From 07253c6d84dd4e27116ec83fd3b98b6dd5d70b26 Mon Sep 17 00:00:00 2001 From: litmusbot Date: Thu, 12 Aug 2021 09:51:21 +0000 Subject: [PATCH] 1123421505: version upgraded for chaos-charts --- charts/cassandra/experiments.yaml | 2 +- charts/gcp/experiments.yaml | 190 +- charts/generic/experiments.yaml | 3916 +++++++++++++++-------------- charts/kafka/experiments.yaml | 240 +- charts/kube-aws/experiments.yaml | 348 +-- charts/openebs/experiments.yaml | 810 +++--- 6 files changed, 2757 insertions(+), 2749 deletions(-) diff --git a/charts/cassandra/experiments.yaml b/charts/cassandra/experiments.yaml index 1054241..b56f172 100644 --- a/charts/cassandra/experiments.yaml +++ b/charts/cassandra/experiments.yaml @@ -82,7 +82,7 @@ spec: value: '15' # SET THE CASSANDRA_LIVENESS_CHECK - # IT CAN BE `enabled` OR `disabled` + # IT CAN BE `enable` OR `disable` - name: CASSANDRA_LIVENESS_CHECK value: '' diff --git a/charts/gcp/experiments.yaml b/charts/gcp/experiments.yaml index 8188d8b..f87140c 100644 --- a/charts/gcp/experiments.yaml +++ b/charts/gcp/experiments.yaml @@ -1,99 +1,4 @@ apiVersion: litmuschaos.io/v1alpha1 -description: - message: | - Causes loss of a non-boot storage persistent disk from a GCP VM instance for a specified duration of time -kind: ChaosExperiment -metadata: - name: gcp-vm-disk-loss - labels: - name: gcp-vm-disk-loss - app.kubernetes.io/part-of: litmus - app.kubernetes.io/component: chaosexperiment - app.kubernetes.io/version: latest -spec: - definition: - scope: Cluster - permissions: - - apiGroups: - - "" - - "batch" - - "litmuschaos.io" - resources: - - "jobs" - - "pods" - - "pods/log" - - "events" - - "secrets" - - "pods/exec" - - "chaosengines" - - "chaosexperiments" - - "chaosresults" - verbs: - - "create" - - "list" - - "get" - - "patch" - - "update" - - "delete" - - "deletecollection" - image: "litmuschaos/go-runner:ci" - imagePullPolicy: Always - args: - - -c - - ./experiments -name gcp-vm-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: '' - - # parallel or serial; determines how chaos is injected - - name: SEQUENCE - value: 'parallel' - - # set the GCP project id - - name: GCP_PROJECT_ID - value: '' - - # set the disk volume name(s) as comma seperated values - # eg. volume1,volume2,... - - name: DISK_VOLUME_NAMES - value: '' - - # set the disk zone(s) as comma seperated values in the corresponding - # order of DISK_VOLUME_NAME - # eg. zone1,zone2,... - - name: DISK_ZONES - value: '' - - # set the device name(s) as comma seperated values in the corresponding - # order of DISK_VOLUME_NAME - # eg. device1,device2,... - - name: DEVICE_NAMES - value: '' - - labels: - name: gcp-vm-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: | Stops GCP VM instances and GKE nodes for a specified duration of time and later restarts them @@ -189,3 +94,98 @@ spec: 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 of time +kind: ChaosExperiment +metadata: + name: gcp-vm-disk-loss + labels: + name: gcp-vm-disk-loss + app.kubernetes.io/part-of: litmus + app.kubernetes.io/component: chaosexperiment + app.kubernetes.io/version: latest +spec: + definition: + scope: Cluster + permissions: + - apiGroups: + - "" + - "batch" + - "litmuschaos.io" + resources: + - "jobs" + - "pods" + - "pods/log" + - "events" + - "secrets" + - "pods/exec" + - "chaosengines" + - "chaosexperiments" + - "chaosresults" + verbs: + - "create" + - "list" + - "get" + - "patch" + - "update" + - "delete" + - "deletecollection" + image: "litmuschaos/go-runner:ci" + imagePullPolicy: Always + args: + - -c + - ./experiments -name gcp-vm-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: '' + + # parallel or serial; determines how chaos is injected + - name: SEQUENCE + value: 'parallel' + + # set the GCP project id + - name: GCP_PROJECT_ID + value: '' + + # set the disk volume name(s) as comma seperated values + # eg. volume1,volume2,... + - name: DISK_VOLUME_NAMES + value: '' + + # set the disk zone(s) as comma seperated values in the corresponding + # order of DISK_VOLUME_NAME + # eg. zone1,zone2,... + - name: DISK_ZONES + value: '' + + # set the device name(s) as comma seperated values in the corresponding + # order of DISK_VOLUME_NAME + # eg. device1,device2,... + - name: DEVICE_NAMES + value: '' + + labels: + name: gcp-vm-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/generic/experiments.yaml b/charts/generic/experiments.yaml index 5db5f5a..431a63c 100644 --- a/charts/generic/experiments.yaml +++ b/charts/generic/experiments.yaml @@ -1,200 +1,12 @@ ---- apiVersion: litmuschaos.io/v1alpha1 description: message: | - Drain the node where application pod is scheduled + Injects network latency on pods belonging to an app deployment kind: ChaosExperiment metadata: - name: node-drain + name: pod-network-latency labels: - name: node-drain - app.kubernetes.io/part-of: litmus - app.kubernetes.io/component: chaosexperiment - app.kubernetes.io/version: latest -spec: - definition: - scope: Cluster - permissions: - - apiGroups: - - "" - - "batch" - - "litmuschaos.io" - - "apps" - resources: - - "jobs" - - "pods" - - "events" - - "pods/log" - - "pods/exec" - - "daemonsets" - - "pods/eviction" - - "chaosengines" - - "chaosexperiments" - - "chaosresults" - verbs: - - "create" - - "list" - - "get" - - "patch" - - "update" - - "delete" - - "deletecollection" - - apiGroups: - - "" - resources: - - "nodes" - verbs: - - "get" - - "list" - - "patch" - image: "litmuschaos/go-runner:latest" - imagePullPolicy: Always - args: - - -c - - ./experiments -name node-drain - command: - - /bin/bash - env: - - - name: TARGET_NODE - value: '' - - - name: 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: | - 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: - - apiGroups: - - "" - - "batch" - - "litmuschaos.io" - resources: - - "jobs" - - "pods" - - "pods/log" - - "pods/exec" - - "events" - - "chaosengines" - - "chaosexperiments" - - "chaosresults" - verbs: - - "create" - - "list" - - "get" - - "patch" - - "update" - - "delete" - - "deletecollection" - - apiGroups: - - "" - resources: - - "nodes" - verbs: - - "get" - - "list" - image: "litmuschaos/go-runner:latest" - imagePullPolicy: Always - args: - - -c - - ./experiments -name node-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: | - Pod DNS Spoof can spoof particular dns requests in target pod container to desired target hostnames -kind: ChaosExperiment -metadata: - name: pod-dns-spoof - labels: - name: pod-dns-spoof + name: pod-network-latency app.kubernetes.io/part-of: litmus app.kubernetes.io/component: chaosexperiment app.kubernetes.io/version: latest @@ -234,52 +46,399 @@ spec: - "delete" - "deletecollection" image: "litmuschaos/go-runner:latest" + imagePullPolicy: Always args: - - -c - - ./experiments -name pod-dns-spoof + - -c + - ./experiments -name pod-network-latency command: - - /bin/bash + - /bin/bash env: - - name: TARGET_CONTAINER - value: "" + + - name: TARGET_CONTAINER + value: '' - # provide lib image - - name: LIB_IMAGE - value: "litmuschaos/go-runner:latest" + - name: NETWORK_INTERFACE + value: 'eth0' + # provide lib image + - name: LIB_IMAGE + value: 'litmuschaos/go-runner:latest' + + - name: TC_IMAGE + value: 'gaiadocker/iproute2' + + - name: NETWORK_LATENCY + value: '2000' #in ms + + - name: TOTAL_CHAOS_DURATION + value: '60' # in seconds + + # Time period to wait before and after injection of chaos in sec + - name: RAMP_TIME + value: '' + + # lib can be litmus or pumba + - name: LIB + value: 'litmus' + + ## percentage of total pods to target + - name: PODS_AFFECTED_PERC + value: '' + + - name: TARGET_PODS + value: '' + + # provide the name of container runtime + # for litmus LIB, it supports docker, containerd, crio + # for pumba LIB, it supports docker only + - name: CONTAINER_RUNTIME + value: 'docker' + + # provide the destination ips + # chaos injection will be triggered for these destination ips + - name: DESTINATION_IPS + value: '' + + # provide the destination hosts + # chaos injection will be triggered for these destination hosts + - name: DESTINATION_HOSTS + value: '' + + # provide the socket file path + - name: SOCKET_PATH + value: '/var/run/docker.sock' + + ## it defines the sequence of chaos execution for multiple target pods + ## supported values: serial, parallel + - name: SEQUENCE + value: 'parallel' + + labels: + name: pod-network-latency + app.kubernetes.io/part-of: litmus + app.kubernetes.io/component: experiment-job + app.kubernetes.io/version: latest + +--- +apiVersion: litmuschaos.io/v1alpha1 +description: + message: | + Injects network packet duplication on pods belonging to an app deployment +kind: ChaosExperiment +metadata: + name: pod-network-duplication + labels: + name: pod-network-duplication + app.kubernetes.io/part-of: litmus + app.kubernetes.io/component: chaosexperiment + app.kubernetes.io/version: latest +spec: + definition: + scope: Namespaced + permissions: + - apiGroups: + - "" + - "batch" + - "apps" + - "apps.openshift.io" + - "argoproj.io" + - "litmuschaos.io" + resources: + - "jobs" + - "pods" + - "pods/log" + - "replicationcontrollers" + - "deployments" + - "statefulsets" + - "daemonsets" + - "replicasets" + - "deploymentconfigs" + - "rollouts" + - "pods/exec" + - "events" + - "chaosengines" + - "chaosexperiments" + - "chaosresults" + verbs: + - "get" + - "list" + - "patch" + - "create" + - "update" + - "delete" + - "deletecollection" + image: "litmuschaos/go-runner:latest" + imagePullPolicy: Always + args: + - -c + - ./experiments -name pod-network-duplication + command: + - /bin/bash + env: + - name: TOTAL_CHAOS_DURATION + value: '60' + + - name: RAMP_TIME + value: '' + + - name: TARGET_CONTAINER + value: '' + + - name: TC_IMAGE + value: 'gaiadocker/iproute2' + + - name: NETWORK_INTERFACE + value: 'eth0' + + - name: NETWORK_PACKET_DUPLICATION_PERCENTAGE + value: '100' # in percentage + + # lib can be litmus or pumba + - name: LIB + value: 'litmus' + + - name: TARGET_PODS + value: '' + + ## percentage of total pods to target + - name: PODS_AFFECTED_PERC + value: '' + + - name: LIB_IMAGE + value: 'litmuschaos/go-runner:latest' + + # provide the name of container runtime + # for litmus LIB, it supports docker, containerd, crio + # for pumba LIB, it supports docker only + - name: CONTAINER_RUNTIME + value: 'docker' + + # provide the destination ips + # chaos injection will be triggered for these destination ips + - name: DESTINATION_IPS + value: '' + + # provide the destination hosts + # chaos injection will be triggered for these destination hosts + - name: DESTINATION_HOSTS + value: '' + + # provide the socket file path + - name: SOCKET_PATH + value: '/var/run/docker.sock' + + ## it defines the sequence of chaos execution for multiple target pods + ## supported values: serial, parallel + - name: SEQUENCE + value: 'parallel' + + labels: + name: pod-network-duplication + app.kubernetes.io/part-of: litmus + app.kubernetes.io/component: experiment-job + app.kubernetes.io/version: latest + +--- +apiVersion: litmuschaos.io/v1alpha1 +description: + message: | + 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: + - apiGroups: + - "" + - "batch" + - "apps" + - "apps.openshift.io" + - "argoproj.io" + - "litmuschaos.io" + resources: + - "jobs" + - "pods" + - "pods/log" + - "events" + - "replicationcontrollers" + - "deployments" + - "statefulsets" + - "daemonsets" + - "replicasets" + - "deploymentconfigs" + - "rollouts" + - "pods/exec" + - "chaosengines" + - "chaosexperiments" + - "chaosresults" + verbs: + - "create" + - "list" + - "get" + - "patch" + - "update" + - "delete" + - "deletecollection" + image: "litmuschaos/go-runner:ci" + 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: | + Injects memory consumption on pods belonging to an app deployment +kind: ChaosExperiment +metadata: + name: pod-memory-hog + labels: + name: pod-memory-hog + app.kubernetes.io/part-of: litmus + app.kubernetes.io/component: chaosexperiment + app.kubernetes.io/version: latest +spec: + definition: + scope: Namespaced + permissions: + - apiGroups: + - "" + - "batch" + - "apps" + - "apps.openshift.io" + - "argoproj.io" + - "litmuschaos.io" + resources: + - "jobs" + - "pods" + - "pods/log" + - "replicationcontrollers" + - "deployments" + - "statefulsets" + - "daemonsets" + - "replicasets" + - "deploymentconfigs" + - "rollouts" + - "pods/exec" + - "events" + - "chaosengines" + - "chaosexperiments" + - "chaosresults" + verbs: + - "create" + - "list" + - "get" + - "patch" + - "update" + - "delete" + - "deletecollection" + image: "litmuschaos/go-runner:ci" + imagePullPolicy: Always + args: + - -c + - ./experiments -name pod-memory-hog + command: + - /bin/bash + env: - name: TOTAL_CHAOS_DURATION - value: "60" # in seconds + value: '60' - # Time period to wait before and after injection of chaos in sec - - name: RAMP_TIME - value: "" + ## enter the amount of memory in megabytes to be consumed by the application pod + - name: MEMORY_CONSUMPTION + value: '500' + + ## Number of workers to perform stress + - name: NUMBER_OF_WORKERS + value: '1' ## percentage of total pods to target - name: PODS_AFFECTED_PERC - value: "" + value: '' - - name: TARGET_PODS - value: "" + ## Period to wait before and after injection of chaos in sec + - name: RAMP_TIME + value: '' - # provide the name of container runtime, it supports docker, containerd, crio + ## 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:ci' + + ## 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" + value: 'docker' # provide the socket file path - name: SOCKET_PATH - value: "/var/run/docker.sock" - + value: '/var/run/docker.sock' + ## it defines the sequence of chaos execution for multiple target pods ## supported values: serial, parallel - name: SEQUENCE - value: "parallel" + value: 'parallel' - # map of the target hostnames eg. '{"abc.com":"spoofabc.com"}' . If empty no queries will be spoofed - - name: SPOOF_MAP - value: "" + - name: TARGET_PODS + value: '' labels: - experiment: pod-dns-spoof + name: pod-memory-hog app.kubernetes.io/part-of: litmus app.kubernetes.io/component: experiment-job app.kubernetes.io/version: latest @@ -410,1082 +569,12 @@ spec: apiVersion: litmuschaos.io/v1alpha1 description: message: | - Kills the kubelet service on the application node to check the resiliency. + Pod DNS Spoof can spoof particular dns requests in target pod container to desired target hostnames kind: ChaosExperiment metadata: - name: kubelet-service-kill + name: pod-dns-spoof labels: - name: kubelet-service-kill - app.kubernetes.io/part-of: litmus - app.kubernetes.io/component: chaosexperiment - app.kubernetes.io/version: latest -spec: - definition: - scope: Cluster - permissions: - - apiGroups: - - "" - - "batch" - - "litmuschaos.io" - resources: - - "jobs" - - "pods" - - "pods/log" - - "pods/exec" - - "events" - - "chaosengines" - - "chaosexperiments" - - "chaosresults" - verbs: - - "create" - - "list" - - "get" - - "patch" - - "update" - - "delete" - - "deletecollection" - - apiGroups: - - "" - resources: - - "nodes" - verbs: - - "get" - - "list" - image: "litmuschaos/go-runner:latest" - imagePullPolicy: Always - args: - - -c - - ./experiments -name kubelet-service-kill - command: - - /bin/bash - env: - - - name: TOTAL_CHAOS_DURATION - value: '60' # in seconds - - # Period to wait before and after injection of chaos in sec - - name: RAMP_TIME - value: '' - - - name: LIB - value: 'litmus' - - - name: NODE_LABEL - value: '' - - # provide lib image - - name: LIB_IMAGE - value: 'ubuntu:16.04' - - # provide the target node name - - name: TARGET_NODE - value: '' - - labels: - name: kubelet-service-kill - app.kubernetes.io/part-of: litmus - app.kubernetes.io/component: experiment-job - app.kubernetes.io/version: latest - ---- -apiVersion: litmuschaos.io/v1alpha1 -description: - message: | - poweroff node -kind: ChaosExperiment -metadata: - name: node-poweroff - labels: - name: node-poweroff - app.kubernetes.io/part-of: litmus - app.kubernetes.io/component: chaosexperiment - app.kubernetes.io/version: latest -spec: - definition: - scope: Cluster - permissions: - - apiGroups: - - "" - - "batch" - - "litmuschaos.io" - resources: - - "jobs" - - "pods" - - "pods/log" - - "pods/exec" - - "events" - - "chaosengines" - - "chaosexperiments" - - "chaosresults" - - "secrets" - verbs: - - "create" - - "list" - - "get" - - "patch" - - "update" - - "delete" - - "deletecollection" - - apiGroups: - - "" - resources: - - "nodes" - verbs: - - "get" - - "list" - image: "litmuschaos/go-runner:latest" - imagePullPolicy: Always - args: - - -c - - ./experiments -name node-restart - command: - - /bin/bash - env: - - name: SSH_USER - value: 'root' - - - name: TOTAL_CHAOS_DURATION - value: '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: "Kills a container belonging to an application pod \n" -kind: ChaosExperiment -metadata: - name: container-kill - labels: - name: container-kill - app.kubernetes.io/part-of: litmus - app.kubernetes.io/component: chaosexperiment - app.kubernetes.io/version: latest -spec: - definition: - scope: Namespaced - permissions: - - apiGroups: - - "" - - "apps" - - "batch" - - "apps.openshift.io" - - "argoproj.io" - - "litmuschaos.io" - resources: - - "jobs" - - "pods" - - "pods/log" - - "events" - - "replicationcontrollers" - - "deployments" - - "statefulsets" - - "daemonsets" - - "replicasets" - - "deploymentconfigs" - - "rollouts" - - "pods/exec" - - "chaosengines" - - "chaosexperiments" - - "chaosresults" - verbs: - - "create" - - "list" - - "get" - - "update" - - "patch" - - "delete" - - "deletecollection" - image: "litmuschaos/go-runner:latest" - imagePullPolicy: Always - args: - - -c - - ./experiments -name container-kill - command: - - /bin/bash - env: - - - name: TARGET_CONTAINER - value: '' - - # Period to wait before and after injection of chaos in sec - - name: RAMP_TIME - value: '' - - # lib can be litmus or pumba - - name: LIB - value: 'litmus' - - - name: TARGET_PODS - value: '' - - # provide the chaos interval - - name: CHAOS_INTERVAL - value: '10' - - - name: SIGNAL - value: 'SIGKILL' - - # provide the socket file path - - name: SOCKET_PATH - value: '/var/run/docker.sock' - - # provide the name of container runtime - # for litmus LIB, it supports docker, containerd, crio - # for pumba LIB, it supports docker only - - name: CONTAINER_RUNTIME - value: 'docker' - - # provide the total chaos duration - - name: TOTAL_CHAOS_DURATION - value: '20' - - ## percentage of total pods to target - - name: PODS_AFFECTED_PERC - value: '' - - - name: LIB_IMAGE - value: 'litmuschaos/go-runner:latest' - - ## it defines the sequence of chaos execution for multiple target pods - ## supported values: serial, parallel - - name: SEQUENCE - value: 'parallel' - - labels: - name: container-kill - app.kubernetes.io/part-of: litmus - app.kubernetes.io/component: experiment-job - app.kubernetes.io/version: latest - ---- ---- -apiVersion: litmuschaos.io/v1alpha1 -description: - message: | - Taint the node where application pod is scheduled -kind: ChaosExperiment -metadata: - name: node-taint - labels: - name: node-taint - app.kubernetes.io/part-of: litmus - app.kubernetes.io/component: chaosexperiment - app.kubernetes.io/version: latest -spec: - definition: - scope: Cluster - permissions: - - apiGroups: - - "" - - "batch" - - "apps" - - "litmuschaos.io" - resources: - - "jobs" - - "pods" - - "events" - - "pods/log" - - "pods/exec" - - "daemonsets" - - "pods/eviction" - - "chaosengines" - - "chaosexperiments" - - "chaosresults" - verbs: - - "create" - - "list" - - "get" - - "patch" - - "update" - - "delete" - - "deletecollection" - - apiGroups: - - "" - resources: - - "nodes" - verbs: - - "get" - - "list" - - "patch" - - "update" - image: "litmuschaos/go-runner:latest" - imagePullPolicy: Always - args: - - -c - - ./experiments -name node-taint - command: - - /bin/bash - env: - - - name: TARGET_NODE - value: '' - - - name: NODE_LABEL - value: '' - - - name: TOTAL_CHAOS_DURATION - value: '60' - - # Provide the LIB here - # Only litmus supported - - name: LIB - value: 'litmus' - - # Period to wait before and after injection of chaos in sec - - name: RAMP_TIME - value: '' - - # set taint label & effect - # key=value:effect or key:effect - - name: TAINTS - value: '' - - labels: - name: node-taint - app.kubernetes.io/part-of: litmus - app.kubernetes.io/component: experiment-job - app.kubernetes.io/version: latest - ---- -apiVersion: litmuschaos.io/v1alpha1 -description: - message: | - Deletes a pod belonging to a deployment/statefulset/daemonset -kind: ChaosExperiment -metadata: - name: k8-pod-delete - labels: - name: k8-pod-delete - app.kubernetes.io/part-of: litmus - app.kubernetes.io/component: chaosexperiment - app.kubernetes.io/version: latest -spec: - definition: - scope: Namespaced - permissions: - - apiGroups: - - "" - - "apps" - - "batch" - - "litmuschaos.io" - resources: - - "deployments" - - "jobs" - - "pods" - - "configmaps" - - "chaosengines" - - "chaosexperiments" - - "chaosresults" - verbs: - - "create" - - "list" - - "get" - - "patch" - - "update" - - "delete" - - apiGroups: - - "" - resources: - - "nodes" - verbs : - - "get" - - "list" - image: "litmuschaos/py-runner:latest" - args: - - -c - - python /litmus/byoc/chaostest/chaostest/kubernetes/k8_wrapper.py; exit 0 - command: - - /bin/bash - env: - - name: CHAOSTOOLKIT_IN_POD - value: 'true' - - - name: FILE - value: 'pod-app-kill-count.json' - - - name: NAME_SPACE - value: '' - - - name: LABEL_NAME - value: '' - - - name: APP_ENDPOINT - value: '' - - - name: PERCENTAGE - value: '50' - - - name: REPORT - value: 'true' - - - name: REPORT_ENDPOINT - value: 'none' - - - name: TEST_NAMESPACE - value: 'default' - - - labels: - name: k8-pod-delete - app.kubernetes.io/part-of: litmus - app.kubernetes.io/component: experiment-job - app.kubernetes.io/version: latest - ---- -apiVersion: litmuschaos.io/v1alpha1 -description: - message: | - Injects network latency on pods belonging to an app deployment -kind: ChaosExperiment -metadata: - name: pod-network-latency - labels: - name: pod-network-latency - app.kubernetes.io/part-of: litmus - app.kubernetes.io/component: chaosexperiment - app.kubernetes.io/version: latest -spec: - definition: - scope: Namespaced - permissions: - - apiGroups: - - "" - - "batch" - - "apps" - - "apps.openshift.io" - - "argoproj.io" - - "litmuschaos.io" - resources: - - "jobs" - - "pods" - - "pods/log" - - "replicationcontrollers" - - "deployments" - - "statefulsets" - - "daemonsets" - - "replicasets" - - "deploymentconfigs" - - "rollouts" - - "pods/exec" - - "events" - - "chaosengines" - - "chaosexperiments" - - "chaosresults" - verbs: - - "create" - - "list" - - "get" - - "patch" - - "update" - - "delete" - - "deletecollection" - image: "litmuschaos/go-runner:latest" - imagePullPolicy: Always - args: - - -c - - ./experiments -name pod-network-latency - command: - - /bin/bash - env: - - - name: TARGET_CONTAINER - value: '' - - - name: NETWORK_INTERFACE - value: 'eth0' - - # provide lib image - - name: LIB_IMAGE - value: 'litmuschaos/go-runner:latest' - - - name: TC_IMAGE - value: 'gaiadocker/iproute2' - - - name: NETWORK_LATENCY - value: '2000' #in ms - - - name: TOTAL_CHAOS_DURATION - value: '60' # in seconds - - # Time period to wait before and after injection of chaos in sec - - name: RAMP_TIME - value: '' - - # lib can be litmus or pumba - - name: LIB - value: 'litmus' - - ## percentage of total pods to target - - name: PODS_AFFECTED_PERC - value: '' - - - name: TARGET_PODS - value: '' - - # provide the name of container runtime - # for litmus LIB, it supports docker, containerd, crio - # for pumba LIB, it supports docker only - - name: CONTAINER_RUNTIME - value: 'docker' - - # provide the destination ips - # chaos injection will be triggered for these destination ips - - name: DESTINATION_IPS - value: '' - - # provide the destination hosts - # chaos injection will be triggered for these destination hosts - - name: DESTINATION_HOSTS - value: '' - - # provide the socket file path - - name: SOCKET_PATH - value: '/var/run/docker.sock' - - ## it defines the sequence of chaos execution for multiple target pods - ## supported values: serial, parallel - - name: SEQUENCE - value: 'parallel' - - labels: - name: pod-network-latency - app.kubernetes.io/part-of: litmus - app.kubernetes.io/component: experiment-job - app.kubernetes.io/version: latest - ---- -apiVersion: litmuschaos.io/v1alpha1 -description: - message: | - Scale the application replicas and test the node autoscaling on cluster -kind: ChaosExperiment -metadata: - name: pod-autoscaler - labels: - name: pod-autoscaler - app.kubernetes.io/part-of: litmus - app.kubernetes.io/component: chaosexperiment - app.kubernetes.io/version: latest -spec: - definition: - scope: Cluster - permissions: - - apiGroups: - - "" - - "batch" - - "apps" - - "litmuschaos.io" - resources: - - "jobs" - - "pods" - - "pods/log" - - "pods/exec" - - "deployments" - - "statefulsets" - - "events" - - "chaosengines" - - "chaosexperiments" - - "chaosresults" - verbs: - - "create" - - "list" - - "get" - - "patch" - - "update" - - "delete" - - "deletecollection" - - apiGroups: - - "" - resources: - - "nodes" - verbs: - - "get" - - "list" - - "create" - - "patch" - - "update" - image: "litmuschaos/go-runner:latest" - imagePullPolicy: Always - args: - - -c - - ./experiments -name pod-autoscaler - command: - - /bin/bash - env: - - - name: TOTAL_CHAOS_DURATION - value: '60' - - # Period to wait before and after injection of chaos in sec - - name: RAMP_TIME - value: '' - - # Number of replicas to scale - - name: REPLICA_COUNT - value: '5' - - # PROVIDE THE LIB HERE - # ONLY LITMUS SUPPORTED - - name: LIB - value: 'litmus' - - labels: - name: pod-autoscaler - app.kubernetes.io/part-of: litmus - app.kubernetes.io/component: experiment-job - app.kubernetes.io/version: latest - ---- ---- -apiVersion: litmuschaos.io/v1alpha1 -description: - message: | - Injects 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: - - apiGroups: - - "" - - "batch" - - "apps" - - "apps.openshift.io" - - "argoproj.io" - - "litmuschaos.io" - resources: - - "jobs" - - "pods" - - "pods/log" - - "replicationcontrollers" - - "deployments" - - "statefulsets" - - "daemonsets" - - "replicasets" - - "deploymentconfigs" - - "rollouts" - - "pods/exec" - - "events" - - "chaosengines" - - "chaosexperiments" - - "chaosresults" - verbs: - - "create" - - "list" - - "get" - - "patch" - - "update" - - "delete" - - "deletecollection" - image: "litmuschaos/go-runner:ci" - 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' - - ## 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: | - Detaching a persistent disk from a node/instance. Supports only for AWS and GCP -kind: ChaosExperiment -metadata: - name: disk-loss - labels: - name: disk-loss - app.kubernetes.io/part-of: litmus - app.kubernetes.io/component: chaosexperiment - app.kubernetes.io/version: latest -spec: - definition: - scope: Cluster - permissions: - - apiGroups: - - "" - - "batch" - - "litmuschaos.io" - resources: - - "jobs" - - "pods" - - "events" - - "pods/log" - - "secrets" - - "chaosengines" - - "chaosexperiments" - - "chaosresults" - verbs: - - "create" - - "list" - - "get" - - "patch" - - "update" - - "delete" - image: "litmuschaos/ansible-runner:latest" - imagePullPolicy: Always - args: - - -c - - ansible-playbook ./experiments/generic/disk_loss/disk_loss_ansible_logic.yml -i /etc/ansible/hosts -vv; exit 0 - command: - - /bin/bash - env: - - name: ANSIBLE_STDOUT_CALLBACK - value: 'default' - - - name: TOTAL_CHAOS_DURATION - value: '15' - - # Period to wait before and after injection of chaos in sec - - name: RAMP_TIME - value: '' - - - name: APP_CHECK - value: 'true' - - # GKE and AWS supported - - name: CLOUD_PLATFORM - value: 'GKE' - - - name: PROJECT_ID - value: '' - - - name: NODE_NAME - value: '' - - - name: DISK_NAME - value: '' - - # provide the LIB - # only litmus supported - - name: LIB - value: 'litmus' - - - name: ZONE_NAME - value: '' - - - name: DEVICE_NAME - value: '' - - labels: - name: disk-loss - app.kubernetes.io/part-of: litmus - app.kubernetes.io/component: experiment-job - app.kubernetes.io/version: latest - secrets: - - name: cloud-secret - mountPath: /tmp/ - ---- -apiVersion: litmuschaos.io/v1alpha1 -description: - message: | - Injects cpu consumption on pods belonging to an app deployment -kind: ChaosExperiment -metadata: - name: pod-cpu-hog - labels: - name: pod-cpu-hog - app.kubernetes.io/part-of: litmus - app.kubernetes.io/component: chaosexperiment - app.kubernetes.io/version: latest -spec: - definition: - scope: Namespaced - permissions: - - apiGroups: - - "" - - "batch" - - "apps" - - "apps.openshift.io" - - "argoproj.io" - - "litmuschaos.io" - resources: - - "jobs" - - "pods" - - "pods/log" - - "events" - - "replicationcontrollers" - - "deployments" - - "statefulsets" - - "daemonsets" - - "replicasets" - - "deploymentconfigs" - - "rollouts" - - "pods/exec" - - "chaosengines" - - "chaosexperiments" - - "chaosresults" - verbs: - - "create" - - "list" - - "get" - - "patch" - - "update" - - "delete" - - "deletecollection" - image: "litmuschaos/go-runner:ci" - imagePullPolicy: Always - args: - - -c - - ./experiments -name pod-cpu-hog - command: - - /bin/bash - env: - - name: TOTAL_CHAOS_DURATION - value: '60' - - ## Number of CPU cores to stress - - name: CPU_CORES - value: '1' - - ## Percentage of total pods to target - - name: PODS_AFFECTED_PERC - value: '' - - ## Period to wait before and after injection of chaos in sec - - name: RAMP_TIME - value: '' - - ## env var that describes the library used to execute the chaos - ## default: litmus. Supported values: litmus, pumba - - name: LIB - value: 'litmus' - - ## It is used in pumba lib only - - name: LIB_IMAGE - value: 'litmuschaos/go-runner:ci' - - ## 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: '' - - ## it defines the sequence of chaos execution for multiple target pods - ## supported values: serial, parallel - - name: SEQUENCE - value: 'parallel' - - labels: - name: pod-cpu-hog - app.kubernetes.io/part-of: litmus - app.kubernetes.io/component: experiment-job - app.kubernetes.io/version: latest - ---- ---- -apiVersion: litmuschaos.io/v1alpha1 -description: - message: | - 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: - - apiGroups: - - "" - - "batch" - - "apps" - - "apps.openshift.io" - - "argoproj.io" - - "litmuschaos.io" - resources: - - "jobs" - - "pods" - - "pods/log" - - "replicationcontrollers" - - "deployments" - - "statefulsets" - - "daemonsets" - - "replicasets" - - "deploymentconfigs" - - "rollouts" - - "pods/exec" - - "events" - - "chaosengines" - - "chaosexperiments" - - "chaosresults" - verbs: - - "create" - - "list" - - "get" - - "patch" - - "update" - - "delete" - - "deletecollection" - image: "litmuschaos/go-runner:ci" - 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: '' - - # 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:ci' - - ## 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/version: latest - ---- -apiVersion: litmuschaos.io/v1alpha1 -description: - message: | - Pod DNS Error injects dns failure/error in target pod containers -kind: ChaosExperiment -metadata: - name: pod-dns-error - labels: - name: pod-dns-error + name: pod-dns-spoof app.kubernetes.io/part-of: litmus app.kubernetes.io/component: chaosexperiment app.kubernetes.io/version: latest @@ -1527,7 +616,7 @@ spec: image: "litmuschaos/go-runner:latest" args: - -c - - ./experiments -name pod-dns-error + - ./experiments -name pod-dns-spoof command: - /bin/bash env: @@ -1565,401 +654,12 @@ spec: - name: SEQUENCE value: "parallel" - # list of the target hostnames or kewywords eg. '["litmuschaos","chaosnative.io"]' . If empty all hostnames are targets - - name: TARGET_HOSTNAMES + # map of the target hostnames eg. '{"abc.com":"spoofabc.com"}' . If empty no queries will be spoofed + - name: SPOOF_MAP value: "" - # can be either exact or substring, determines whether the dns query has to match exactly with one of the targets or can have any of the targets as substring - - name: MATCH_SCHEME - value: "exact" - labels: - experiment: pod-dns-error - app.kubernetes.io/part-of: litmus - app.kubernetes.io/component: experiment-job - app.kubernetes.io/version: latest - ---- -apiVersion: litmuschaos.io/v1alpha1 -description: - message: | - Give a cpu spike on a node belonging to a deployment -kind: ChaosExperiment -metadata: - name: node-cpu-hog - labels: - name: node-cpu-hog - app.kubernetes.io/part-of: litmus - app.kubernetes.io/component: chaosexperiment - app.kubernetes.io/version: latest -spec: - definition: - scope: Cluster - permissions: - - apiGroups: - - "" - - "batch" - - "litmuschaos.io" - resources: - - "jobs" - - "pods" - - "pods/log" - - "pods/exec" - - "events" - - "chaosengines" - - "chaosexperiments" - - "chaosresults" - verbs: - - "create" - - "list" - - "get" - - "patch" - - "update" - - "delete" - - "deletecollection" - - apiGroups: - - "" - resources: - - "nodes" - verbs: - - "get" - - "list" - image: "litmuschaos/go-runner:latest" - imagePullPolicy: Always - args: - - -c - - ./experiments -name node-cpu-hog - command: - - /bin/bash - env: - - - name: TOTAL_CHAOS_DURATION - value: '60' - - # Period to wait before and after injection of chaos in sec - - name: RAMP_TIME - value: '' - - ## ENTER THE NUMBER OF CORES OF CPU FOR CPU HOGGING - ## OPTIONAL VALUE IN CASE OF EMPTY VALUE IT WILL TAKE NODE CPU CAPACITY - - name: NODE_CPU_CORE - value: '' - - # ENTER THE COMMA SEPARATED TARGET NODES NAME - - name: TARGET_NODES - value: '' - - - name: NODE_LABEL - value: '' - - # PROVIDE THE LIB HERE - # ONLY LITMUS SUPPORTED - - name: LIB - value: 'litmus' - - # provide lib image - - name: LIB_IMAGE - value: 'litmuschaos/go-runner:latest' - - ## percentage of total nodes to target - - name: NODES_AFFECTED_PERC - value: '' - - ## it defines the sequence of chaos execution for multiple target nodes - ## supported values: serial, parallel - - name: SEQUENCE - value: 'parallel' - - labels: - name: node-cpu-hog - app.kubernetes.io/part-of: litmus - app.kubernetes.io/component: experiment-job - app.kubernetes.io/version: latest - ---- -apiVersion: litmuschaos.io/v1alpha1 -description: - message: | - Kills the docker service on the application node to check the resiliency. -kind: ChaosExperiment -metadata: - name: docker-service-kill - labels: - name: docker-service-kill - app.kubernetes.io/part-of: litmus - app.kubernetes.io/component: chaosexperiment - app.kubernetes.io/version: latest -spec: - definition: - scope: Cluster - permissions: - - apiGroups: - - "" - - "batch" - - "apps" - - "litmuschaos.io" - resources: - - "jobs" - - "pods" - - "pods/log" - - "events" - - "chaosengines" - - "chaosexperiments" - - "chaosresults" - verbs: - - "create" - - "list" - - "get" - - "patch" - - "update" - - "delete" - - apiGroups: - - "" - resources: - - "nodes" - verbs: - - "get" - - "list" - image: "litmuschaos/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/version: latest - - ---- -apiVersion: litmuschaos.io/v1alpha1 -description: - message: | - Restart node -kind: ChaosExperiment -metadata: - name: node-restart - labels: - name: node-restart - app.kubernetes.io/part-of: litmus - app.kubernetes.io/component: chaosexperiment - app.kubernetes.io/version: latest -spec: - definition: - scope: Cluster - permissions: - - apiGroups: - - "" - - "batch" - - "litmuschaos.io" - resources: - - "jobs" - - "pods" - - "pods/log" - - "pods/exec" - - "events" - - "chaosengines" - - "chaosexperiments" - - "chaosresults" - - "secrets" - verbs: - - "create" - - "list" - - "get" - - "patch" - - "update" - - "delete" - - "deletecollection" - - apiGroups: - - "" - resources: - - "nodes" - verbs: - - "get" - - "list" - image: "litmuschaos/go-runner:latest" - imagePullPolicy: Always - args: - - -c - - ./experiments -name node-restart - command: - - /bin/bash - env: - - name: SSH_USER - value: 'root' - - - name: TOTAL_CHAOS_DURATION - value: '60' - - # Period to wait before and after injection of chaos in sec - - name: RAMP_TIME - value: '' - - # PROVIDE THE LIB HERE - # ONLY LITMUS SUPPORTED - - name: LIB - value: 'litmus' - - # provide lib image - - name: LIB_IMAGE - value: "litmuschaos/go-runner:latest" - - # ENTER THE TARGET NODE NAME - - name: TARGET_NODE - value: '' - - - name: NODE_LABEL - value: '' - - # ENTER THE TARGET NODE IP - - name: TARGET_NODE_IP - value: '' - - labels: - name: node-restart - app.kubernetes.io/part-of: litmus - app.kubernetes.io/component: experiment-job - app.kubernetes.io/version: latest - secrets: - - name: id-rsa - mountPath: /mnt/ - ---- -apiVersion: litmuschaos.io/v1alpha1 -description: - message: | - Give IO disk stress on a node belonging to a deployment -kind: ChaosExperiment -metadata: - name: node-io-stress - labels: - name: node-io-stress - app.kubernetes.io/part-of: litmus - app.kubernetes.io/component: chaosexperiment - app.kubernetes.io/version: latest -spec: - definition: - scope: Cluster - permissions: - - apiGroups: - - "" - - "batch" - - "litmuschaos.io" - resources: - - "jobs" - - "pods" - - "pods/log" - - "pods/exec" - - "events" - - "chaosengines" - - "chaosexperiments" - - "chaosresults" - verbs: - - "create" - - "list" - - "get" - - "patch" - - "update" - - "delete" - - "deletecollection" - - apiGroups: - - "" - resources: - - "nodes" - verbs: - - "get" - - "list" - image: "litmuschaos/go-runner:latest" - imagePullPolicy: Always - args: - - -c - - ./experiments -name node-io-stress - command: - - /bin/bash - env: - - - name: TOTAL_CHAOS_DURATION - value: '120' - - ## specify the size as percentage of free space on the file system - ## default value 90 (in percentage) - - name: FILESYSTEM_UTILIZATION_PERCENTAGE - value: '10' - - ## we can specify the size in Gigabyte (Gb) also in place of percentage of free space - ## NOTE: for selecting this option FILESYSTEM_UTILIZATION_PERCENTAGE should be empty - - name: FILESYSTEM_UTILIZATION_BYTES - value: '' - - ## Number of core of CPU - - name: CPU - value: '1' - - ## Total number of workers default value is 4 - - name: NUMBER_OF_WORKERS - value: '4' - - ## Total number of vm workers - - name: VM_WORKERS - value: '1' - - ## enter the comma separated target nodes name - - name: TARGET_NODES - value: '' - - - 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 + experiment: pod-dns-spoof app.kubernetes.io/part-of: litmus app.kubernetes.io/component: experiment-job app.kubernetes.io/version: latest @@ -2090,12 +790,389 @@ spec: apiVersion: litmuschaos.io/v1alpha1 description: message: | - Injects cpu consumption on pods belonging to an app deployment + Give a cpu spike on a node belonging to a deployment kind: ChaosExperiment metadata: - name: pod-cpu-hog-exec + name: node-cpu-hog labels: - name: pod-cpu-hog-exec + name: node-cpu-hog + app.kubernetes.io/part-of: litmus + app.kubernetes.io/component: chaosexperiment + app.kubernetes.io/version: latest +spec: + definition: + scope: Cluster + permissions: + - apiGroups: + - "" + - "batch" + - "litmuschaos.io" + resources: + - "jobs" + - "pods" + - "pods/log" + - "pods/exec" + - "events" + - "chaosengines" + - "chaosexperiments" + - "chaosresults" + verbs: + - "create" + - "list" + - "get" + - "patch" + - "update" + - "delete" + - "deletecollection" + - apiGroups: + - "" + resources: + - "nodes" + verbs: + - "get" + - "list" + image: "litmuschaos/go-runner:latest" + imagePullPolicy: Always + args: + - -c + - ./experiments -name node-cpu-hog + command: + - /bin/bash + env: + + - name: TOTAL_CHAOS_DURATION + value: '60' + + # Period to wait before and after injection of chaos in sec + - name: RAMP_TIME + value: '' + + ## ENTER THE NUMBER OF CORES OF CPU FOR CPU HOGGING + ## OPTIONAL VALUE IN CASE OF EMPTY VALUE IT WILL TAKE NODE CPU CAPACITY + - name: NODE_CPU_CORE + value: '' + + # ENTER THE COMMA SEPARATED TARGET NODES NAME + - name: TARGET_NODES + value: '' + + - name: NODE_LABEL + value: '' + + # PROVIDE THE LIB HERE + # ONLY LITMUS SUPPORTED + - name: LIB + value: 'litmus' + + # provide lib image + - name: LIB_IMAGE + value: 'litmuschaos/go-runner:latest' + + ## percentage of total nodes to target + - name: NODES_AFFECTED_PERC + value: '' + + ## it defines the sequence of chaos execution for multiple target nodes + ## supported values: serial, parallel + - name: SEQUENCE + value: 'parallel' + + labels: + name: node-cpu-hog + app.kubernetes.io/part-of: litmus + app.kubernetes.io/component: experiment-job + app.kubernetes.io/version: latest + +--- +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: + - apiGroups: + - "" + - "batch" + - "litmuschaos.io" + resources: + - "jobs" + - "pods" + - "pods/log" + - "pods/exec" + - "events" + - "chaosengines" + - "chaosexperiments" + - "chaosresults" + verbs: + - "create" + - "list" + - "get" + - "patch" + - "update" + - "delete" + - "deletecollection" + - apiGroups: + - "" + resources: + - "nodes" + verbs: + - "get" + - "list" + image: "litmuschaos/go-runner:latest" + imagePullPolicy: Always + args: + - -c + - ./experiments -name node-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: | + Restart node +kind: ChaosExperiment +metadata: + name: node-restart + labels: + name: node-restart + app.kubernetes.io/part-of: litmus + app.kubernetes.io/component: chaosexperiment + app.kubernetes.io/version: latest +spec: + definition: + scope: Cluster + permissions: + - apiGroups: + - "" + - "batch" + - "litmuschaos.io" + resources: + - "jobs" + - "pods" + - "pods/log" + - "pods/exec" + - "events" + - "chaosengines" + - "chaosexperiments" + - "chaosresults" + - "secrets" + verbs: + - "create" + - "list" + - "get" + - "patch" + - "update" + - "delete" + - "deletecollection" + - apiGroups: + - "" + resources: + - "nodes" + verbs: + - "get" + - "list" + image: "litmuschaos/go-runner:latest" + imagePullPolicy: Always + args: + - -c + - ./experiments -name node-restart + command: + - /bin/bash + env: + - name: SSH_USER + value: 'root' + + - name: TOTAL_CHAOS_DURATION + value: '60' + + # Period to wait before and after injection of chaos in sec + - name: RAMP_TIME + value: '' + + # PROVIDE THE LIB HERE + # ONLY LITMUS SUPPORTED + - name: LIB + value: 'litmus' + + # provide lib image + - name: LIB_IMAGE + value: "litmuschaos/go-runner:latest" + + # ENTER THE TARGET NODE NAME + - name: TARGET_NODE + value: '' + + - name: NODE_LABEL + value: '' + + # ENTER THE TARGET NODE IP + - name: TARGET_NODE_IP + value: '' + + labels: + name: node-restart + app.kubernetes.io/part-of: litmus + app.kubernetes.io/component: experiment-job + app.kubernetes.io/version: latest + secrets: + - name: id-rsa + mountPath: /mnt/ + +--- +apiVersion: litmuschaos.io/v1alpha1 +description: + message: | + Kills the docker service on the application node to check the resiliency. +kind: ChaosExperiment +metadata: + name: docker-service-kill + labels: + name: docker-service-kill + app.kubernetes.io/part-of: litmus + app.kubernetes.io/component: chaosexperiment + app.kubernetes.io/version: latest +spec: + definition: + scope: Cluster + permissions: + - apiGroups: + - "" + - "batch" + - "apps" + - "litmuschaos.io" + resources: + - "jobs" + - "pods" + - "pods/log" + - "events" + - "chaosengines" + - "chaosexperiments" + - "chaosresults" + verbs: + - "create" + - "list" + - "get" + - "patch" + - "update" + - "delete" + - apiGroups: + - "" + resources: + - "nodes" + verbs: + - "get" + - "list" + image: "litmuschaos/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/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 @@ -2110,6 +1187,365 @@ spec: - "apps.openshift.io" - "argoproj.io" - "litmuschaos.io" + resources: + - "jobs" + - "pods" + - "pods/log" + - "replicationcontrollers" + - "deployments" + - "statefulsets" + - "daemonsets" + - "replicasets" + - "deploymentconfigs" + - "rollouts" + - "pods/exec" + - "events" + - "chaosengines" + - "chaosexperiments" + - "chaosresults" + verbs: + - "create" + - "list" + - "get" + - "patch" + - "update" + - "delete" + - "deletecollection" + image: "litmuschaos/go-runner:ci" + 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: | + Scale the application replicas and test the node autoscaling on cluster +kind: ChaosExperiment +metadata: + name: pod-autoscaler + labels: + name: pod-autoscaler + app.kubernetes.io/part-of: litmus + app.kubernetes.io/component: chaosexperiment + app.kubernetes.io/version: latest +spec: + definition: + scope: Cluster + permissions: + - apiGroups: + - "" + - "batch" + - "apps" + - "litmuschaos.io" + resources: + - "jobs" + - "pods" + - "pods/log" + - "pods/exec" + - "deployments" + - "statefulsets" + - "events" + - "chaosengines" + - "chaosexperiments" + - "chaosresults" + verbs: + - "create" + - "list" + - "get" + - "patch" + - "update" + - "delete" + - "deletecollection" + - apiGroups: + - "" + resources: + - "nodes" + verbs: + - "get" + - "list" + - "create" + - "patch" + - "update" + image: "litmuschaos/go-runner:latest" + imagePullPolicy: Always + args: + - -c + - ./experiments -name pod-autoscaler + command: + - /bin/bash + env: + + - name: TOTAL_CHAOS_DURATION + value: '60' + + # Period to wait before and after injection of chaos in sec + - name: RAMP_TIME + value: '' + + # Number of replicas to scale + - name: REPLICA_COUNT + value: '5' + + # PROVIDE THE LIB HERE + # ONLY LITMUS SUPPORTED + - name: LIB + value: 'litmus' + + labels: + name: pod-autoscaler + app.kubernetes.io/part-of: litmus + app.kubernetes.io/component: experiment-job + app.kubernetes.io/version: latest + +--- +apiVersion: litmuschaos.io/v1alpha1 +description: + message: | + Pod DNS Error injects dns failure/error in target pod containers +kind: ChaosExperiment +metadata: + name: pod-dns-error + labels: + name: pod-dns-error + app.kubernetes.io/part-of: litmus + app.kubernetes.io/component: chaosexperiment + app.kubernetes.io/version: latest +spec: + definition: + scope: Namespaced + permissions: + - apiGroups: + - "" + - "batch" + - "apps" + - "apps.openshift.io" + - "argoproj.io" + - "litmuschaos.io" + resources: + - "jobs" + - "pods" + - "pods/log" + - "replicationcontrollers" + - "deployments" + - "statefulsets" + - "daemonsets" + - "replicasets" + - "deploymentconfigs" + - "rollouts" + - "pods/exec" + - "events" + - "chaosengines" + - "chaosexperiments" + - "chaosresults" + verbs: + - "create" + - "list" + - "get" + - "patch" + - "update" + - "delete" + - "deletecollection" + image: "litmuschaos/go-runner:latest" + args: + - -c + - ./experiments -name pod-dns-error + command: + - /bin/bash + env: + - name: TARGET_CONTAINER + value: "" + + # provide lib image + - name: LIB_IMAGE + value: "litmuschaos/go-runner:latest" + + - name: TOTAL_CHAOS_DURATION + value: "60" # in seconds + + # Time period to wait before and after injection of chaos in sec + - name: RAMP_TIME + value: "" + + ## percentage of total pods to target + - name: PODS_AFFECTED_PERC + value: "" + + - name: TARGET_PODS + value: "" + + # provide the name of container runtime, it supports docker, containerd, crio + - name: CONTAINER_RUNTIME + value: "docker" + + # provide the socket file path + - name: SOCKET_PATH + value: "/var/run/docker.sock" + + ## it defines the sequence of chaos execution for multiple target pods + ## supported values: serial, parallel + - name: SEQUENCE + value: "parallel" + + # list of the target hostnames or kewywords eg. '["litmuschaos","chaosnative.io"]' . If empty all hostnames are targets + - name: TARGET_HOSTNAMES + value: "" + + # can be either exact or substring, determines whether the dns query has to match exactly with one of the targets or can have any of the targets as substring + - name: MATCH_SCHEME + value: "exact" + + labels: + experiment: pod-dns-error + app.kubernetes.io/part-of: litmus + app.kubernetes.io/component: experiment-job + app.kubernetes.io/version: latest + +--- +apiVersion: litmuschaos.io/v1alpha1 +description: + message: | + Kills the kubelet service on the application node to check the resiliency. +kind: ChaosExperiment +metadata: + name: kubelet-service-kill + labels: + name: kubelet-service-kill + app.kubernetes.io/part-of: litmus + app.kubernetes.io/component: chaosexperiment + app.kubernetes.io/version: latest +spec: + definition: + scope: Cluster + permissions: + - apiGroups: + - "" + - "batch" + - "litmuschaos.io" + resources: + - "jobs" + - "pods" + - "pods/log" + - "pods/exec" + - "events" + - "chaosengines" + - "chaosexperiments" + - "chaosresults" + verbs: + - "create" + - "list" + - "get" + - "patch" + - "update" + - "delete" + - "deletecollection" + - apiGroups: + - "" + resources: + - "nodes" + verbs: + - "get" + - "list" + image: "litmuschaos/go-runner:latest" + imagePullPolicy: Always + args: + - -c + - ./experiments -name kubelet-service-kill + command: + - /bin/bash + env: + + - name: TOTAL_CHAOS_DURATION + value: '60' # in seconds + + # Period to wait before and after injection of chaos in sec + - name: RAMP_TIME + value: '' + + - name: LIB + value: 'litmus' + + - name: NODE_LABEL + value: '' + + # provide lib image + - name: LIB_IMAGE + value: 'ubuntu:16.04' + + # provide the target node name + - name: TARGET_NODE + value: '' + + labels: + name: kubelet-service-kill + app.kubernetes.io/part-of: litmus + app.kubernetes.io/component: experiment-job + app.kubernetes.io/version: latest + +--- +apiVersion: litmuschaos.io/v1alpha1 +description: + message: "Kills a container belonging to an application pod \n" +kind: ChaosExperiment +metadata: + name: container-kill + labels: + name: container-kill + app.kubernetes.io/part-of: litmus + app.kubernetes.io/component: chaosexperiment + app.kubernetes.io/version: latest +spec: + definition: + scope: Namespaced + permissions: + - apiGroups: + - "" + - "apps" + - "batch" + - "apps.openshift.io" + - "argoproj.io" + - "litmuschaos.io" resources: - "jobs" - "pods" @@ -2130,139 +1566,43 @@ spec: - "create" - "list" - "get" - - "patch" - "update" + - "patch" - "delete" - "deletecollection" - image: "litmuschaos/go-runner:ci" - 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' - - - 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: | - Injects network packet duplication on pods belonging to an app deployment -kind: ChaosExperiment -metadata: - name: pod-network-duplication - labels: - name: pod-network-duplication - app.kubernetes.io/part-of: litmus - app.kubernetes.io/component: chaosexperiment - app.kubernetes.io/version: latest -spec: - definition: - scope: Namespaced - permissions: - - apiGroups: - - "" - - "batch" - - "apps" - - "apps.openshift.io" - - "argoproj.io" - - "litmuschaos.io" - resources: - - "jobs" - - "pods" - - "pods/log" - - "replicationcontrollers" - - "deployments" - - "statefulsets" - - "daemonsets" - - "replicasets" - - "deploymentconfigs" - - "rollouts" - - "pods/exec" - - "events" - - "chaosengines" - - "chaosexperiments" - - "chaosresults" - verbs: - - "get" - - "list" - - "patch" - - "create" - - "update" - - "delete" - - "deletecollection" image: "litmuschaos/go-runner:latest" imagePullPolicy: Always args: - -c - - ./experiments -name pod-network-duplication + - ./experiments -name container-kill command: - /bin/bash env: - - name: TOTAL_CHAOS_DURATION - value: '60' - - - name: RAMP_TIME - value: '' - name: TARGET_CONTAINER value: '' - - name: TC_IMAGE - value: 'gaiadocker/iproute2' - - - name: NETWORK_INTERFACE - value: 'eth0' - - - name: NETWORK_PACKET_DUPLICATION_PERCENTAGE - value: '100' # in percentage + # 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' - + value: 'litmus' + - name: TARGET_PODS - value: '' - - ## percentage of total pods to target - - name: PODS_AFFECTED_PERC value: '' - - name: LIB_IMAGE - value: 'litmuschaos/go-runner:latest' + # provide the 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 @@ -2270,19 +1610,16 @@ spec: - name: CONTAINER_RUNTIME value: 'docker' - # provide the destination ips - # chaos injection will be triggered for these destination ips - - name: DESTINATION_IPS + # provide the total chaos duration + - name: TOTAL_CHAOS_DURATION + value: '20' + + ## 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 - value: '' - - # provide the socket file path - - name: SOCKET_PATH - value: '/var/run/docker.sock' + - name: LIB_IMAGE + value: 'litmuschaos/go-runner:latest' ## it defines the sequence of chaos execution for multiple target pods ## supported values: serial, parallel @@ -2290,7 +1627,7 @@ spec: value: 'parallel' labels: - name: pod-network-duplication + name: container-kill app.kubernetes.io/part-of: litmus app.kubernetes.io/component: experiment-job app.kubernetes.io/version: latest @@ -2302,9 +1639,9 @@ description: Deletes a pod belonging to a deployment/statefulset/daemonset kind: ChaosExperiment metadata: - name: pod-delete + name: k8-pod-delete labels: - name: pod-delete + name: k8-pod-delete app.kubernetes.io/part-of: litmus app.kubernetes.io/component: chaosexperiment app.kubernetes.io/version: latest @@ -2315,24 +1652,13 @@ spec: - apiGroups: - "" - "apps" - - "apps.openshift.io" - - "argoproj.io" - "batch" - "litmuschaos.io" resources: - "deployments" - "jobs" - "pods" - - "pods/log" - - "replicationcontrollers" - - "deployments" - - "statefulsets" - - "daemonsets" - - "replicasets" - - "deploymentconfigs" - - "rollouts" - - "pods/exec" - - "events" + - "configmaps" - "chaosengines" - "chaosexperiments" - "chaosresults" @@ -2343,160 +1669,149 @@ spec: - "patch" - "update" - "delete" + - apiGroups: + - "" + resources: + - "nodes" + verbs : + - "get" + - "list" + image: "litmuschaos/py-runner:latest" + args: + - -c + - python /litmus/byoc/chaostest/chaostest/kubernetes/k8_wrapper.py; exit 0 + command: + - /bin/bash + env: + - name: CHAOSTOOLKIT_IN_POD + value: 'true' + + - name: FILE + value: 'pod-app-kill-count.json' + + - name: NAME_SPACE + value: '' + + - name: LABEL_NAME + value: '' + + - name: APP_ENDPOINT + value: '' + + - name: PERCENTAGE + value: '50' + + - name: REPORT + value: 'true' + + - name: REPORT_ENDPOINT + value: 'none' + + - name: TEST_NAMESPACE + value: 'default' + + + labels: + name: k8-pod-delete + app.kubernetes.io/part-of: litmus + app.kubernetes.io/component: experiment-job + app.kubernetes.io/version: latest + +--- +apiVersion: litmuschaos.io/v1alpha1 +description: + message: | + poweroff node +kind: ChaosExperiment +metadata: + name: node-poweroff + labels: + name: node-poweroff + app.kubernetes.io/part-of: litmus + app.kubernetes.io/component: chaosexperiment + app.kubernetes.io/version: latest +spec: + definition: + scope: Cluster + permissions: + - apiGroups: + - "" + - "batch" + - "litmuschaos.io" + resources: + - "jobs" + - "pods" + - "pods/log" + - "pods/exec" + - "events" + - "chaosengines" + - "chaosexperiments" + - "chaosresults" + - "secrets" + verbs: + - "create" + - "list" + - "get" + - "patch" + - "update" + - "delete" - "deletecollection" + - apiGroups: + - "" + resources: + - "nodes" + verbs: + - "get" + - "list" image: "litmuschaos/go-runner:latest" imagePullPolicy: Always args: - -c - - ./experiments -name pod-delete + - ./experiments -name node-restart command: - /bin/bash env: + - name: SSH_USER + value: 'root' - name: TOTAL_CHAOS_DURATION - value: '15' + 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: '' - - name: FORCE - value: 'true' - - - name: CHAOS_INTERVAL - value: '5' - - ## percentage of total pods to target - - name: PODS_AFFECTED_PERC - value: '' - + # PROVIDE THE LIB HERE + # ONLY LITMUS SUPPORTED - name: LIB - value: 'litmus' + value: 'litmus' - - name: TARGET_PODS + # 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: '' - ## it defines the sequence of chaos execution for multiple target pods - ## supported values: serial, parallel - - name: SEQUENCE - value: 'parallel' - labels: - name: pod-delete - app.kubernetes.io/part-of: litmus - app.kubernetes.io/component: experiment-job - app.kubernetes.io/version: latest - ---- ---- -apiVersion: litmuschaos.io/v1alpha1 -description: - message: | - Injects memory consumption on pods belonging to an app deployment -kind: ChaosExperiment -metadata: - name: pod-memory-hog - labels: - name: pod-memory-hog - app.kubernetes.io/part-of: litmus - app.kubernetes.io/component: chaosexperiment - app.kubernetes.io/version: latest -spec: - definition: - scope: Namespaced - permissions: - - apiGroups: - - "" - - "batch" - - "apps" - - "apps.openshift.io" - - "argoproj.io" - - "litmuschaos.io" - resources: - - "jobs" - - "pods" - - "pods/log" - - "replicationcontrollers" - - "deployments" - - "statefulsets" - - "daemonsets" - - "replicasets" - - "deploymentconfigs" - - "rollouts" - - "pods/exec" - - "events" - - "chaosengines" - - "chaosexperiments" - - "chaosresults" - verbs: - - "create" - - "list" - - "get" - - "patch" - - "update" - - "delete" - - "deletecollection" - image: "litmuschaos/go-runner:ci" - imagePullPolicy: Always - args: - - -c - - ./experiments -name pod-memory-hog - command: - - /bin/bash - env: - - name: TOTAL_CHAOS_DURATION - value: '60' - - ## enter the amount of memory in megabytes to be consumed by the application pod - - name: MEMORY_CONSUMPTION - value: '500' - - ## Number of workers to perform stress - - name: NUMBER_OF_WORKERS - value: '1' - - ## percentage of total pods to target - - name: PODS_AFFECTED_PERC - value: '' - - ## Period to wait before and after injection of chaos in sec - - name: RAMP_TIME - value: '' - - ## env var that describes the library used to execute the chaos - ## default: litmus. Supported values: litmus, pumba - - name: LIB - value: 'litmus' - - ## It is used in pumba lib only - - name: LIB_IMAGE - value: 'litmuschaos/go-runner:ci' - - ## 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' - - ## it defines the sequence of chaos execution for multiple target pods - ## supported values: serial, parallel - - name: SEQUENCE - value: 'parallel' - - - name: TARGET_PODS - value: '' - - labels: - name: pod-memory-hog + name: 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 @@ -2608,3 +1923,696 @@ spec: 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: + - apiGroups: + - "" + - "batch" + - "apps" + - "apps.openshift.io" + - "argoproj.io" + - "litmuschaos.io" + resources: + - "jobs" + - "pods" + - "pods/log" + - "replicationcontrollers" + - "deployments" + - "statefulsets" + - "daemonsets" + - "replicasets" + - "deploymentconfigs" + - "rollouts" + - "pods/exec" + - "events" + - "chaosengines" + - "chaosexperiments" + - "chaosresults" + verbs: + - "create" + - "list" + - "get" + - "patch" + - "update" + - "delete" + - "deletecollection" + image: "litmuschaos/go-runner:ci" + 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: '' + + # 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:ci' + + ## 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/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: + - apiGroups: + - "" + - "batch" + - "litmuschaos.io" + resources: + - "jobs" + - "pods" + - "pods/log" + - "pods/exec" + - "events" + - "chaosengines" + - "chaosexperiments" + - "chaosresults" + verbs: + - "create" + - "list" + - "get" + - "patch" + - "update" + - "delete" + - "deletecollection" + - apiGroups: + - "" + resources: + - "nodes" + verbs: + - "get" + - "list" + image: "litmuschaos/go-runner:latest" + imagePullPolicy: Always + args: + - -c + - ./experiments -name node-io-stress + command: + - /bin/bash + env: + + - name: TOTAL_CHAOS_DURATION + value: '120' + + ## specify the size as percentage of free space on the file system + ## default value 90 (in percentage) + - name: FILESYSTEM_UTILIZATION_PERCENTAGE + value: '10' + + ## we can specify the size in Gigabyte (Gb) also in place of percentage of free space + ## NOTE: for selecting this option FILESYSTEM_UTILIZATION_PERCENTAGE should be empty + - name: FILESYSTEM_UTILIZATION_BYTES + value: '' + + ## Number of core of CPU + - name: CPU + value: '1' + + ## Total number of workers default value is 4 + - name: NUMBER_OF_WORKERS + value: '4' + + ## Total number of vm workers + - name: VM_WORKERS + value: '1' + + ## enter the comma separated target nodes name + - name: TARGET_NODES + value: '' + + - 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: | + Detaching a persistent disk from a node/instance. Supports only for AWS and GCP +kind: ChaosExperiment +metadata: + name: disk-loss + labels: + name: disk-loss + app.kubernetes.io/part-of: litmus + app.kubernetes.io/component: chaosexperiment + app.kubernetes.io/version: latest +spec: + definition: + scope: Cluster + permissions: + - apiGroups: + - "" + - "batch" + - "litmuschaos.io" + resources: + - "jobs" + - "pods" + - "events" + - "pods/log" + - "secrets" + - "chaosengines" + - "chaosexperiments" + - "chaosresults" + verbs: + - "create" + - "list" + - "get" + - "patch" + - "update" + - "delete" + image: "litmuschaos/ansible-runner:latest" + imagePullPolicy: Always + args: + - -c + - ansible-playbook ./experiments/generic/disk_loss/disk_loss_ansible_logic.yml -i /etc/ansible/hosts -vv; exit 0 + command: + - /bin/bash + env: + - name: ANSIBLE_STDOUT_CALLBACK + value: 'default' + + - name: TOTAL_CHAOS_DURATION + value: '15' + + # Period to wait before and after injection of chaos in sec + - name: RAMP_TIME + value: '' + + - name: APP_CHECK + value: 'true' + + # GKE and AWS supported + - name: CLOUD_PLATFORM + value: 'GKE' + + - name: PROJECT_ID + value: '' + + - name: NODE_NAME + value: '' + + - name: DISK_NAME + value: '' + + # provide the LIB + # only litmus supported + - name: LIB + value: 'litmus' + + - name: ZONE_NAME + value: '' + + - name: DEVICE_NAME + value: '' + + labels: + name: disk-loss + app.kubernetes.io/part-of: litmus + app.kubernetes.io/component: experiment-job + app.kubernetes.io/version: latest + secrets: + - name: cloud-secret + mountPath: /tmp/ + +--- +--- +apiVersion: litmuschaos.io/v1alpha1 +description: + message: | + Drain the node where application pod is scheduled +kind: ChaosExperiment +metadata: + name: node-drain + labels: + name: node-drain + app.kubernetes.io/part-of: litmus + app.kubernetes.io/component: chaosexperiment + app.kubernetes.io/version: latest +spec: + definition: + scope: Cluster + permissions: + - apiGroups: + - "" + - "batch" + - "litmuschaos.io" + - "apps" + resources: + - "jobs" + - "pods" + - "events" + - "pods/log" + - "pods/exec" + - "daemonsets" + - "pods/eviction" + - "chaosengines" + - "chaosexperiments" + - "chaosresults" + verbs: + - "create" + - "list" + - "get" + - "patch" + - "update" + - "delete" + - "deletecollection" + - apiGroups: + - "" + resources: + - "nodes" + verbs: + - "get" + - "list" + - "patch" + image: "litmuschaos/go-runner:latest" + imagePullPolicy: Always + args: + - -c + - ./experiments -name node-drain + command: + - /bin/bash + env: + + - name: TARGET_NODE + value: '' + + - name: 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: | + Taint the node where application pod is scheduled +kind: ChaosExperiment +metadata: + name: node-taint + labels: + name: node-taint + app.kubernetes.io/part-of: litmus + app.kubernetes.io/component: chaosexperiment + app.kubernetes.io/version: latest +spec: + definition: + scope: Cluster + permissions: + - apiGroups: + - "" + - "batch" + - "apps" + - "litmuschaos.io" + resources: + - "jobs" + - "pods" + - "events" + - "pods/log" + - "pods/exec" + - "daemonsets" + - "pods/eviction" + - "chaosengines" + - "chaosexperiments" + - "chaosresults" + verbs: + - "create" + - "list" + - "get" + - "patch" + - "update" + - "delete" + - "deletecollection" + - apiGroups: + - "" + resources: + - "nodes" + verbs: + - "get" + - "list" + - "patch" + - "update" + image: "litmuschaos/go-runner:latest" + imagePullPolicy: Always + args: + - -c + - ./experiments -name node-taint + command: + - /bin/bash + env: + + - name: TARGET_NODE + value: '' + + - name: NODE_LABEL + value: '' + + - name: TOTAL_CHAOS_DURATION + value: '60' + + # Provide the LIB here + # Only litmus supported + - name: LIB + value: 'litmus' + + # Period to wait before and after injection of chaos in sec + - name: RAMP_TIME + value: '' + + # set taint label & effect + # key=value:effect or key:effect + - name: TAINTS + value: '' + + labels: + name: node-taint + app.kubernetes.io/part-of: litmus + app.kubernetes.io/component: experiment-job + app.kubernetes.io/version: latest + +--- +apiVersion: litmuschaos.io/v1alpha1 +description: + message: | + Injects cpu consumption on pods belonging to an app deployment +kind: ChaosExperiment +metadata: + name: pod-cpu-hog + labels: + name: pod-cpu-hog + app.kubernetes.io/part-of: litmus + app.kubernetes.io/component: chaosexperiment + app.kubernetes.io/version: latest +spec: + definition: + scope: Namespaced + permissions: + - apiGroups: + - "" + - "batch" + - "apps" + - "apps.openshift.io" + - "argoproj.io" + - "litmuschaos.io" + resources: + - "jobs" + - "pods" + - "pods/log" + - "events" + - "replicationcontrollers" + - "deployments" + - "statefulsets" + - "daemonsets" + - "replicasets" + - "deploymentconfigs" + - "rollouts" + - "pods/exec" + - "chaosengines" + - "chaosexperiments" + - "chaosresults" + verbs: + - "create" + - "list" + - "get" + - "patch" + - "update" + - "delete" + - "deletecollection" + image: "litmuschaos/go-runner:ci" + imagePullPolicy: Always + args: + - -c + - ./experiments -name pod-cpu-hog + command: + - /bin/bash + env: + - name: TOTAL_CHAOS_DURATION + value: '60' + + ## Number of CPU cores to stress + - name: CPU_CORES + value: '1' + + ## Percentage of total pods to target + - name: PODS_AFFECTED_PERC + value: '' + + ## Period to wait before and after injection of chaos in sec + - name: RAMP_TIME + value: '' + + ## env var that describes the library used to execute the chaos + ## default: litmus. Supported values: litmus, pumba + - name: LIB + value: 'litmus' + + ## It is used in pumba lib only + - name: LIB_IMAGE + value: 'litmuschaos/go-runner:ci' + + ## 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: '' + + ## it defines the sequence of chaos execution for multiple target pods + ## supported values: serial, parallel + - name: SEQUENCE + value: 'parallel' + + labels: + name: pod-cpu-hog + app.kubernetes.io/part-of: litmus + app.kubernetes.io/component: experiment-job + app.kubernetes.io/version: latest + +--- +apiVersion: litmuschaos.io/v1alpha1 +description: + message: | + Deletes a pod belonging to a deployment/statefulset/daemonset +kind: ChaosExperiment +metadata: + name: pod-delete + labels: + name: pod-delete + app.kubernetes.io/part-of: litmus + app.kubernetes.io/component: chaosexperiment + app.kubernetes.io/version: latest +spec: + definition: + scope: Namespaced + permissions: + - apiGroups: + - "" + - "apps" + - "apps.openshift.io" + - "argoproj.io" + - "batch" + - "litmuschaos.io" + resources: + - "deployments" + - "jobs" + - "pods" + - "pods/log" + - "replicationcontrollers" + - "deployments" + - "statefulsets" + - "daemonsets" + - "replicasets" + - "deploymentconfigs" + - "rollouts" + - "pods/exec" + - "events" + - "chaosengines" + - "chaosexperiments" + - "chaosresults" + verbs: + - "create" + - "list" + - "get" + - "patch" + - "update" + - "delete" + - "deletecollection" + image: "litmuschaos/go-runner:latest" + imagePullPolicy: Always + args: + - -c + - ./experiments -name pod-delete + command: + - /bin/bash + env: + + - name: TOTAL_CHAOS_DURATION + value: '15' + + # Period to wait before and after injection of chaos in sec + - name: RAMP_TIME + value: '' + + - name: FORCE + value: 'true' + + - name: CHAOS_INTERVAL + value: '5' + + ## percentage of total pods to target + - name: PODS_AFFECTED_PERC + value: '' + + - name: LIB + value: 'litmus' + + - name: TARGET_PODS + value: '' + + ## it defines the sequence of chaos execution for multiple target pods + ## supported values: serial, parallel + - name: SEQUENCE + value: 'parallel' + + labels: + name: pod-delete + app.kubernetes.io/part-of: litmus + app.kubernetes.io/component: experiment-job + app.kubernetes.io/version: latest + +--- diff --git a/charts/kafka/experiments.yaml b/charts/kafka/experiments.yaml index 2549c04..2206e1d 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 773df32..a61cf7a 100644 --- a/charts/kube-aws/experiments.yaml +++ b/charts/kube-aws/experiments.yaml @@ -3,180 +3,6 @@ description: message: | Detaching an ebs volume from ec2 instance. kind: ChaosExperiment -metadata: - name: ec2-terminate-by-id - labels: - name: ec2-terminate-by-id - app.kubernetes.io/part-of: litmus - app.kubernetes.io/component: chaosexperiment - app.kubernetes.io/version: latest -spec: - definition: - scope: Cluster - permissions: - - apiGroups: - - "" - - "batch" - - "litmuschaos.io" - resources: - - "jobs" - - "pods" - - "events" - - "pods/log" - - "pods/exec" - - "secrets" - - "chaosengines" - - "chaosexperiments" - - "chaosresults" - verbs: - - "create" - - "list" - - "get" - - "patch" - - "update" - - "delete" - image: "litmuschaos/go-runner:latest" - imagePullPolicy: Always - args: - - -c - - ./experiments -name ec2-terminate-by-id - command: - - /bin/bash - env: - - name: TOTAL_CHAOS_DURATION - value: '30' - - - name: CHAOS_INTERVAL - value: '30' - - # Period to wait before and after injection of chaos in sec - - name: RAMP_TIME - value: '' - - # enable it if the target instance is a part of self-managed nodegroup. - - name: MANAGED_NODEGROUP - value: 'disable' - - # Instance ID of the target ec2 instance - # Multiple IDs can also be provided as comma separated values ex: id1,id2 - - name: EC2_INSTANCE_ID - value: '' - - - name: REGION - value: '' - - - name: SEQUENCE - value: 'parallel' - - # Provide the path of aws credentials mounted from secret - - name: AWS_SHARED_CREDENTIALS_FILE - value: '/tmp/cloud_config.yml' - - # provide the LIB - # only litmus supported - - name: LIB - value: 'litmus' - - labels: - name: ec2-terminate-by-id - app.kubernetes.io/part-of: litmus - app.kubernetes.io/component: experiment-job - app.kubernetes.io/version: latest - secrets: - - name: cloud-secret - mountPath: /tmp/ - ---- -apiVersion: litmuschaos.io/v1alpha1 -description: - message: | - 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: - - apiGroups: - - "" - - "batch" - - "litmuschaos.io" - resources: - - "jobs" - - "pods" - - "events" - - "pods/log" - - "pods/exec" - - "secrets" - - "chaosengines" - - "chaosexperiments" - - "chaosresults" - verbs: - - "create" - - "list" - - "get" - - "patch" - - "update" - - "delete" - image: "litmuschaos/go-runner:latest" - imagePullPolicy: Always - args: - - -c - - ./experiments -name 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: - message: | - Detaching an ebs volume from ec2 instance. -kind: ChaosExperiment metadata: name: ebs-loss-by-id labels: @@ -346,3 +172,177 @@ spec: 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: + - apiGroups: + - "" + - "batch" + - "litmuschaos.io" + resources: + - "jobs" + - "pods" + - "events" + - "pods/log" + - "pods/exec" + - "secrets" + - "chaosengines" + - "chaosexperiments" + - "chaosresults" + verbs: + - "create" + - "list" + - "get" + - "patch" + - "update" + - "delete" + image: "litmuschaos/go-runner:latest" + imagePullPolicy: Always + args: + - -c + - ./experiments -name 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: + message: | + Detaching an ebs volume from ec2 instance. +kind: ChaosExperiment +metadata: + name: ec2-terminate-by-id + labels: + name: ec2-terminate-by-id + app.kubernetes.io/part-of: litmus + app.kubernetes.io/component: chaosexperiment + app.kubernetes.io/version: latest +spec: + definition: + scope: Cluster + permissions: + - apiGroups: + - "" + - "batch" + - "litmuschaos.io" + resources: + - "jobs" + - "pods" + - "events" + - "pods/log" + - "pods/exec" + - "secrets" + - "chaosengines" + - "chaosexperiments" + - "chaosresults" + verbs: + - "create" + - "list" + - "get" + - "patch" + - "update" + - "delete" + image: "litmuschaos/go-runner:latest" + imagePullPolicy: Always + args: + - -c + - ./experiments -name ec2-terminate-by-id + command: + - /bin/bash + env: + - name: TOTAL_CHAOS_DURATION + value: '30' + + - name: CHAOS_INTERVAL + value: '30' + + # Period to wait before and after injection of chaos in sec + - name: RAMP_TIME + value: '' + + # enable it if the target instance is a part of self-managed nodegroup. + - name: MANAGED_NODEGROUP + value: 'disable' + + # Instance ID of the target ec2 instance + # Multiple IDs can also be provided as comma separated values ex: id1,id2 + - name: EC2_INSTANCE_ID + value: '' + + - name: REGION + value: '' + + - name: SEQUENCE + value: 'parallel' + + # Provide the path of aws credentials mounted from secret + - name: AWS_SHARED_CREDENTIALS_FILE + value: '/tmp/cloud_config.yml' + + # provide the LIB + # only litmus supported + - name: LIB + value: 'litmus' + + labels: + name: ec2-terminate-by-id + app.kubernetes.io/part-of: litmus + app.kubernetes.io/component: experiment-job + app.kubernetes.io/version: latest + secrets: + - name: cloud-secret + mountPath: /tmp/ + +--- diff --git a/charts/openebs/experiments.yaml b/charts/openebs/experiments.yaml index 318198a..e9db7f4 100644 --- a/charts/openebs/experiments.yaml +++ b/charts/openebs/experiments.yaml @@ -96,16 +96,16 @@ spec: apiVersion: litmuschaos.io/v1alpha1 description: message: | - Kill the cstor target/Jiva controller pod and check if gets created again + Kill the pool pod and check if gets scheduled again kind: ChaosExperiment metadata: labels: litmuschaos.io/name: openebs - name: openebs-target-pod-failure + name: openebs-pool-pod-failure app.kubernetes.io/part-of: litmus app.kubernetes.io/component: chaosexperiment app.kubernetes.io/version: latest - name: openebs-target-pod-failure + name: openebs-pool-pod-failure spec: definition: scope: Cluster @@ -116,23 +116,23 @@ spec: - "apps" - "batch" - "litmuschaos.io" + - "openebs.io" - "storage.k8s.io" resources: - "deployments" + - "replicasets" - "jobs" + - "pods/log" - "events" - "pods" - - "pods/log" - - "pods/exec" - "configmaps" - "secrets" - - "services" + - "storageclasses" + - "persistentvolumeclaims" + - "cstorvolumereplicas" - "chaosengines" - "chaosexperiments" - "chaosresults" - - "persistentvolumeclaims" - - "storageclasses" - - "persistentvolumes" verbs: - "create" - "get" @@ -151,154 +151,44 @@ spec: imagePullPolicy: Always args: - -c - - ansible-playbook ./experiments/openebs/openebs-target-pod-failure/openebs_target_pod_failure_ansible_logic.yml -i /etc/ansible/hosts -vv; exit 0 + - ansible-playbook ./experiments/openebs/openebs-pool-pod-failure/openebs_pool_pod_failure_ansible_logic.yml -i /etc/ansible/hosts -vv; exit 0 command: - /bin/bash env: - name: ANSIBLE_STDOUT_CALLBACK - value: 'default' + value: default - - name: OPENEBS_NAMESPACE + - name: OPENEBS_NS value: 'openebs' - + - name: APP_PVC value: '' - - name: FORCE - value: 'true' - - name: LIVENESS_APP_LABEL value: '' - name: LIVENESS_APP_NAMESPACE - value: '' + value: '' - - name: DATA_PERSISTENCE - value: '' - - - name: TOTAL_CHAOS_DURATION - value: '60' + - name: CHAOS_ITERATIONS + value: '2' # provide the kill count - name: KILL_COUNT value: '' - - name: CHAOS_INTERVAL - value: '15' - - - name: DEPLOY_TYPE - value: 'deployment' + - name: DATA_PERSISTENCE + value: '' labels: - name: openebs-target-pod-failure + name: openebs-pool-pod-failure app.kubernetes.io/part-of: litmus app.kubernetes.io/component: experiment-job app.kubernetes.io/version: latest #configmaps: - #- name: openebs-target-pod-failure + #- name: openebs-pool-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 @@ -496,52 +386,55 @@ spec: apiVersion: litmuschaos.io/v1alpha1 description: message: | - Kill the cstor target/Jiva controller container and check if gets created again + Kill all openebs control plane pod and check if gets scheduled again kind: ChaosExperiment metadata: labels: litmuschaos.io/name: openebs - name: openebs-target-container-failure + name: openebs-control-plane-chaos app.kubernetes.io/part-of: litmus app.kubernetes.io/component: chaosexperiment app.kubernetes.io/version: latest - name: openebs-target-container-failure + name: openebs-control-plane-chaos spec: definition: - scope: Cluster + scope: Namespaced permissions: - apiGroups: - "" - - "apps" - - "batch" - "litmuschaos.io" - - "storage.k8s.io" + - "batch" + - "apps" resources: - - "jobs" - "pods" - - "events" - - "pods/exec" - "pods/log" + - "deployments" + - "events" + - "jobs" - "configmaps" - - "secrets" - - "persistentvolumeclaims" - - "storageclasses" - - "persistentvolumes" - "chaosengines" - "chaosexperiments" - "chaosresults" verbs: - "create" - - "delete" - - "get" - "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-target-container-failure/openebs_target_container_failure_ansible_logic.yml -i /etc/ansible/hosts -vv; exit 0 + - 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: @@ -551,258 +444,23 @@ spec: - name: OPENEBS_NAMESPACE value: 'openebs' - - name: APP_PVC + ## Period to wait before injection of chaos + - name: RAMP_TIME 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: '' + ## env var that describes the library used to execute the chaos + ## default: litmus. Supported values: litmus, powerfulseal + - name: LIB + value: 'litmus' - - 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 + name: openebs-control-plane-chaos 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: | - 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 pool pod and check if gets scheduled again -kind: ChaosExperiment -metadata: - labels: - litmuschaos.io/name: openebs - name: openebs-pool-pod-failure - app.kubernetes.io/part-of: litmus - app.kubernetes.io/component: chaosexperiment - app.kubernetes.io/version: latest - name: openebs-pool-pod-failure -spec: - definition: - scope: Cluster - permissions: - - apiGroups: - - "" - - "extensions" - - "apps" - - "batch" - - "litmuschaos.io" - - "openebs.io" - - "storage.k8s.io" - resources: - - "deployments" - - "replicasets" - - "jobs" - - "pods/log" - - "events" - - "pods" - - "configmaps" - - "secrets" - - "storageclasses" - - "persistentvolumeclaims" - - "cstorvolumereplicas" - - "chaosengines" - - "chaosexperiments" - - "chaosresults" - verbs: - - "create" - - "get" - - "delete" - - "list" - - "patch" - - "update" - - apiGroups: - - "" - resources: - - "nodes" - verbs: - - "get" - - "list" - image: "litmuschaos/ansible-runner:latest" - imagePullPolicy: Always - args: - - -c - - ansible-playbook ./experiments/openebs/openebs-pool-pod-failure/openebs_pool_pod_failure_ansible_logic.yml -i /etc/ansible/hosts -vv; exit 0 - command: - - /bin/bash - env: - - name: ANSIBLE_STDOUT_CALLBACK - value: default - - - name: OPENEBS_NS - value: 'openebs' - - - name: APP_PVC - value: '' - - - name: LIVENESS_APP_LABEL - value: '' - - - name: LIVENESS_APP_NAMESPACE - value: '' - - - name: CHAOS_ITERATIONS - value: '2' - - # provide the kill count - - name: KILL_COUNT - value: '' - - - name: DATA_PERSISTENCE - value: '' - - labels: - name: openebs-pool-pod-failure - app.kubernetes.io/part-of: litmus - app.kubernetes.io/component: experiment-job - app.kubernetes.io/version: latest - #configmaps: - #- name: openebs-pool-pod-failure - # mountPath: /mnt - --- --- @@ -917,6 +575,212 @@ spec: - name: cloud-secret mountPath: /tmp/ +--- +--- +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 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: @@ -1018,35 +882,42 @@ spec: apiVersion: litmuschaos.io/v1alpha1 description: message: | - Kill all openebs control plane pod and check if gets scheduled again + 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-control-plane-chaos + name: openebs-nfs-provisioner-kill app.kubernetes.io/part-of: litmus app.kubernetes.io/component: chaosexperiment app.kubernetes.io/version: latest - name: openebs-control-plane-chaos + name: openebs-nfs-provisioner-kill spec: definition: - scope: Namespaced + scope: Cluster permissions: - apiGroups: - "" + - "apps" - "litmuschaos.io" - "batch" - - "apps" + - "extensions" + - "storage.k8s.io" resources: - "pods" + - "pods/exec" - "pods/log" - "deployments" - "events" - "jobs" - "configmaps" - - "chaosengines" + - "services" + - "persistentvolumeclaims" + - "storageclasses" + - "persistentvolumes" - "chaosexperiments" - "chaosresults" + - "chaosengines" verbs: - "create" - "list" @@ -1066,7 +937,99 @@ spec: imagePullPolicy: Always args: - -c - - ansible-playbook ./experiments/openebs/openebs-control-plane-chaos/openebs_control_plane_chaos_ansible_logic.yml -i /etc/ansible/hosts -vv; exit 0 + - ansible-playbook ./experiments/openebs/openebs-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 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: @@ -1076,22 +1039,59 @@ spec: - name: OPENEBS_NAMESPACE value: 'openebs' - ## Period to wait before injection of chaos - - name: RAMP_TIME + - 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: '' - ## env var that describes the library used to execute the chaos - ## default: litmus. Supported values: litmus, powerfulseal - - name: LIB - value: 'litmus' + - 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-control-plane-chaos + 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 ---