' + # provide the chaos interval + - name: CHAOS_INTERVAL + value: '10' - # provide the kill count - - name: KILL_COUNT - value: '' + # provide the total chaos duration + - name: TOTAL_CHAOS_DURATION + value: '20' - name: DATA_PERSISTENCE value: '' + - name: CHAOS_ITERATIONS + value: '2' + labels: - name: openebs-pool-pod-failure + name: openebs-pool-container-failure app.kubernetes.io/part-of: litmus app.kubernetes.io/component: experiment-job app.kubernetes.io/version: latest #configmaps: - #- name: openebs-pool-pod-failure + #- name: openebs-pool-container-failure # mountPath: /mnt - --- apiVersion: litmuschaos.io/v1alpha1 @@ -586,119 +987,6 @@ spec: #- name: openebs-target-network-delay # mountPath: /mnt ---- ---- -apiVersion: litmuschaos.io/v1alpha1 -description: - message: | - OpenEBS Pool Disk Loss contains chaos to disrupt state of infra resources. Experiments can inject disk loss against openEBS pool. -kind: ChaosExperiment -metadata: - labels: - litmuschaos.io/name: openebs - name: openebs-pool-disk-loss - app.kubernetes.io/part-of: litmus - app.kubernetes.io/component: chaosexperiment - app.kubernetes.io/version: latest - name: openebs-pool-disk-loss -spec: - definition: - scope: Cluster - permissions: - - apiGroups: - - "" - - "apps" - - "litmuschaos.io" - - "batch" - - "extensions" - - "storage.k8s.io" - - "openebs.io" - resources: - - "pods" - - "jobs" - - "pods/log" - - "events" - - "pods/exec" - - "cstorpools" - - "configmaps" - - "secrets" - - "storageclasses" - - "persistentvolumes" - - "persistentvolumeclaims" - - "cstorvolumereplicas" - - "chaosexperiments" - - "chaosresults" - - "chaosengines" - verbs: - - "create" - - "list" - - "get" - - "patch" - - "update" - - "delete" - image: "litmuschaos/ansible-runner:latest" - imagePullPolicy: Always - args: - - -c - - ansible-playbook ./experiments/openebs/openebs-pool-disk-loss/openebs_pool_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: '60' - - # Period to wait before injection of chaos in sec - - name: RAMP_TIME - value: '' - - # GKE and AWS supported - - name: CLOUD_PLATFORM - value: 'GKE' - - - name: PROJECT_ID - value: '' - - - name: NODE_NAME - value: '' - - - name: DISK_NAME - value: '' - - - name: ZONE_NAME - value: '' - - - name: DEVICE_NAME - value: '' - - - name: LIVENESS_APP_LABEL - value: '' - - - name: LIVENESS_APP_NAMESPACE - value: '' - - - name: DATA_PERSISTENCE - value: '' - - - name: OPENEBS_NAMESPACE - value: 'openebs' - - labels: - name: openebs-pool-disk-loss - app.kubernetes.io/part-of: litmus - app.kubernetes.io/component: experiment-job - app.kubernetes.io/version: latest - - configmaps: - - name: openebs-pool-disk-loss - mountPath: /mnt/ - - secrets: - - name: cloud-secret - mountPath: /tmp/ - --- --- apiVersion: litmuschaos.io/v1alpha1 @@ -807,291 +1095,3 @@ spec: # mountPath: /mnt --- ---- -apiVersion: litmuschaos.io/v1alpha1 -description: - message: | - Kill the pool container and check if gets scheduled again -kind: ChaosExperiment -metadata: - labels: - litmuschaos.io/name: openebs - name: openebs-pool-container-failure - app.kubernetes.io/part-of: litmus - app.kubernetes.io/component: chaosexperiment - app.kubernetes.io/version: latest - name: openebs-pool-container-failure -spec: - definition: - scope: Cluster - permissions: - - apiGroups: - - "" - - "extensions" - - "apps" - - "batch" - - "litmuschaos.io" - - "openebs.io" - - "storage.k8s.io" - resources: - - "replicasets" - - "events" - - "jobs" - - "pods" - - "pods/log" - - "pods/exec" - - "configmaps" - - "secrets" - - "persistentvolumeclaims" - - "cstorvolumereplicas" - - "chaosengines" - - "chaosexperiments" - - "chaosresults" - verbs: - - "create" - - "get" - - "delete" - - "list" - - "patch" - - "update" - image: "litmuschaos/ansible-runner:latest" - imagePullPolicy: Always - args: - - -c - - ansible-playbook ./experiments/openebs/openebs-pool-container-failure/openebs_pool_container_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: '' - - # only pumba supported - # For pumba image use : gaiaadm/pumba:0.6.5 - - name: LIB_IMAGE - value: 'gaiaadm/pumba:0.6.5' - - - name: LIVENESS_APP_NAMESPACE - value: '' - - # provide the chaos interval - - name: CHAOS_INTERVAL - value: '10' - - # provide the total chaos duration - - name: TOTAL_CHAOS_DURATION - value: '20' - - - name: DATA_PERSISTENCE - value: '' - - - name: CHAOS_ITERATIONS - value: '2' - - labels: - name: openebs-pool-container-failure - app.kubernetes.io/part-of: litmus - app.kubernetes.io/component: experiment-job - app.kubernetes.io/version: latest - #configmaps: - #- name: openebs-pool-container-failure - # mountPath: /mnt - ---- -apiVersion: litmuschaos.io/v1alpha1 -description: - message: | - Network loss to pool pod belonging to a OpenEBS PVC -kind: ChaosExperiment -metadata: - labels: - litmuschaos.io/name: openebs - name: openebs-pool-network-loss - app.kubernetes.io/part-of: litmus - app.kubernetes.io/component: chaosexperiment - app.kubernetes.io/version: latest - name: openebs-pool-network-loss -spec: - definition: - scope: Cluster - permissions: - - apiGroups: - - "" - - "apps" - - "litmuschaos.io" - - "batch" - - "extensions" - - "storage.k8s.io" - - "openebs.io" - resources: - - "pods" - - "pods/log" - - "pods/exec" - - "events" - - "jobs" - - "configmaps" - - "services" - - "persistentvolumeclaims" - - "storageclasses" - - "persistentvolumeclaims" - - "persistentvolumes" - - "chaosengines" - - "chaosexperiments" - - "chaosresults" - - "cstorpools" - - "cstorvolumereplicas" - - "replicasets" - verbs: - - "create" - - "get" - - "delete" - - "list" - - "patch" - - "update" - image: "litmuschaos/ansible-runner:latest" - imagePullPolicy: Always - args: - - -c - - ansible-playbook ./experiments/openebs/openebs-pool-network-loss/openebs_pool_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' - - # only pumba supported - # For pumba image use : gaiaadm/pumba:0.6.5 - - name: LIB_IMAGE - value: 'gaiaadm/pumba:0.6.5' - - - name: TC_IMAGE - value: 'gaiadocker/iproute2' - - - 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-pool-network-loss - app.kubernetes.io/part-of: litmus - app.kubernetes.io/component: experiment-job - app.kubernetes.io/version: latest - ---- -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 - ----