diff --git a/charts/gcp/experiments.yaml b/charts/gcp/experiments.yaml index 95f05ac..2388c62 100644 --- a/charts/gcp/experiments.yaml +++ b/charts/gcp/experiments.yaml @@ -1,4 +1,101 @@ apiVersion: litmuschaos.io/v1alpha1 +description: + message: | + Stops GCP VM instances and GKE nodes filtered by a label for a specified duration and later restarts them +kind: ChaosExperiment +metadata: + name: gcp-vm-instance-stop-by-label + labels: + name: gcp-vm-instance-stop-by-label + app.kubernetes.io/part-of: litmus + app.kubernetes.io/component: chaosexperiment + app.kubernetes.io/version: latest +spec: + definition: + scope: Cluster + permissions: + # Create and monitor the experiment & helper pods + - apiGroups: [""] + resources: ["pods"] + verbs: ["create","delete","get","list","patch","update", "deletecollection"] + # Performs CRUD operations on the events inside chaosengine and chaosresult + - apiGroups: [""] + resources: ["events"] + verbs: ["create","get","list","patch","update"] + # Fetch configmaps & secrets details and mount it to the experiment pod (if specified) + - apiGroups: [""] + resources: ["secrets","configmaps"] + verbs: ["get","list",] + # Track and get the runner, experiment, and helper pods log + - apiGroups: [""] + resources: ["pods/log"] + verbs: ["get","list","watch"] + # for configuring and monitor the experiment job by the chaos-runner pod + - apiGroups: ["batch"] + resources: ["jobs"] + verbs: ["create","list","get","delete","deletecollection"] + # for creation, status polling and deletion of litmus chaos resources used within a chaos workflow + - apiGroups: ["litmuschaos.io"] + resources: ["chaosengines","chaosexperiments","chaosresults"] + verbs: ["create","list","get","patch","update","delete"] + # for experiment to perform node status checks + - apiGroups: [""] + resources: ["nodes"] + verbs: ["get","list"] + image: "litmuschaos/go-runner:latest" + imagePullPolicy: Always + args: + - -c + - ./experiments -name gcp-vm-instance-stop-by-label + command: + - /bin/bash + env: + + # set chaos duration (in sec) as desired + - name: TOTAL_CHAOS_DURATION + value: '30' + + # set chaos interval (in sec) as desired + - name: CHAOS_INTERVAL + value: '30' + + - name: SEQUENCE + value: 'parallel' + + # GCP project ID to which the vm instances belong + - name: GCP_PROJECT_ID + value: '' + + # Label of the target vm instance(s) + - name: INSTANCE_LABEL + value: '' + + # Zone in which the target vm instance(s) filtered by the label exist + # all the instances should lie in a single zone + - name: ZONES + value: '' + + # enable it if the target instance is a part of a managed instance group + - name: MANAGED_INSTANCE_GROUP + value: 'disable' + + # set the percentage value of the instances with the given label + # which should be targeted as part of the chaos injection + - name: INSTANCE_AFFECTED_PERC + value: '' + + labels: + name: gcp-vm-instance-stop-by-label + 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: | Causes loss of a non-boot storage persistent disk from a GCP VM instance for a specified duration before attaching them back @@ -173,103 +270,6 @@ spec: - name: cloud-secret mountPath: /tmp/ ---- -apiVersion: litmuschaos.io/v1alpha1 -description: - message: | - Stops GCP VM instances and GKE nodes filtered by a label for a specified duration and later restarts them -kind: ChaosExperiment -metadata: - name: gcp-vm-instance-stop-by-label - labels: - name: gcp-vm-instance-stop-by-label - app.kubernetes.io/part-of: litmus - app.kubernetes.io/component: chaosexperiment - app.kubernetes.io/version: latest -spec: - definition: - scope: Cluster - permissions: - # Create and monitor the experiment & helper pods - - apiGroups: [""] - resources: ["pods"] - verbs: ["create","delete","get","list","patch","update", "deletecollection"] - # Performs CRUD operations on the events inside chaosengine and chaosresult - - apiGroups: [""] - resources: ["events"] - verbs: ["create","get","list","patch","update"] - # Fetch configmaps & secrets details and mount it to the experiment pod (if specified) - - apiGroups: [""] - resources: ["secrets","configmaps"] - verbs: ["get","list",] - # Track and get the runner, experiment, and helper pods log - - apiGroups: [""] - resources: ["pods/log"] - verbs: ["get","list","watch"] - # for configuring and monitor the experiment job by the chaos-runner pod - - apiGroups: ["batch"] - resources: ["jobs"] - verbs: ["create","list","get","delete","deletecollection"] - # for creation, status polling and deletion of litmus chaos resources used within a chaos workflow - - apiGroups: ["litmuschaos.io"] - resources: ["chaosengines","chaosexperiments","chaosresults"] - verbs: ["create","list","get","patch","update","delete"] - # for experiment to perform node status checks - - apiGroups: [""] - resources: ["nodes"] - verbs: ["get","list"] - image: "litmuschaos/go-runner:latest" - imagePullPolicy: Always - args: - - -c - - ./experiments -name gcp-vm-instance-stop-by-label - command: - - /bin/bash - env: - - # set chaos duration (in sec) as desired - - name: TOTAL_CHAOS_DURATION - value: '30' - - # set chaos interval (in sec) as desired - - name: CHAOS_INTERVAL - value: '30' - - - name: SEQUENCE - value: 'parallel' - - # GCP project ID to which the vm instances belong - - name: GCP_PROJECT_ID - value: '' - - # Label of the target vm instance(s) - - name: INSTANCE_LABEL - value: '' - - # Zone in which the target vm instance(s) filtered by the label exist - # all the instances should lie in a single zone - - name: ZONES - value: '' - - # enable it if the target instance is a part of a managed instance group - - name: MANAGED_INSTANCE_GROUP - value: 'disable' - - # set the percentage value of the instances with the given label - # which should be targeted as part of the chaos injection - - name: INSTANCE_AFFECTED_PERC - value: '' - - labels: - name: gcp-vm-instance-stop-by-label - 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: diff --git a/charts/generic/experiments.yaml b/charts/generic/experiments.yaml index 6cee3bf..ee2c98e 100644 --- a/charts/generic/experiments.yaml +++ b/charts/generic/experiments.yaml @@ -1,4 +1,949 @@ 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: + # Create and monitor the experiment & helper pods + - apiGroups: [""] + resources: ["pods"] + verbs: ["create","delete","get","list","patch","update", "deletecollection"] + # Performs CRUD operations on the events inside chaosengine and chaosresult + - apiGroups: [""] + resources: ["events"] + verbs: ["create","get","list","patch","update"] + # Fetch configmaps details and mount it to the experiment pod (if specified) + - apiGroups: [""] + resources: ["configmaps"] + verbs: ["get","list",] + # Track and get the runner, experiment, and helper pods log + - apiGroups: [""] + resources: ["pods/log"] + verbs: ["get","list","watch"] + # for creating and managing to execute comands inside target container + - apiGroups: [""] + resources: ["pods/exec"] + verbs: ["get","list","create"] + # deriving the parent/owner details of the pod(if parent is anyof {deployment, statefulset, daemonsets}) + - apiGroups: ["apps"] + resources: ["deployments","statefulsets","replicasets", "daemonsets"] + verbs: ["list","get"] + # deriving the parent/owner details of the pod(if parent is deploymentConfig) + - apiGroups: ["apps.openshift.io"] + resources: ["deploymentconfigs"] + verbs: ["list","get"] + # deriving the parent/owner details of the pod(if parent is deploymentConfig) + - apiGroups: [""] + resources: ["replicationcontrollers"] + verbs: ["get","list"] + # deriving the parent/owner details of the pod(if parent is argo-rollouts) + - apiGroups: ["argoproj.io"] + resources: ["rollouts"] + verbs: ["list","get"] + # for configuring and monitor the experiment job by the chaos-runner pod + - apiGroups: ["batch"] + resources: ["jobs"] + verbs: ["create","list","get","delete","deletecollection"] + # for creation, status polling and deletion of litmus chaos resources used within a chaos workflow + - apiGroups: ["litmuschaos.io"] + resources: ["chaosengines","chaosexperiments","chaosresults"] + verbs: ["create","list","get","patch","update","delete"] + image: "litmuschaos/go-runner:latest" + imagePullPolicy: Always + args: + - -c + - ./experiments -name pod-cpu-hog + command: + - /bin/bash + env: + - name: TOTAL_CHAOS_DURATION + value: '60' + + ## Number of CPU cores to stress + - name: CPU_CORES + value: '1' + + ## LOAD CPU WITH GIVEN PERCENT LOADING FOR THE CPU STRESS WORKERS. + ## 0 IS EFFECTIVELY A SLEEP (NO LOAD) AND 100 IS FULL LOADING + - name: CPU_LOAD + value: '100' + + ## 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 cluster runtime + - name: CONTAINER_RUNTIME + value: 'docker' + + # provide the socket file path + - name: SOCKET_PATH + value: '/var/run/docker.sock' + + - name: TARGET_PODS + value: '' + + # To select pods on specific node(s) + - name: NODE_LABEL + value: '' + + ## it defines the sequence of chaos execution for multiple target pods + ## supported values: serial, parallel + - name: SEQUENCE + value: 'parallel' + + labels: + name: pod-cpu-hog + app.kubernetes.io/part-of: litmus + app.kubernetes.io/component: experiment-job + app.kubernetes.io/runtime-api-usage: "true" + 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: + # Create and monitor the experiment & helper pods + - apiGroups: [""] + resources: ["pods"] + verbs: ["create","delete","get","list","patch","update", "deletecollection"] + # Performs CRUD operations on the events inside chaosengine and chaosresult + - apiGroups: [""] + resources: ["events"] + verbs: ["create","get","list","patch","update"] + # Fetch configmaps details and mount it to the experiment pod (if specified) + - apiGroups: [""] + resources: ["configmaps"] + verbs: ["get","list",] + # Track and get the runner, experiment, and helper pods log + - apiGroups: [""] + resources: ["pods/log"] + verbs: ["get","list","watch"] + # for creating and managing to execute comands inside target container + - apiGroups: [""] + resources: ["pods/exec","pods/eviction"] + verbs: ["get","list","create"] + # ignore daemonsets while draining the node + - apiGroups: ["apps"] + resources: ["daemonsets"] + verbs: ["list","get","delete"] + # for configuring and monitor the experiment job by the chaos-runner pod + - apiGroups: ["batch"] + resources: ["jobs"] + verbs: ["create","list","get","delete","deletecollection"] + # for creation, status polling and deletion of litmus chaos resources used within a chaos workflow + - apiGroups: ["litmuschaos.io"] + resources: ["chaosengines","chaosexperiments","chaosresults"] + verbs: ["create","list","get","patch","update","delete"] + # for experiment to perform node status checks + - 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: 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: '' + + # 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: | + It injects the chaos inside the pod which modifies the header of the request/response from the provided application server to the headers provided by the user and reverts after a specified duration +kind: ChaosExperiment +metadata: + name: pod-http-modify-header + labels: + name: pod-http-modify-header + app.kubernetes.io/part-of: litmus + app.kubernetes.io/component: chaosexperiment + app.kubernetes.io/version: latest +spec: + definition: + scope: Namespaced + permissions: + # Create and monitor the experiment & helper pods + - apiGroups: [""] + resources: ["pods"] + verbs: ["create","delete","get","list","patch","update", "deletecollection"] + # Performs CRUD operations on the events inside chaosengine and chaosresult + - apiGroups: [""] + resources: ["events"] + verbs: ["create","get","list","patch","update"] + # Fetch configmaps details and mount it to the experiment pod (if specified) + - apiGroups: [""] + resources: ["configmaps"] + verbs: ["get","list",] + # Track and get the runner, experiment, and helper pods log + - apiGroups: [""] + resources: ["pods/log"] + verbs: ["get","list","watch"] + # for creating and managing to execute comands inside target container + - apiGroups: [""] + resources: ["pods/exec"] + verbs: ["get","list","create"] + # deriving the parent/owner details of the pod(if parent is anyof {deployment, statefulset, daemonsets}) + - apiGroups: ["apps"] + resources: ["deployments","statefulsets","replicasets", "daemonsets"] + verbs: ["list","get"] + # deriving the parent/owner details of the pod(if parent is deploymentConfig) + - apiGroups: ["apps.openshift.io"] + resources: ["deploymentconfigs"] + verbs: ["list","get"] + # deriving the parent/owner details of the pod(if parent is deploymentConfig) + - apiGroups: [""] + resources: ["replicationcontrollers"] + verbs: ["get","list"] + # deriving the parent/owner details of the pod(if parent is argo-rollouts) + - apiGroups: ["argoproj.io"] + resources: ["rollouts"] + verbs: ["list","get"] + # for configuring and monitor the experiment job by the chaos-runner pod + - apiGroups: ["batch"] + resources: ["jobs"] + verbs: ["create","list","get","delete","deletecollection"] + # for creation, status polling and deletion of litmus chaos resources used within a chaos workflow + - apiGroups: ["litmuschaos.io"] + resources: ["chaosengines","chaosexperiments","chaosresults"] + verbs: ["create","list","get","patch","update","delete"] + image: "litmuschaos/go-runner:latest" + imagePullPolicy: Always + args: + - -c + - ./experiments -name pod-http-modify-header + command: + - /bin/bash + env: + + - name: TARGET_CONTAINER + value: '' + + # provide lib image + - name: LIB_IMAGE + value: 'litmuschaos/go-runner:latest' + + # map of headers to modify/add; Eg: {"X-Litmus-Test-Header": "X-Litmus-Test-Value"} + # to remove a header, just set the value to ""; Eg: {"X-Litmus-Test-Header": ""} + - name: HEADERS_MAP + value: '{}' + + # whether to modify response headers or request headers. Accepted values: request, response + - name: HEADER_MODE + value: 'response' + + # port of the target service + - name: TARGET_SERVICE_PORT + value: "80" + + # port on which the proxy will listen + - name: PROXY_PORT + value: "20000" + + # network interface on which the proxy will listen + - name: NETWORK_INTERFACE + value: "eth0" + + - 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 socket file path + - name: SOCKET_PATH + value: '/var/run/docker.sock' + + # To select pods on specific node(s) + - name: NODE_LABEL + value: '' + + ## it defines the sequence of chaos execution for multiple target pods + ## supported values: serial, parallel + - name: SEQUENCE + value: 'parallel' + + labels: + name: pod-http-modify-header + app.kubernetes.io/part-of: litmus + app.kubernetes.io/component: experiment-job + app.kubernetes.io/runtime-api-usage: "true" + app.kubernetes.io/version: latest + +--- +--- +apiVersion: litmuschaos.io/v1alpha1 +description: + message: | + Injects memory consumption on pods belonging to an app deployment +kind: ChaosExperiment +metadata: + name: pod-memory-hog-exec + labels: + name: pod-memory-hog-exec + app.kubernetes.io/part-of: litmus + app.kubernetes.io/component: chaosexperiment + app.kubernetes.io/version: latest +spec: + definition: + scope: Namespaced + permissions: + # Create and monitor the experiment & helper pods + - apiGroups: [""] + resources: ["pods"] + verbs: ["create","delete","get","list","patch","update", "deletecollection"] + # Performs CRUD operations on the events inside chaosengine and chaosresult + - apiGroups: [""] + resources: ["events"] + verbs: ["create","get","list","patch","update"] + # Fetch configmaps details and mount it to the experiment pod (if specified) + - apiGroups: [""] + resources: ["configmaps"] + verbs: ["get","list",] + # Track and get the runner, experiment, and helper pods log + - apiGroups: [""] + resources: ["pods/log"] + verbs: ["get","list","watch"] + # for creating and managing to execute comands inside target container + - apiGroups: [""] + resources: ["pods/exec"] + verbs: ["get","list","create"] + # deriving the parent/owner details of the pod(if parent is anyof {deployment, statefulset, daemonsets}) + - apiGroups: ["apps"] + resources: ["deployments","statefulsets","replicasets", "daemonsets"] + verbs: ["list","get"] + # deriving the parent/owner details of the pod(if parent is deploymentConfig) + - apiGroups: ["apps.openshift.io"] + resources: ["deploymentconfigs"] + verbs: ["list","get"] + # deriving the parent/owner details of the pod(if parent is deploymentConfig) + - apiGroups: [""] + resources: ["replicationcontrollers"] + verbs: ["get","list"] + # deriving the parent/owner details of the pod(if parent is argo-rollouts) + - apiGroups: ["argoproj.io"] + resources: ["rollouts"] + verbs: ["list","get"] + # for configuring and monitor the experiment job by the chaos-runner pod + - apiGroups: ["batch"] + resources: ["jobs"] + verbs: ["create","list","get","delete","deletecollection"] + # for creation, status polling and deletion of litmus chaos resources used within a chaos workflow + - apiGroups: ["litmuschaos.io"] + resources: ["chaosengines","chaosexperiments","chaosresults"] + verbs: ["create","list","get","patch","update","delete"] + image: "litmuschaos/go-runner:latest" + imagePullPolicy: Always + args: + - -c + - ./experiments -name pod-memory-hog-exec + 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 + - name: LIB + value: 'litmus' + + # The command to kill the chaos process + - name: CHAOS_KILL_COMMAND + value: "kill $(find /proc -name exe -lname '*/dd' 2>&1 | grep -v 'Permission denied' | awk -F/ '{print $(NF-1)}' | head -n 1)" + + ## 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-exec + app.kubernetes.io/part-of: litmus + app.kubernetes.io/component: experiment-job + app.kubernetes.io/version: latest + +--- +apiVersion: litmuschaos.io/v1alpha1 +description: + message: | + It injects the chaos inside the pod which modifies the body of the response from the provided application server to the body string provided by the user and reverts after a specified duration +kind: ChaosExperiment +metadata: + name: pod-http-modify-body + labels: + name: pod-http-modify-body + app.kubernetes.io/part-of: litmus + app.kubernetes.io/component: chaosexperiment + app.kubernetes.io/version: latest +spec: + definition: + scope: Namespaced + permissions: + # Create and monitor the experiment & helper pods + - apiGroups: [""] + resources: ["pods"] + verbs: ["create","delete","get","list","patch","update", "deletecollection"] + # Performs CRUD operations on the events inside chaosengine and chaosresult + - apiGroups: [""] + resources: ["events"] + verbs: ["create","get","list","patch","update"] + # Fetch configmaps details and mount it to the experiment pod (if specified) + - apiGroups: [""] + resources: ["configmaps"] + verbs: ["get","list",] + # Track and get the runner, experiment, and helper pods log + - apiGroups: [""] + resources: ["pods/log"] + verbs: ["get","list","watch"] + # for creating and managing to execute comands inside target container + - apiGroups: [""] + resources: ["pods/exec"] + verbs: ["get","list","create"] + # deriving the parent/owner details of the pod(if parent is anyof {deployment, statefulset, daemonsets}) + - apiGroups: ["apps"] + resources: ["deployments","statefulsets","replicasets", "daemonsets"] + verbs: ["list","get"] + # deriving the parent/owner details of the pod(if parent is deploymentConfig) + - apiGroups: ["apps.openshift.io"] + resources: ["deploymentconfigs"] + verbs: ["list","get"] + # deriving the parent/owner details of the pod(if parent is deploymentConfig) + - apiGroups: [""] + resources: ["replicationcontrollers"] + verbs: ["get","list"] + # deriving the parent/owner details of the pod(if parent is argo-rollouts) + - apiGroups: ["argoproj.io"] + resources: ["rollouts"] + verbs: ["list","get"] + # for configuring and monitor the experiment job by the chaos-runner pod + - apiGroups: ["batch"] + resources: ["jobs"] + verbs: ["create","list","get","delete","deletecollection"] + # for creation, status polling and deletion of litmus chaos resources used within a chaos workflow + - apiGroups: ["litmuschaos.io"] + resources: ["chaosengines","chaosexperiments","chaosresults"] + verbs: ["create","list","get","patch","update","delete"] + image: "litmuschaos/go-runner:latest" + imagePullPolicy: Always + args: + - -c + - ./experiments -name pod-http-modify-body + command: + - /bin/bash + env: + + - name: TARGET_CONTAINER + value: '' + + # provide lib image + - name: LIB_IMAGE + value: 'litmuschaos/go-runner:latest' + + # provide the body string to overwrite the response body + # if no value is provided, response will be an empty body. + - name: RESPONSE_BODY + value: '' + + # port of the target service + - name: TARGET_SERVICE_PORT + value: "80" + + # port on which the proxy will listen + - name: PROXY_PORT + value: "20000" + + # network interface on which the proxy will listen + - name: NETWORK_INTERFACE + value: "eth0" + + - 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 socket file path + - name: SOCKET_PATH + value: '/var/run/docker.sock' + + # To select pods on specific node(s) + - name: NODE_LABEL + value: '' + + ## it defines the sequence of chaos execution for multiple target pods + ## supported values: serial, parallel + - name: SEQUENCE + value: 'parallel' + + labels: + name: pod-http-modify-body + 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: + # Create and monitor the experiment & helper pods + - apiGroups: [""] + resources: ["pods"] + verbs: ["create","delete","get","list","patch","update", "deletecollection"] + # Performs CRUD operations on the events inside chaosengine and chaosresult + - apiGroups: [""] + resources: ["events"] + verbs: ["create","get","list","patch","update"] + # Fetch configmaps details and mount it to the experiment pod (if specified) + - apiGroups: [""] + resources: ["configmaps"] + verbs: ["get","list",] + # Track and get the runner, experiment, and helper pods log + - apiGroups: [""] + resources: ["pods/log"] + verbs: ["get","list","watch"] + # for creating and managing to execute comands inside target container + - apiGroups: [""] + resources: ["pods/exec"] + verbs: ["get","list","create"] + # for configuring and monitor the experiment job by the chaos-runner pod + - apiGroups: ["batch"] + resources: ["jobs"] + verbs: ["create","list","get","delete","deletecollection"] + # for creation, status polling and deletion of litmus chaos resources used within a chaos workflow + - apiGroups: ["litmuschaos.io"] + resources: ["chaosengines","chaosexperiments","chaosresults"] + verbs: ["create","list","get","patch","update","delete"] + # for experiment to perform node status checks + - apiGroups: [""] + resources: ["nodes"] + verbs: ["get","list"] + image: "litmuschaos/go-runner:latest" + imagePullPolicy: Always + args: + - -c + - ./experiments -name docker-service-kill + command: + - /bin/bash + env: + + - 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' + + - 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: docker-service-kill + app.kubernetes.io/part-of: litmus + app.kubernetes.io/component: experiment-job + app.kubernetes.io/service-kill: "true" + 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: + # Create and monitor the experiment & helper pods + - apiGroups: [""] + resources: ["pods"] + verbs: ["create","delete","get","list","patch","update", "deletecollection"] + # Performs CRUD operations on the events inside chaosengine and chaosresult + - apiGroups: [""] + resources: ["events"] + verbs: ["create","get","list","patch","update"] + # Fetch configmaps details and mount it to the experiment pod (if specified) + - apiGroups: [""] + resources: ["configmaps"] + verbs: ["get","list",] + # Track and get the runner, experiment, and helper pods log + - apiGroups: [""] + resources: ["pods/log"] + verbs: ["get","list","watch"] + # for creating and managing to execute comands inside target container + - apiGroups: [""] + resources: ["pods/exec"] + verbs: ["get","list","create"] + # deriving the parent/owner details of the pod(if parent is anyof {deployment, statefulset, daemonsets}) + - apiGroups: ["apps"] + resources: ["deployments","statefulsets","replicasets", "daemonsets"] + verbs: ["list","get"] + # deriving the parent/owner details of the pod(if parent is deploymentConfig) + - apiGroups: ["apps.openshift.io"] + resources: ["deploymentconfigs"] + verbs: ["list","get"] + # deriving the parent/owner details of the pod(if parent is deploymentConfig) + - apiGroups: [""] + resources: ["replicationcontrollers"] + verbs: ["get","list"] + # deriving the parent/owner details of the pod(if parent is argo-rollouts) + - apiGroups: ["argoproj.io"] + resources: ["rollouts"] + verbs: ["list","get"] + # for configuring and monitor the experiment job by the chaos-runner pod + - apiGroups: ["batch"] + resources: ["jobs"] + verbs: ["create","list","get","delete","deletecollection"] + # for creation, status polling and deletion of litmus chaos resources used within a chaos workflow + - apiGroups: ["litmuschaos.io"] + resources: ["chaosengines","chaosexperiments","chaosresults"] + verbs: ["create","list","get","patch","update","delete"] + image: "litmuschaos/go-runner:latest" + imagePullPolicy: Always + args: + - -c + - ./experiments -name pod-network-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: '' + + - name: JITTER + value: '0' + + # 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' + + # To select pods on specific node(s) + - name: NODE_LABEL + value: '' + + ## it defines the sequence of chaos execution for multiple target pods + ## supported values: serial, parallel + - name: SEQUENCE + value: 'parallel' + + labels: + name: pod-network-latency + app.kubernetes.io/part-of: litmus + app.kubernetes.io/component: experiment-job + app.kubernetes.io/runtime-api-usage: "true" + 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-exec + labels: + name: pod-cpu-hog-exec + app.kubernetes.io/part-of: litmus + app.kubernetes.io/component: chaosexperiment + app.kubernetes.io/version: latest +spec: + definition: + scope: Namespaced + permissions: + # Create and monitor the experiment & helper pods + - apiGroups: [""] + resources: ["pods"] + verbs: ["create","delete","get","list","patch","update", "deletecollection"] + # Performs CRUD operations on the events inside chaosengine and chaosresult + - apiGroups: [""] + resources: ["events"] + verbs: ["create","get","list","patch","update"] + # Fetch configmaps details and mount it to the experiment pod (if specified) + - apiGroups: [""] + resources: ["configmaps"] + verbs: ["get","list",] + # Track and get the runner, experiment, and helper pods log + - apiGroups: [""] + resources: ["pods/log"] + verbs: ["get","list","watch"] + # for creating and managing to execute comands inside target container + - apiGroups: [""] + resources: ["pods/exec"] + verbs: ["get","list","create"] + # deriving the parent/owner details of the pod(if parent is anyof {deployment, statefulset, daemonsets}) + - apiGroups: ["apps"] + resources: ["deployments","statefulsets","replicasets", "daemonsets"] + verbs: ["list","get"] + # deriving the parent/owner details of the pod(if parent is deploymentConfig) + - apiGroups: ["apps.openshift.io"] + resources: ["deploymentconfigs"] + verbs: ["list","get"] + # deriving the parent/owner details of the pod(if parent is deploymentConfig) + - apiGroups: [""] + resources: ["replicationcontrollers"] + verbs: ["get","list"] + # deriving the parent/owner details of the pod(if parent is argo-rollouts) + - apiGroups: ["argoproj.io"] + resources: ["rollouts"] + verbs: ["list","get"] + # for configuring and monitor the experiment job by the chaos-runner pod + - apiGroups: ["batch"] + resources: ["jobs"] + verbs: ["create","list","get","delete","deletecollection"] + # for creation, status polling and deletion of litmus chaos resources used within a chaos workflow + - apiGroups: ["litmuschaos.io"] + resources: ["chaosengines","chaosexperiments","chaosresults"] + verbs: ["create","list","get","patch","update","delete"] + image: "litmuschaos/go-runner:latest" + imagePullPolicy: Always + args: + - -c + - ./experiments -name pod-cpu-hog-exec + 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 + - name: LIB + value: 'litmus' + + # The command to kill the chaos process + - name: CHAOS_KILL_COMMAND + value: "kill $(find /proc -name exe -lname '*/md5sum' 2>&1 | grep -v 'Permission denied' | awk -F/ '{print $(NF-1)}')" + + - 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-exec + 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 memory hog on a node belonging to a deployment @@ -106,6 +1051,108 @@ spec: app.kubernetes.io/component: experiment-job app.kubernetes.io/version: latest +--- +apiVersion: litmuschaos.io/v1alpha1 +description: + message: | + Injects 100% network packet loss on pods belonging to an app deployment +kind: ChaosExperiment +metadata: + name: pod-network-partition + labels: + name: pod-network-partition + app.kubernetes.io/part-of: litmus + app.kubernetes.io/component: chaosexperiment + app.kubernetes.io/version: latest +spec: + definition: + scope: Namespaced + permissions: + # Create and monitor the experiment & helper pods + - apiGroups: [""] + resources: ["pods"] + verbs: ["create","delete","get","list","patch","update", "deletecollection"] + # Performs CRUD operations on the events inside chaosengine and chaosresult + - apiGroups: [""] + resources: ["events"] + verbs: ["create","get","list","patch","update"] + # Fetch configmaps details and mount it to the experiment pod (if specified) + - apiGroups: [""] + resources: ["configmaps"] + verbs: ["get","list",] + # Track and get the runner, experiment, and helper pods log + - apiGroups: [""] + resources: ["pods/log"] + verbs: ["get","list","watch"] + # for creating and managing to execute comands inside target container + - apiGroups: [""] + resources: ["pods/exec"] + verbs: ["get","list","create"] + # for configuring and monitor the experiment job by the chaos-runner pod + - apiGroups: ["batch"] + resources: ["jobs"] + verbs: ["create","list","get","delete","deletecollection"] + # performs CRUD operations on the network policies + - apiGroups: ["networking.k8s.io"] + resources: ["networkpolicies"] + verbs: ["create","delete","list","get"] + # for creation, status polling and deletion of litmus chaos resources used within a chaos workflow + - apiGroups: ["litmuschaos.io"] + resources: ["chaosengines","chaosexperiments","chaosresults"] + verbs: ["create","list","get","patch","update","delete"] + image: "litmuschaos/go-runner:latest" + imagePullPolicy: Always + args: + - -c + - ./experiments -name pod-network-partition + command: + - /bin/bash + env: + + - name: TOTAL_CHAOS_DURATION + value: '60' # in seconds + + # ime period to wait before and after injection of chaos in sec + - name: RAMP_TIME + value: '' + + # it should be litmus + - name: LIB + value: 'litmus' + + # 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 network policy type + # support ingress, egress, all values + - name: POLICY_TYPES + value: 'all' + + # provide labels of the destination pods + - name: POD_SELECTOR + value: '' + + # provide labels the destination namespaces + - name: NAMESPACE_SELECTOR + value: '' + + # provide comma separated ports + - name: PORTS + value: '' + + labels: + name: pod-network-partition + app.kubernetes.io/part-of: litmus + app.kubernetes.io/component: experiment-job + app.kubernetes.io/version: latest + --- --- apiVersion: litmuschaos.io/v1alpha1 @@ -197,12 +1244,12 @@ spec: apiVersion: litmuschaos.io/v1alpha1 description: message: | - Injects http request latency on pods belonging to an app deployment + it injects chaos into the pod which stops outgoing http requests by resetting the TCP connection and then reverts back to the original state after a specified duration kind: ChaosExperiment metadata: - name: pod-http-latency + name: pod-http-reset-peer labels: - name: pod-http-latency + name: pod-http-reset-peer app.kubernetes.io/part-of: litmus app.kubernetes.io/component: chaosexperiment app.kubernetes.io/version: latest @@ -258,21 +1305,21 @@ spec: imagePullPolicy: Always args: - -c - - ./experiments -name pod-http-latency + - ./experiments -name pod-http-reset-peer command: - /bin/bash env: - + - name: TARGET_CONTAINER value: '' # provide lib image - name: LIB_IMAGE value: 'litmuschaos/go-runner:latest' - - # set latency value for the chaos - - name: LATENCY - value: '2000' #in ms + + # reset timeout specifies after how much duration to reset the connection + - name: RESET_TIMEOUT + value: '0' #in ms # port of the target service - name: TARGET_SERVICE_PORT @@ -318,18 +1365,828 @@ spec: - name: NODE_LABEL value: '' + ## it defines the sequence of chaos execution for multiple target pods + ## supported values: serial, parallel + - name: SEQUENCE + value: 'parallel' + + labels: + name: pod-http-reset-peer + app.kubernetes.io/part-of: litmus + app.kubernetes.io/component: experiment-job + app.kubernetes.io/version: latest + +--- +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: + # Create and monitor the experiment & helper pods + - apiGroups: [""] + resources: ["pods"] + verbs: ["create","delete","get","list","patch","update", "deletecollection"] + # Performs CRUD operations on the events inside chaosengine and chaosresult + - apiGroups: [""] + resources: ["events"] + verbs: ["create","get","list","patch","update"] + # Fetch configmaps details and mount it to the experiment pod (if specified) + - apiGroups: [""] + resources: ["configmaps"] + verbs: ["get","list",] + # Track and get the runner, experiment, and helper pods log + - apiGroups: [""] + resources: ["pods/log"] + verbs: ["get","list","watch"] + # for creating and managing to execute comands inside target container + - apiGroups: [""] + resources: ["pods/exec"] + verbs: ["get","list","create"] + # for configuring and monitor the experiment job by the chaos-runner pod + - apiGroups: ["batch"] + resources: ["jobs"] + verbs: ["create","list","get","delete","deletecollection"] + # for creation, status polling and deletion of litmus chaos resources used within a chaos workflow + - apiGroups: ["litmuschaos.io"] + resources: ["chaosengines","chaosexperiments","chaosresults"] + verbs: ["create","list","get","patch","update","delete"] + # for experiment to perform node status checks + - 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: '' + + - name: NODE_LABEL + 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: "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: + # Create and monitor the experiment & helper pods + - apiGroups: [""] + resources: ["pods"] + verbs: ["create","delete","get","list","patch","update", "deletecollection"] + # Performs CRUD operations on the events inside chaosengine and chaosresult + - apiGroups: [""] + resources: ["events"] + verbs: ["create","get","list","patch","update"] + # Fetch configmaps details and mount it to the experiment pod (if specified) + - apiGroups: [""] + resources: ["configmaps"] + verbs: ["get","list",] + # Track and get the runner, experiment, and helper pods log + - apiGroups: [""] + resources: ["pods/log"] + verbs: ["get","list","watch"] + # for creating and managing to execute comands inside target container + - apiGroups: [""] + resources: ["pods/exec"] + verbs: ["get","list","create"] + # deriving the parent/owner details of the pod(if parent is anyof {deployment, statefulset, daemonsets}) + - apiGroups: ["apps"] + resources: ["deployments","statefulsets","replicasets", "daemonsets"] + verbs: ["list","get"] + # deriving the parent/owner details of the pod(if parent is deploymentConfig) + - apiGroups: ["apps.openshift.io"] + resources: ["deploymentconfigs"] + verbs: ["list","get"] + # deriving the parent/owner details of the pod(if parent is deploymentConfig) + - apiGroups: [""] + resources: ["replicationcontrollers"] + verbs: ["get","list"] + # deriving the parent/owner details of the pod(if parent is argo-rollouts) + - apiGroups: ["argoproj.io"] + resources: ["rollouts"] + verbs: ["list","get"] + # for configuring and monitor the experiment job by the chaos-runner pod + - apiGroups: ["batch"] + resources: ["jobs"] + verbs: ["create","list","get","delete","deletecollection"] + # for creation, status polling and deletion of litmus chaos resources used within a chaos workflow + - apiGroups: ["litmuschaos.io"] + resources: ["chaosengines","chaosexperiments","chaosresults"] + verbs: ["create","list","get","patch","update","delete"] + image: "litmuschaos/go-runner:latest" + imagePullPolicy: Always + args: + - -c + - ./experiments -name 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: '' + + # To select pods on specific node(s) + - name: NODE_LABEL + 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: pod-http-latency + name: container-kill + app.kubernetes.io/part-of: litmus + app.kubernetes.io/component: experiment-job + app.kubernetes.io/runtime-api-usage: "true" + app.kubernetes.io/version: latest + +--- +apiVersion: litmuschaos.io/v1alpha1 +description: + message: | + Pod DNS Spoof can spoof particular dns requests in target pod container to desired target hostnames +kind: ChaosExperiment +metadata: + name: pod-dns-spoof + labels: + name: pod-dns-spoof + app.kubernetes.io/part-of: litmus + app.kubernetes.io/component: chaosexperiment + app.kubernetes.io/version: latest +spec: + definition: + scope: Namespaced + permissions: + # Create and monitor the experiment & helper pods + - apiGroups: [""] + resources: ["pods"] + verbs: ["create","delete","get","list","patch","update", "deletecollection"] + # Performs CRUD operations on the events inside chaosengine and chaosresult + - apiGroups: [""] + resources: ["events"] + verbs: ["create","get","list","patch","update"] + # Fetch configmaps details and mount it to the experiment pod (if specified) + - apiGroups: [""] + resources: ["configmaps"] + verbs: ["get","list",] + # Track and get the runner, experiment, and helper pods log + - apiGroups: [""] + resources: ["pods/log"] + verbs: ["get","list","watch"] + # for creating and managing to execute comands inside target container + - apiGroups: [""] + resources: ["pods/exec"] + verbs: ["get","list","create"] + # deriving the parent/owner details of the pod(if parent is anyof {deployment, statefulset, daemonsets}) + - apiGroups: ["apps"] + resources: ["deployments","statefulsets","replicasets", "daemonsets"] + verbs: ["list","get"] + # deriving the parent/owner details of the pod(if parent is deploymentConfig) + - apiGroups: ["apps.openshift.io"] + resources: ["deploymentconfigs"] + verbs: ["list","get"] + # deriving the parent/owner details of the pod(if parent is deploymentConfig) + - apiGroups: [""] + resources: ["replicationcontrollers"] + verbs: ["get","list"] + # deriving the parent/owner details of the pod(if parent is argo-rollouts) + - apiGroups: ["argoproj.io"] + resources: ["rollouts"] + verbs: ["list","get"] + # for configuring and monitor the experiment job by the chaos-runner pod + - apiGroups: ["batch"] + resources: ["jobs"] + verbs: ["create","list","get","delete","deletecollection"] + # for creation, status polling and deletion of litmus chaos resources used within a chaos workflow + - apiGroups: ["litmuschaos.io"] + resources: ["chaosengines","chaosexperiments","chaosresults"] + verbs: ["create","list","get","patch","update","delete"] + image: "litmuschaos/go-runner:latest" + args: + - -c + - ./experiments -name pod-dns-spoof + 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" + + # map of the target hostnames eg. '{"abc.com":"spoofabc.com"}' . If empty no queries will be spoofed + - name: SPOOF_MAP + value: "" + + labels: + experiment: pod-dns-spoof app.kubernetes.io/part-of: litmus app.kubernetes.io/component: experiment-job app.kubernetes.io/runtime-api-usage: "true" 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: + # Create and monitor the experiment & helper pods + - apiGroups: [""] + resources: ["pods"] + verbs: ["create","delete","get","list","patch","update", "deletecollection"] + # Performs CRUD operations on the events inside chaosengine and chaosresult + - apiGroups: [""] + resources: ["events"] + verbs: ["create","get","list","patch","update"] + # Fetch configmaps details and mount it to the experiment pod (if specified) + - apiGroups: [""] + resources: ["configmaps"] + verbs: ["get","list",] + # Track and get the runner, experiment, and helper pods log + - apiGroups: [""] + resources: ["pods/log"] + verbs: ["get","list","watch"] + # for creating and managing to execute comands inside target container + - apiGroups: [""] + resources: ["pods/exec"] + verbs: ["get","list","create"] + # deriving the parent/owner details of the pod(if parent is anyof {deployment, statefulset, daemonsets}) + - apiGroups: ["apps"] + resources: ["deployments","statefulsets","replicasets", "daemonsets"] + verbs: ["list","get"] + # deriving the parent/owner details of the pod(if parent is deploymentConfig) + - apiGroups: ["apps.openshift.io"] + resources: ["deploymentconfigs"] + verbs: ["list","get"] + # deriving the parent/owner details of the pod(if parent is deploymentConfig) + - apiGroups: [""] + resources: ["replicationcontrollers"] + verbs: ["get","list"] + # deriving the parent/owner details of the pod(if parent is argo-rollouts) + - apiGroups: ["argoproj.io"] + resources: ["rollouts"] + verbs: ["list","get"] + # for configuring and monitor the experiment job by the chaos-runner pod + - apiGroups: ["batch"] + resources: ["jobs"] + verbs: ["create","list","get","delete","deletecollection"] + # for creation, status polling and deletion of litmus chaos resources used within a chaos workflow + - apiGroups: ["litmuschaos.io"] + resources: ["chaosengines","chaosexperiments","chaosresults"] + verbs: ["create","list","get","patch","update","delete"] + image: "litmuschaos/go-runner:latest" + imagePullPolicy: Always + args: + - -c + - ./experiments -name pod-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: '' + + # To select pods on specific node(s) + - name: NODE_LABEL + value: '' + + ## it defines the sequence of chaos execution for multiple target pods + ## supported values: serial, parallel + - name: SEQUENCE + value: 'parallel' + + labels: + name: pod-delete + app.kubernetes.io/part-of: litmus + app.kubernetes.io/component: experiment-job + app.kubernetes.io/version: latest + +--- +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: + # Create and monitor the experiment & helper pods + - apiGroups: [""] + resources: ["pods"] + verbs: ["create","delete","get","list","patch","update", "deletecollection"] + # Performs CRUD operations on the events inside chaosengine and chaosresult + - apiGroups: [""] + resources: ["events"] + verbs: ["create","get","list","patch","update"] + # Fetch configmaps details and mount it to the experiment pod (if specified) + - apiGroups: [""] + resources: ["configmaps"] + verbs: ["get","list",] + # Track and get the runner, experiment, and helper pods log + - apiGroups: [""] + resources: ["pods/log"] + verbs: ["get","list","watch"] + # for creating and managing to execute comands inside target container + - apiGroups: [""] + resources: ["pods/exec"] + verbs: ["get","list","create"] + # for configuring and monitor the experiment job by the chaos-runner pod + - apiGroups: ["batch"] + resources: ["jobs"] + verbs: ["create","list","get","delete","deletecollection"] + # for creation, status polling and deletion of litmus chaos resources used within a chaos workflow + - apiGroups: ["litmuschaos.io"] + resources: ["chaosengines","chaosexperiments","chaosresults"] + verbs: ["create","list","get","patch","update","delete"] + # for experiment to perform node status checks + - 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: '' + + ## LOAD CPU WITH GIVEN PERCENT LOADING FOR THE CPU STRESS WORKERS. + ## 0 IS EFFECTIVELY A SLEEP (NO LOAD) AND 100 IS FULL LOADING + - name: CPU_LOAD + value: '100' + + # 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 + +--- +apiVersion: litmuschaos.io/v1alpha1 +description: + message: | + It injects chaos inside the pod which modifies the status code of the response from the provided application server to desired status code provided by the user and reverts after a specified duration +kind: ChaosExperiment +metadata: + name: pod-http-status-code + labels: + name: pod-http-status-code + app.kubernetes.io/part-of: litmus + app.kubernetes.io/component: chaosexperiment + app.kubernetes.io/version: latest +spec: + definition: + scope: Namespaced + permissions: + # Create and monitor the experiment & helper pods + - apiGroups: [""] + resources: ["pods"] + verbs: ["create","delete","get","list","patch","update", "deletecollection"] + # Performs CRUD operations on the events inside chaosengine and chaosresult + - apiGroups: [""] + resources: ["events"] + verbs: ["create","get","list","patch","update"] + # Fetch configmaps details and mount it to the experiment pod (if specified) + - apiGroups: [""] + resources: ["configmaps"] + verbs: ["get","list",] + # Track and get the runner, experiment, and helper pods log + - apiGroups: [""] + resources: ["pods/log"] + verbs: ["get","list","watch"] + # for creating and managing to execute comands inside target container + - apiGroups: [""] + resources: ["pods/exec"] + verbs: ["get","list","create"] + # deriving the parent/owner details of the pod(if parent is anyof {deployment, statefulset, daemonsets}) + - apiGroups: ["apps"] + resources: ["deployments","statefulsets","replicasets", "daemonsets"] + verbs: ["list","get"] + # deriving the parent/owner details of the pod(if parent is deploymentConfig) + - apiGroups: ["apps.openshift.io"] + resources: ["deploymentconfigs"] + verbs: ["list","get"] + # deriving the parent/owner details of the pod(if parent is deploymentConfig) + - apiGroups: [""] + resources: ["replicationcontrollers"] + verbs: ["get","list"] + # deriving the parent/owner details of the pod(if parent is argo-rollouts) + - apiGroups: ["argoproj.io"] + resources: ["rollouts"] + verbs: ["list","get"] + # for configuring and monitor the experiment job by the chaos-runner pod + - apiGroups: ["batch"] + resources: ["jobs"] + verbs: ["create","list","get","delete","deletecollection"] + # for creation, status polling and deletion of litmus chaos resources used within a chaos workflow + - apiGroups: ["litmuschaos.io"] + resources: ["chaosengines","chaosexperiments","chaosresults"] + verbs: ["create","list","get","patch","update","delete"] + image: "litmuschaos/go-runner:latest" + imagePullPolicy: Always + args: + - -c + - ./experiments -name pod-http-status-code + command: + - /bin/bash + env: + + - name: TARGET_CONTAINER + value: '' + + # provide lib image + - name: LIB_IMAGE + value: 'litmuschaos/go-runner:latest' + + # modified status code for the http response + # if no value is provided, a random status code from the supported code list will selected + # if an invalid status code is provided, the experiment will fail + # supported status code list: [200, 201, 202, 204, 300, 301, 302, 304, 307, 400, 401, 403, 404, 500, 501, 502, 503, 504] + - name: STATUS_CODE + value: '' + + # whether to modify the body as per the status code provided + - name: "MODIFY_RESPONSE_BODY" + value: "true" + + # port of the target service + - name: TARGET_SERVICE_PORT + value: "80" + + # port on which the proxy will listen + - name: PROXY_PORT + value: "20000" + + # network interface on which the proxy will listen + - name: NETWORK_INTERFACE + value: "eth0" + + - 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 socket file path + - name: SOCKET_PATH + value: '/var/run/docker.sock' + + # To select pods on specific node(s) + - name: NODE_LABEL + value: '' + + ## it defines the sequence of chaos execution for multiple target pods + ## supported values: serial, parallel + - name: SEQUENCE + value: 'parallel' + + labels: + name: pod-http-status-code + 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: + # Create and monitor the experiment & helper pods + - apiGroups: [""] + resources: ["pods"] + verbs: ["create","delete","get","list","patch","update", "deletecollection"] + # Performs CRUD operations on the events inside chaosengine and chaosresult + - apiGroups: [""] + resources: ["events"] + verbs: ["create","get","list","patch","update"] + # Fetch configmaps & secrets details and mount it to the experiment pod (if specified) + - apiGroups: [""] + resources: ["configmaps","secrets"] + verbs: ["get","list",] + # Track and get the runner, experiment, and helper pods log + - apiGroups: [""] + resources: ["pods/log"] + verbs: ["get","list","watch"] + # for creating and managing to execute comands inside target container + - apiGroups: [""] + resources: ["pods/exec"] + verbs: ["get","list","create"] + # for configuring and monitor the experiment job by the chaos-runner pod + - apiGroups: ["batch"] + resources: ["jobs"] + verbs: ["create","list","get","delete","deletecollection"] + # for creation, status polling and deletion of litmus chaos resources used within a chaos workflow + - apiGroups: ["litmuschaos.io"] + resources: ["chaosengines","chaosexperiments","chaosresults"] + verbs: ["create","list","get","patch","update","delete"] + # for experiment to perform node status checks + - 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 @@ -596,346 +2453,6 @@ spec: app.kubernetes.io/runtime-api-usage: "true" app.kubernetes.io/version: latest ---- -apiVersion: litmuschaos.io/v1alpha1 -description: - message: | - it injects chaos into the pod which stops outgoing http requests by resetting the TCP connection and then reverts back to the original state after a specified duration -kind: ChaosExperiment -metadata: - name: pod-http-reset-peer - labels: - name: pod-http-reset-peer - app.kubernetes.io/part-of: litmus - app.kubernetes.io/component: chaosexperiment - app.kubernetes.io/version: latest -spec: - definition: - scope: Namespaced - permissions: - # Create and monitor the experiment & helper pods - - apiGroups: [""] - resources: ["pods"] - verbs: ["create","delete","get","list","patch","update", "deletecollection"] - # Performs CRUD operations on the events inside chaosengine and chaosresult - - apiGroups: [""] - resources: ["events"] - verbs: ["create","get","list","patch","update"] - # Fetch configmaps details and mount it to the experiment pod (if specified) - - apiGroups: [""] - resources: ["configmaps"] - verbs: ["get","list",] - # Track and get the runner, experiment, and helper pods log - - apiGroups: [""] - resources: ["pods/log"] - verbs: ["get","list","watch"] - # for creating and managing to execute comands inside target container - - apiGroups: [""] - resources: ["pods/exec"] - verbs: ["get","list","create"] - # deriving the parent/owner details of the pod(if parent is anyof {deployment, statefulset, daemonsets}) - - apiGroups: ["apps"] - resources: ["deployments","statefulsets","replicasets", "daemonsets"] - verbs: ["list","get"] - # deriving the parent/owner details of the pod(if parent is deploymentConfig) - - apiGroups: ["apps.openshift.io"] - resources: ["deploymentconfigs"] - verbs: ["list","get"] - # deriving the parent/owner details of the pod(if parent is deploymentConfig) - - apiGroups: [""] - resources: ["replicationcontrollers"] - verbs: ["get","list"] - # deriving the parent/owner details of the pod(if parent is argo-rollouts) - - apiGroups: ["argoproj.io"] - resources: ["rollouts"] - verbs: ["list","get"] - # for configuring and monitor the experiment job by the chaos-runner pod - - apiGroups: ["batch"] - resources: ["jobs"] - verbs: ["create","list","get","delete","deletecollection"] - # for creation, status polling and deletion of litmus chaos resources used within a chaos workflow - - apiGroups: ["litmuschaos.io"] - resources: ["chaosengines","chaosexperiments","chaosresults"] - verbs: ["create","list","get","patch","update","delete"] - image: "litmuschaos/go-runner:latest" - imagePullPolicy: Always - args: - - -c - - ./experiments -name pod-http-reset-peer - command: - - /bin/bash - env: - - - name: TARGET_CONTAINER - value: '' - - # provide lib image - - name: LIB_IMAGE - value: 'litmuschaos/go-runner:latest' - - # reset timeout specifies after how much duration to reset the connection - - name: RESET_TIMEOUT - value: '0' #in ms - - # port of the target service - - name: TARGET_SERVICE_PORT - value: "80" - - # port on which the proxy will listen - - name: PROXY_PORT - value: "20000" - - # network interface on which the proxy will listen - - name: NETWORK_INTERFACE - value: "eth0" - - - 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 socket file path - - name: SOCKET_PATH - value: '/var/run/docker.sock' - - # To select pods on specific node(s) - - name: NODE_LABEL - value: '' - - ## it defines the sequence of chaos execution for multiple target pods - ## supported values: serial, parallel - - name: SEQUENCE - value: 'parallel' - - labels: - name: pod-http-reset-peer - 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: - # Create and monitor the experiment & helper pods - - apiGroups: [""] - resources: ["pods"] - verbs: ["create","delete","get","list","patch","update", "deletecollection"] - # Performs CRUD operations on the events inside chaosengine and chaosresult - - apiGroups: [""] - resources: ["events"] - verbs: ["create","get","list","patch","update"] - # Fetch configmaps & secrets details and mount it to the experiment pod (if specified) - - apiGroups: [""] - resources: ["configmaps","secrets"] - verbs: ["get","list",] - # Track and get the runner, experiment, and helper pods log - - apiGroups: [""] - resources: ["pods/log"] - verbs: ["get","list","watch"] - # for creating and managing to execute comands inside target container - - apiGroups: [""] - resources: ["pods/exec"] - verbs: ["get","list","create"] - # for configuring and monitor the experiment job by the chaos-runner pod - - apiGroups: ["batch"] - resources: ["jobs"] - verbs: ["create","list","get","delete","deletecollection"] - # for creation, status polling and deletion of litmus chaos resources used within a chaos workflow - - apiGroups: ["litmuschaos.io"] - resources: ["chaosengines","chaosexperiments","chaosresults"] - verbs: ["create","list","get","patch","update","delete"] - # for experiment to perform node status checks - - 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: - message: | - Deletes a pod belonging to a deployment/statefulset/daemonset -kind: ChaosExperiment -metadata: - name: pod-delete - labels: - name: pod-delete - app.kubernetes.io/part-of: litmus - app.kubernetes.io/component: chaosexperiment - app.kubernetes.io/version: latest -spec: - definition: - scope: Namespaced - permissions: - # Create and monitor the experiment & helper pods - - apiGroups: [""] - resources: ["pods"] - verbs: ["create","delete","get","list","patch","update", "deletecollection"] - # Performs CRUD operations on the events inside chaosengine and chaosresult - - apiGroups: [""] - resources: ["events"] - verbs: ["create","get","list","patch","update"] - # Fetch configmaps details and mount it to the experiment pod (if specified) - - apiGroups: [""] - resources: ["configmaps"] - verbs: ["get","list",] - # Track and get the runner, experiment, and helper pods log - - apiGroups: [""] - resources: ["pods/log"] - verbs: ["get","list","watch"] - # for creating and managing to execute comands inside target container - - apiGroups: [""] - resources: ["pods/exec"] - verbs: ["get","list","create"] - # deriving the parent/owner details of the pod(if parent is anyof {deployment, statefulset, daemonsets}) - - apiGroups: ["apps"] - resources: ["deployments","statefulsets","replicasets", "daemonsets"] - verbs: ["list","get"] - # deriving the parent/owner details of the pod(if parent is deploymentConfig) - - apiGroups: ["apps.openshift.io"] - resources: ["deploymentconfigs"] - verbs: ["list","get"] - # deriving the parent/owner details of the pod(if parent is deploymentConfig) - - apiGroups: [""] - resources: ["replicationcontrollers"] - verbs: ["get","list"] - # deriving the parent/owner details of the pod(if parent is argo-rollouts) - - apiGroups: ["argoproj.io"] - resources: ["rollouts"] - verbs: ["list","get"] - # for configuring and monitor the experiment job by the chaos-runner pod - - apiGroups: ["batch"] - resources: ["jobs"] - verbs: ["create","list","get","delete","deletecollection"] - # for creation, status polling and deletion of litmus chaos resources used within a chaos workflow - - apiGroups: ["litmuschaos.io"] - resources: ["chaosengines","chaosexperiments","chaosresults"] - verbs: ["create","list","get","patch","update","delete"] - image: "litmuschaos/go-runner:latest" - imagePullPolicy: Always - args: - - -c - - ./experiments -name pod-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: '' - - # To select pods on specific node(s) - - name: NODE_LABEL - value: '' - - ## it defines the sequence of chaos execution for multiple target pods - ## supported values: serial, parallel - - name: SEQUENCE - value: 'parallel' - - labels: - name: pod-delete - app.kubernetes.io/part-of: litmus - app.kubernetes.io/component: experiment-job - app.kubernetes.io/version: latest - --- apiVersion: litmuschaos.io/v1alpha1 description: @@ -1076,17 +2593,16 @@ spec: app.kubernetes.io/runtime-api-usage: "true" app.kubernetes.io/version: latest ---- --- apiVersion: litmuschaos.io/v1alpha1 description: message: | - Taint the node where application pod is scheduled + poweroff node kind: ChaosExperiment metadata: - name: node-taint + name: node-poweroff labels: - name: node-taint + name: node-poweroff app.kubernetes.io/part-of: litmus app.kubernetes.io/component: chaosexperiment app.kubernetes.io/version: latest @@ -1102,342 +2618,9 @@ spec: - apiGroups: [""] resources: ["events"] verbs: ["create","get","list","patch","update"] - # Fetch configmaps details and mount it to the experiment pod (if specified) + # Fetch configmaps & secrets details and mount it to the experiment pod (if specified) - apiGroups: [""] - resources: ["configmaps"] - verbs: ["get","list",] - # Track and get the runner, experiment, and helper pods log - - apiGroups: [""] - resources: ["pods/log"] - verbs: ["get","list","watch"] - # for creating and managing to execute comands inside target container - - apiGroups: [""] - resources: ["pods/exec","pods/eviction"] - verbs: ["get","list","create"] - # ignore daemonsets while draining the node - - apiGroups: ["apps"] - resources: ["daemonsets"] - verbs: ["list","get","delete"] - # for configuring and monitor the experiment job by the chaos-runner pod - - apiGroups: ["batch"] - resources: ["jobs"] - verbs: ["create","list","get","delete","deletecollection"] - # for creation, status polling and deletion of litmus chaos resources used within a chaos workflow - - apiGroups: ["litmuschaos.io"] - resources: ["chaosengines","chaosexperiments","chaosresults"] - verbs: ["create","list","get","patch","update","delete"] - # for experiment to perform node status checks - - 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: 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: '' - - # 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: | - Pod DNS Spoof can spoof particular dns requests in target pod container to desired target hostnames -kind: ChaosExperiment -metadata: - name: pod-dns-spoof - labels: - name: pod-dns-spoof - app.kubernetes.io/part-of: litmus - app.kubernetes.io/component: chaosexperiment - app.kubernetes.io/version: latest -spec: - definition: - scope: Namespaced - permissions: - # Create and monitor the experiment & helper pods - - apiGroups: [""] - resources: ["pods"] - verbs: ["create","delete","get","list","patch","update", "deletecollection"] - # Performs CRUD operations on the events inside chaosengine and chaosresult - - apiGroups: [""] - resources: ["events"] - verbs: ["create","get","list","patch","update"] - # Fetch configmaps details and mount it to the experiment pod (if specified) - - apiGroups: [""] - resources: ["configmaps"] - verbs: ["get","list",] - # Track and get the runner, experiment, and helper pods log - - apiGroups: [""] - resources: ["pods/log"] - verbs: ["get","list","watch"] - # for creating and managing to execute comands inside target container - - apiGroups: [""] - resources: ["pods/exec"] - verbs: ["get","list","create"] - # deriving the parent/owner details of the pod(if parent is anyof {deployment, statefulset, daemonsets}) - - apiGroups: ["apps"] - resources: ["deployments","statefulsets","replicasets", "daemonsets"] - verbs: ["list","get"] - # deriving the parent/owner details of the pod(if parent is deploymentConfig) - - apiGroups: ["apps.openshift.io"] - resources: ["deploymentconfigs"] - verbs: ["list","get"] - # deriving the parent/owner details of the pod(if parent is deploymentConfig) - - apiGroups: [""] - resources: ["replicationcontrollers"] - verbs: ["get","list"] - # deriving the parent/owner details of the pod(if parent is argo-rollouts) - - apiGroups: ["argoproj.io"] - resources: ["rollouts"] - verbs: ["list","get"] - # for configuring and monitor the experiment job by the chaos-runner pod - - apiGroups: ["batch"] - resources: ["jobs"] - verbs: ["create","list","get","delete","deletecollection"] - # for creation, status polling and deletion of litmus chaos resources used within a chaos workflow - - apiGroups: ["litmuschaos.io"] - resources: ["chaosengines","chaosexperiments","chaosresults"] - verbs: ["create","list","get","patch","update","delete"] - image: "litmuschaos/go-runner:latest" - args: - - -c - - ./experiments -name pod-dns-spoof - 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" - - # map of the target hostnames eg. '{"abc.com":"spoofabc.com"}' . If empty no queries will be spoofed - - name: SPOOF_MAP - value: "" - - labels: - experiment: pod-dns-spoof - app.kubernetes.io/part-of: litmus - app.kubernetes.io/component: experiment-job - app.kubernetes.io/runtime-api-usage: "true" - 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: - # Create and monitor the experiment & helper pods - - apiGroups: [""] - resources: ["pods"] - verbs: ["create","delete","get","list","patch","update", "deletecollection"] - # Performs CRUD operations on the events inside chaosengine and chaosresult - - apiGroups: [""] - resources: ["events"] - verbs: ["create","get","list","patch","update"] - # Fetch configmaps details and mount it to the experiment pod (if specified) - - apiGroups: [""] - resources: ["configmaps"] - verbs: ["get","list",] - # Track and get the runner, experiment, and helper pods log - - apiGroups: [""] - resources: ["pods/log"] - verbs: ["get","list","watch"] - # for creating and managing to execute comands inside target container - - apiGroups: [""] - resources: ["pods/exec"] - verbs: ["get","list","create"] - # deriving the parent/owner details of the pod(if parent is anyof {deployment, statefulset, daemonsets}) - - apiGroups: ["apps"] - resources: ["deployments","statefulsets","replicasets", "daemonsets"] - verbs: ["list","get"] - # deriving the parent/owner details of the pod(if parent is deploymentConfig) - - apiGroups: ["apps.openshift.io"] - resources: ["deploymentconfigs"] - verbs: ["list","get"] - # deriving the parent/owner details of the pod(if parent is deploymentConfig) - - apiGroups: [""] - resources: ["replicationcontrollers"] - verbs: ["get","list"] - # deriving the parent/owner details of the pod(if parent is argo-rollouts) - - apiGroups: ["argoproj.io"] - resources: ["rollouts"] - verbs: ["list","get"] - # for configuring and monitor the experiment job by the chaos-runner pod - - apiGroups: ["batch"] - resources: ["jobs"] - verbs: ["create","list","get","delete","deletecollection"] - # for creation, status polling and deletion of litmus chaos resources used within a chaos workflow - - apiGroups: ["litmuschaos.io"] - resources: ["chaosengines","chaosexperiments","chaosresults"] - verbs: ["create","list","get","patch","update","delete"] - image: "litmuschaos/go-runner:latest" - imagePullPolicy: Always - args: - - -c - - ./experiments -name pod-cpu-hog - command: - - /bin/bash - env: - - name: TOTAL_CHAOS_DURATION - value: '60' - - ## Number of CPU cores to stress - - name: CPU_CORES - value: '1' - - ## LOAD CPU WITH GIVEN PERCENT LOADING FOR THE CPU STRESS WORKERS. - ## 0 IS EFFECTIVELY A SLEEP (NO LOAD) AND 100 IS FULL LOADING - - name: CPU_LOAD - value: '100' - - ## 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 cluster runtime - - name: CONTAINER_RUNTIME - value: 'docker' - - # provide the socket file path - - name: SOCKET_PATH - value: '/var/run/docker.sock' - - - name: TARGET_PODS - value: '' - - # To select pods on specific node(s) - - name: NODE_LABEL - value: '' - - ## it defines the sequence of chaos execution for multiple target pods - ## supported values: serial, parallel - - name: SEQUENCE - value: 'parallel' - - labels: - name: pod-cpu-hog - app.kubernetes.io/part-of: litmus - app.kubernetes.io/component: experiment-job - app.kubernetes.io/runtime-api-usage: "true" - 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: - # Create and monitor the experiment & helper pods - - apiGroups: [""] - resources: ["pods"] - verbs: ["create","delete","get","list","patch","update", "deletecollection"] - # Performs CRUD operations on the events inside chaosengine and chaosresult - - apiGroups: [""] - resources: ["events"] - verbs: ["create","get","list","patch","update"] - # Fetch configmaps details and mount it to the experiment pod (if specified) - - apiGroups: [""] - resources: ["configmaps"] + resources: ["configmaps","secrets"] verbs: ["get","list",] # Track and get the runner, experiment, and helper pods log - apiGroups: [""] @@ -1463,54 +2646,68 @@ spec: imagePullPolicy: Always args: - -c - - ./experiments -name kubelet-service-kill + - ./experiments -name node-restart command: - /bin/bash env: - + - name: SSH_USER + value: 'root' + - name: TOTAL_CHAOS_DURATION - value: '60' # in seconds + value: '60' + + - 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' - - name: NODE_LABEL - value: '' - # provide lib image - name: LIB_IMAGE - value: 'ubuntu:16.04' - - # provide the target node name + 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: kubelet-service-kill + name: node-poweroff app.kubernetes.io/part-of: litmus app.kubernetes.io/component: experiment-job - app.kubernetes.io/service-kill: "true" app.kubernetes.io/version: latest + secrets: + - name: id-rsa + mountPath: /mnt/ --- apiVersion: litmuschaos.io/v1alpha1 description: - message: "Kills a container belonging to an application pod \n" + message: | + Scale the application replicas and test the node autoscaling on cluster kind: ChaosExperiment metadata: - name: container-kill + name: pod-autoscaler labels: - name: container-kill + name: pod-autoscaler app.kubernetes.io/part-of: litmus app.kubernetes.io/component: chaosexperiment app.kubernetes.io/version: latest spec: definition: - scope: Namespaced + scope: Cluster permissions: # Create and monitor the experiment & helper pods - apiGroups: [""] @@ -1532,22 +2729,10 @@ spec: - apiGroups: [""] resources: ["pods/exec"] verbs: ["get","list","create"] - # deriving the parent/owner details of the pod(if parent is anyof {deployment, statefulset, daemonsets}) + # performs CRUD operations on the deployments and statefulsets - apiGroups: ["apps"] - resources: ["deployments","statefulsets","replicasets", "daemonsets"] - verbs: ["list","get"] - # deriving the parent/owner details of the pod(if parent is deploymentConfig) - - apiGroups: ["apps.openshift.io"] - resources: ["deploymentconfigs"] - verbs: ["list","get"] - # deriving the parent/owner details of the pod(if parent is deploymentConfig) - - apiGroups: [""] - resources: ["replicationcontrollers"] - verbs: ["get","list"] - # deriving the parent/owner details of the pod(if parent is argo-rollouts) - - apiGroups: ["argoproj.io"] - resources: ["rollouts"] - verbs: ["list","get"] + resources: ["deployments","statefulsets"] + verbs: ["list","get","patch","update"] # for configuring and monitor the experiment job by the chaos-runner pod - apiGroups: ["batch"] resources: ["jobs"] @@ -1560,67 +2745,31 @@ spec: imagePullPolicy: Always args: - -c - - ./experiments -name container-kill + - ./experiments -name pod-autoscaler command: - /bin/bash env: - - name: TARGET_CONTAINER - value: '' + - name: TOTAL_CHAOS_DURATION + value: '60' # Period to wait before and after injection of chaos in sec - name: RAMP_TIME value: '' - # lib can be litmus or pumba + # Number of replicas to scale + - name: REPLICA_COUNT + value: '5' + + # PROVIDE THE LIB HERE + # ONLY LITMUS SUPPORTED - 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: '' - - # To select pods on specific node(s) - - name: NODE_LABEL - 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 + name: pod-autoscaler app.kubernetes.io/part-of: litmus app.kubernetes.io/component: experiment-job - app.kubernetes.io/runtime-api-usage: "true" app.kubernetes.io/version: latest --- @@ -1759,6 +2908,229 @@ spec: app.kubernetes.io/runtime-api-usage: "true" app.kubernetes.io/version: latest +--- +apiVersion: litmuschaos.io/v1alpha1 +description: + message: | + Injects http request latency on pods belonging to an app deployment +kind: ChaosExperiment +metadata: + name: pod-http-latency + labels: + name: pod-http-latency + app.kubernetes.io/part-of: litmus + app.kubernetes.io/component: chaosexperiment + app.kubernetes.io/version: latest +spec: + definition: + scope: Namespaced + permissions: + # Create and monitor the experiment & helper pods + - apiGroups: [""] + resources: ["pods"] + verbs: ["create","delete","get","list","patch","update", "deletecollection"] + # Performs CRUD operations on the events inside chaosengine and chaosresult + - apiGroups: [""] + resources: ["events"] + verbs: ["create","get","list","patch","update"] + # Fetch configmaps details and mount it to the experiment pod (if specified) + - apiGroups: [""] + resources: ["configmaps"] + verbs: ["get","list",] + # Track and get the runner, experiment, and helper pods log + - apiGroups: [""] + resources: ["pods/log"] + verbs: ["get","list","watch"] + # for creating and managing to execute comands inside target container + - apiGroups: [""] + resources: ["pods/exec"] + verbs: ["get","list","create"] + # deriving the parent/owner details of the pod(if parent is anyof {deployment, statefulset, daemonsets}) + - apiGroups: ["apps"] + resources: ["deployments","statefulsets","replicasets", "daemonsets"] + verbs: ["list","get"] + # deriving the parent/owner details of the pod(if parent is deploymentConfig) + - apiGroups: ["apps.openshift.io"] + resources: ["deploymentconfigs"] + verbs: ["list","get"] + # deriving the parent/owner details of the pod(if parent is deploymentConfig) + - apiGroups: [""] + resources: ["replicationcontrollers"] + verbs: ["get","list"] + # deriving the parent/owner details of the pod(if parent is argo-rollouts) + - apiGroups: ["argoproj.io"] + resources: ["rollouts"] + verbs: ["list","get"] + # for configuring and monitor the experiment job by the chaos-runner pod + - apiGroups: ["batch"] + resources: ["jobs"] + verbs: ["create","list","get","delete","deletecollection"] + # for creation, status polling and deletion of litmus chaos resources used within a chaos workflow + - apiGroups: ["litmuschaos.io"] + resources: ["chaosengines","chaosexperiments","chaosresults"] + verbs: ["create","list","get","patch","update","delete"] + image: "litmuschaos/go-runner:latest" + imagePullPolicy: Always + args: + - -c + - ./experiments -name pod-http-latency + command: + - /bin/bash + env: + + - name: TARGET_CONTAINER + value: '' + + # provide lib image + - name: LIB_IMAGE + value: 'litmuschaos/go-runner:latest' + + # set latency value for the chaos + - name: LATENCY + value: '2000' #in ms + + # port of the target service + - name: TARGET_SERVICE_PORT + value: "80" + + # port on which the proxy will listen + - name: PROXY_PORT + value: "20000" + + # network interface on which the proxy will listen + - name: NETWORK_INTERFACE + value: "eth0" + + - 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 socket file path + - name: SOCKET_PATH + value: '/var/run/docker.sock' + + # To select pods on specific node(s) + - name: NODE_LABEL + value: '' + + ## it defines the sequence of chaos execution for multiple target pods + ## supported values: serial, parallel + - name: SEQUENCE + value: 'parallel' + + labels: + name: pod-http-latency + app.kubernetes.io/part-of: litmus + app.kubernetes.io/component: experiment-job + app.kubernetes.io/runtime-api-usage: "true" + 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: + # Create and monitor the experiment & helper pods + - apiGroups: [""] + resources: ["pods"] + verbs: ["create","delete","get","list","patch","update", "deletecollection"] + # Performs CRUD operations on the events inside chaosengine and chaosresult + - apiGroups: [""] + resources: ["events"] + verbs: ["create","get","list","patch","update"] + # Fetch configmaps details and mount it to the experiment pod (if specified) + - apiGroups: [""] + resources: ["configmaps"] + verbs: ["get","list",] + # Track and get the runner, experiment, and helper pods log + - apiGroups: [""] + resources: ["pods/log"] + verbs: ["get","list","watch"] + # for creating and managing to execute comands inside target container + - apiGroups: [""] + resources: ["pods/exec"] + verbs: ["get","list","create"] + # for configuring and monitor the experiment job by the chaos-runner pod + - apiGroups: ["batch"] + resources: ["jobs"] + verbs: ["create","list","get","delete","deletecollection"] + # for creation, status polling and deletion of litmus chaos resources used within a chaos workflow + - apiGroups: ["litmuschaos.io"] + resources: ["chaosengines","chaosexperiments","chaosresults"] + verbs: ["create","list","get","patch","update","delete"] + # for experiment to perform node status checks + - 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: '60' # in seconds + + # Period to wait before and after injection of chaos in sec + - name: RAMP_TIME + 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: kubelet-service-kill + app.kubernetes.io/part-of: litmus + app.kubernetes.io/component: experiment-job + app.kubernetes.io/service-kill: "true" + app.kubernetes.io/version: latest + --- apiVersion: litmuschaos.io/v1alpha1 description: @@ -1876,1272 +3248,6 @@ spec: app.kubernetes.io/runtime-api-usage: "true" 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: - # Create and monitor the experiment & helper pods - - apiGroups: [""] - resources: ["pods"] - verbs: ["create","delete","get","list","patch","update", "deletecollection"] - # Performs CRUD operations on the events inside chaosengine and chaosresult - - apiGroups: [""] - resources: ["events"] - verbs: ["create","get","list","patch","update"] - # Fetch configmaps details and mount it to the experiment pod (if specified) - - apiGroups: [""] - resources: ["configmaps"] - verbs: ["get","list",] - # Track and get the runner, experiment, and helper pods log - - apiGroups: [""] - resources: ["pods/log"] - verbs: ["get","list","watch"] - # for creating and managing to execute comands inside target container - - apiGroups: [""] - resources: ["pods/exec"] - verbs: ["get","list","create"] - # performs CRUD operations on the deployments and statefulsets - - apiGroups: ["apps"] - resources: ["deployments","statefulsets"] - verbs: ["list","get","patch","update"] - # for configuring and monitor the experiment job by the chaos-runner pod - - apiGroups: ["batch"] - resources: ["jobs"] - verbs: ["create","list","get","delete","deletecollection"] - # for creation, status polling and deletion of litmus chaos resources used within a chaos workflow - - apiGroups: ["litmuschaos.io"] - resources: ["chaosengines","chaosexperiments","chaosresults"] - verbs: ["create","list","get","patch","update","delete"] - image: "litmuschaos/go-runner:latest" - imagePullPolicy: Always - args: - - -c - - ./experiments -name pod-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: | - It injects chaos inside the pod which modifies the status code of the response from the provided application server to desired status code provided by the user and reverts after a specified duration -kind: ChaosExperiment -metadata: - name: pod-http-status-code - labels: - name: pod-http-status-code - app.kubernetes.io/part-of: litmus - app.kubernetes.io/component: chaosexperiment - app.kubernetes.io/version: latest -spec: - definition: - scope: Namespaced - permissions: - # Create and monitor the experiment & helper pods - - apiGroups: [""] - resources: ["pods"] - verbs: ["create","delete","get","list","patch","update", "deletecollection"] - # Performs CRUD operations on the events inside chaosengine and chaosresult - - apiGroups: [""] - resources: ["events"] - verbs: ["create","get","list","patch","update"] - # Fetch configmaps details and mount it to the experiment pod (if specified) - - apiGroups: [""] - resources: ["configmaps"] - verbs: ["get","list",] - # Track and get the runner, experiment, and helper pods log - - apiGroups: [""] - resources: ["pods/log"] - verbs: ["get","list","watch"] - # for creating and managing to execute comands inside target container - - apiGroups: [""] - resources: ["pods/exec"] - verbs: ["get","list","create"] - # deriving the parent/owner details of the pod(if parent is anyof {deployment, statefulset, daemonsets}) - - apiGroups: ["apps"] - resources: ["deployments","statefulsets","replicasets", "daemonsets"] - verbs: ["list","get"] - # deriving the parent/owner details of the pod(if parent is deploymentConfig) - - apiGroups: ["apps.openshift.io"] - resources: ["deploymentconfigs"] - verbs: ["list","get"] - # deriving the parent/owner details of the pod(if parent is deploymentConfig) - - apiGroups: [""] - resources: ["replicationcontrollers"] - verbs: ["get","list"] - # deriving the parent/owner details of the pod(if parent is argo-rollouts) - - apiGroups: ["argoproj.io"] - resources: ["rollouts"] - verbs: ["list","get"] - # for configuring and monitor the experiment job by the chaos-runner pod - - apiGroups: ["batch"] - resources: ["jobs"] - verbs: ["create","list","get","delete","deletecollection"] - # for creation, status polling and deletion of litmus chaos resources used within a chaos workflow - - apiGroups: ["litmuschaos.io"] - resources: ["chaosengines","chaosexperiments","chaosresults"] - verbs: ["create","list","get","patch","update","delete"] - image: "litmuschaos/go-runner:latest" - imagePullPolicy: Always - args: - - -c - - ./experiments -name pod-http-status-code - command: - - /bin/bash - env: - - - name: TARGET_CONTAINER - value: '' - - # provide lib image - - name: LIB_IMAGE - value: 'litmuschaos/go-runner:latest' - - # modified status code for the http response - # if no value is provided, a random status code from the supported code list will selected - # if an invalid status code is provided, the experiment will fail - # supported status code list: [200, 201, 202, 204, 300, 301, 302, 304, 307, 400, 401, 403, 404, 500, 501, 502, 503, 504] - - name: STATUS_CODE - value: '' - - # whether to modify the body as per the status code provided - - name: "MODIFY_RESPONSE_BODY" - value: "true" - - # port of the target service - - name: TARGET_SERVICE_PORT - value: "80" - - # port on which the proxy will listen - - name: PROXY_PORT - value: "20000" - - # network interface on which the proxy will listen - - name: NETWORK_INTERFACE - value: "eth0" - - - 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 socket file path - - name: SOCKET_PATH - value: '/var/run/docker.sock' - - # To select pods on specific node(s) - - name: NODE_LABEL - value: '' - - ## it defines the sequence of chaos execution for multiple target pods - ## supported values: serial, parallel - - name: SEQUENCE - value: 'parallel' - - labels: - name: pod-http-status-code - 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: - # Create and monitor the experiment & helper pods - - apiGroups: [""] - resources: ["pods"] - verbs: ["create","delete","get","list","patch","update", "deletecollection"] - # Performs CRUD operations on the events inside chaosengine and chaosresult - - apiGroups: [""] - resources: ["events"] - verbs: ["create","get","list","patch","update"] - # Fetch configmaps details and mount it to the experiment pod (if specified) - - apiGroups: [""] - resources: ["configmaps"] - verbs: ["get","list",] - # Track and get the runner, experiment, and helper pods log - - apiGroups: [""] - resources: ["pods/log"] - verbs: ["get","list","watch"] - # for creating and managing to execute comands inside target container - - apiGroups: [""] - resources: ["pods/exec"] - verbs: ["get","list","create"] - # deriving the parent/owner details of the pod(if parent is anyof {deployment, statefulset, daemonsets}) - - apiGroups: ["apps"] - resources: ["deployments","statefulsets","replicasets", "daemonsets"] - verbs: ["list","get"] - # deriving the parent/owner details of the pod(if parent is deploymentConfig) - - apiGroups: ["apps.openshift.io"] - resources: ["deploymentconfigs"] - verbs: ["list","get"] - # deriving the parent/owner details of the pod(if parent is deploymentConfig) - - apiGroups: [""] - resources: ["replicationcontrollers"] - verbs: ["get","list"] - # deriving the parent/owner details of the pod(if parent is argo-rollouts) - - apiGroups: ["argoproj.io"] - resources: ["rollouts"] - verbs: ["list","get"] - # for configuring and monitor the experiment job by the chaos-runner pod - - apiGroups: ["batch"] - resources: ["jobs"] - verbs: ["create","list","get","delete","deletecollection"] - # for creation, status polling and deletion of litmus chaos resources used within a chaos workflow - - apiGroups: ["litmuschaos.io"] - resources: ["chaosengines","chaosexperiments","chaosresults"] - verbs: ["create","list","get","patch","update","delete"] - image: "litmuschaos/go-runner:latest" - imagePullPolicy: Always - args: - - -c - - ./experiments -name pod-network-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: '' - - - name: JITTER - value: '0' - - # 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' - - # To select pods on specific node(s) - - name: NODE_LABEL - value: '' - - ## it defines the sequence of chaos execution for multiple target pods - ## supported values: serial, parallel - - name: SEQUENCE - value: 'parallel' - - labels: - name: pod-network-latency - app.kubernetes.io/part-of: litmus - app.kubernetes.io/component: experiment-job - app.kubernetes.io/runtime-api-usage: "true" - app.kubernetes.io/version: latest - ---- ---- -apiVersion: litmuschaos.io/v1alpha1 -description: - message: | - Injects memory consumption on pods belonging to an app deployment -kind: ChaosExperiment -metadata: - name: pod-memory-hog-exec - labels: - name: pod-memory-hog-exec - app.kubernetes.io/part-of: litmus - app.kubernetes.io/component: chaosexperiment - app.kubernetes.io/version: latest -spec: - definition: - scope: Namespaced - permissions: - # Create and monitor the experiment & helper pods - - apiGroups: [""] - resources: ["pods"] - verbs: ["create","delete","get","list","patch","update", "deletecollection"] - # Performs CRUD operations on the events inside chaosengine and chaosresult - - apiGroups: [""] - resources: ["events"] - verbs: ["create","get","list","patch","update"] - # Fetch configmaps details and mount it to the experiment pod (if specified) - - apiGroups: [""] - resources: ["configmaps"] - verbs: ["get","list",] - # Track and get the runner, experiment, and helper pods log - - apiGroups: [""] - resources: ["pods/log"] - verbs: ["get","list","watch"] - # for creating and managing to execute comands inside target container - - apiGroups: [""] - resources: ["pods/exec"] - verbs: ["get","list","create"] - # deriving the parent/owner details of the pod(if parent is anyof {deployment, statefulset, daemonsets}) - - apiGroups: ["apps"] - resources: ["deployments","statefulsets","replicasets", "daemonsets"] - verbs: ["list","get"] - # deriving the parent/owner details of the pod(if parent is deploymentConfig) - - apiGroups: ["apps.openshift.io"] - resources: ["deploymentconfigs"] - verbs: ["list","get"] - # deriving the parent/owner details of the pod(if parent is deploymentConfig) - - apiGroups: [""] - resources: ["replicationcontrollers"] - verbs: ["get","list"] - # deriving the parent/owner details of the pod(if parent is argo-rollouts) - - apiGroups: ["argoproj.io"] - resources: ["rollouts"] - verbs: ["list","get"] - # for configuring and monitor the experiment job by the chaos-runner pod - - apiGroups: ["batch"] - resources: ["jobs"] - verbs: ["create","list","get","delete","deletecollection"] - # for creation, status polling and deletion of litmus chaos resources used within a chaos workflow - - apiGroups: ["litmuschaos.io"] - resources: ["chaosengines","chaosexperiments","chaosresults"] - verbs: ["create","list","get","patch","update","delete"] - image: "litmuschaos/go-runner:latest" - imagePullPolicy: Always - args: - - -c - - ./experiments -name pod-memory-hog-exec - 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 - - name: LIB - value: 'litmus' - - # The command to kill the chaos process - - name: CHAOS_KILL_COMMAND - value: "kill $(find /proc -name exe -lname '*/dd' 2>&1 | grep -v 'Permission denied' | awk -F/ '{print $(NF-1)}' | head -n 1)" - - ## 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-exec - app.kubernetes.io/part-of: litmus - app.kubernetes.io/component: experiment-job - app.kubernetes.io/version: latest - ---- -apiVersion: litmuschaos.io/v1alpha1 -description: - message: | - It injects the chaos inside the pod which modifies the header of the request/response from the provided application server to the headers provided by the user and reverts after a specified duration -kind: ChaosExperiment -metadata: - name: pod-http-modify-header - labels: - name: pod-http-modify-header - app.kubernetes.io/part-of: litmus - app.kubernetes.io/component: chaosexperiment - app.kubernetes.io/version: latest -spec: - definition: - scope: Namespaced - permissions: - # Create and monitor the experiment & helper pods - - apiGroups: [""] - resources: ["pods"] - verbs: ["create","delete","get","list","patch","update", "deletecollection"] - # Performs CRUD operations on the events inside chaosengine and chaosresult - - apiGroups: [""] - resources: ["events"] - verbs: ["create","get","list","patch","update"] - # Fetch configmaps details and mount it to the experiment pod (if specified) - - apiGroups: [""] - resources: ["configmaps"] - verbs: ["get","list",] - # Track and get the runner, experiment, and helper pods log - - apiGroups: [""] - resources: ["pods/log"] - verbs: ["get","list","watch"] - # for creating and managing to execute comands inside target container - - apiGroups: [""] - resources: ["pods/exec"] - verbs: ["get","list","create"] - # deriving the parent/owner details of the pod(if parent is anyof {deployment, statefulset, daemonsets}) - - apiGroups: ["apps"] - resources: ["deployments","statefulsets","replicasets", "daemonsets"] - verbs: ["list","get"] - # deriving the parent/owner details of the pod(if parent is deploymentConfig) - - apiGroups: ["apps.openshift.io"] - resources: ["deploymentconfigs"] - verbs: ["list","get"] - # deriving the parent/owner details of the pod(if parent is deploymentConfig) - - apiGroups: [""] - resources: ["replicationcontrollers"] - verbs: ["get","list"] - # deriving the parent/owner details of the pod(if parent is argo-rollouts) - - apiGroups: ["argoproj.io"] - resources: ["rollouts"] - verbs: ["list","get"] - # for configuring and monitor the experiment job by the chaos-runner pod - - apiGroups: ["batch"] - resources: ["jobs"] - verbs: ["create","list","get","delete","deletecollection"] - # for creation, status polling and deletion of litmus chaos resources used within a chaos workflow - - apiGroups: ["litmuschaos.io"] - resources: ["chaosengines","chaosexperiments","chaosresults"] - verbs: ["create","list","get","patch","update","delete"] - image: "litmuschaos/go-runner:latest" - imagePullPolicy: Always - args: - - -c - - ./experiments -name pod-http-modify-header - command: - - /bin/bash - env: - - - name: TARGET_CONTAINER - value: '' - - # provide lib image - - name: LIB_IMAGE - value: 'litmuschaos/go-runner:latest' - - # map of headers to modify/add; Eg: {"X-Litmus-Test-Header": "X-Litmus-Test-Value"} - # to remove a header, just set the value to ""; Eg: {"X-Litmus-Test-Header": ""} - - name: HEADERS_MAP - value: '{}' - - # whether to modify response headers or request headers. Accepted values: request, response - - name: HEADER_MODE - value: 'response' - - # port of the target service - - name: TARGET_SERVICE_PORT - value: "80" - - # port on which the proxy will listen - - name: PROXY_PORT - value: "20000" - - # network interface on which the proxy will listen - - name: NETWORK_INTERFACE - value: "eth0" - - - 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 socket file path - - name: SOCKET_PATH - value: '/var/run/docker.sock' - - # To select pods on specific node(s) - - name: NODE_LABEL - value: '' - - ## it defines the sequence of chaos execution for multiple target pods - ## supported values: serial, parallel - - name: SEQUENCE - value: 'parallel' - - labels: - name: pod-http-modify-header - app.kubernetes.io/part-of: litmus - app.kubernetes.io/component: experiment-job - app.kubernetes.io/runtime-api-usage: "true" - app.kubernetes.io/version: latest - ---- -apiVersion: litmuschaos.io/v1alpha1 -description: - message: | - It injects the chaos inside the pod which modifies the body of the response from the provided application server to the body string provided by the user and reverts after a specified duration -kind: ChaosExperiment -metadata: - name: pod-http-modify-body - labels: - name: pod-http-modify-body - app.kubernetes.io/part-of: litmus - app.kubernetes.io/component: chaosexperiment - app.kubernetes.io/version: latest -spec: - definition: - scope: Namespaced - permissions: - # Create and monitor the experiment & helper pods - - apiGroups: [""] - resources: ["pods"] - verbs: ["create","delete","get","list","patch","update", "deletecollection"] - # Performs CRUD operations on the events inside chaosengine and chaosresult - - apiGroups: [""] - resources: ["events"] - verbs: ["create","get","list","patch","update"] - # Fetch configmaps details and mount it to the experiment pod (if specified) - - apiGroups: [""] - resources: ["configmaps"] - verbs: ["get","list",] - # Track and get the runner, experiment, and helper pods log - - apiGroups: [""] - resources: ["pods/log"] - verbs: ["get","list","watch"] - # for creating and managing to execute comands inside target container - - apiGroups: [""] - resources: ["pods/exec"] - verbs: ["get","list","create"] - # deriving the parent/owner details of the pod(if parent is anyof {deployment, statefulset, daemonsets}) - - apiGroups: ["apps"] - resources: ["deployments","statefulsets","replicasets", "daemonsets"] - verbs: ["list","get"] - # deriving the parent/owner details of the pod(if parent is deploymentConfig) - - apiGroups: ["apps.openshift.io"] - resources: ["deploymentconfigs"] - verbs: ["list","get"] - # deriving the parent/owner details of the pod(if parent is deploymentConfig) - - apiGroups: [""] - resources: ["replicationcontrollers"] - verbs: ["get","list"] - # deriving the parent/owner details of the pod(if parent is argo-rollouts) - - apiGroups: ["argoproj.io"] - resources: ["rollouts"] - verbs: ["list","get"] - # for configuring and monitor the experiment job by the chaos-runner pod - - apiGroups: ["batch"] - resources: ["jobs"] - verbs: ["create","list","get","delete","deletecollection"] - # for creation, status polling and deletion of litmus chaos resources used within a chaos workflow - - apiGroups: ["litmuschaos.io"] - resources: ["chaosengines","chaosexperiments","chaosresults"] - verbs: ["create","list","get","patch","update","delete"] - image: "litmuschaos/go-runner:latest" - imagePullPolicy: Always - args: - - -c - - ./experiments -name pod-http-modify-body - command: - - /bin/bash - env: - - - name: TARGET_CONTAINER - value: '' - - # provide lib image - - name: LIB_IMAGE - value: 'litmuschaos/go-runner:latest' - - # provide the body string to overwrite the response body - # if no value is provided, response will be an empty body. - - name: RESPONSE_BODY - value: '' - - # port of the target service - - name: TARGET_SERVICE_PORT - value: "80" - - # port on which the proxy will listen - - name: PROXY_PORT - value: "20000" - - # network interface on which the proxy will listen - - name: NETWORK_INTERFACE - value: "eth0" - - - 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 socket file path - - name: SOCKET_PATH - value: '/var/run/docker.sock' - - # To select pods on specific node(s) - - name: NODE_LABEL - value: '' - - ## it defines the sequence of chaos execution for multiple target pods - ## supported values: serial, parallel - - name: SEQUENCE - value: 'parallel' - - labels: - name: pod-http-modify-body - 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: - # Create and monitor the experiment & helper pods - - apiGroups: [""] - resources: ["pods"] - verbs: ["create","delete","get","list","patch","update", "deletecollection"] - # Performs CRUD operations on the events inside chaosengine and chaosresult - - apiGroups: [""] - resources: ["events"] - verbs: ["create","get","list","patch","update"] - # Fetch configmaps & secrets details and mount it to the experiment pod (if specified) - - apiGroups: [""] - resources: ["configmaps","secrets"] - verbs: ["get","list",] - # Track and get the runner, experiment, and helper pods log - - apiGroups: [""] - resources: ["pods/log"] - verbs: ["get","list","watch"] - # for creating and managing to execute comands inside target container - - apiGroups: [""] - resources: ["pods/exec"] - verbs: ["get","list","create"] - # for configuring and monitor the experiment job by the chaos-runner pod - - apiGroups: ["batch"] - resources: ["jobs"] - verbs: ["create","list","get","delete","deletecollection"] - # for creation, status polling and deletion of litmus chaos resources used within a chaos workflow - - apiGroups: ["litmuschaos.io"] - resources: ["chaosengines","chaosexperiments","chaosresults"] - verbs: ["create","list","get","patch","update","delete"] - # for experiment to perform node status checks - - 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' - - - 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: | - Injects cpu consumption on pods belonging to an app deployment -kind: ChaosExperiment -metadata: - name: pod-cpu-hog-exec - labels: - name: pod-cpu-hog-exec - app.kubernetes.io/part-of: litmus - app.kubernetes.io/component: chaosexperiment - app.kubernetes.io/version: latest -spec: - definition: - scope: Namespaced - permissions: - # Create and monitor the experiment & helper pods - - apiGroups: [""] - resources: ["pods"] - verbs: ["create","delete","get","list","patch","update", "deletecollection"] - # Performs CRUD operations on the events inside chaosengine and chaosresult - - apiGroups: [""] - resources: ["events"] - verbs: ["create","get","list","patch","update"] - # Fetch configmaps details and mount it to the experiment pod (if specified) - - apiGroups: [""] - resources: ["configmaps"] - verbs: ["get","list",] - # Track and get the runner, experiment, and helper pods log - - apiGroups: [""] - resources: ["pods/log"] - verbs: ["get","list","watch"] - # for creating and managing to execute comands inside target container - - apiGroups: [""] - resources: ["pods/exec"] - verbs: ["get","list","create"] - # deriving the parent/owner details of the pod(if parent is anyof {deployment, statefulset, daemonsets}) - - apiGroups: ["apps"] - resources: ["deployments","statefulsets","replicasets", "daemonsets"] - verbs: ["list","get"] - # deriving the parent/owner details of the pod(if parent is deploymentConfig) - - apiGroups: ["apps.openshift.io"] - resources: ["deploymentconfigs"] - verbs: ["list","get"] - # deriving the parent/owner details of the pod(if parent is deploymentConfig) - - apiGroups: [""] - resources: ["replicationcontrollers"] - verbs: ["get","list"] - # deriving the parent/owner details of the pod(if parent is argo-rollouts) - - apiGroups: ["argoproj.io"] - resources: ["rollouts"] - verbs: ["list","get"] - # for configuring and monitor the experiment job by the chaos-runner pod - - apiGroups: ["batch"] - resources: ["jobs"] - verbs: ["create","list","get","delete","deletecollection"] - # for creation, status polling and deletion of litmus chaos resources used within a chaos workflow - - apiGroups: ["litmuschaos.io"] - resources: ["chaosengines","chaosexperiments","chaosresults"] - verbs: ["create","list","get","patch","update","delete"] - image: "litmuschaos/go-runner:latest" - imagePullPolicy: Always - args: - - -c - - ./experiments -name pod-cpu-hog-exec - 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 - - name: LIB - value: 'litmus' - - # The command to kill the chaos process - - name: CHAOS_KILL_COMMAND - value: "kill $(find /proc -name exe -lname '*/md5sum' 2>&1 | grep -v 'Permission denied' | awk -F/ '{print $(NF-1)}')" - - - 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-exec - 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: - # Create and monitor the experiment & helper pods - - apiGroups: [""] - resources: ["pods"] - verbs: ["create","delete","get","list","patch","update", "deletecollection"] - # Performs CRUD operations on the events inside chaosengine and chaosresult - - apiGroups: [""] - resources: ["events"] - verbs: ["create","get","list","patch","update"] - # Fetch configmaps details and mount it to the experiment pod (if specified) - - apiGroups: [""] - resources: ["configmaps"] - verbs: ["get","list",] - # Track and get the runner, experiment, and helper pods log - - apiGroups: [""] - resources: ["pods/log"] - verbs: ["get","list","watch"] - # for creating and managing to execute comands inside target container - - apiGroups: [""] - resources: ["pods/exec"] - verbs: ["get","list","create"] - # for configuring and monitor the experiment job by the chaos-runner pod - - apiGroups: ["batch"] - resources: ["jobs"] - verbs: ["create","list","get","delete","deletecollection"] - # for creation, status polling and deletion of litmus chaos resources used within a chaos workflow - - apiGroups: ["litmuschaos.io"] - resources: ["chaosengines","chaosexperiments","chaosresults"] - verbs: ["create","list","get","patch","update","delete"] - # for experiment to perform node status checks - - apiGroups: [""] - resources: ["nodes"] - verbs: ["get","list"] - image: "litmuschaos/go-runner:latest" - imagePullPolicy: Always - args: - - -c - - ./experiments -name docker-service-kill - command: - - /bin/bash - env: - - - 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' - - - 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: docker-service-kill - app.kubernetes.io/part-of: litmus - app.kubernetes.io/component: experiment-job - app.kubernetes.io/service-kill: "true" - app.kubernetes.io/version: latest - - ---- -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: - # Create and monitor the experiment & helper pods - - apiGroups: [""] - resources: ["pods"] - verbs: ["create","delete","get","list","patch","update", "deletecollection"] - # Performs CRUD operations on the events inside chaosengine and chaosresult - - apiGroups: [""] - resources: ["events"] - verbs: ["create","get","list","patch","update"] - # Fetch configmaps details and mount it to the experiment pod (if specified) - - apiGroups: [""] - resources: ["configmaps"] - verbs: ["get","list",] - # Track and get the runner, experiment, and helper pods log - - apiGroups: [""] - resources: ["pods/log"] - verbs: ["get","list","watch"] - # for creating and managing to execute comands inside target container - - apiGroups: [""] - resources: ["pods/exec"] - verbs: ["get","list","create"] - # for configuring and monitor the experiment job by the chaos-runner pod - - apiGroups: ["batch"] - resources: ["jobs"] - verbs: ["create","list","get","delete","deletecollection"] - # for creation, status polling and deletion of litmus chaos resources used within a chaos workflow - - apiGroups: ["litmuschaos.io"] - resources: ["chaosengines","chaosexperiments","chaosresults"] - verbs: ["create","list","get","patch","update","delete"] - # for experiment to perform node status checks - - 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: '' - - - name: NODE_LABEL - 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: | - Injects 100% network packet loss on pods belonging to an app deployment -kind: ChaosExperiment -metadata: - name: pod-network-partition - labels: - name: pod-network-partition - app.kubernetes.io/part-of: litmus - app.kubernetes.io/component: chaosexperiment - app.kubernetes.io/version: latest -spec: - definition: - scope: Namespaced - permissions: - # Create and monitor the experiment & helper pods - - apiGroups: [""] - resources: ["pods"] - verbs: ["create","delete","get","list","patch","update", "deletecollection"] - # Performs CRUD operations on the events inside chaosengine and chaosresult - - apiGroups: [""] - resources: ["events"] - verbs: ["create","get","list","patch","update"] - # Fetch configmaps details and mount it to the experiment pod (if specified) - - apiGroups: [""] - resources: ["configmaps"] - verbs: ["get","list",] - # Track and get the runner, experiment, and helper pods log - - apiGroups: [""] - resources: ["pods/log"] - verbs: ["get","list","watch"] - # for creating and managing to execute comands inside target container - - apiGroups: [""] - resources: ["pods/exec"] - verbs: ["get","list","create"] - # for configuring and monitor the experiment job by the chaos-runner pod - - apiGroups: ["batch"] - resources: ["jobs"] - verbs: ["create","list","get","delete","deletecollection"] - # performs CRUD operations on the network policies - - apiGroups: ["networking.k8s.io"] - resources: ["networkpolicies"] - verbs: ["create","delete","list","get"] - # for creation, status polling and deletion of litmus chaos resources used within a chaos workflow - - apiGroups: ["litmuschaos.io"] - resources: ["chaosengines","chaosexperiments","chaosresults"] - verbs: ["create","list","get","patch","update","delete"] - image: "litmuschaos/go-runner:latest" - imagePullPolicy: Always - args: - - -c - - ./experiments -name pod-network-partition - command: - - /bin/bash - env: - - - name: TOTAL_CHAOS_DURATION - value: '60' # in seconds - - # ime period to wait before and after injection of chaos in sec - - name: RAMP_TIME - value: '' - - # it should be litmus - - name: LIB - value: 'litmus' - - # 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 network policy type - # support ingress, egress, all values - - name: POLICY_TYPES - value: 'all' - - # provide labels of the destination pods - - name: POD_SELECTOR - value: '' - - # provide labels the destination namespaces - - name: NAMESPACE_SELECTOR - value: '' - - # provide comma separated ports - - name: PORTS - value: '' - - labels: - name: pod-network-partition - app.kubernetes.io/part-of: litmus - app.kubernetes.io/component: experiment-job - app.kubernetes.io/version: latest - --- apiVersion: litmuschaos.io/v1alpha1 description: @@ -3282,112 +3388,6 @@ spec: app.kubernetes.io/runtime-api-usage: "true" 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: - # Create and monitor the experiment & helper pods - - apiGroups: [""] - resources: ["pods"] - verbs: ["create","delete","get","list","patch","update", "deletecollection"] - # Performs CRUD operations on the events inside chaosengine and chaosresult - - apiGroups: [""] - resources: ["events"] - verbs: ["create","get","list","patch","update"] - # Fetch configmaps details and mount it to the experiment pod (if specified) - - apiGroups: [""] - resources: ["configmaps"] - verbs: ["get","list",] - # Track and get the runner, experiment, and helper pods log - - apiGroups: [""] - resources: ["pods/log"] - verbs: ["get","list","watch"] - # for creating and managing to execute comands inside target container - - apiGroups: [""] - resources: ["pods/exec"] - verbs: ["get","list","create"] - # for configuring and monitor the experiment job by the chaos-runner pod - - apiGroups: ["batch"] - resources: ["jobs"] - verbs: ["create","list","get","delete","deletecollection"] - # for creation, status polling and deletion of litmus chaos resources used within a chaos workflow - - apiGroups: ["litmuschaos.io"] - resources: ["chaosengines","chaosexperiments","chaosresults"] - verbs: ["create","list","get","patch","update","delete"] - # for experiment to perform node status checks - - 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: '' - - ## LOAD CPU WITH GIVEN PERCENT LOADING FOR THE CPU STRESS WORKERS. - ## 0 IS EFFECTIVELY A SLEEP (NO LOAD) AND 100 IS FULL LOADING - - name: CPU_LOAD - value: '100' - - # 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 - --- apiVersion: litmuschaos.io/v1alpha1 description: diff --git a/charts/kafka/experiments.yaml b/charts/kafka/experiments.yaml index 09ea53a..893dc2b 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 @@ -127,123 +247,3 @@ 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 efd13a3..f9c32af 100644 --- a/charts/kube-aws/experiments.yaml +++ b/charts/kube-aws/experiments.yaml @@ -91,12 +91,12 @@ spec: apiVersion: litmuschaos.io/v1alpha1 description: message: | - Detaching an ebs volume from ec2 instance. + Stopping an EC2 instance identified by tag. kind: ChaosExperiment metadata: - name: ebs-loss-by-tag + name: ec2-terminate-by-tag labels: - name: ebs-loss-by-tag + name: ec2-terminate-by-tag app.kubernetes.io/part-of: litmus app.kubernetes.io/component: chaosexperiment app.kubernetes.io/version: latest @@ -132,11 +132,15 @@ spec: - apiGroups: ["litmuschaos.io"] resources: ["chaosengines","chaosexperiments","chaosresults"] verbs: ["create","list","get","patch","update","delete"] + # for experiment to perform node status checks + - apiGroups: [""] + resources: ["nodes"] + verbs: ["get","list"] image: "litmuschaos/go-runner:latest" imagePullPolicy: Always args: - -c - - ./experiments -name ebs-loss-by-tag + - ./experiments -name ec2-terminate-by-tag command: - /bin/bash env: @@ -146,22 +150,28 @@ spec: - name: CHAOS_INTERVAL value: '30' + # Period to wait before and after injection of chaos in sec - name: RAMP_TIME value: '' - - name: EBS_VOLUME_TAG + - name: INSTANCE_TAG 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' + value: 'parallel' - - name: VOLUME_AFFECTED_PERC - value: '' - - # Provide the path of aws credentials mounted from secret + # Provide the path of aws credentials mounted from secret - name: AWS_SHARED_CREDENTIALS_FILE value: '/tmp/cloud_config.yml' @@ -171,7 +181,7 @@ spec: value: 'litmus' labels: - name: ebs-loss-by-tag + name: ec2-terminate-by-tag app.kubernetes.io/part-of: litmus app.kubernetes.io/component: experiment-job app.kubernetes.io/version: latest @@ -361,12 +371,12 @@ spec: apiVersion: litmuschaos.io/v1alpha1 description: message: | - Stopping an EC2 instance identified by tag. + Detaching an ebs volume from ec2 instance. kind: ChaosExperiment metadata: - name: ec2-terminate-by-tag + name: ebs-loss-by-tag labels: - name: ec2-terminate-by-tag + name: ebs-loss-by-tag app.kubernetes.io/part-of: litmus app.kubernetes.io/component: chaosexperiment app.kubernetes.io/version: latest @@ -402,15 +412,11 @@ spec: - apiGroups: ["litmuschaos.io"] resources: ["chaosengines","chaosexperiments","chaosresults"] verbs: ["create","list","get","patch","update","delete"] - # for experiment to perform node status checks - - apiGroups: [""] - resources: ["nodes"] - verbs: ["get","list"] image: "litmuschaos/go-runner:latest" imagePullPolicy: Always args: - -c - - ./experiments -name ec2-terminate-by-tag + - ./experiments -name ebs-loss-by-tag command: - /bin/bash env: @@ -420,28 +426,22 @@ spec: - name: CHAOS_INTERVAL value: '30' - # Period to wait before and after injection of chaos in sec - name: RAMP_TIME value: '' - - name: INSTANCE_TAG + - name: EBS_VOLUME_TAG 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' + value: 'parallel' - # Provide the path of aws credentials mounted from secret + - name: VOLUME_AFFECTED_PERC + value: '' + + # Provide the path of aws credentials mounted from secret - name: AWS_SHARED_CREDENTIALS_FILE value: '/tmp/cloud_config.yml' @@ -451,7 +451,7 @@ spec: value: 'litmus' labels: - name: ec2-terminate-by-tag + name: ebs-loss-by-tag 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 e7ef516..9a09155 100644 --- a/charts/openebs/experiments.yaml +++ b/charts/openebs/experiments.yaml @@ -1,3 +1,98 @@ +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: @@ -96,194 +191,6 @@ spec: #- name: openebs-pool-container-failure # 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: 'litmus' - - 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 cstor target/Jiva controller pod and check if gets created again -kind: ChaosExperiment -metadata: - labels: - litmuschaos.io/name: openebs - name: openebs-target-pod-failure - app.kubernetes.io/part-of: litmus - app.kubernetes.io/component: chaosexperiment - app.kubernetes.io/version: latest - name: openebs-target-pod-failure -spec: - definition: - scope: Cluster - permissions: - - apiGroups: - - "" - - "extensions" - - "apps" - - "batch" - - "litmuschaos.io" - - "storage.k8s.io" - resources: - - "deployments" - - "jobs" - - "events" - - "pods" - - "pods/log" - - "pods/exec" - - "configmaps" - - "secrets" - - "services" - - "chaosengines" - - "chaosexperiments" - - "chaosresults" - - "persistentvolumeclaims" - - "storageclasses" - - "persistentvolumes" - 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-target-pod-failure/openebs_target_pod_failure_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: 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: @@ -380,6 +287,296 @@ 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 +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 +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: 'litmus' + + 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: @@ -576,20 +773,21 @@ spec: - name: openebs-nfs-provisioner-kill mountPath: /mnt/ +--- --- apiVersion: litmuschaos.io/v1alpha1 description: message: | - Network loss to target pod belonging to a OpenEBS PVC + Kill the pool pod and check if gets scheduled again kind: ChaosExperiment metadata: labels: litmuschaos.io/name: openebs - name: openebs-target-network-loss + name: openebs-pool-pod-failure app.kubernetes.io/part-of: litmus app.kubernetes.io/component: chaosexperiment app.kubernetes.io/version: latest - name: openebs-target-network-loss + name: openebs-pool-pod-failure spec: definition: scope: Cluster @@ -600,19 +798,20 @@ spec: - "apps" - "batch" - "litmuschaos.io" + - "openebs.io" - "storage.k8s.io" resources: + - "deployments" + - "replicasets" - "jobs" - - "pods" - - "events" - - "services" - "pods/log" - - "pods/exec" + - "events" + - "pods" - "configmaps" - "secrets" - - "persistentvolumeclaims" - "storageclasses" - - "persistentvolumes" + - "persistentvolumeclaims" + - "cstorvolumereplicas" - "chaosengines" - "chaosexperiments" - "chaosresults" @@ -623,149 +822,55 @@ spec: - "list" - "patch" - "update" + - apiGroups: + - "" + resources: + - "nodes" + verbs: + - "get" + - "list" 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 + - 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' + value: default - - name: OPENEBS_NAMESPACE + - name: OPENEBS_NS 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: CHAOS_ITERATIONS + value: '2' + + # provide the kill count + - name: KILL_COUNT value: '' - name: DATA_PERSISTENCE value: '' labels: - name: openebs-target-network-loss + 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-target-network-loss + #- name: openebs-pool-pod-failure # mountPath: /mnt - ---- -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 + --- --- @@ -887,129 +992,16 @@ spec: 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. + Kill the cstor target/Jiva controller pod and check if gets created again kind: ChaosExperiment metadata: labels: litmuschaos.io/name: openebs - name: openebs-pool-disk-loss + name: openebs-target-pod-failure 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 + name: openebs-target-pod-failure spec: definition: scope: Cluster @@ -1020,23 +1012,23 @@ spec: - "apps" - "batch" - "litmuschaos.io" - - "openebs.io" - "storage.k8s.io" resources: - "deployments" - - "replicasets" - "jobs" - - "pods/log" - "events" - "pods" + - "pods/log" + - "pods/exec" - "configmaps" - "secrets" - - "storageclasses" - - "persistentvolumeclaims" - - "cstorvolumereplicas" + - "services" - "chaosengines" - "chaosexperiments" - "chaosresults" + - "persistentvolumeclaims" + - "storageclasses" + - "persistentvolumes" verbs: - "create" - "get" @@ -1055,43 +1047,51 @@ spec: 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-target-pod-failure/openebs_target_pod_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 + - name: OPENEBS_NAMESPACE value: 'openebs' - + - name: APP_PVC value: '' + - name: FORCE + value: 'true' + - 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: '' + - 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-pool-pod-failure + 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-pool-pod-failure + #- name: openebs-target-pod-failure # mountPath: /mnt - --- diff --git a/charts/spring-boot/experiments.yaml b/charts/spring-boot/experiments.yaml new file mode 100644 index 0000000..b1c2048 --- /dev/null +++ b/charts/spring-boot/experiments.yaml @@ -0,0 +1,635 @@ +apiVersion: litmuschaos.io/v1alpha1 +description: + message: | + It can target random pods with a Spring Boot application and allows configuring the assaults to inject cpu-stress +kind: ChaosExperiment +metadata: + name: spring-boot-faults + labels: + name: spring-boot-faults + app.kubernetes.io/part-of: litmus + app.kubernetes.io/component: chaosexperiment + app.kubernetes.io/version: latest +spec: + definition: + scope: Namespaced + permissions: + # Create and monitor the experiment & helper pods + - apiGroups: [ "" ] + resources: [ "pods" ] + verbs: [ "create","delete","get","list","patch","update", "deletecollection" ] + # Performs CRUD operations on the events inside chaosengine and chaosresult + - apiGroups: [ "" ] + resources: [ "events" ] + verbs: [ "create","get","list","patch","update" ] + # Track and get the runner, experiment, and helper pods log + - apiGroups: [ "" ] + resources: [ "pods/log" ] + verbs: [ "get","list","watch" ] + # for creating and managing to execute commands inside target container + - apiGroups: [ "" ] + resources: [ "pods/exec" ] + verbs: [ "get","list","create" ] + # for configuring and monitor the experiment job by the chaos-runner pod + - apiGroups: [ "batch" ] + resources: [ "jobs" ] + verbs: [ "create","list","get","delete","deletecollection" ] + # for creation, status polling and deletion of litmus chaos resources used within a chaos workflow + - apiGroups: [ "litmuschaos.io" ] + resources: [ "chaosengines","chaosexperiments","chaosresults" ] + verbs: [ "create","list","get","patch","update","delete" ] + image: "litmuschaos/go-runner:latest" + imagePullPolicy: Always + args: + - -c + - ./experiments -name spring-boot-faults + command: + - /bin/bash + env: + + # it enables spring app-kill fault + - name: CM_KILL_APPLICATION_ACTIVE + value: '' + + # it enables spring-boot latency fault + - name: CM_LATENCY_ACTIVE + value: '' + + # provide the latency (ms) + # it is applicable when latency is active + - name: LATENCY + value: '2000' + + # it enables spring-boot memory stress fault + - name: CM_MEMORY_ACTIVE + value: '' + + # it contains fraction of memory to be stressed(0.70 equals 70%) + # it supports value in range [0.01,0.95] + # it is applicable when memory is active + - name: MEMORY_FILL_FRACTION + value: '0.70' + + # it enables spring-boot cpu stress fault + - name: CM_CPU_ACTIVE + value: '' + + # it contains fraction of cpu to be stressed(0.95 equals 95%) + # it supports value in range [0.1,1.0] + # it is applicable when cpu is active + - name: CPU_LOAD_FRACTION + value: '0.9' + + # it enables spring-boot exceptions fault + - name: CM_EXCEPTIONS_ACTIVE + value: '' + + # Type of raised exception + # it is applicable when exceptions is active + - name: CM_EXCEPTIONS_TYPE + value: 'java.lang.IllegalArgumentException' + + # Argument of raised exception + # it is applicable when exceptions is active + - name: CM_EXCEPTIONS_ARGUMENTS + value: 'java.lang.String:custom illegal argument exception' + + # port of the spring boot application + - name: CM_PORT + value: '' + + #it contains number of requests are to be attacked + # n value means nth request will be affected + - name: CM_LEVEL + value: '1' + + # it limits watched packages/classes/methods + - name: CM_WATCHED_CUSTOM_SERVICES + value: '' + + # provide name of watcher + # it supports controller, restController, service, repository, component, webClient + - name: CM_WATCHERS + value: 'restController' + + - name: TOTAL_CHAOS_DURATION + value: '30' + + ## percentage of total pods to target + - name: PODS_AFFECTED_PERC + value: '' + + ## Period to wait before and after injection of chaos + - name: RAMP_TIME + value: '' + + ## it defines the sequence of chaos execution for multiple target pods + ## supported values: serial, parallel + - name: SEQUENCE + value: 'parallel' + + ## env var that describes the library used to execute the chaos + ## default: litmus. Supported values: litmus + - name: LIB + value: 'litmus' + + labels: + name: spring-boot-faults + app.kubernetes.io/part-of: litmus + app.kubernetes.io/component: experiment-job + app.kubernetes.io/version: latest + +--- +apiVersion: litmuschaos.io/v1alpha1 +description: + message: | + It can target random pods with a Spring Boot application and allows configuring the assaults to inject memory-stress +kind: ChaosExperiment +metadata: + name: spring-boot-memory-stress + labels: + name: spring-boot-memory-stress + app.kubernetes.io/part-of: litmus + app.kubernetes.io/component: chaosexperiment + app.kubernetes.io/version: latest +spec: + definition: + scope: Namespaced + permissions: + # Create and monitor the experiment & helper pods + - apiGroups: [ "" ] + resources: [ "pods" ] + verbs: [ "create","delete","get","list","patch","update", "deletecollection" ] + # Performs CRUD operations on the events inside chaosengine and chaosresult + - apiGroups: [ "" ] + resources: [ "events" ] + verbs: [ "create","get","list","patch","update" ] + # Track and get the runner, experiment, and helper pods log + - apiGroups: [ "" ] + resources: [ "pods/log" ] + verbs: [ "get","list","watch" ] + # for creating and managing to execute commands inside target container + - apiGroups: [ "" ] + resources: [ "pods/exec" ] + verbs: [ "get","list","create" ] + # for configuring and monitor the experiment job by the chaos-runner pod + - apiGroups: [ "batch" ] + resources: [ "jobs" ] + verbs: [ "create","list","get","delete","deletecollection" ] + # for creation, status polling and deletion of litmus chaos resources used within a chaos workflow + - apiGroups: [ "litmuschaos.io" ] + resources: [ "chaosengines","chaosexperiments","chaosresults" ] + verbs: [ "create","list","get","patch","update","delete" ] + image: "litmuschaos/go-runner:latest" + imagePullPolicy: Always + args: + - -c + - ./experiments -name spring-boot-memory-stress + command: + - /bin/bash + env: + + # it contains fraction of memory to be stressed(0.70 equals 70%) + # it supports value in range [0.01,0.95] + - name: MEMORY_FILL_FRACTION + value: '0.70' + + # port of the spring boot application + - name: CM_PORT + value: '' + + # it contains number of requests are to be attacked + # n value means nth request will be affected + - name: CM_LEVEL + value: '1' + + # it limits watched packages/classes/methods + - name: CM_WATCHED_CUSTOM_SERVICES + value: '' + + # provide name of watcher + # it supports controller, restController, service, repository, component, webClient + - name: CM_WATCHERS + value: 'restController' + + - name: TOTAL_CHAOS_DURATION + value: '30' + + ## percentage of total pods to target + - name: PODS_AFFECTED_PERC + value: '' + + ## Period to wait before and after injection of chaos + - name: RAMP_TIME + value: '' + + ## it defines the sequence of chaos execution for multiple target pods + ## supported values: serial, parallel + - name: SEQUENCE + value: 'parallel' + + ## env var that describes the library used to execute the chaos + ## default: litmus. Supported values: litmus + - name: LIB + value: 'litmus' + + labels: + name: spring-boot-memory-stress + app.kubernetes.io/part-of: litmus + app.kubernetes.io/component: experiment-job + app.kubernetes.io/version: latest + +--- +apiVersion: litmuschaos.io/v1alpha1 +description: + message: | + It can target random pods with a Spring Boot application and allows configuring the assaults to inject network latency +kind: ChaosExperiment +metadata: + name: spring-boot-exceptions + labels: + name: spring-boot-exceptions + app.kubernetes.io/part-of: litmus + app.kubernetes.io/component: chaosexperiment + app.kubernetes.io/version: latest +spec: + definition: + scope: Namespaced + permissions: + # Create and monitor the experiment & helper pods + - apiGroups: [ "" ] + resources: [ "pods" ] + verbs: [ "create","delete","get","list","patch","update", "deletecollection" ] + # Performs CRUD operations on the events inside chaosengine and chaosresult + - apiGroups: [ "" ] + resources: [ "events" ] + verbs: [ "create","get","list","patch","update" ] + # Track and get the runner, experiment, and helper pods log + - apiGroups: [ "" ] + resources: [ "pods/log" ] + verbs: [ "get","list","watch" ] + # for creating and managing to execute commands inside target container + - apiGroups: [ "" ] + resources: [ "pods/exec" ] + verbs: [ "get","list","create" ] + # for configuring and monitor the experiment job by the chaos-runner pod + - apiGroups: [ "batch" ] + resources: [ "jobs" ] + verbs: [ "create","list","get","delete","deletecollection" ] + # for creation, status polling and deletion of litmus chaos resources used within a chaos workflow + - apiGroups: [ "litmuschaos.io" ] + resources: [ "chaosengines","chaosexperiments","chaosresults" ] + verbs: [ "create","list","get","patch","update","delete" ] + image: "litmuschaos/go-runner:latest" + imagePullPolicy: Always + args: + - -c + - ./experiments -name spring-boot-exceptions + command: + - /bin/bash + env: + + # Type of raised exception + - name: CM_EXCEPTIONS_TYPE + value: 'java.lang.IllegalArgumentException' + + # Argument of raised exception + - name: CM_EXCEPTIONS_ARGUMENTS + value: 'java.lang.String:custom illegal argument exception' + + # port of the spring boot application + - name: CM_PORT + value: '' + + #it contains number of requests are to be attacked + # n value means nth request will be affected + - name: CM_LEVEL + value: '1' + + # it limits watched packages/classes/methods + - name: CM_WATCHED_CUSTOM_SERVICES + value: '' + + # provide name of watcher + # it supports controller, restController, service, repository, component, webClient + - name: CM_WATCHERS + value: 'restController' + + - name: TOTAL_CHAOS_DURATION + value: '30' + + ## percentage of total pods to target + - name: PODS_AFFECTED_PERC + value: '' + + ## Period to wait before and after injection of chaos + - name: RAMP_TIME + value: '' + + ## it defines the sequence of chaos execution for multiple target pods + ## supported values: serial, parallel + - name: SEQUENCE + value: 'parallel' + + ## env var that describes the library used to execute the chaos + ## default: litmus. Supported values: litmus + - name: LIB + value: 'litmus' + + labels: + name: spring-boot-exceptions + app.kubernetes.io/part-of: litmus + app.kubernetes.io/component: experiment-job + app.kubernetes.io/version: latest + +--- +apiVersion: litmuschaos.io/v1alpha1 +description: + message: | + It can target random pods with a Spring Boot application and allows configuring the assaults to inject app-kill +kind: ChaosExperiment +metadata: + name: spring-boot-app-kill + labels: + name: spring-boot-app-kill + app.kubernetes.io/part-of: litmus + app.kubernetes.io/component: chaosexperiment + app.kubernetes.io/version: latest +spec: + definition: + scope: Namespaced + permissions: + # Create and monitor the experiment & helper pods + - apiGroups: [ "" ] + resources: [ "pods" ] + verbs: [ "create","delete","get","list","patch","update", "deletecollection" ] + # Performs CRUD operations on the events inside chaosengine and chaosresult + - apiGroups: [ "" ] + resources: [ "events" ] + verbs: [ "create","get","list","patch","update" ] + # Track and get the runner, experiment, and helper pods log + - apiGroups: [ "" ] + resources: [ "pods/log" ] + verbs: [ "get","list","watch" ] + # for creating and managing to execute commands inside target container + - apiGroups: [ "" ] + resources: [ "pods/exec" ] + verbs: [ "get","list","create" ] + # for configuring and monitor the experiment job by the chaos-runner pod + - apiGroups: [ "batch" ] + resources: [ "jobs" ] + verbs: [ "create","list","get","delete","deletecollection" ] + # for creation, status polling and deletion of litmus chaos resources used within a chaos workflow + - apiGroups: [ "litmuschaos.io" ] + resources: [ "chaosengines","chaosexperiments","chaosresults" ] + verbs: [ "create","list","get","patch","update","delete" ] + image: "litmuschaos/go-runner:latest" + imagePullPolicy: Always + args: + - -c + - ./experiments -name spring-boot-app-kill + command: + - /bin/bash + env: + # port of the spring boot application + - name: CM_PORT + value: '' + + #it contains number of requests are to be attacked + # n value means nth request will be affected + - name: CM_LEVEL + value: '1' + + # it limits watched packages/classes/methods + - name: CM_WATCHED_CUSTOM_SERVICES + value: '' + + # provide name of watcher + # it supports controller, restController, service, repository, component, webClient + - name: CM_WATCHERS + value: 'restController' + + ## percentage of total pods to target + - name: PODS_AFFECTED_PERC + value: '' + + ## Period to wait before and after injection of chaos + - name: RAMP_TIME + value: '' + + ## it defines the sequence of chaos execution for multiple target pods + ## supported values: serial, parallel + - name: SEQUENCE + value: 'parallel' + + ## env var that describes the library used to execute the chaos + ## default: litmus. Supported values: litmus + - name: LIB + value: 'litmus' + + labels: + name: spring-boot-app-kill + app.kubernetes.io/part-of: litmus + app.kubernetes.io/component: experiment-job + app.kubernetes.io/version: latest + +--- +apiVersion: litmuschaos.io/v1alpha1 +description: + message: | + It can target random pods with a Spring Boot application and allows configuring the assaults to inject network latency +kind: ChaosExperiment +metadata: + name: spring-boot-latency + labels: + name: spring-boot-latency + app.kubernetes.io/part-of: litmus + app.kubernetes.io/component: chaosexperiment + app.kubernetes.io/version: latest +spec: + definition: + scope: Namespaced + permissions: + # Create and monitor the experiment & helper pods + - apiGroups: [ "" ] + resources: [ "pods" ] + verbs: [ "create","delete","get","list","patch","update", "deletecollection" ] + # Performs CRUD operations on the events inside chaosengine and chaosresult + - apiGroups: [ "" ] + resources: [ "events" ] + verbs: [ "create","get","list","patch","update" ] + # Track and get the runner, experiment, and helper pods log + - apiGroups: [ "" ] + resources: [ "pods/log" ] + verbs: [ "get","list","watch" ] + # for creating and managing to execute commands inside target container + - apiGroups: [ "" ] + resources: [ "pods/exec" ] + verbs: [ "get","list","create" ] + # for configuring and monitor the experiment job by the chaos-runner pod + - apiGroups: [ "batch" ] + resources: [ "jobs" ] + verbs: [ "create","list","get","delete","deletecollection" ] + # for creation, status polling and deletion of litmus chaos resources used within a chaos workflow + - apiGroups: [ "litmuschaos.io" ] + resources: [ "chaosengines","chaosexperiments","chaosresults" ] + verbs: [ "create","list","get","patch","update","delete" ] + image: "litmuschaos/go-runner:latest" + imagePullPolicy: Always + args: + - -c + - ./experiments -name spring-boot-latency + command: + - /bin/bash + env: + + # provide the latency (ms) + - name: LATENCY + value: '2000' + + # port of the spring boot application + - name: CM_PORT + value: '' + + # it contains number of requests are to be attacked + # n value means nth request will be affected + - name: CM_LEVEL + value: '1' + + # it limits watched packages/classes/methods + - name: CM_WATCHED_CUSTOM_SERVICES + value: '' + + # provide name of watcher + # it supports controller, restController, service, repository, component, webClient + - name: CM_WATCHERS + value: 'restController' + + - name: TOTAL_CHAOS_DURATION + value: '30' + + ## percentage of total pods to target + - name: PODS_AFFECTED_PERC + value: '' + + ## Period to wait before and after injection of chaos + - name: RAMP_TIME + value: '' + + ## it defines the sequence of chaos execution for multiple target pods + ## supported values: serial, parallel + - name: SEQUENCE + value: 'parallel' + + ## env var that describes the library used to execute the chaos + ## default: litmus. Supported values: litmus + - name: LIB + value: 'litmus' + + labels: + name: spring-boot-latency + app.kubernetes.io/part-of: litmus + app.kubernetes.io/component: experiment-job + app.kubernetes.io/version: latest + +--- +apiVersion: litmuschaos.io/v1alpha1 +description: + message: | + It can target random pods with a Spring Boot application and allows configuring the assaults to inject cpu-stress +kind: ChaosExperiment +metadata: + name: spring-boot-cpu-stress + labels: + name: spring-boot-cpu-stress + app.kubernetes.io/part-of: litmus + app.kubernetes.io/component: chaosexperiment + app.kubernetes.io/version: latest +spec: + definition: + scope: Namespaced + permissions: + # Create and monitor the experiment & helper pods + - apiGroups: [ "" ] + resources: [ "pods" ] + verbs: [ "create","delete","get","list","patch","update", "deletecollection" ] + # Performs CRUD operations on the events inside chaosengine and chaosresult + - apiGroups: [ "" ] + resources: [ "events" ] + verbs: [ "create","get","list","patch","update" ] + # Track and get the runner, experiment, and helper pods log + - apiGroups: [ "" ] + resources: [ "pods/log" ] + verbs: [ "get","list","watch" ] + # for creating and managing to execute commands inside target container + - apiGroups: [ "" ] + resources: [ "pods/exec" ] + verbs: [ "get","list","create" ] + # for configuring and monitor the experiment job by the chaos-runner pod + - apiGroups: [ "batch" ] + resources: [ "jobs" ] + verbs: [ "create","list","get","delete","deletecollection" ] + # for creation, status polling and deletion of litmus chaos resources used within a chaos workflow + - apiGroups: [ "litmuschaos.io" ] + resources: [ "chaosengines","chaosexperiments","chaosresults" ] + verbs: [ "create","list","get","patch","update","delete" ] + image: "litmuschaos/go-runner:latest" + imagePullPolicy: Always + args: + - -c + - ./experiments -name spring-boot-cpu-stress + command: + - /bin/bash + env: + + # it contains fraction of cpu to be stressed(0.95 equals 95%) + # it supports value in range [0.1,1.0] + - name: CPU_LOAD_FRACTION + value: '0.9' + + # port of the spring boot application + - name: CM_PORT + value: '' + + #it contains number of requests are to be attacked + # n value means nth request will be affected + - name: CM_LEVEL + value: '1' + + # it limits watched packages/classes/methods + - name: CM_WATCHED_CUSTOM_SERVICES + value: '' + + # provide name of watcher + # it supports controller, restController, service, repository, component, webClient + - name: CM_WATCHERS + value: 'restController' + + - name: TOTAL_CHAOS_DURATION + value: '30' + + ## percentage of total pods to target + - name: PODS_AFFECTED_PERC + value: '' + + ## Period to wait before and after injection of chaos + - name: RAMP_TIME + value: '' + + ## it defines the sequence of chaos execution for multiple target pods + ## supported values: serial, parallel + - name: SEQUENCE + value: 'parallel' + + ## env var that describes the library used to execute the chaos + ## default: litmus. Supported values: litmus + - name: LIB + value: 'litmus' + + labels: + name: spring-boot-cpu-stress + app.kubernetes.io/part-of: litmus + app.kubernetes.io/component: experiment-job + app.kubernetes.io/version: latest + +---