diff --git a/charts/aws-ssm/experiments.yaml b/charts/aws-ssm/experiments.yaml index 6915473..53a9c06 100644 --- a/charts/aws-ssm/experiments.yaml +++ b/charts/aws-ssm/experiments.yaml @@ -1,135 +1,4 @@ apiVersion: litmuschaos.io/v1alpha1 -description: - message: | - Execute AWS SSM Chaos on given ec2 instance IDs -kind: ChaosExperiment -metadata: - name: aws-ssm-chaos-by-id - labels: - name: aws-ssm-chaos-by-id - 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 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"] - image: "litmuschaos/go-runner:latest" - imagePullPolicy: Always - args: - - -c - - ./experiments -name aws-ssm-chaos-by-id - command: - - /bin/bash - env: - - name: TOTAL_CHAOS_DURATION - value: '60' - - - name: CHAOS_INTERVAL - value: '60' - - # Period to wait before and after injection of chaos in sec - - name: RAMP_TIME - value: '' - - # Instance ID of the target ec2 instance - # Multiple IDs can also be provided as comma separated values ex: id1,id2 - - name: EC2_INSTANCE_ID - value: '' - - - name: REGION - value: '' - - # it defines the sequence of chaos execution for multiple target instances - # supported values: serial, parallel - - name: SEQUENCE - value: 'parallel' - - # Provide the path of aws credentials mounted from secret - - name: AWS_SHARED_CREDENTIALS_FILE - value: '/tmp/cloud_config.yml' - - # Provide the name of ssm doc - # if not using the default stress docs - - name: DOCUMENT_NAME - value: '' - - # Provide the type of ssm doc - # if not using the default stress docs - - name: DOCUMENT_TYPE - value: '' - - # Provide the format of ssm doc - # if not using the default stress docs - - name: DOCUMENT_FORMAT - value: '' - - # Provide the path of ssm doc - # if not using the default stress docs - - name: DOCUMENT_PATH - value: '' - - # if you want to install dependencies to run default ssm docs - - name: INSTALL_DEPENDENCIES - value: 'True' - - # provide the number of workers for memory stress - - name: NUMBER_OF_WORKERS - value: '1' - - # provide the percentage of available memory to stress - - name: MEMORY_PERCENTAGE - value: '80' - - # provide the CPU chores to be comsumed - # 0 will consume all the available cpu cores - - name: CPU_CORE - value: '0' - - # provide the LIB - # only litmus supported - - name: LIB - value: 'litmus' - - labels: - name: aws-ssm-chaos-by-id - app.kubernetes.io/part-of: litmus - app.kubernetes.io/component: experiment-job - app.kubernetes.io/version: latest - secrets: - - name: cloud-secret - mountPath: /tmp/ - ---- -apiVersion: litmuschaos.io/v1alpha1 description: message: | Execute AWS SSM Chaos on given ec2 instance Tag @@ -264,3 +133,134 @@ spec: mountPath: /tmp/ --- +apiVersion: litmuschaos.io/v1alpha1 +description: + message: | + Execute AWS SSM Chaos on given ec2 instance IDs +kind: ChaosExperiment +metadata: + name: aws-ssm-chaos-by-id + labels: + name: aws-ssm-chaos-by-id + 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 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"] + image: "litmuschaos/go-runner:latest" + imagePullPolicy: Always + args: + - -c + - ./experiments -name aws-ssm-chaos-by-id + command: + - /bin/bash + env: + - name: TOTAL_CHAOS_DURATION + value: '60' + + - name: CHAOS_INTERVAL + value: '60' + + # Period to wait before and after injection of chaos in sec + - name: RAMP_TIME + value: '' + + # Instance ID of the target ec2 instance + # Multiple IDs can also be provided as comma separated values ex: id1,id2 + - name: EC2_INSTANCE_ID + value: '' + + - name: REGION + value: '' + + # it defines the sequence of chaos execution for multiple target instances + # supported values: serial, parallel + - name: SEQUENCE + value: 'parallel' + + # Provide the path of aws credentials mounted from secret + - name: AWS_SHARED_CREDENTIALS_FILE + value: '/tmp/cloud_config.yml' + + # Provide the name of ssm doc + # if not using the default stress docs + - name: DOCUMENT_NAME + value: '' + + # Provide the type of ssm doc + # if not using the default stress docs + - name: DOCUMENT_TYPE + value: '' + + # Provide the format of ssm doc + # if not using the default stress docs + - name: DOCUMENT_FORMAT + value: '' + + # Provide the path of ssm doc + # if not using the default stress docs + - name: DOCUMENT_PATH + value: '' + + # if you want to install dependencies to run default ssm docs + - name: INSTALL_DEPENDENCIES + value: 'True' + + # provide the number of workers for memory stress + - name: NUMBER_OF_WORKERS + value: '1' + + # provide the percentage of available memory to stress + - name: MEMORY_PERCENTAGE + value: '80' + + # provide the CPU chores to be comsumed + # 0 will consume all the available cpu cores + - name: CPU_CORE + value: '0' + + # provide the LIB + # only litmus supported + - name: LIB + value: 'litmus' + + labels: + name: aws-ssm-chaos-by-id + app.kubernetes.io/part-of: litmus + app.kubernetes.io/component: experiment-job + app.kubernetes.io/version: latest + secrets: + - name: cloud-secret + mountPath: /tmp/ + +--- diff --git a/charts/azure/experiments.yaml b/charts/azure/experiments.yaml index 06d46d2..27045bc 100644 --- a/charts/azure/experiments.yaml +++ b/charts/azure/experiments.yaml @@ -1,4 +1,101 @@ apiVersion: litmuschaos.io/v1alpha1 +description: + message: | + Detaches disk from the VM and then re-attaches disk to the VM +kind: ChaosExperiment +metadata: + name: azure-disk-loss + labels: + name: azure-disk-loss + 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 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"] + image: "litmuschaos/go-runner:latest" + imagePullPolicy: Always + args: + - -c + - ./experiments -name azure-disk-loss + command: + - /bin/bash + env: + + - name: TOTAL_CHAOS_DURATION + value: '30' + + - name: CHAOS_INTERVAL + value: '30' + + - name: LIB + value: 'litmus' + + # Period to wait before and after injection of chaos in sec + - name: RAMP_TIME + value: '' + + # provide the resource group of the instance + - name: RESOURCE_GROUP + value: '' + + # accepts enable/disable, default is disable + - name: SCALE_SET + value: '' + + # provide the virtual disk names (comma separated if multiple) + - name: VIRTUAL_DISK_NAMES + value: '' + + # provide the sequence type for the run. Options: serial/parallel + - name: SEQUENCE + value: 'parallel' + + # provide the path to aks credentials mounted from secret + - name: AZURE_AUTH_LOCATION + value: '/tmp/azure.auth' + + labels: + name: azure-disk-loss + app.kubernetes.io/part-of: litmus + app.kubernetes.io/component: experiment-job + app.kubernetes.io/version: latest + + secrets: + - name: cloud-secret + mountPath: /tmp/ + +--- +apiVersion: litmuschaos.io/v1alpha1 description: message: | Terminating azure VM instance @@ -96,100 +193,3 @@ spec: --- -apiVersion: litmuschaos.io/v1alpha1 -description: - message: | - Detaches disk from the VM and then re-attaches disk to the VM -kind: ChaosExperiment -metadata: - name: azure-disk-loss - labels: - name: azure-disk-loss - 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 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"] - image: "litmuschaos/go-runner:latest" - imagePullPolicy: Always - args: - - -c - - ./experiments -name azure-disk-loss - command: - - /bin/bash - env: - - - name: TOTAL_CHAOS_DURATION - value: '30' - - - name: CHAOS_INTERVAL - value: '30' - - - name: LIB - value: 'litmus' - - # Period to wait before and after injection of chaos in sec - - name: RAMP_TIME - value: '' - - # provide the resource group of the instance - - name: RESOURCE_GROUP - value: '' - - # accepts enable/disable, default is disable - - name: SCALE_SET - value: '' - - # provide the virtual disk names (comma separated if multiple) - - name: VIRTUAL_DISK_NAMES - value: '' - - # provide the sequence type for the run. Options: serial/parallel - - name: SEQUENCE - value: 'parallel' - - # provide the path to aks credentials mounted from secret - - name: AZURE_AUTH_LOCATION - value: '/tmp/azure.auth' - - labels: - name: azure-disk-loss - app.kubernetes.io/part-of: litmus - app.kubernetes.io/component: experiment-job - app.kubernetes.io/version: latest - - secrets: - - name: cloud-secret - mountPath: /tmp/ - ---- diff --git a/charts/gcp/experiments.yaml b/charts/gcp/experiments.yaml index 9341c6a..c1e15f9 100644 --- a/charts/gcp/experiments.yaml +++ b/charts/gcp/experiments.yaml @@ -1,202 +1,4 @@ apiVersion: litmuschaos.io/v1alpha1 -description: - message: | - Stops GCP VM instances and GKE nodes for a specified duration and later restarts them -kind: ChaosExperiment -metadata: - name: gcp-vm-instance-stop - labels: - name: gcp-vm-instance-stop - 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 - command: - - /bin/bash - env: - - - name: TOTAL_CHAOS_DURATION - value: '30' - - - name: CHAOS_INTERVAL - value: '30' - - # parallel or serial; determines how the VM instances are terminated, all at once or one at a time - - name: SEQUENCE - value: 'parallel' - - # provide the LIB - # only litmus supported - - name: LIB - value: 'litmus' - - # period to wait before and after injection of chaos in sec - - name: RAMP_TIME - value: '' - - # enable or disable; shall be set to enable if the target instances are a part of a managed instance group - - name: MANAGED_INSTANCE_GROUP - value: 'disable' - - # Instance name of the target vm instance(s) - # Multiple instance names can be provided as comma separated values ex: instance1,instance2 - - name: VM_INSTANCE_NAMES - value: '' - - # GCP project ID to which the vm instances belong - - name: GCP_PROJECT_ID - value: '' - - # Instance zone(s) of the target vm instance(s) - # If more than one instance is targetted, provide zone for each in the order of their - # respective instance name in VM_INSTANCE_NAME as comma separated values ex: zone1,zone2 - - name: INSTANCE_ZONES - value: '' - - labels: - name: gcp-vm-instance-stop - 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: | - 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: INSTANCE_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 @@ -372,3 +174,201 @@ spec: 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: INSTANCE_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: | + Stops GCP VM instances and GKE nodes for a specified duration and later restarts them +kind: ChaosExperiment +metadata: + name: gcp-vm-instance-stop + labels: + name: gcp-vm-instance-stop + 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 + command: + - /bin/bash + env: + + - name: TOTAL_CHAOS_DURATION + value: '30' + + - name: CHAOS_INTERVAL + value: '30' + + # parallel or serial; determines how the VM instances are terminated, all at once or one at a time + - name: SEQUENCE + value: 'parallel' + + # provide the LIB + # only litmus supported + - name: LIB + value: 'litmus' + + # period to wait before and after injection of chaos in sec + - name: RAMP_TIME + value: '' + + # enable or disable; shall be set to enable if the target instances are a part of a managed instance group + - name: MANAGED_INSTANCE_GROUP + value: 'disable' + + # Instance name of the target vm instance(s) + # Multiple instance names can be provided as comma separated values ex: instance1,instance2 + - name: VM_INSTANCE_NAMES + value: '' + + # GCP project ID to which the vm instances belong + - name: GCP_PROJECT_ID + value: '' + + # Instance zone(s) of the target vm instance(s) + # If more than one instance is targetted, provide zone for each in the order of their + # respective instance name in VM_INSTANCE_NAME as comma separated values ex: zone1,zone2 + - name: INSTANCE_ZONES + value: '' + + labels: + name: gcp-vm-instance-stop + app.kubernetes.io/part-of: litmus + app.kubernetes.io/component: experiment-job + app.kubernetes.io/version: latest + secrets: + - name: cloud-secret + mountPath: /tmp/ + +--- diff --git a/charts/generic/experiments.yaml b/charts/generic/experiments.yaml index 94da7ea..6cee3bf 100644 --- a/charts/generic/experiments.yaml +++ b/charts/generic/experiments.yaml @@ -1,387 +1,12 @@ apiVersion: litmuschaos.io/v1alpha1 description: message: | - Inject network packet corruption into application pod + Give a memory hog on a node belonging to a deployment kind: ChaosExperiment metadata: - name: pod-network-corruption + name: node-memory-hog labels: - name: pod-network-corruption - 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-corruption - command: - - /bin/bash - env: - - - name: TARGET_CONTAINER - value: '' - - # provide lib image - - name: LIB_IMAGE - value: 'litmuschaos/go-runner:latest' - - - name: NETWORK_INTERFACE - value: 'eth0' - - - name: TC_IMAGE - value: 'gaiadocker/iproute2' - - - name: NETWORK_PACKET_CORRUPTION_PERCENTAGE - value: '100' #in PERCENTAGE - - - name: TOTAL_CHAOS_DURATION - value: '60' # in seconds - - # Time period to wait before and after injection of chaos in sec - - name: RAMP_TIME - value: '' - - # 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: '' - - # To select pods on specific node(s) - - name: NODE_LABEL - value: '' - - # provide the name of container runtime - # for litmus LIB, it supports docker, containerd, crio - # for pumba LIB, it supports docker only - - name: CONTAINER_RUNTIME - value: 'docker' - - # provide the destination ips - # chaos injection will be triggered for these destination ips - - name: DESTINATION_IPS - value: '' - - # provide the destination hosts - # chaos injection will be triggered for these destination hosts - - name: DESTINATION_HOSTS - value: '' - - # provide the socket file path - - name: SOCKET_PATH - value: '/var/run/docker.sock' - - ## it defines the sequence of chaos execution for multiple target pods - ## supported values: serial, parallel - - name: SEQUENCE - value: 'parallel' - - labels: - name: pod-network-corruption - 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 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: 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: | - 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: | - poweroff node -kind: ChaosExperiment -metadata: - name: node-poweroff - labels: - name: node-poweroff + name: node-memory-hog app.kubernetes.io/part-of: litmus app.kubernetes.io/component: chaosexperiment app.kubernetes.io/version: latest @@ -397,9 +22,9 @@ spec: - apiGroups: [""] resources: ["events"] verbs: ["create","get","list","patch","update"] - # Fetch configmaps & secrets details and mount it to the experiment pod (if specified) + # Fetch configmaps details and mount it to the experiment pod (if specified) - apiGroups: [""] - resources: ["configmaps","secrets"] + resources: ["configmaps"] verbs: ["get","list",] # Track and get the runner, experiment, and helper pods log - apiGroups: [""] @@ -425,347 +50,73 @@ spec: imagePullPolicy: Always args: - -c - - ./experiments -name node-restart + - ./experiments -name node-memory-hog command: - /bin/bash env: - - name: SSH_USER - value: 'root' - name: TOTAL_CHAOS_DURATION - value: '60' + value: '120' - - name: REBOOT_COMMAND - value: '-o ServerAliveInterval=1 -o ServerAliveCountMax=1 "sudo systemctl poweroff --force --force" ; true' + ## Specify the size as percent of total node capacity Ex: '30' + ## NOTE: for selecting this option keep MEMORY_CONSUMPTION_MEBIBYTES empty + - name: MEMORY_CONSUMPTION_PERCENTAGE + value: '' + + ## Specify the amount of memory to be consumed in mebibytes + ## NOTE: for selecting this option keep MEMORY_CONSUMPTION_PERCENTAGE empty + - name: MEMORY_CONSUMPTION_MEBIBYTES + value: '' + + - name: NUMBER_OF_WORKERS + value: '1' + + # ENTER THE COMMA SEPARATED TARGET NODES NAME + - name: TARGET_NODES + value: '' + + - 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 + # 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: | - 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 + ## percentage of total nodes to target + - name: NODES_AFFECTED_PERC 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 + ## it defines the sequence of chaos execution for multiple target nodes ## supported values: serial, parallel - name: SEQUENCE value: 'parallel' - + labels: - name: pod-http-modify-header + name: node-memory-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: | - Injects network latency on pods belonging to an app deployment + Drain the node where application pod is scheduled kind: ChaosExperiment metadata: - name: pod-network-latency + name: node-drain 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: | - Restart node -kind: ChaosExperiment -metadata: - name: node-restart - labels: - name: node-restart + name: node-drain app.kubernetes.io/part-of: litmus app.kubernetes.io/component: chaosexperiment app.kubernetes.io/version: latest @@ -781,9 +132,9 @@ spec: - apiGroups: [""] resources: ["events"] verbs: ["create","get","list","patch","update"] - # Fetch configmaps & secrets details and mount it to the experiment pod (if specified) + # Fetch configmaps details and mount it to the experiment pod (if specified) - apiGroups: [""] - resources: ["configmaps","secrets"] + resources: ["configmaps"] verbs: ["get","list",] # Track and get the runner, experiment, and helper pods log - apiGroups: [""] @@ -791,8 +142,12 @@ spec: verbs: ["get","list","watch"] # for creating and managing to execute comands inside target container - apiGroups: [""] - resources: ["pods/exec"] + 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"] @@ -804,374 +159,36 @@ spec: # for experiment to perform node status checks - apiGroups: [""] resources: ["nodes"] - verbs: ["get","list"] + verbs: ["get","list","patch"] image: "litmuschaos/go-runner:latest" imagePullPolicy: Always args: - -c - - ./experiments -name node-restart + - ./experiments -name node-drain 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: | - 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 + # 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 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: | - 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 + name: node-drain app.kubernetes.io/part-of: litmus app.kubernetes.io/component: experiment-job app.kubernetes.io/version: latest @@ -1313,142 +330,6 @@ spec: app.kubernetes.io/runtime-api-usage: "true" app.kubernetes.io/version: latest ---- ---- -apiVersion: litmuschaos.io/v1alpha1 -description: - message: | - IO stress on a app pods belonging to an app deployment -kind: ChaosExperiment -metadata: - name: pod-io-stress - labels: - name: pod-io-stress - app.kubernetes.io/part-of: litmus - app.kubernetes.io/component: chaosexperiment - app.kubernetes.io/version: latest -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-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: '' - - ## Total number of workers default value is 4 - - name: NUMBER_OF_WORKERS - value: '4' - - ## Percentage of total pods to target - - name: PODS_AFFECTED_PERC - value: '' - - # provide volume mount path - - name: VOLUME_MOUNT_PATH - value: '' - - ## specify the comma separated target pods - - name: TARGET_PODS - value: '' - - # To select pods on specific node(s) - - name: NODE_LABEL - value: '' - - # Period to wait before and after injection of chaos in sec - - name: RAMP_TIME - value: '' - - # Provide the LIB here - # support litmus and pumba - - name: LIB - value: 'litmus' - - # provide lib image - - name: LIB_IMAGE - value: 'litmuschaos/go-runner:latest' - - ## provide the cluster runtime - - 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' - - labels: - name: pod-io-stress - 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 @@ -1578,820 +459,6 @@ spec: app.kubernetes.io/runtime-api-usage: "true" app.kubernetes.io/version: latest ---- ---- -apiVersion: litmuschaos.io/v1alpha1 -description: - message: | - Drain the node where application pod is scheduled -kind: ChaosExperiment -metadata: - name: node-drain - labels: - name: node-drain - app.kubernetes.io/part-of: litmus - app.kubernetes.io/component: chaosexperiment - app.kubernetes.io/version: latest -spec: - definition: - scope: Cluster - permissions: - # 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"] - image: "litmuschaos/go-runner:latest" - imagePullPolicy: Always - args: - - -c - - ./experiments -name node-drain - 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: '' - - labels: - name: node-drain - app.kubernetes.io/part-of: litmus - app.kubernetes.io/component: experiment-job - app.kubernetes.io/version: latest - ---- -apiVersion: litmuschaos.io/v1alpha1 -description: - message: | - 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: | - 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 -kind: ChaosExperiment -metadata: - name: node-memory-hog - labels: - name: node-memory-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-memory-hog - command: - - /bin/bash - env: - - - name: TOTAL_CHAOS_DURATION - value: '120' - - ## Specify the size as percent of total node capacity Ex: '30' - ## NOTE: for selecting this option keep MEMORY_CONSUMPTION_MEBIBYTES empty - - name: MEMORY_CONSUMPTION_PERCENTAGE - value: '' - - ## Specify the amount of memory to be consumed in mebibytes - ## NOTE: for selecting this option keep MEMORY_CONSUMPTION_PERCENTAGE empty - - name: MEMORY_CONSUMPTION_MEBIBYTES - value: '' - - - name: NUMBER_OF_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-memory-hog - app.kubernetes.io/part-of: litmus - app.kubernetes.io/component: experiment-job - app.kubernetes.io/version: latest - ---- -apiVersion: litmuschaos.io/v1alpha1 -description: - message: | - Fillup Ephemeral Storage of a Resource -kind: ChaosExperiment -metadata: - name: disk-fill - labels: - name: disk-fill - app.kubernetes.io/part-of: litmus - app.kubernetes.io/component: chaosexperiment - app.kubernetes.io/version: latest -spec: - definition: - scope: Namespaced - permissions: - # 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 disk-fill - command: - - /bin/bash - env: - - - name: TARGET_CONTAINER - value: '' - - - name: FILL_PERCENTAGE - value: '80' - - - name: TOTAL_CHAOS_DURATION - value: '60' - - # Period to wait before and after injection of chaos in sec - - name: RAMP_TIME - value: '' - - # Provide the LIB here - # Only litmus supported - - name: LIB - value: 'litmus' - - # provide the data block size - # supported unit is KB - - name: DATA_BLOCK_SIZE - value: '256' - - - name: TARGET_PODS - value: '' - - - name: EPHEMERAL_STORAGE_MEBIBYTES - value: '' - - # To select pods on specific node(s) - - name: NODE_LABEL - value: '' - - ## percentage of total pods to target - - name: PODS_AFFECTED_PERC - value: '' - - - name: LIB_IMAGE - value: 'litmuschaos/go-runner:latest' - - # Provide the container runtime path - # Default set to docker container path - - name: CONTAINER_PATH - value: '/var/lib/docker/containers' - - ## it defines the sequence of chaos execution for multiple target pods - ## supported values: serial, parallel - - name: SEQUENCE - value: 'parallel' - - labels: - name: disk-fill - app.kubernetes.io/part-of: litmus - app.kubernetes.io/component: experiment-job - app.kubernetes.io/host-path-usage: "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 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: @@ -2533,99 +600,12 @@ spec: apiVersion: litmuschaos.io/v1alpha1 description: message: | - Kills the docker service on the application node to check the resiliency. + 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: docker-service-kill + name: pod-http-reset-peer 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 100% network packet loss on pods belonging to an app deployment -kind: ChaosExperiment -metadata: - name: pod-network-partition - labels: - name: pod-network-partition + name: pod-http-reset-peer app.kubernetes.io/part-of: litmus app.kubernetes.io/component: chaosexperiment app.kubernetes.io/version: latest @@ -2653,14 +633,26 @@ spec: - 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"] - # 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"] @@ -2669,51 +661,277 @@ spec: imagePullPolicy: Always args: - -c - - ./experiments -name pod-network-partition + - ./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 - # ime period to wait before and after injection of chaos in sec + # Time period to wait before and after injection of chaos in sec - name: RAMP_TIME value: '' - # it should be litmus + # lib can be litmus or pumba - name: LIB value: 'litmus' - # provide the destination ips - # chaos injection will be triggered for these destination ips - - name: DESTINATION_IPS + # percentage of total pods to target + - name: PODS_AFFECTED_PERC value: '' - # provide the destination hosts - # chaos injection will be triggered for these destination hosts - - name: DESTINATION_HOSTS + - name: TARGET_PODS value: '' - # provide network policy type - # support ingress, egress, all values - - name: POLICY_TYPES - value: 'all' + # 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 labels of the destination pods - - name: POD_SELECTOR + # provide the socket file path + - name: SOCKET_PATH + value: '/var/run/docker.sock' + + # To select pods on specific node(s) + - name: NODE_LABEL value: '' - # provide labels the destination namespaces - - name: NAMESPACE_SELECTOR + ## 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 comma separated ports - - name: PORTS + # 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: pod-network-partition + 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 @@ -2858,112 +1076,6 @@ 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 @@ -3169,6 +1281,135 @@ spec: 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: @@ -3255,6 +1496,269 @@ spec: app.kubernetes.io/service-kill: "true" 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: 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: | + IO stress on a app pods belonging to an app deployment +kind: ChaosExperiment +metadata: + name: pod-io-stress + labels: + name: pod-io-stress + app.kubernetes.io/part-of: litmus + app.kubernetes.io/component: chaosexperiment + app.kubernetes.io/version: latest +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-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: '' + + ## Total number of workers default value is 4 + - name: NUMBER_OF_WORKERS + value: '4' + + ## Percentage of total pods to target + - name: PODS_AFFECTED_PERC + value: '' + + # provide volume mount path + - name: VOLUME_MOUNT_PATH + value: '' + + ## specify the comma separated target pods + - name: TARGET_PODS + value: '' + + # To select pods on specific node(s) + - name: NODE_LABEL + value: '' + + # Period to wait before and after injection of chaos in sec + - name: RAMP_TIME + value: '' + + # Provide the LIB here + # support litmus and pumba + - name: LIB + value: 'litmus' + + # provide lib image + - name: LIB_IMAGE + value: 'litmuschaos/go-runner:latest' + + ## provide the cluster runtime + - 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' + + labels: + name: pod-io-stress + 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: @@ -3372,6 +1876,86 @@ 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: @@ -3516,3 +2100,1419 @@ spec: 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: + message: | + Inject network packet corruption into application pod +kind: ChaosExperiment +metadata: + name: pod-network-corruption + labels: + name: pod-network-corruption + 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-corruption + command: + - /bin/bash + env: + + - name: TARGET_CONTAINER + value: '' + + # provide lib image + - name: LIB_IMAGE + value: 'litmuschaos/go-runner:latest' + + - name: NETWORK_INTERFACE + value: 'eth0' + + - name: TC_IMAGE + value: 'gaiadocker/iproute2' + + - name: NETWORK_PACKET_CORRUPTION_PERCENTAGE + value: '100' #in PERCENTAGE + + - name: TOTAL_CHAOS_DURATION + value: '60' # in seconds + + # Time period to wait before and after injection of chaos in sec + - name: RAMP_TIME + value: '' + + # 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: '' + + # To select pods on specific node(s) + - name: NODE_LABEL + value: '' + + # provide the name of container runtime + # for litmus LIB, it supports docker, containerd, crio + # for pumba LIB, it supports docker only + - name: CONTAINER_RUNTIME + value: 'docker' + + # provide the destination ips + # chaos injection will be triggered for these destination ips + - name: DESTINATION_IPS + value: '' + + # provide the destination hosts + # chaos injection will be triggered for these destination hosts + - name: DESTINATION_HOSTS + value: '' + + # provide the socket file path + - name: SOCKET_PATH + value: '/var/run/docker.sock' + + ## it defines the sequence of chaos execution for multiple target pods + ## supported values: serial, parallel + - name: SEQUENCE + value: 'parallel' + + labels: + name: pod-network-corruption + 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: | + 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: | + Fillup Ephemeral Storage of a Resource +kind: ChaosExperiment +metadata: + name: disk-fill + labels: + name: disk-fill + app.kubernetes.io/part-of: litmus + app.kubernetes.io/component: chaosexperiment + app.kubernetes.io/version: latest +spec: + definition: + scope: Namespaced + permissions: + # 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 disk-fill + command: + - /bin/bash + env: + + - name: TARGET_CONTAINER + value: '' + + - name: FILL_PERCENTAGE + value: '80' + + - name: TOTAL_CHAOS_DURATION + value: '60' + + # Period to wait before and after injection of chaos in sec + - name: RAMP_TIME + value: '' + + # Provide the LIB here + # Only litmus supported + - name: LIB + value: 'litmus' + + # provide the data block size + # supported unit is KB + - name: DATA_BLOCK_SIZE + value: '256' + + - name: TARGET_PODS + value: '' + + - name: EPHEMERAL_STORAGE_MEBIBYTES + value: '' + + # To select pods on specific node(s) + - name: NODE_LABEL + value: '' + + ## percentage of total pods to target + - name: PODS_AFFECTED_PERC + value: '' + + - name: LIB_IMAGE + value: 'litmuschaos/go-runner:latest' + + # Provide the container runtime path + # Default set to docker container path + - name: CONTAINER_PATH + value: '/var/lib/docker/containers' + + ## it defines the sequence of chaos execution for multiple target pods + ## supported values: serial, parallel + - name: SEQUENCE + value: 'parallel' + + labels: + name: disk-fill + app.kubernetes.io/part-of: litmus + app.kubernetes.io/component: experiment-job + app.kubernetes.io/host-path-usage: "true" + app.kubernetes.io/version: latest + +--- diff --git a/charts/kafka/experiments.yaml b/charts/kafka/experiments.yaml index 893dc2b..09ea53a 100644 --- a/charts/kafka/experiments.yaml +++ b/charts/kafka/experiments.yaml @@ -1,124 +1,4 @@ apiVersion: litmuschaos.io/v1alpha1 -description: - message: | - Detaching a persistent disk from a node/instance for kafka. -kind: ChaosExperiment -metadata: - name: kafka-broker-disk-failure - labels: - name: kafka-broker-disk-failure - app.kubernetes.io/part-of: litmus - app.kubernetes.io/component: chaosexperiment - app.kubernetes.io/version: latest -spec: - definition: - scope: Cluster - permissions: - - apiGroups: - - "" - - "apps" - - "batch" - - "litmuschaos.io" - resources: - - "statefulsets" - - "secrets" - - "jobs" - - "pods/log" - - "events" - - "pods" - - "pods/exec" - - "chaosengines" - - "chaosexperiments" - - "chaosresults" - verbs: - - "create" - - "delete" - - "get" - - "list" - - "patch" - image: "litmuschaos/ansible-runner:latest" - imagePullPolicy: Always - args: - - -c - - ansible-playbook ./experiments/kafka/kafka-broker-disk-failure/kafka-broker-disk-failure-ansible-logic.yml -i /etc/ansible/hosts -vv; exit 0 - command: - - /bin/bash - env: - - name: ANSIBLE_STDOUT_CALLBACK - value: 'default' - - - name: KAFKA_KIND - value: 'statefulset' - - - name: KAFKA_LIVENESS_STREAM - value: 'enabled' - - - name: KAFKA_LIVENESS_IMAGE - value: 'litmuschaos/kafka-client:ci' - - - name: KAFKA_CONSUMER_TIMEOUT - value: '30000' - - - name: TOTAL_CHAOS_DURATION - value: '15' - - - name: PROJECT_ID - value: '' - - - name: DISK_NAME - value: '' - - - name: ZONE_NAME - value: '' - - # GKE and AWS supported - - name: CLOUD_PLATFORM - value: 'GKE' - - - name: KAFKA_NAMESPACE - value: '' - - - name: KAFKA_LABEL - value: '' - - - name: KAFKA_BROKER - value: '' - - - name: KAFKA_INSTANCE_NAME - value: '' - - - name: KAFKA_REPLICATION_FACTOR - value: '' - - - name: KAFKA_SERVICE - value: '' - - - name: KAFKA_PORT - value: '' - - - name: ZOOKEEPER_NAMESPACE - value: '' - - - name: ZOOKEEPER_LABEL - value: '' - - - name: ZOOKEEPER_SERVICE - value: '' - - - name: ZOOKEEPER_PORT - value: '' - labels: - name: kafka-broker-disk-failure - app.kubernetes.io/part-of: litmus - app.kubernetes.io/component: experiment-job - app.kubernetes.io/version: latest - secrets: - - name: kafka-broker-disk-failure - mountPath: /tmp/ - - ---- -apiVersion: litmuschaos.io/v1alpha1 description: message: | Deleting a kafka broker pod @@ -247,3 +127,123 @@ spec: app.kubernetes.io/version: latest --- +apiVersion: litmuschaos.io/v1alpha1 +description: + message: | + Detaching a persistent disk from a node/instance for kafka. +kind: ChaosExperiment +metadata: + name: kafka-broker-disk-failure + labels: + name: kafka-broker-disk-failure + app.kubernetes.io/part-of: litmus + app.kubernetes.io/component: chaosexperiment + app.kubernetes.io/version: latest +spec: + definition: + scope: Cluster + permissions: + - apiGroups: + - "" + - "apps" + - "batch" + - "litmuschaos.io" + resources: + - "statefulsets" + - "secrets" + - "jobs" + - "pods/log" + - "events" + - "pods" + - "pods/exec" + - "chaosengines" + - "chaosexperiments" + - "chaosresults" + verbs: + - "create" + - "delete" + - "get" + - "list" + - "patch" + image: "litmuschaos/ansible-runner:latest" + imagePullPolicy: Always + args: + - -c + - ansible-playbook ./experiments/kafka/kafka-broker-disk-failure/kafka-broker-disk-failure-ansible-logic.yml -i /etc/ansible/hosts -vv; exit 0 + command: + - /bin/bash + env: + - name: ANSIBLE_STDOUT_CALLBACK + value: 'default' + + - name: KAFKA_KIND + value: 'statefulset' + + - name: KAFKA_LIVENESS_STREAM + value: 'enabled' + + - name: KAFKA_LIVENESS_IMAGE + value: 'litmuschaos/kafka-client:ci' + + - name: KAFKA_CONSUMER_TIMEOUT + value: '30000' + + - name: TOTAL_CHAOS_DURATION + value: '15' + + - name: PROJECT_ID + value: '' + + - name: DISK_NAME + value: '' + + - name: ZONE_NAME + value: '' + + # GKE and AWS supported + - name: CLOUD_PLATFORM + value: 'GKE' + + - name: KAFKA_NAMESPACE + value: '' + + - name: KAFKA_LABEL + value: '' + + - name: KAFKA_BROKER + value: '' + + - name: KAFKA_INSTANCE_NAME + value: '' + + - name: KAFKA_REPLICATION_FACTOR + value: '' + + - name: KAFKA_SERVICE + value: '' + + - name: KAFKA_PORT + value: '' + + - name: ZOOKEEPER_NAMESPACE + value: '' + + - name: ZOOKEEPER_LABEL + value: '' + + - name: ZOOKEEPER_SERVICE + value: '' + + - name: ZOOKEEPER_PORT + value: '' + labels: + name: kafka-broker-disk-failure + app.kubernetes.io/part-of: litmus + app.kubernetes.io/component: experiment-job + app.kubernetes.io/version: latest + secrets: + - name: kafka-broker-disk-failure + mountPath: /tmp/ + + +--- diff --git a/charts/kube-aws/experiments.yaml b/charts/kube-aws/experiments.yaml index e2900ff..efd13a3 100644 --- a/charts/kube-aws/experiments.yaml +++ b/charts/kube-aws/experiments.yaml @@ -1,106 +1,4 @@ apiVersion: litmuschaos.io/v1alpha1 -description: - message: | - Stopping an EC2 instance identified by tag. -kind: ChaosExperiment -metadata: - name: ec2-terminate-by-tag - labels: - name: ec2-terminate-by-tag - app.kubernetes.io/part-of: litmus - app.kubernetes.io/component: chaosexperiment - app.kubernetes.io/version: latest -spec: - definition: - scope: Cluster - permissions: - # 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 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 ec2-terminate-by-tag - command: - - /bin/bash - env: - - name: TOTAL_CHAOS_DURATION - value: '30' - - - name: CHAOS_INTERVAL - value: '30' - - # Period to wait before and after injection of chaos in sec - - name: RAMP_TIME - value: '' - - - 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' - - # Provide the path of aws credentials mounted from secret - - name: AWS_SHARED_CREDENTIALS_FILE - value: '/tmp/cloud_config.yml' - - # provide the LIB - # only litmus supported - - name: LIB - value: 'litmus' - - labels: - name: ec2-terminate-by-tag - app.kubernetes.io/part-of: litmus - app.kubernetes.io/component: experiment-job - app.kubernetes.io/version: latest - secrets: - - name: cloud-secret - mountPath: /tmp/ - ---- -apiVersion: litmuschaos.io/v1alpha1 description: message: | Detaching an ebs volume from ec2 instance. @@ -189,6 +87,98 @@ spec: - name: cloud-secret mountPath: /tmp/ +--- +apiVersion: litmuschaos.io/v1alpha1 +description: + message: | + Detaching an ebs volume from ec2 instance. +kind: ChaosExperiment +metadata: + name: ebs-loss-by-tag + labels: + name: ebs-loss-by-tag + 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 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"] + image: "litmuschaos/go-runner:latest" + imagePullPolicy: Always + args: + - -c + - ./experiments -name ebs-loss-by-tag + command: + - /bin/bash + env: + - name: TOTAL_CHAOS_DURATION + value: '30' + + - name: CHAOS_INTERVAL + value: '30' + + - name: RAMP_TIME + value: '' + + - name: EBS_VOLUME_TAG + value: '' + + - name: REGION + value: '' + + - name: SEQUENCE + value: 'parallel' + + - name: VOLUME_AFFECTED_PERC + value: '' + + # Provide the path of aws credentials mounted from secret + - name: AWS_SHARED_CREDENTIALS_FILE + value: '/tmp/cloud_config.yml' + + # provide the LIB + # only litmus supported + - name: LIB + value: 'litmus' + + labels: + name: ebs-loss-by-tag + app.kubernetes.io/part-of: litmus + app.kubernetes.io/component: experiment-job + app.kubernetes.io/version: latest + secrets: + - name: cloud-secret + mountPath: /tmp/ + --- apiVersion: litmuschaos.io/v1alpha1 description: @@ -371,12 +361,12 @@ 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 @@ -412,11 +402,15 @@ 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: @@ -426,22 +420,28 @@ 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' @@ -451,7 +451,7 @@ 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 diff --git a/charts/openebs/experiments.yaml b/charts/openebs/experiments.yaml index 3b3beb3..e7ef516 100644 --- a/charts/openebs/experiments.yaml +++ b/charts/openebs/experiments.yaml @@ -1,3 +1,386 @@ +--- +apiVersion: litmuschaos.io/v1alpha1 +description: + message: | + Kill the pool container and check if gets scheduled again +kind: ChaosExperiment +metadata: + labels: + litmuschaos.io/name: openebs + name: openebs-pool-container-failure + app.kubernetes.io/part-of: litmus + app.kubernetes.io/component: chaosexperiment + app.kubernetes.io/version: latest + name: openebs-pool-container-failure +spec: + definition: + scope: Cluster + permissions: + - apiGroups: + - "" + - "extensions" + - "apps" + - "batch" + - "litmuschaos.io" + - "openebs.io" + - "storage.k8s.io" + resources: + - "replicasets" + - "events" + - "jobs" + - "pods" + - "pods/log" + - "pods/exec" + - "configmaps" + - "secrets" + - "persistentvolumeclaims" + - "cstorvolumereplicas" + - "chaosengines" + - "chaosexperiments" + - "chaosresults" + verbs: + - "create" + - "get" + - "delete" + - "list" + - "patch" + - "update" + image: "litmuschaos/ansible-runner:latest" + imagePullPolicy: Always + args: + - -c + - ansible-playbook ./experiments/openebs/openebs-pool-container-failure/openebs_pool_container_failure_ansible_logic.yml -i /etc/ansible/hosts -vv; exit 0 + command: + - /bin/bash + env: + - name: ANSIBLE_STDOUT_CALLBACK + value: 'default' + + - name: OPENEBS_NS + value: 'openebs' + + - name: APP_PVC + value: '' + + - name: LIVENESS_APP_LABEL + value: '' + + # only pumba supported + # For pumba image use : gaiaadm/pumba:0.6.5 + - name: LIB_IMAGE + value: 'gaiaadm/pumba:0.6.5' + + - name: LIVENESS_APP_NAMESPACE + value: '' + + # provide the chaos interval + - name: CHAOS_INTERVAL + value: '10' + + # provide the total chaos duration + - name: TOTAL_CHAOS_DURATION + value: '20' + + - name: DATA_PERSISTENCE + value: '' + + - name: CHAOS_ITERATIONS + value: '2' + + labels: + name: openebs-pool-container-failure + app.kubernetes.io/part-of: litmus + app.kubernetes.io/component: experiment-job + app.kubernetes.io/version: latest + #configmaps: + #- name: openebs-pool-container-failure + # mountPath: /mnt + +--- +--- +apiVersion: litmuschaos.io/v1alpha1 +description: + message: | + 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: + message: | + Network delay to target pod belonging to a deployment/statefulset/daemonset +kind: ChaosExperiment +metadata: + labels: + litmuschaos.io/name: openebs + name: openebs-target-network-delay + app.kubernetes.io/part-of: litmus + app.kubernetes.io/component: chaosexperiment + app.kubernetes.io/version: latest + name: openebs-target-network-delay +spec: + definition: + scope: Cluster + permissions: + - apiGroups: + - "" + - "extensions" + - "apps" + - "batch" + - "litmuschaos.io" + - "storage.k8s.io" + resources: + - "jobs" + - "pods" + - "services" + - "events" + - "pods/exec" + - "pods/log" + - "configmaps" + - "secrets" + - "persistentvolumeclaims" + - "storageclasses" + - "persistentvolumes" + - "chaosengines" + - "chaosexperiments" + - "chaosresults" + verbs: + - "create" + - "get" + - "delete" + - "list" + - "patch" + - "update" + image: "litmuschaos/ansible-runner:latest" + imagePullPolicy: Always + args: + - -c + - ansible-playbook ./experiments/openebs/openebs-target-network-delay/openebs_target_network_delay_ansible_logic.yml -i /etc/ansible/hosts -vv; exit 0 + command: + - /bin/bash + env: + - name: ANSIBLE_STDOUT_CALLBACK + value: 'default' + + - name: OPENEBS_NAMESPACE + value: 'openebs' + + - name: APP_PVC + value: '' + + - name: TC_IMAGE + value: 'gaiadocker/iproute2' + + # only pumba supported + # For pumba image use : gaiaadm/pumba:0.6.5 + - name: LIB_IMAGE + value: 'gaiaadm/pumba:0.6.5' + + - name: NETWORK_DELAY + value: '60000' # in milliseconds + + - name: TOTAL_CHAOS_DURATION + value: '60' # in seconds + + - name: LIVENESS_APP_LABEL + value: '' + + - name: LIVENESS_APP_NAMESPACE + value: '' + + - name: DATA_PERSISTENCE + value: '' + + labels: + name: openebs-target-network-delay + app.kubernetes.io/part-of: litmus + app.kubernetes.io/component: experiment-job + app.kubernetes.io/version: latest + #configmaps: + #- name: openebs-target-network-delay + # mountPath: /mnt + +--- apiVersion: litmuschaos.io/v1alpha1 description: message: | @@ -91,6 +474,414 @@ spec: app.kubernetes.io/component: experiment-job app.kubernetes.io/version: latest +--- +--- +apiVersion: litmuschaos.io/v1alpha1 +description: + message: | + Kill the OpenEBS NFS provisioner container and check if pods consuming the NFS PVs continue to be available and volumes are writable (RWM mode) +kind: ChaosExperiment +metadata: + labels: + litmuschaos.io/name: openebs + name: openebs-nfs-provisioner-kill + app.kubernetes.io/part-of: litmus + app.kubernetes.io/component: chaosexperiment + app.kubernetes.io/version: latest + name: openebs-nfs-provisioner-kill +spec: + definition: + scope: Cluster + permissions: + - apiGroups: + - "" + - "apps" + - "litmuschaos.io" + - "batch" + - "extensions" + - "storage.k8s.io" + resources: + - "pods" + - "pods/exec" + - "pods/log" + - "deployments" + - "events" + - "jobs" + - "configmaps" + - "services" + - "persistentvolumeclaims" + - "storageclasses" + - "persistentvolumes" + - "chaosexperiments" + - "chaosresults" + - "chaosengines" + 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-nfs-provisioner-kill/openebs_nfs_provisioner_kill_ansible_logic.yml -i /etc/ansible/hosts -vv; exit 0 + command: + - /bin/bash + env: + - name: ANSIBLE_STDOUT_CALLBACK + value: 'default' + + # NFS default container + - name: TARGET_CONTAINER + value: 'nfs-provisioner' + + # Period to wait before injection of chaos in sec + - name: RAMP_TIME + value: '' + + # It supports pumba and containerd + - name: LIB + value: 'pumba' + + # LIB_IMAGE can be - gaiaadm/pumba:0.6.5, gprasath/crictl:ci + # For pumba image use: gaiaadm/pumba:0.6.5 + # For containerd image use: gprasath/crictl:ci + - name: LIB_IMAGE + value: 'gaiaadm/pumba:0.6.5' + + # provide the chaos interval + - name: CHAOS_INTERVAL + value: '10' + + # provide the total chaos duration + - name: TOTAL_CHAOS_DURATION + value: '20' + + labels: + name: openebs-nfs-provisioner-kill + app.kubernetes.io/part-of: litmus + app.kubernetes.io/component: experiment-job + app.kubernetes.io/version: latest + configmaps: + - name: openebs-nfs-provisioner-kill + mountPath: /mnt/ + +--- +apiVersion: litmuschaos.io/v1alpha1 +description: + message: | + Network loss to target pod belonging to a OpenEBS PVC +kind: ChaosExperiment +metadata: + labels: + litmuschaos.io/name: openebs + name: openebs-target-network-loss + app.kubernetes.io/part-of: litmus + app.kubernetes.io/component: chaosexperiment + app.kubernetes.io/version: latest + name: openebs-target-network-loss +spec: + definition: + scope: Cluster + permissions: + - apiGroups: + - "" + - "extensions" + - "apps" + - "batch" + - "litmuschaos.io" + - "storage.k8s.io" + resources: + - "jobs" + - "pods" + - "events" + - "services" + - "pods/log" + - "pods/exec" + - "configmaps" + - "secrets" + - "persistentvolumeclaims" + - "storageclasses" + - "persistentvolumes" + - "chaosengines" + - "chaosexperiments" + - "chaosresults" + verbs: + - "create" + - "get" + - "delete" + - "list" + - "patch" + - "update" + image: "litmuschaos/ansible-runner:latest" + imagePullPolicy: Always + args: + - -c + - ansible-playbook ./experiments/openebs/openebs-target-network-loss/openebs_target_network_loss_ansible_logic.yml -i /etc/ansible/hosts -vv; exit 0 + command: + - /bin/bash + env: + - name: ANSIBLE_STDOUT_CALLBACK + value: 'default' + + - name: OPENEBS_NAMESPACE + value: 'openebs' + + - name: APP_PVC + value: '' + + - name: TC_IMAGE + value: 'gaiadocker/iproute2' + + # only pumba supported + # For pumba image use : gaiaadm/pumba:0.6.5 + - name: LIB_IMAGE + value: 'gaiaadm/pumba:0.6.5' + + - name: NETWORK_PACKET_LOSS_PERCENTAGE + value: '100' # in percentage + + - name: TOTAL_CHAOS_DURATION + value: '120' # in seconds + + - name: LIVENESS_APP_LABEL + value: '' + + - name: LIVENESS_APP_NAMESPACE + value: '' + + - name: DATA_PERSISTENCE + value: '' + + labels: + name: openebs-target-network-loss + app.kubernetes.io/part-of: litmus + app.kubernetes.io/component: experiment-job + app.kubernetes.io/version: latest + #configmaps: + #- name: openebs-target-network-loss + # mountPath: /mnt + +--- +apiVersion: litmuschaos.io/v1alpha1 +description: + message: | + Network delay to pool pod belonging to a OpenEBS PVC + This experiment is using pumba lib for network chaos +kind: ChaosExperiment +metadata: + labels: + litmuschaos.io/name: openebs + name: openebs-pool-network-delay + app.kubernetes.io/part-of: litmus + app.kubernetes.io/component: chaosexperiment + app.kubernetes.io/version: latest + name: openebs-pool-network-delay +spec: + definition: + scope: Cluster + permissions: + - apiGroups: + - "" + - "apps" + - "litmuschaos.io" + - "batch" + - "extensions" + - "storage.k8s.io" + - "openebs.io" + resources: + - "pods" + - "pods/exec" + - "jobs" + - "pods/log" + - "events" + - "configmaps" + - "services" + - "persistentvolumeclaims" + - "storageclasses" + - "persistentvolumes" + - "chaosengines" + - "chaosexperiments" + - "chaosresults" + - "cstorpools" + - "cstorvolumereplicas" + - "replicasets" + verbs: + - "create" + - "get" + - "list" + - "patch" + - "update" + - "delete" + image: "litmuschaos/ansible-runner:latest" + imagePullPolicy: Always + args: + - -c + - ansible-playbook ./experiments/openebs/openebs-pool-network-delay/openebs_pool_network_delay_ansible_logic.yml -i /etc/ansible/hosts -vv; exit 0 + command: + - /bin/bash + env: + - name: ANSIBLE_STDOUT_CALLBACK + value: 'default' + + - name: OPENEBS_NAMESPACE + value: 'openebs' + + # only pumba supported + # For pumba image use : gaiaadm/pumba:0.6.5 + - name: LIB_IMAGE + value: 'gaiaadm/pumba:0.6.5' + + # in milliseconds + - name: NETWORK_DELAY + value: '60000' + + - name: TC_IMAGE + value: 'gaiadocker/iproute2' + + - name: TOTAL_CHAOS_DURATION + value: '60' # in seconds + + - name: LIVENESS_APP_LABEL + value: '' + + - name: LIVENESS_APP_NAMESPACE + value: '' + + - name: DATA_PERSISTENCE + value: '' + + labels: + name: openebs-pool-network-delay + app.kubernetes.io/part-of: litmus + app.kubernetes.io/component: experiment-job + app.kubernetes.io/version: latest + +--- +--- +apiVersion: litmuschaos.io/v1alpha1 +description: + message: | + Kill the cstor target/Jiva controller container and check if gets created again +kind: ChaosExperiment +metadata: + labels: + litmuschaos.io/name: openebs + name: openebs-target-container-failure + app.kubernetes.io/part-of: litmus + app.kubernetes.io/component: chaosexperiment + app.kubernetes.io/version: latest + name: openebs-target-container-failure +spec: + definition: + scope: Cluster + permissions: + - apiGroups: + - "" + - "apps" + - "batch" + - "litmuschaos.io" + - "storage.k8s.io" + resources: + - "jobs" + - "pods" + - "events" + - "pods/exec" + - "pods/log" + - "configmaps" + - "secrets" + - "persistentvolumeclaims" + - "storageclasses" + - "persistentvolumes" + - "chaosengines" + - "chaosexperiments" + - "chaosresults" + verbs: + - "create" + - "delete" + - "get" + - "list" + - "patch" + - "update" + image: "litmuschaos/ansible-runner:latest" + imagePullPolicy: Always + args: + - -c + - ansible-playbook ./experiments/openebs/openebs-target-container-failure/openebs_target_container_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: '' + + # LIB_IMAGE can be - gaiaadm/pumba:0.6.5, gprasath/crictl:ci + # For pumba image use : gaiaadm/pumba:0.6.5 + # For containerd image use : gprasath/crictl:ci + - name: LIB_IMAGE + value: 'gaiaadm/pumba:0.6.5' + + # Specify the container runtime used , to pick the relevant chaos util + - name: CONTAINER_RUNTIME + value: 'docker' + + # TARGET_CONTAINER values: cstor-volume-mgmt , cstor-istgt + # For cstor-volume-istgt container kill use : cstor-istgt + # For volume-mgmt-kill container use : cstor-volume-mgmt + + - name: TARGET_CONTAINER + value: 'cstor-volume-mgmt' + + - name: FORCE + value: 'true' + + - name: LIVENESS_APP_LABEL + value: '' + + - name: LIVENESS_APP_NAMESPACE + value: '' + + - name: DATA_PERSISTENCE + value: '' + + - name: DEPLOY_TYPE + value: 'deployment' + + # provide the chaos interval + - name: CHAOS_INTERVAL + value: '10' + + # provide the total chaos duration + - name: TOTAL_CHAOS_DURATION + value: '20' + + - name: SOAK_TIME + value: '60' + + labels: + name: openebs-target-container-failure + app.kubernetes.io/part-of: litmus + app.kubernetes.io/component: experiment-job + app.kubernetes.io/version: latest + #configmaps: + #- name: openebs-target-container-failure + # mountPath: /mnt + --- --- apiVersion: litmuschaos.io/v1alpha1 @@ -204,278 +995,6 @@ spec: - name: cloud-secret mountPath: /tmp/ ---- ---- -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: | - Network delay to pool pod belonging to a OpenEBS PVC - This experiment is using pumba lib for network chaos -kind: ChaosExperiment -metadata: - labels: - litmuschaos.io/name: openebs - name: openebs-pool-network-delay - app.kubernetes.io/part-of: litmus - app.kubernetes.io/component: chaosexperiment - app.kubernetes.io/version: latest - name: openebs-pool-network-delay -spec: - definition: - scope: Cluster - permissions: - - apiGroups: - - "" - - "apps" - - "litmuschaos.io" - - "batch" - - "extensions" - - "storage.k8s.io" - - "openebs.io" - resources: - - "pods" - - "pods/exec" - - "jobs" - - "pods/log" - - "events" - - "configmaps" - - "services" - - "persistentvolumeclaims" - - "storageclasses" - - "persistentvolumes" - - "chaosengines" - - "chaosexperiments" - - "chaosresults" - - "cstorpools" - - "cstorvolumereplicas" - - "replicasets" - verbs: - - "create" - - "get" - - "list" - - "patch" - - "update" - - "delete" - image: "litmuschaos/ansible-runner:latest" - imagePullPolicy: Always - args: - - -c - - ansible-playbook ./experiments/openebs/openebs-pool-network-delay/openebs_pool_network_delay_ansible_logic.yml -i /etc/ansible/hosts -vv; exit 0 - command: - - /bin/bash - env: - - name: ANSIBLE_STDOUT_CALLBACK - value: 'default' - - - name: OPENEBS_NAMESPACE - value: 'openebs' - - # only pumba supported - # For pumba image use : gaiaadm/pumba:0.6.5 - - name: LIB_IMAGE - value: 'gaiaadm/pumba:0.6.5' - - # in milliseconds - - name: NETWORK_DELAY - value: '60000' - - - name: TC_IMAGE - value: 'gaiadocker/iproute2' - - - name: TOTAL_CHAOS_DURATION - value: '60' # in seconds - - - name: LIVENESS_APP_LABEL - value: '' - - - name: LIVENESS_APP_NAMESPACE - value: '' - - - name: DATA_PERSISTENCE - value: '' - - labels: - name: openebs-pool-network-delay - app.kubernetes.io/part-of: litmus - app.kubernetes.io/component: experiment-job - app.kubernetes.io/version: latest - ---- -apiVersion: litmuschaos.io/v1alpha1 -description: - message: | - 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 @@ -576,522 +1095,3 @@ spec: --- ---- -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: - message: | - Kill the OpenEBS NFS provisioner container and check if pods consuming the NFS PVs continue to be available and volumes are writable (RWM mode) -kind: ChaosExperiment -metadata: - labels: - litmuschaos.io/name: openebs - name: openebs-nfs-provisioner-kill - app.kubernetes.io/part-of: litmus - app.kubernetes.io/component: chaosexperiment - app.kubernetes.io/version: latest - name: openebs-nfs-provisioner-kill -spec: - definition: - scope: Cluster - permissions: - - apiGroups: - - "" - - "apps" - - "litmuschaos.io" - - "batch" - - "extensions" - - "storage.k8s.io" - resources: - - "pods" - - "pods/exec" - - "pods/log" - - "deployments" - - "events" - - "jobs" - - "configmaps" - - "services" - - "persistentvolumeclaims" - - "storageclasses" - - "persistentvolumes" - - "chaosexperiments" - - "chaosresults" - - "chaosengines" - 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-nfs-provisioner-kill/openebs_nfs_provisioner_kill_ansible_logic.yml -i /etc/ansible/hosts -vv; exit 0 - command: - - /bin/bash - env: - - name: ANSIBLE_STDOUT_CALLBACK - value: 'default' - - # NFS default container - - name: TARGET_CONTAINER - value: 'nfs-provisioner' - - # Period to wait before injection of chaos in sec - - name: RAMP_TIME - value: '' - - # It supports pumba and containerd - - name: LIB - value: 'pumba' - - # LIB_IMAGE can be - gaiaadm/pumba:0.6.5, gprasath/crictl:ci - # For pumba image use: gaiaadm/pumba:0.6.5 - # For containerd image use: gprasath/crictl:ci - - name: LIB_IMAGE - value: 'gaiaadm/pumba:0.6.5' - - # provide the chaos interval - - name: CHAOS_INTERVAL - value: '10' - - # provide the total chaos duration - - name: TOTAL_CHAOS_DURATION - value: '20' - - labels: - name: openebs-nfs-provisioner-kill - app.kubernetes.io/part-of: litmus - app.kubernetes.io/component: experiment-job - app.kubernetes.io/version: latest - configmaps: - - name: openebs-nfs-provisioner-kill - mountPath: /mnt/ - ---- ---- -apiVersion: litmuschaos.io/v1alpha1 -description: - message: | - Kill the pool container and check if gets scheduled again -kind: ChaosExperiment -metadata: - labels: - litmuschaos.io/name: openebs - name: openebs-pool-container-failure - app.kubernetes.io/part-of: litmus - app.kubernetes.io/component: chaosexperiment - app.kubernetes.io/version: latest - name: openebs-pool-container-failure -spec: - definition: - scope: Cluster - permissions: - - apiGroups: - - "" - - "extensions" - - "apps" - - "batch" - - "litmuschaos.io" - - "openebs.io" - - "storage.k8s.io" - resources: - - "replicasets" - - "events" - - "jobs" - - "pods" - - "pods/log" - - "pods/exec" - - "configmaps" - - "secrets" - - "persistentvolumeclaims" - - "cstorvolumereplicas" - - "chaosengines" - - "chaosexperiments" - - "chaosresults" - verbs: - - "create" - - "get" - - "delete" - - "list" - - "patch" - - "update" - image: "litmuschaos/ansible-runner:latest" - imagePullPolicy: Always - args: - - -c - - ansible-playbook ./experiments/openebs/openebs-pool-container-failure/openebs_pool_container_failure_ansible_logic.yml -i /etc/ansible/hosts -vv; exit 0 - command: - - /bin/bash - env: - - name: ANSIBLE_STDOUT_CALLBACK - value: 'default' - - - name: OPENEBS_NS - value: 'openebs' - - - name: APP_PVC - value: '' - - - name: LIVENESS_APP_LABEL - value: '' - - # only pumba supported - # For pumba image use : gaiaadm/pumba:0.6.5 - - name: LIB_IMAGE - value: 'gaiaadm/pumba:0.6.5' - - - name: LIVENESS_APP_NAMESPACE - value: '' - - # provide the chaos interval - - name: CHAOS_INTERVAL - value: '10' - - # provide the total chaos duration - - name: TOTAL_CHAOS_DURATION - value: '20' - - - name: DATA_PERSISTENCE - value: '' - - - name: CHAOS_ITERATIONS - value: '2' - - labels: - name: openebs-pool-container-failure - app.kubernetes.io/part-of: litmus - app.kubernetes.io/component: experiment-job - app.kubernetes.io/version: latest - #configmaps: - #- name: openebs-pool-container-failure - # mountPath: /mnt - ---- ---- -apiVersion: litmuschaos.io/v1alpha1 -description: - message: | - Kill the cstor target/Jiva controller container and check if gets created again -kind: ChaosExperiment -metadata: - labels: - litmuschaos.io/name: openebs - name: openebs-target-container-failure - app.kubernetes.io/part-of: litmus - app.kubernetes.io/component: chaosexperiment - app.kubernetes.io/version: latest - name: openebs-target-container-failure -spec: - definition: - scope: Cluster - permissions: - - apiGroups: - - "" - - "apps" - - "batch" - - "litmuschaos.io" - - "storage.k8s.io" - resources: - - "jobs" - - "pods" - - "events" - - "pods/exec" - - "pods/log" - - "configmaps" - - "secrets" - - "persistentvolumeclaims" - - "storageclasses" - - "persistentvolumes" - - "chaosengines" - - "chaosexperiments" - - "chaosresults" - verbs: - - "create" - - "delete" - - "get" - - "list" - - "patch" - - "update" - image: "litmuschaos/ansible-runner:latest" - imagePullPolicy: Always - args: - - -c - - ansible-playbook ./experiments/openebs/openebs-target-container-failure/openebs_target_container_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: '' - - # LIB_IMAGE can be - gaiaadm/pumba:0.6.5, gprasath/crictl:ci - # For pumba image use : gaiaadm/pumba:0.6.5 - # For containerd image use : gprasath/crictl:ci - - name: LIB_IMAGE - value: 'gaiaadm/pumba:0.6.5' - - # Specify the container runtime used , to pick the relevant chaos util - - name: CONTAINER_RUNTIME - value: 'docker' - - # TARGET_CONTAINER values: cstor-volume-mgmt , cstor-istgt - # For cstor-volume-istgt container kill use : cstor-istgt - # For volume-mgmt-kill container use : cstor-volume-mgmt - - - name: TARGET_CONTAINER - value: 'cstor-volume-mgmt' - - - name: FORCE - value: 'true' - - - name: LIVENESS_APP_LABEL - value: '' - - - name: LIVENESS_APP_NAMESPACE - value: '' - - - name: DATA_PERSISTENCE - value: '' - - - name: DEPLOY_TYPE - value: 'deployment' - - # provide the chaos interval - - name: CHAOS_INTERVAL - value: '10' - - # provide the total chaos duration - - name: TOTAL_CHAOS_DURATION - value: '20' - - - name: SOAK_TIME - value: '60' - - labels: - name: openebs-target-container-failure - app.kubernetes.io/part-of: litmus - app.kubernetes.io/component: experiment-job - app.kubernetes.io/version: latest - #configmaps: - #- name: openebs-target-container-failure - # mountPath: /mnt - ---- -apiVersion: litmuschaos.io/v1alpha1 -description: - message: | - Network delay to target pod belonging to a deployment/statefulset/daemonset -kind: ChaosExperiment -metadata: - labels: - litmuschaos.io/name: openebs - name: openebs-target-network-delay - app.kubernetes.io/part-of: litmus - app.kubernetes.io/component: chaosexperiment - app.kubernetes.io/version: latest - name: openebs-target-network-delay -spec: - definition: - scope: Cluster - permissions: - - apiGroups: - - "" - - "extensions" - - "apps" - - "batch" - - "litmuschaos.io" - - "storage.k8s.io" - resources: - - "jobs" - - "pods" - - "services" - - "events" - - "pods/exec" - - "pods/log" - - "configmaps" - - "secrets" - - "persistentvolumeclaims" - - "storageclasses" - - "persistentvolumes" - - "chaosengines" - - "chaosexperiments" - - "chaosresults" - verbs: - - "create" - - "get" - - "delete" - - "list" - - "patch" - - "update" - image: "litmuschaos/ansible-runner:latest" - imagePullPolicy: Always - args: - - -c - - ansible-playbook ./experiments/openebs/openebs-target-network-delay/openebs_target_network_delay_ansible_logic.yml -i /etc/ansible/hosts -vv; exit 0 - command: - - /bin/bash - env: - - name: ANSIBLE_STDOUT_CALLBACK - value: 'default' - - - name: OPENEBS_NAMESPACE - value: 'openebs' - - - name: APP_PVC - value: '' - - - name: TC_IMAGE - value: 'gaiadocker/iproute2' - - # only pumba supported - # For pumba image use : gaiaadm/pumba:0.6.5 - - name: LIB_IMAGE - value: 'gaiaadm/pumba:0.6.5' - - - name: NETWORK_DELAY - value: '60000' # in milliseconds - - - name: TOTAL_CHAOS_DURATION - value: '60' # in seconds - - - name: LIVENESS_APP_LABEL - value: '' - - - name: LIVENESS_APP_NAMESPACE - value: '' - - - name: DATA_PERSISTENCE - value: '' - - labels: - name: openebs-target-network-delay - app.kubernetes.io/part-of: litmus - app.kubernetes.io/component: experiment-job - app.kubernetes.io/version: latest - #configmaps: - #- name: openebs-target-network-delay - # mountPath: /mnt - ----