refactors directory and file structure
Signed-off-by: neelanjan00 <neelanjan.manna@harness.io>
This commit is contained in:
neelanjan00
@@ -0,0 +1,33 @@
|
||||
---
|
||||
apiVersion: litmuschaos.io/v1alpha1
|
||||
kind: ChartServiceVersion
|
||||
metadata:
|
||||
name: container-kill
|
||||
version: 0.1.0
|
||||
annotations:
|
||||
categories: "Kubernetes"
|
||||
vendor: "Harness"
|
||||
spec:
|
||||
displayName: Container Kill
|
||||
categoryDescription: |
|
||||
Container kill fault disrupts state of kubernetes resources. This fault injects random container delete failures against specified application.
|
||||
- Executes SIGKILL on containers of random replicas of an application deployment.
|
||||
- Tests deployment sanity (replica availability & uninterrupted service) and recovery workflows of the application pod.
|
||||
keywords:
|
||||
- Kubernetes
|
||||
platforms:
|
||||
- GKE
|
||||
- Minikube
|
||||
- Packet(Kubeadm)
|
||||
- EKS
|
||||
- AKS
|
||||
minKubeVersion: 1.12.0
|
||||
labels:
|
||||
app.kubernetes.io/component: chartserviceversion
|
||||
app.kubernetes.io/version: ci
|
||||
links:
|
||||
- name: Documentation
|
||||
url: https://docs.harness.io/category/kl0mxwpfw1-hce-category
|
||||
icon:
|
||||
- url:
|
||||
mediatype: ""
|
||||
41
faults/kubernetes/container-kill/engine.yaml
Normal file
41
faults/kubernetes/container-kill/engine.yaml
Normal file
@@ -0,0 +1,41 @@
|
||||
---
|
||||
apiVersion: litmuschaos.io/v1alpha1
|
||||
kind: ChaosEngine
|
||||
metadata:
|
||||
name: nginx-chaos
|
||||
namespace: default
|
||||
spec:
|
||||
# It can be active/stop
|
||||
engineState: 'active'
|
||||
appinfo:
|
||||
appns: ''
|
||||
applabel: ''
|
||||
appkind: ''
|
||||
chaosServiceAccount: container-kill-sa
|
||||
experiments:
|
||||
- name: container-kill
|
||||
spec:
|
||||
components:
|
||||
env:
|
||||
# provide the total chaos duration
|
||||
- name: TOTAL_CHAOS_DURATION
|
||||
value: '20'
|
||||
|
||||
# provide the chaos interval
|
||||
- name: CHAOS_INTERVAL
|
||||
value: '10'
|
||||
|
||||
# provide the name of container runtime
|
||||
# it supports docker, containerd, crio
|
||||
- name: CONTAINER_RUNTIME
|
||||
value: 'containerd'
|
||||
|
||||
# provide the socket file path
|
||||
- name: SOCKET_PATH
|
||||
value: '/run/containerd/containerd.sock'
|
||||
|
||||
- name: PODS_AFFECTED_PERC
|
||||
value: ''
|
||||
|
||||
- name: TARGET_CONTAINER
|
||||
value: ''
|
||||
123
faults/kubernetes/container-kill/fault.yaml
Normal file
123
faults/kubernetes/container-kill/fault.yaml
Normal file
@@ -0,0 +1,123 @@
|
||||
---
|
||||
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: ci
|
||||
spec:
|
||||
definition:
|
||||
scope: Namespaced
|
||||
permissions:
|
||||
# Create and monitor the experiment & helper pods
|
||||
- apiGroups: [""]
|
||||
resources: ["pods"]
|
||||
verbs: ["create", "delete", "get", "list", "patch", "update", "deletecollection"]
|
||||
# Performs CRUD operations on the events inside chaosengine and chaosresult
|
||||
- apiGroups: [""]
|
||||
resources: ["events"]
|
||||
verbs: ["create", "get", "list", "patch", "update"]
|
||||
# Fetch configmaps details and mount it to the experiment pod (if specified)
|
||||
- apiGroups: [""]
|
||||
resources: ["configmaps"]
|
||||
verbs: ["get", "list"]
|
||||
# Track and get the runner, experiment, and helper pods log
|
||||
- apiGroups: [""]
|
||||
resources: ["pods/log"]
|
||||
verbs: ["get", "list", "watch"]
|
||||
# for creating and managing to execute commands inside target container
|
||||
- apiGroups: [""]
|
||||
resources: ["pods/exec"]
|
||||
verbs: ["get", "list", "create"]
|
||||
# deriving the parent/owner details of the pod(if parent is anyof {deployment, statefulset, daemonsets})
|
||||
- apiGroups: ["apps"]
|
||||
resources: ["deployments", "statefulsets", "replicasets", "daemonsets"]
|
||||
verbs: ["list", "get"]
|
||||
# deriving the parent/owner details of the pod(if parent is deploymentConfig)
|
||||
- apiGroups: ["apps.openshift.io"]
|
||||
resources: ["deploymentconfigs"]
|
||||
verbs: ["list", "get"]
|
||||
# deriving the parent/owner details of the pod(if parent is deploymentConfig)
|
||||
- apiGroups: [""]
|
||||
resources: ["replicationcontrollers"]
|
||||
verbs: ["get", "list"]
|
||||
# deriving the parent/owner details of the pod(if parent is argo-rollouts)
|
||||
- apiGroups: ["argoproj.io"]
|
||||
resources: ["rollouts"]
|
||||
verbs: ["list", "get"]
|
||||
# for configuring and monitor the experiment job by the chaos-runner pod
|
||||
- apiGroups: ["batch"]
|
||||
resources: ["jobs"]
|
||||
verbs: ["create", "list", "get", "delete", "deletecollection"]
|
||||
# for creation, status polling and deletion of litmus chaos resources used within a chaos workflow
|
||||
- apiGroups: ["litmuschaos.io"]
|
||||
resources: ["chaosengines", "chaosexperiments", "chaosresults"]
|
||||
verbs: ["create", "list", "get", "patch", "update", "delete"]
|
||||
image: "chaosnative/go-runner:ci"
|
||||
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: ''
|
||||
|
||||
- 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: '/run/containerd/containerd.sock'
|
||||
|
||||
# provide the name of container runtime
|
||||
# it supports docker, containerd, crio
|
||||
- name: CONTAINER_RUNTIME
|
||||
value: 'containerd'
|
||||
|
||||
# provide the total chaos duration
|
||||
- name: TOTAL_CHAOS_DURATION
|
||||
value: '20'
|
||||
|
||||
## percentage of total pods to target
|
||||
- name: PODS_AFFECTED_PERC
|
||||
value: ''
|
||||
|
||||
# To select pods on specific node(s)
|
||||
- name: NODE_LABEL
|
||||
value: ''
|
||||
|
||||
- name: DEFAULT_HEALTH_CHECK
|
||||
value: 'false'
|
||||
|
||||
- name: LIB_IMAGE
|
||||
value: 'chaosnative/go-runner:ci'
|
||||
|
||||
## it defines the sequence of chaos execution for multiple target pods
|
||||
## supported values: serial, parallel
|
||||
- name: SEQUENCE
|
||||
value: 'parallel'
|
||||
|
||||
labels:
|
||||
name: container-kill
|
||||
app.kubernetes.io/part-of: litmus
|
||||
app.kubernetes.io/component: experiment-job
|
||||
app.kubernetes.io/runtime-api-usage: "true"
|
||||
app.kubernetes.io/version: ci
|
||||
@@ -0,0 +1,37 @@
|
||||
---
|
||||
apiVersion: litmuschaos.io/v1alpha1
|
||||
kind: ChartServiceVersion
|
||||
metadata:
|
||||
name: disk-fill
|
||||
version: 0.1.0
|
||||
annotations:
|
||||
categories: Kubernetes
|
||||
vendor: Harness
|
||||
support: https://slack.kubernetes.io/
|
||||
spec:
|
||||
displayName: Disk Fill
|
||||
categoryDescription: |
|
||||
Disk fill fault disrupts state of kubernetes resources.
|
||||
- Causes (forced/graceful) Disk Stress by filling up the Ephemeral Storage of the Pod using one of it containers.
|
||||
- Causes Pod to get Evicted if the Pod exceeds it Ephemeral Storage Limit.
|
||||
- Tests the Ephemeral Storage Limits, to ensure those parameters are sufficient.
|
||||
keywords:
|
||||
- Kubernetes
|
||||
platforms:
|
||||
- GKE
|
||||
- EKS
|
||||
- AKS
|
||||
experiments:
|
||||
- sock-shop
|
||||
- sock-shop-promProbe
|
||||
chaosType: infra
|
||||
minKubeVersion: 1.12.0
|
||||
labels:
|
||||
app.kubernetes.io/component: chartserviceversion
|
||||
app.kubernetes.io/version: ci
|
||||
links:
|
||||
- name: Documentation
|
||||
url: https://docs.harness.io/category/kl0mxwpfw1-hce-category
|
||||
icon:
|
||||
- url:
|
||||
mediatype: ""
|
||||
36
faults/kubernetes/disk-fill/engine.yaml
Normal file
36
faults/kubernetes/disk-fill/engine.yaml
Normal file
@@ -0,0 +1,36 @@
|
||||
---
|
||||
apiVersion: litmuschaos.io/v1alpha1
|
||||
kind: ChaosEngine
|
||||
metadata:
|
||||
name: nginx-chaos
|
||||
namespace: default
|
||||
spec:
|
||||
# It can be active/stop
|
||||
engineState: 'active'
|
||||
#ex. values: ns1:name=percona,ns2:run=nginx
|
||||
auxiliaryAppInfo: ''
|
||||
appinfo:
|
||||
appns: ''
|
||||
applabel: ''
|
||||
appkind: ''
|
||||
chaosServiceAccount: disk-fill-sa
|
||||
experiments:
|
||||
- name: disk-fill
|
||||
spec:
|
||||
components:
|
||||
env:
|
||||
- name: TOTAL_CHAOS_DURATION
|
||||
value: '60'
|
||||
|
||||
# specify the fill percentage according to the disk pressure required
|
||||
- name: FILL_PERCENTAGE
|
||||
value: '80'
|
||||
|
||||
- name: PODS_AFFECTED_PERC
|
||||
value: ''
|
||||
|
||||
# Provide the container runtime path
|
||||
# Default set to docker container path
|
||||
- name: CONTAINER_PATH
|
||||
value: '/var/lib/docker/containers'
|
||||
|
||||
123
faults/kubernetes/disk-fill/fault.yaml
Normal file
123
faults/kubernetes/disk-fill/fault.yaml
Normal file
@@ -0,0 +1,123 @@
|
||||
---
|
||||
apiVersion: litmuschaos.io/v1alpha1
|
||||
description:
|
||||
message: |
|
||||
Fillup Ephemeral Storage of a Resource
|
||||
kind: ChaosExperiment
|
||||
metadata:
|
||||
name: disk-fill
|
||||
labels:
|
||||
name: disk-fill
|
||||
app.kubernetes.io/part-of: litmus
|
||||
app.kubernetes.io/component: chaosexperiment
|
||||
app.kubernetes.io/version: ci
|
||||
spec:
|
||||
definition:
|
||||
scope: Namespaced
|
||||
permissions:
|
||||
# Create and monitor the experiment & helper pods
|
||||
- apiGroups: [""]
|
||||
resources: ["pods"]
|
||||
verbs: ["create", "delete", "get", "list", "patch", "update", "deletecollection"]
|
||||
# Performs CRUD operations on the events inside chaosengine and chaosresult
|
||||
- apiGroups: [""]
|
||||
resources: ["events"]
|
||||
verbs: ["create", "get", "list", "patch", "update"]
|
||||
# Fetch configmaps details and mount it to the experiment pod (if specified)
|
||||
- apiGroups: [""]
|
||||
resources: ["configmaps"]
|
||||
verbs: ["get", "list"]
|
||||
# Track and get the runner, experiment, and helper pods log
|
||||
- apiGroups: [""]
|
||||
resources: ["pods/log"]
|
||||
verbs: ["get", "list", "watch"]
|
||||
# for creating and managing to execute commands inside target container
|
||||
- apiGroups: [""]
|
||||
resources: ["pods/exec"]
|
||||
verbs: ["get", "list", "create"]
|
||||
# deriving the parent/owner details of the pod(if parent is anyof {deployment, statefulset, daemonsets})
|
||||
- apiGroups: ["apps"]
|
||||
resources: ["deployments", "statefulsets", "replicasets", "daemonsets"]
|
||||
verbs: ["list", "get"]
|
||||
# deriving the parent/owner details of the pod(if parent is deploymentConfig)
|
||||
- apiGroups: ["apps.openshift.io"]
|
||||
resources: ["deploymentconfigs"]
|
||||
verbs: ["list", "get"]
|
||||
# deriving the parent/owner details of the pod(if parent is deploymentConfig)
|
||||
- apiGroups: [""]
|
||||
resources: ["replicationcontrollers"]
|
||||
verbs: ["get", "list"]
|
||||
# deriving the parent/owner details of the pod(if parent is argo-rollouts)
|
||||
- apiGroups: ["argoproj.io"]
|
||||
resources: ["rollouts"]
|
||||
verbs: ["list", "get"]
|
||||
# for configuring and monitor the experiment job by the chaos-runner pod
|
||||
- apiGroups: ["batch"]
|
||||
resources: ["jobs"]
|
||||
verbs: ["create", "list", "get", "delete", "deletecollection"]
|
||||
# for creation, status polling and deletion of litmus chaos resources used within a chaos workflow
|
||||
- apiGroups: ["litmuschaos.io"]
|
||||
resources: ["chaosengines", "chaosexperiments", "chaosresults"]
|
||||
verbs: ["create", "list", "get", "patch", "update", "delete"]
|
||||
image: "chaosnative/go-runner:ci"
|
||||
imagePullPolicy: Always
|
||||
args:
|
||||
- -c
|
||||
- ./experiments -name disk-fill
|
||||
command:
|
||||
- /bin/bash
|
||||
env:
|
||||
- name: TARGET_CONTAINER
|
||||
value: ''
|
||||
|
||||
- name: FILL_PERCENTAGE
|
||||
value: '80'
|
||||
|
||||
- name: TOTAL_CHAOS_DURATION
|
||||
value: '60'
|
||||
|
||||
# Period to wait before and after injection of chaos in sec
|
||||
- name: RAMP_TIME
|
||||
value: ''
|
||||
|
||||
# provide the data block size
|
||||
# supported unit is KB
|
||||
- name: DATA_BLOCK_SIZE
|
||||
value: '256'
|
||||
|
||||
- name: TARGET_PODS
|
||||
value: ''
|
||||
|
||||
- name: EPHEMERAL_STORAGE_MEBIBYTES
|
||||
value: ''
|
||||
|
||||
# To select pods on specific node(s)
|
||||
- name: NODE_LABEL
|
||||
value: ''
|
||||
|
||||
## percentage of total pods to target
|
||||
- name: PODS_AFFECTED_PERC
|
||||
value: ''
|
||||
|
||||
- name: DEFAULT_HEALTH_CHECK
|
||||
value: 'false'
|
||||
|
||||
- name: LIB_IMAGE
|
||||
value: 'chaosnative/go-runner:ci'
|
||||
|
||||
# Provide the container runtime path
|
||||
# Default set to docker container path
|
||||
- name: CONTAINER_PATH
|
||||
value: '/var/lib/docker/containers'
|
||||
|
||||
## it defines the sequence of chaos execution for multiple target pods
|
||||
## supported values: serial, parallel
|
||||
- name: SEQUENCE
|
||||
value: 'parallel'
|
||||
|
||||
labels:
|
||||
name: disk-fill
|
||||
app.kubernetes.io/part-of: litmus
|
||||
app.kubernetes.io/component: experiment-job
|
||||
app.kubernetes.io/host-path-usage: "true"
|
||||
app.kubernetes.io/version: ci
|
||||
@@ -0,0 +1,30 @@
|
||||
---
|
||||
apiVersion: litmuschaos.io/v1alpha1
|
||||
kind: ChartServiceVersion
|
||||
metadata:
|
||||
name: docker-service-kill
|
||||
version: 0.1.0
|
||||
annotations:
|
||||
categories: Kubernetes
|
||||
vendor: Harness
|
||||
spec:
|
||||
displayName: Docker Service Kill
|
||||
categoryDescription: |
|
||||
docker-service-kill fault kills the Docker service gracefully for a certain chaos duration.
|
||||
- Causes replicas to be evicted or become unreachable on account of nodes turning unschedulable (Not Ready) due to Docker service kill.
|
||||
- The application node should be healthy once the chaos is stopped and the services are re-accessable.
|
||||
keywords:
|
||||
- Kubernetes
|
||||
platforms:
|
||||
- GKE
|
||||
- AKS
|
||||
minKubeVersion: 1.12.0
|
||||
labels:
|
||||
app.kubernetes.io/component: chartserviceversion
|
||||
app.kubernetes.io/version: ci
|
||||
links:
|
||||
- name: Documentation
|
||||
url: https://docs.harness.io/category/kl0mxwpfw1-hce-category
|
||||
icon:
|
||||
- base64data: ""
|
||||
mediatype: ""
|
||||
27
faults/kubernetes/docker-service-kill/engine.yaml
Normal file
27
faults/kubernetes/docker-service-kill/engine.yaml
Normal file
@@ -0,0 +1,27 @@
|
||||
---
|
||||
apiVersion: litmuschaos.io/v1alpha1
|
||||
kind: ChaosEngine
|
||||
metadata:
|
||||
name: nginx-chaos
|
||||
namespace: default
|
||||
spec:
|
||||
# It can be active/stop
|
||||
engineState: 'active'
|
||||
auxiliaryAppInfo: ''
|
||||
chaosServiceAccount: docker-service-kill-sa
|
||||
experiments:
|
||||
- name: docker-service-kill
|
||||
spec:
|
||||
components:
|
||||
# nodeSelector:
|
||||
# # provide the node labels
|
||||
# kubernetes.io/hostname: 'node02'
|
||||
env:
|
||||
- name: TOTAL_CHAOS_DURATION
|
||||
value: '90' # in seconds
|
||||
|
||||
- name: TARGET_NODE
|
||||
value: ''
|
||||
|
||||
- name: NODE_LABEL
|
||||
value: ""
|
||||
84
faults/kubernetes/docker-service-kill/fault.yaml
Normal file
84
faults/kubernetes/docker-service-kill/fault.yaml
Normal file
@@ -0,0 +1,84 @@
|
||||
---
|
||||
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: ci
|
||||
spec:
|
||||
definition:
|
||||
scope: Cluster
|
||||
permissions:
|
||||
# Create and monitor the experiment & helper pods
|
||||
- apiGroups: [""]
|
||||
resources: ["pods"]
|
||||
verbs: ["create", "delete", "get", "list", "patch", "update", "deletecollection"]
|
||||
# Performs CRUD operations on the events inside chaosengine and chaosresult
|
||||
- apiGroups: [""]
|
||||
resources: ["events"]
|
||||
verbs: ["create", "get", "list", "patch", "update"]
|
||||
# Fetch configmaps details and mount it to the experiment pod (if specified)
|
||||
- apiGroups: [""]
|
||||
resources: ["configmaps"]
|
||||
verbs: ["get", "list"]
|
||||
# Track and get the runner, experiment, and helper pods log
|
||||
- apiGroups: [""]
|
||||
resources: ["pods/log"]
|
||||
verbs: ["get", "list", "watch"]
|
||||
# for creating and managing to execute commands inside target container
|
||||
- apiGroups: [""]
|
||||
resources: ["pods/exec"]
|
||||
verbs: ["get", "list", "create"]
|
||||
# for configuring and monitor the experiment job by the chaos-runner pod
|
||||
- apiGroups: ["batch"]
|
||||
resources: ["jobs"]
|
||||
verbs: ["create", "list", "get", "delete", "deletecollection"]
|
||||
# for creation, status polling and deletion of litmus chaos resources used within a chaos workflow
|
||||
- apiGroups: ["litmuschaos.io"]
|
||||
resources: ["chaosengines", "chaosexperiments", "chaosresults"]
|
||||
verbs: ["create", "list", "get", "patch", "update", "delete"]
|
||||
# for experiment to perform node status checks
|
||||
- apiGroups: [""]
|
||||
resources: ["nodes"]
|
||||
verbs: ["get", "list"]
|
||||
image: "chaosnative/go-runner:ci"
|
||||
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: NODE_LABEL
|
||||
value: ''
|
||||
|
||||
# provide lib image
|
||||
- name: LIB_IMAGE
|
||||
value: 'ubuntu:16.04'
|
||||
|
||||
# provide the target node name
|
||||
- name: TARGET_NODE
|
||||
value: ''
|
||||
|
||||
- name: DEFAULT_HEALTH_CHECK
|
||||
value: 'false'
|
||||
|
||||
labels:
|
||||
name: docker-service-kill
|
||||
app.kubernetes.io/part-of: litmus
|
||||
app.kubernetes.io/component: experiment-job
|
||||
app.kubernetes.io/service-kill: "true"
|
||||
app.kubernetes.io/version: ci
|
||||
BIN
faults/kubernetes/icons/container-kill.png
Normal file
BIN
faults/kubernetes/icons/container-kill.png
Normal file
Binary file not shown.
|
After Width: | Height: | Size: 2.2 KiB |
BIN
faults/kubernetes/icons/disk-fill.png
Normal file
BIN
faults/kubernetes/icons/disk-fill.png
Normal file
Binary file not shown.
|
After Width: | Height: | Size: 1.7 KiB |
BIN
faults/kubernetes/icons/docker-service-kill.png
Normal file
BIN
faults/kubernetes/icons/docker-service-kill.png
Normal file
Binary file not shown.
|
After Width: | Height: | Size: 12 KiB |
BIN
faults/kubernetes/icons/kubelet-service-kill.png
Normal file
BIN
faults/kubernetes/icons/kubelet-service-kill.png
Normal file
Binary file not shown.
|
After Width: | Height: | Size: 2.6 KiB |
BIN
faults/kubernetes/icons/node-cpu-hog.png
Normal file
BIN
faults/kubernetes/icons/node-cpu-hog.png
Normal file
Binary file not shown.
|
After Width: | Height: | Size: 2.4 KiB |
BIN
faults/kubernetes/icons/node-drain.png
Normal file
BIN
faults/kubernetes/icons/node-drain.png
Normal file
Binary file not shown.
|
After Width: | Height: | Size: 1.9 KiB |
BIN
faults/kubernetes/icons/node-io-stress.png
Normal file
BIN
faults/kubernetes/icons/node-io-stress.png
Normal file
Binary file not shown.
|
After Width: | Height: | Size: 12 KiB |
BIN
faults/kubernetes/icons/node-memory-hog.png
Normal file
BIN
faults/kubernetes/icons/node-memory-hog.png
Normal file
Binary file not shown.
|
After Width: | Height: | Size: 1.5 KiB |
BIN
faults/kubernetes/icons/node-poweroff.png
Normal file
BIN
faults/kubernetes/icons/node-poweroff.png
Normal file
Binary file not shown.
|
After Width: | Height: | Size: 12 KiB |
BIN
faults/kubernetes/icons/node-restart.png
Normal file
BIN
faults/kubernetes/icons/node-restart.png
Normal file
Binary file not shown.
|
After Width: | Height: | Size: 12 KiB |
BIN
faults/kubernetes/icons/node-taint.png
Normal file
BIN
faults/kubernetes/icons/node-taint.png
Normal file
Binary file not shown.
|
After Width: | Height: | Size: 12 KiB |
BIN
faults/kubernetes/icons/pod-autoscaler.png
Normal file
BIN
faults/kubernetes/icons/pod-autoscaler.png
Normal file
Binary file not shown.
|
After Width: | Height: | Size: 12 KiB |
BIN
faults/kubernetes/icons/pod-cpu-hog-exec.png
Normal file
BIN
faults/kubernetes/icons/pod-cpu-hog-exec.png
Normal file
Binary file not shown.
|
After Width: | Height: | Size: 2.0 KiB |
BIN
faults/kubernetes/icons/pod-cpu-hog.png
Normal file
BIN
faults/kubernetes/icons/pod-cpu-hog.png
Normal file
Binary file not shown.
|
After Width: | Height: | Size: 2.0 KiB |
BIN
faults/kubernetes/icons/pod-delete.png
Normal file
BIN
faults/kubernetes/icons/pod-delete.png
Normal file
Binary file not shown.
|
After Width: | Height: | Size: 959 B |
BIN
faults/kubernetes/icons/pod-dns-error.png
Normal file
BIN
faults/kubernetes/icons/pod-dns-error.png
Normal file
Binary file not shown.
|
After Width: | Height: | Size: 12 KiB |
BIN
faults/kubernetes/icons/pod-dns-spoof.png
Normal file
BIN
faults/kubernetes/icons/pod-dns-spoof.png
Normal file
Binary file not shown.
|
After Width: | Height: | Size: 12 KiB |
BIN
faults/kubernetes/icons/pod-http-latency.png
Normal file
BIN
faults/kubernetes/icons/pod-http-latency.png
Normal file
Binary file not shown.
|
After Width: | Height: | Size: 12 KiB |
BIN
faults/kubernetes/icons/pod-http-modify-body.png
Normal file
BIN
faults/kubernetes/icons/pod-http-modify-body.png
Normal file
Binary file not shown.
|
After Width: | Height: | Size: 12 KiB |
BIN
faults/kubernetes/icons/pod-http-modify-header.png
Normal file
BIN
faults/kubernetes/icons/pod-http-modify-header.png
Normal file
Binary file not shown.
|
After Width: | Height: | Size: 12 KiB |
BIN
faults/kubernetes/icons/pod-http-reset-peer.png
Normal file
BIN
faults/kubernetes/icons/pod-http-reset-peer.png
Normal file
Binary file not shown.
|
After Width: | Height: | Size: 12 KiB |
BIN
faults/kubernetes/icons/pod-http-status-code.png
Normal file
BIN
faults/kubernetes/icons/pod-http-status-code.png
Normal file
Binary file not shown.
|
After Width: | Height: | Size: 12 KiB |
BIN
faults/kubernetes/icons/pod-io-stress.png
Normal file
BIN
faults/kubernetes/icons/pod-io-stress.png
Normal file
Binary file not shown.
|
After Width: | Height: | Size: 12 KiB |
BIN
faults/kubernetes/icons/pod-memory-hog-exec.png
Normal file
BIN
faults/kubernetes/icons/pod-memory-hog-exec.png
Normal file
Binary file not shown.
|
After Width: | Height: | Size: 1.5 KiB |
BIN
faults/kubernetes/icons/pod-memory-hog.png
Normal file
BIN
faults/kubernetes/icons/pod-memory-hog.png
Normal file
Binary file not shown.
|
After Width: | Height: | Size: 1.5 KiB |
BIN
faults/kubernetes/icons/pod-network-corruption.png
Normal file
BIN
faults/kubernetes/icons/pod-network-corruption.png
Normal file
Binary file not shown.
|
After Width: | Height: | Size: 2.6 KiB |
BIN
faults/kubernetes/icons/pod-network-duplication.png
Normal file
BIN
faults/kubernetes/icons/pod-network-duplication.png
Normal file
Binary file not shown.
|
After Width: | Height: | Size: 12 KiB |
BIN
faults/kubernetes/icons/pod-network-latency.png
Normal file
BIN
faults/kubernetes/icons/pod-network-latency.png
Normal file
Binary file not shown.
|
After Width: | Height: | Size: 2.4 KiB |
BIN
faults/kubernetes/icons/pod-network-loss.png
Normal file
BIN
faults/kubernetes/icons/pod-network-loss.png
Normal file
Binary file not shown.
|
After Width: | Height: | Size: 2.7 KiB |
BIN
faults/kubernetes/icons/pod-network-partition.png
Normal file
BIN
faults/kubernetes/icons/pod-network-partition.png
Normal file
Binary file not shown.
|
After Width: | Height: | Size: 12 KiB |
26
faults/kubernetes/kubelet-service-kill/engine.yaml
Normal file
26
faults/kubernetes/kubelet-service-kill/engine.yaml
Normal file
@@ -0,0 +1,26 @@
|
||||
---
|
||||
apiVersion: litmuschaos.io/v1alpha1
|
||||
kind: ChaosEngine
|
||||
metadata:
|
||||
name: nginx-chaos
|
||||
namespace: default
|
||||
spec:
|
||||
# It can be active/stop
|
||||
engineState: 'active'
|
||||
#ex. values: ns1:name=percona,ns2:run=nginx
|
||||
auxiliaryAppInfo: ''
|
||||
chaosServiceAccount: kubelet-service-kill-sa
|
||||
experiments:
|
||||
- name: kubelet-service-kill
|
||||
spec:
|
||||
components:
|
||||
# nodeSelector:
|
||||
# # provide the node labels
|
||||
# kubernetes.io/hostname: 'node02'
|
||||
env:
|
||||
- name: TOTAL_CHAOS_DURATION
|
||||
value: '60' # in seconds
|
||||
|
||||
# provide the target node name
|
||||
- name: TARGET_NODE
|
||||
value: ''
|
||||
84
faults/kubernetes/kubelet-service-kill/fault.yaml
Normal file
84
faults/kubernetes/kubelet-service-kill/fault.yaml
Normal file
@@ -0,0 +1,84 @@
|
||||
---
|
||||
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: ci
|
||||
spec:
|
||||
definition:
|
||||
scope: Cluster
|
||||
permissions:
|
||||
# Create and monitor the experiment & helper pods
|
||||
- apiGroups: [""]
|
||||
resources: ["pods"]
|
||||
verbs: ["create", "delete", "get", "list", "patch", "update", "deletecollection"]
|
||||
# Performs CRUD operations on the events inside chaosengine and chaosresult
|
||||
- apiGroups: [""]
|
||||
resources: ["events"]
|
||||
verbs: ["create", "get", "list", "patch", "update"]
|
||||
# Fetch configmaps details and mount it to the experiment pod (if specified)
|
||||
- apiGroups: [""]
|
||||
resources: ["configmaps"]
|
||||
verbs: ["get", "list"]
|
||||
# Track and get the runner, experiment, and helper pods log
|
||||
- apiGroups: [""]
|
||||
resources: ["pods/log"]
|
||||
verbs: ["get", "list", "watch"]
|
||||
# for creating and managing to execute commands inside target container
|
||||
- apiGroups: [""]
|
||||
resources: ["pods/exec"]
|
||||
verbs: ["get", "list", "create"]
|
||||
# for configuring and monitor the experiment job by the chaos-runner pod
|
||||
- apiGroups: ["batch"]
|
||||
resources: ["jobs"]
|
||||
verbs: ["create", "list", "get", "delete", "deletecollection"]
|
||||
# for creation, status polling and deletion of litmus chaos resources used within a chaos workflow
|
||||
- apiGroups: ["litmuschaos.io"]
|
||||
resources: ["chaosengines", "chaosexperiments", "chaosresults"]
|
||||
verbs: ["create", "list", "get", "patch", "update", "delete"]
|
||||
# for experiment to perform node status checks
|
||||
- apiGroups: [""]
|
||||
resources: ["nodes"]
|
||||
verbs: ["get", "list"]
|
||||
image: "chaosnative/go-runner:ci"
|
||||
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: NODE_LABEL
|
||||
value: ''
|
||||
|
||||
# provide lib image
|
||||
- name: LIB_IMAGE
|
||||
value: 'ubuntu:16.04'
|
||||
|
||||
# provide the target node name
|
||||
- name: TARGET_NODE
|
||||
value: ''
|
||||
|
||||
- name: DEFAULT_HEALTH_CHECK
|
||||
value: 'false'
|
||||
|
||||
labels:
|
||||
name: kubelet-service-kill
|
||||
app.kubernetes.io/part-of: litmus
|
||||
app.kubernetes.io/component: experiment-job
|
||||
app.kubernetes.io/service-kill: "true"
|
||||
app.kubernetes.io/version: ci
|
||||
@@ -0,0 +1,33 @@
|
||||
---
|
||||
apiVersion: litmuschaos.io/v1alpha1
|
||||
kind: ChartServiceVersion
|
||||
metadata:
|
||||
name: kubelet-service-kill
|
||||
version: 0.1.0
|
||||
annotations:
|
||||
categories: Kubernetes
|
||||
vendor: Harness
|
||||
spec:
|
||||
displayName: Kubelet Service Kill
|
||||
categoryDescription: |
|
||||
kubelet-service-kill fault kills the Kubelet service gracefully for a certain chaos duration.
|
||||
- Replicas may be evicted or become unreachable on account on nodes turning unschedulable (Not Ready) due to Kubelet service kill.
|
||||
- The application node should be healthy once chaos is stopped and the services are reaccessable.
|
||||
keywords:
|
||||
- Kubernetes
|
||||
platforms:
|
||||
- GKE
|
||||
- Packet(Kubeadm)
|
||||
- Minikube
|
||||
- EKS
|
||||
- AKS
|
||||
minKubeVersion: 1.12.0
|
||||
labels:
|
||||
app.kubernetes.io/component: chartserviceversion
|
||||
app.kubernetes.io/version: ci
|
||||
links:
|
||||
- name: Documentation
|
||||
url: https://docs.harness.io/category/kl0mxwpfw1-hce-category
|
||||
icon:
|
||||
- base64data: ""
|
||||
mediatype: ""
|
||||
120
faults/kubernetes/kubernetes.chartserviceversion.yaml
Normal file
120
faults/kubernetes/kubernetes.chartserviceversion.yaml
Normal file
@@ -0,0 +1,120 @@
|
||||
---
|
||||
apiVersion: litmuschaos.io/v1alpha1
|
||||
kind: ChartServiceVersion
|
||||
metadata:
|
||||
name: kubernetes
|
||||
version: 0.1.0
|
||||
annotations:
|
||||
categories: Kubernetes
|
||||
chartDescription: Injects kubernetes chaos experiment
|
||||
executionPlane: "kubernetes"
|
||||
spec:
|
||||
displayName: Kubernetes
|
||||
categoryDescription: >
|
||||
Kubernetes is an open-source system for automating deployment, scaling, and management of containerized applications. It groups containers that make up an application into logical units for easier management and discovery. It will install all the experiments which can be used to inject chaos into containerized applications.
|
||||
faults:
|
||||
- name: pod-delete
|
||||
description: It injects pod-delete chaos in a Kubernetes pod.
|
||||
displayName: "Pod Delete"
|
||||
- name: container-kill
|
||||
description: It injects container-kill chaos in a Kubernetes pod .
|
||||
displayName: "Container Kill"
|
||||
- name: pod-cpu-hog
|
||||
description: It injects cpu-hog chaos in a Kubernetes pod.
|
||||
displayName: "Pod CPU Hog"
|
||||
- name: pod-network-loss
|
||||
description: It injects network-loss chaos in a Kubernetes pod.
|
||||
displayName: "Pod Network Loss"
|
||||
- name: pod-network-latency
|
||||
description: It injects network-latency chaos in a Kubernetes pod.
|
||||
displayName: "Pod Network Latency"
|
||||
- name: pod-network-corruption
|
||||
description: It injects network-corruption chaos in a Kubernetes pod.
|
||||
displayName: "Pod Network Corruption"
|
||||
- name: node-drain
|
||||
description: It injects node-drain chaos in a Kubernetes node.
|
||||
displayName: "Node Drain"
|
||||
- name: node-cpu-hog
|
||||
description: It injects node-cpu-hog chaos in a Kubernetes node.
|
||||
displayName: "Node CPU Hog"
|
||||
- name: node-restart
|
||||
description: It injects node-restart chaos in a Kubernetes node.
|
||||
displayName: "Node Restart"
|
||||
- name: disk-fill
|
||||
description: It injects disk-fill chaos in a Kubernetes node.
|
||||
displayName: "Disk Fill"
|
||||
- name: node-memory-hog
|
||||
description: It injects node-memory-hog chaos in a Kubernetes node.
|
||||
displayName: "Node Memory Hog"
|
||||
- name: node-poweroff
|
||||
description: Node poweroff contains chaos experiment to poweroff a node via SSH.
|
||||
displayName: "Node Poweroff"
|
||||
- name: pod-memory-hog
|
||||
description: It injects pod-memory-hog chaos in a Kubernetes pod.
|
||||
displayName: "Pod Memory Hog"
|
||||
- name: kubelet-service-kill
|
||||
description: It injects kubelet-service-kill chaos in a Kubernetes node.
|
||||
displayName: "Kubelet Service Kill"
|
||||
- name: pod-network-duplication
|
||||
description: It injects pod-network-duplication chaos in a Kubernetes pod.
|
||||
displayName: "Pod Network Duplication"
|
||||
- name: node-taint
|
||||
description: It injects node-taint chaos in a Kubernetes node.
|
||||
displayName: "Node Taint"
|
||||
- name: docker-service-kill
|
||||
description: It injects docker-service-kill chaos in a Kubernetes pod.
|
||||
displayName: "Docker Service Kill"
|
||||
- name: pod-autoscaler
|
||||
description: It injects pod-autoscaler chaos in a Kubernetes pod.
|
||||
displayName: "Pod Autoscaler"
|
||||
- name: node-io-stress
|
||||
description: It injects node-io-stress chaos in a Kubernetes node.
|
||||
displayName: "Node IO Stress"
|
||||
- name: pod-io-stress
|
||||
description: It injects pod-io-stress chaos in a Kubernetes pod.
|
||||
displayName: "Pod IO Stress"
|
||||
- name: pod-dns-error
|
||||
description: It injects pod-dns-error chaos in a Kubernetes pod.
|
||||
displayName: "Pod DNS Error"
|
||||
- name: pod-dns-spoof
|
||||
description: It injects pod-dns-spoof chaos in a Kubernetes pod.
|
||||
displayName: "Pod DNS Spoof"
|
||||
- name: pod-cpu-hog-exec
|
||||
description: It injects pod-cpu-hog-exec chaos in a Kubernetes pod.
|
||||
displayName: "Pod CPU Hog Exec"
|
||||
- name: pod-memory-hog-exec
|
||||
description: It injects pod-memory-hog-exec chaos in a Kubernetes pod.
|
||||
displayName: "Pod Memory Hog Exec"
|
||||
- name: pod-network-partition
|
||||
description: It injects pod-network-partition chaos in a Kubernetes pod.
|
||||
displayName: "Pod Network Partition"
|
||||
- name: pod-http-latency
|
||||
description: It injects pod-http-latency chaos in a Kubernetes pod.
|
||||
displayName: "Pod HTTP Latency"
|
||||
- name: pod-http-status-code
|
||||
description: It injects pod-http-status-code chaos in a Kubernetes pod.
|
||||
displayName: "Pod HTTP Status Code"
|
||||
- name: pod-http-modify-header
|
||||
description: It injects pod-http-modify-header chaos in a Kubernetes pod.
|
||||
displayName: "Pod HTTP Modify Header"
|
||||
- name: pod-http-modify-body
|
||||
description: It injects pod-http-modify-body chaos in a Kubernetes pod.
|
||||
displayName: "Pod HTTP Modify Body"
|
||||
- name: pod-http-reset-peer
|
||||
description: It injects pod-http-reset-peer chaos in a Kubernetes pod.
|
||||
displayName: "Pod HTTP Reset Peer"
|
||||
keywords:
|
||||
- Kubernetes
|
||||
minKubeVersion: 1.12.0
|
||||
links:
|
||||
- name: Kubernetes Website
|
||||
url: https://kubernetes.io
|
||||
- name: Source Code
|
||||
url: https://github.com/kubernetes/kubernetes
|
||||
- name: Kubernetes Slack
|
||||
url: https://slack.kubernetes.io/
|
||||
- name: Documentation
|
||||
url: https://litmuschaos.github.io/litmus/experiments/categories/contents/#kubernetes
|
||||
icon:
|
||||
- url: https://raw.githubusercontent.com/litmuschaos/charthub.litmuschaos.io/master/public/litmus.ico
|
||||
mediatype: image/png
|
||||
102
faults/kubernetes/kubernetes.package.yaml
Normal file
102
faults/kubernetes/kubernetes.package.yaml
Normal file
@@ -0,0 +1,102 @@
|
||||
---
|
||||
packageName: kubernetes
|
||||
faults:
|
||||
- name: pod-delete
|
||||
CSV: pod-delete.chartserviceversion.yaml
|
||||
desc: "pod-delete"
|
||||
- name: container-kill
|
||||
CSV: container-kill.chartserviceversion.yaml
|
||||
desc: "container-kill"
|
||||
- name: pod-network-loss
|
||||
CSV: pod-network-loss.chartserviceversion.yaml
|
||||
desc: "pod-network-loss"
|
||||
- name: pod-network-latency
|
||||
CSV: pod-network-latency.chartserviceversion.yaml
|
||||
desc: "pod-network-latency"
|
||||
- name: pod-cpu-hog
|
||||
CSV: pod-cpu-hog.chartserviceversion.yaml
|
||||
desc: "pod-cpu-hog"
|
||||
- name: node-cpu-hog
|
||||
CSV: node-cpu-hog.chartserviceversion.yaml
|
||||
desc: "node-cpu-hog"
|
||||
- name: disk-fill
|
||||
CSV: disk-fill.chartserviceversion.yaml
|
||||
desc: "disk-fill"
|
||||
- name: node-drain
|
||||
CSV: node-drain.chartserviceversion.yaml
|
||||
desc: "node-drain"
|
||||
- name: pod-network-corruption
|
||||
CSV: pod-network-corruption.chartserviceversion.yaml
|
||||
desc: "pod-network-corruption"
|
||||
- name: node-memory-hog
|
||||
CSV: node-memory-hog.chartserviceversion.yaml
|
||||
desc: "node-memory-hog"
|
||||
- name: node-poweroff
|
||||
CSV: node-poweroff.chartserviceversion.yaml
|
||||
desc: "node-poweroff"
|
||||
- name: node-restart
|
||||
CSV: node-restart.chartserviceversion.yaml
|
||||
desc: "node-restart"
|
||||
- name: pod-memory-hog
|
||||
CSV: pod-memory-hog.chartserviceversion.yaml
|
||||
desc: "pod-memory-hog"
|
||||
- name: kubelet-service-kill
|
||||
CSV: kubelet-service-kill.chartserviceversion.yaml
|
||||
desc: "kubelet-service-kill"
|
||||
- name: pod-network-duplication
|
||||
CSV: pod-network-duplication.chartserviceversion.yaml
|
||||
desc: "pod-network-duplication"
|
||||
- name: node-taint
|
||||
CSV: node-taint.chartserviceversion.yaml
|
||||
desc: "node-taint"
|
||||
- name: docker-service-kill
|
||||
CSV: docker-service-kill.chartserviceversion.yaml
|
||||
desc: "docker-service-kill"
|
||||
- name: pod-autoscaler
|
||||
CSV: pod-autoscaler.chartserviceversion.yaml
|
||||
desc: "pod-autoscaler"
|
||||
- name: node-io-stress
|
||||
CSV: node-io-stress.chartserviceversion.yaml
|
||||
desc: "node-io-stress"
|
||||
- name: pod-io-stress
|
||||
CSV: pod-io-stress.chartserviceversion.yaml
|
||||
desc: "pod-io-stress"
|
||||
- name: pod-dns-error
|
||||
CSV: pod-dns-error.chartserviceversion.yaml
|
||||
desc: "pod-dns-error"
|
||||
- name: pod-dns-spoof
|
||||
CSV: pod-dns-spoof.chartserviceversion.yaml
|
||||
desc: "pod-dns-spoof"
|
||||
- name: pod-cpu-hog-exec
|
||||
CSV: pod-cpu-hog-exec.chartserviceversion.yaml
|
||||
desc: "pod-cpu-hog-exec"
|
||||
- name: pod-memory-hog-exec
|
||||
CSV: pod-memory-hog-exec.chartserviceversion.yaml
|
||||
desc: "pod-memory-hog-exec"
|
||||
- name: pod-network-partition
|
||||
CSV: pod-network-partition.chartserviceversion.yaml
|
||||
desc: "pod-network-partition"
|
||||
- name: pod-http-latency
|
||||
CSV: pod-http-latency.chartserviceversion.yaml
|
||||
desc: "pod-http-latency"
|
||||
- name: pod-http-status-code
|
||||
CSV: pod-http-status-code.chartserviceversion.yaml
|
||||
desc: "pod-http-status-code"
|
||||
- name: pod-http-modify-header
|
||||
CSV: pod-http-modify-header.chartserviceversion.yaml
|
||||
desc: "pod-http-modify-header"
|
||||
- name: pod-http-modify-body
|
||||
CSV: pod-http-modify-body.chartserviceversion.yaml
|
||||
desc: "pod-http-modify-body"
|
||||
- name: pod-http-reset-peer
|
||||
CSV: pod-http-reset-peer.chartserviceversion.yaml
|
||||
desc: "pod-http-reset-peer"
|
||||
- name: node-network-latency
|
||||
CSV: node-network-latency.chartserviceversion.yaml
|
||||
desc: "node-network-latency"
|
||||
- name: node-network-loss
|
||||
CSV: node-network-loss.chartserviceversion.yaml
|
||||
desc: "node-network-loss"
|
||||
- name: time-chaos
|
||||
CSV: time-chaos.chartserviceversion.yaml
|
||||
desc: "time-chaos"
|
||||
38
faults/kubernetes/node-cpu-hog/engine.yaml
Normal file
38
faults/kubernetes/node-cpu-hog/engine.yaml
Normal file
@@ -0,0 +1,38 @@
|
||||
---
|
||||
apiVersion: litmuschaos.io/v1alpha1
|
||||
kind: ChaosEngine
|
||||
metadata:
|
||||
name: nginx-chaos
|
||||
namespace: default
|
||||
spec:
|
||||
# It can be active/stop
|
||||
engineState: 'active'
|
||||
#ex. values: ns1:name=percona,ns2:run=nginx
|
||||
auxiliaryAppInfo: ''
|
||||
chaosServiceAccount: node-cpu-hog-sa
|
||||
experiments:
|
||||
- name: node-cpu-hog
|
||||
spec:
|
||||
components:
|
||||
env:
|
||||
# set chaos duration (in sec) as desired
|
||||
- name: TOTAL_CHAOS_DURATION
|
||||
value: '60'
|
||||
|
||||
## 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: '1'
|
||||
|
||||
## LOAD CPU WITH GIVEN PERCENT LOADING FOR THE CPU STRESS WORKERS.
|
||||
## 0 IS EFFECTIVELY A SLEEP (NO LOAD) AND 100 IS FULL LOADING
|
||||
- name: CPU_LOAD
|
||||
value: '0'
|
||||
|
||||
## percentage of total nodes to target
|
||||
- name: NODES_AFFECTED_PERC
|
||||
value: ''
|
||||
|
||||
# provide the comma separated target node names
|
||||
- name: TARGET_NODES
|
||||
value: ''
|
||||
102
faults/kubernetes/node-cpu-hog/fault.yaml
Normal file
102
faults/kubernetes/node-cpu-hog/fault.yaml
Normal file
@@ -0,0 +1,102 @@
|
||||
---
|
||||
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: ci
|
||||
spec:
|
||||
definition:
|
||||
scope: Cluster
|
||||
permissions:
|
||||
# Create and monitor the experiment & helper pods
|
||||
- apiGroups: [""]
|
||||
resources: ["pods"]
|
||||
verbs: ["create", "delete", "get", "list", "patch", "update", "deletecollection"]
|
||||
# Performs CRUD operations on the events inside chaosengine and chaosresult
|
||||
- apiGroups: [""]
|
||||
resources: ["events"]
|
||||
verbs: ["create", "get", "list", "patch", "update"]
|
||||
# Fetch configmaps details and mount it to the experiment pod (if specified)
|
||||
- apiGroups: [""]
|
||||
resources: ["configmaps"]
|
||||
verbs: ["get", "list"]
|
||||
# Track and get the runner, experiment, and helper pods log
|
||||
- apiGroups: [""]
|
||||
resources: ["pods/log"]
|
||||
verbs: ["get", "list", "watch"]
|
||||
# for creating and managing to execute commands inside target container
|
||||
- apiGroups: [""]
|
||||
resources: ["pods/exec"]
|
||||
verbs: ["get", "list", "create"]
|
||||
# for configuring and monitor the experiment job by the chaos-runner pod
|
||||
- apiGroups: ["batch"]
|
||||
resources: ["jobs"]
|
||||
verbs: ["create", "list", "get", "delete", "deletecollection"]
|
||||
# for creation, status polling and deletion of litmus chaos resources used within a chaos workflow
|
||||
- apiGroups: ["litmuschaos.io"]
|
||||
resources: ["chaosengines", "chaosexperiments", "chaosresults"]
|
||||
verbs: ["create", "list", "get", "patch", "update", "delete"]
|
||||
# for experiment to perform node status checks
|
||||
- apiGroups: [""]
|
||||
resources: ["nodes"]
|
||||
verbs: ["get", "list"]
|
||||
image: "chaosnative/go-runner:ci"
|
||||
imagePullPolicy: Always
|
||||
args:
|
||||
- -c
|
||||
- ./experiments -name node-cpu-hog
|
||||
command:
|
||||
- /bin/bash
|
||||
env:
|
||||
- name: TOTAL_CHAOS_DURATION
|
||||
value: '60'
|
||||
|
||||
# Period to wait before and after injection of chaos in sec
|
||||
- name: RAMP_TIME
|
||||
value: ''
|
||||
|
||||
## ENTER THE NUMBER OF CORES OF CPU FOR CPU HOGGING
|
||||
## OPTIONAL VALUE IN CASE OF EMPTY VALUE IT WILL TAKE NODE CPU CAPACITY
|
||||
- name: NODE_CPU_CORE
|
||||
value: ''
|
||||
|
||||
## LOAD CPU WITH GIVEN PERCENT LOADING FOR THE CPU STRESS WORKERS.
|
||||
## 0 IS EFFECTIVELY A SLEEP (NO LOAD) AND 100 IS FULL LOADING
|
||||
- name: CPU_LOAD
|
||||
value: '100'
|
||||
|
||||
# ENTER THE COMMA SEPARATED TARGET NODES NAME
|
||||
- name: TARGET_NODES
|
||||
value: ''
|
||||
|
||||
- name: NODE_LABEL
|
||||
value: ''
|
||||
|
||||
# provide lib image
|
||||
- name: LIB_IMAGE
|
||||
value: 'chaosnative/go-runner:ci'
|
||||
|
||||
## percentage of total nodes to target
|
||||
- name: NODES_AFFECTED_PERC
|
||||
value: ''
|
||||
|
||||
- name: DEFAULT_HEALTH_CHECK
|
||||
value: 'false'
|
||||
|
||||
## 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: ci
|
||||
@@ -0,0 +1,37 @@
|
||||
---
|
||||
apiVersion: litmuschaos.io/v1alpha1
|
||||
kind: ChartServiceVersion
|
||||
metadata:
|
||||
name: node-cpu-hog
|
||||
version: 0.1.0
|
||||
annotations:
|
||||
categories: Kubernetes
|
||||
vendor: Harness
|
||||
spec:
|
||||
displayName: Node CPU Hog
|
||||
categoryDescription: |
|
||||
Node CPU hog fault disrupts the state of Kubernetes resources. This fault injects a CPU spike on a node where the application pod is scheduled.
|
||||
- CPU hog on a particular node where the application deployment is available.
|
||||
- After test, the recovery should be manual for the application pod and node in case they are not in an appropriate state.
|
||||
keywords:
|
||||
- Kubernetes
|
||||
platforms:
|
||||
- GKE
|
||||
- EKS
|
||||
- AKS
|
||||
- Kind
|
||||
- Rancher
|
||||
- OpenShift(OKD)
|
||||
experiments:
|
||||
- node-cpu-hog
|
||||
chaosType: infra
|
||||
minKubeVersion: 1.12.0
|
||||
labels:
|
||||
app.kubernetes.io/component: chartserviceversion
|
||||
app.kubernetes.io/version: ci
|
||||
links:
|
||||
- name: Documentation
|
||||
url: https://docs.harness.io/category/kl0mxwpfw1-hce-category
|
||||
icon:
|
||||
- url:
|
||||
mediatype: ""
|
||||
26
faults/kubernetes/node-drain/engine.yaml
Normal file
26
faults/kubernetes/node-drain/engine.yaml
Normal file
@@ -0,0 +1,26 @@
|
||||
---
|
||||
apiVersion: litmuschaos.io/v1alpha1
|
||||
kind: ChaosEngine
|
||||
metadata:
|
||||
name: nginx-chaos
|
||||
namespace: default
|
||||
spec:
|
||||
# It can be active/stop
|
||||
engineState: 'active'
|
||||
#ex. values: ns1:name=percona,ns2:run=nginx
|
||||
auxiliaryAppInfo: ''
|
||||
chaosServiceAccount: node-drain-sa
|
||||
experiments:
|
||||
- name: node-drain
|
||||
spec:
|
||||
components:
|
||||
# nodeSelector:
|
||||
# # provide the node labels
|
||||
# kubernetes.io/hostname: 'node02'
|
||||
env:
|
||||
- name: TOTAL_CHAOS_DURATION
|
||||
value: '60'
|
||||
|
||||
# enter the target node name
|
||||
- name: TARGET_NODE
|
||||
value: ''
|
||||
82
faults/kubernetes/node-drain/fault.yaml
Normal file
82
faults/kubernetes/node-drain/fault.yaml
Normal file
@@ -0,0 +1,82 @@
|
||||
---
|
||||
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: ci
|
||||
spec:
|
||||
definition:
|
||||
scope: Cluster
|
||||
permissions:
|
||||
# Create and monitor the experiment & helper pods
|
||||
- apiGroups: [""]
|
||||
resources: ["pods"]
|
||||
verbs: ["create", "delete", "get", "list", "patch", "update", "deletecollection"]
|
||||
# Performs CRUD operations on the events inside chaosengine and chaosresult
|
||||
- apiGroups: [""]
|
||||
resources: ["events"]
|
||||
verbs: ["create", "get", "list", "patch", "update"]
|
||||
# Fetch configmaps details and mount it to the experiment pod (if specified)
|
||||
- apiGroups: [""]
|
||||
resources: ["configmaps"]
|
||||
verbs: ["get", "list"]
|
||||
# Track and get the runner, experiment, and helper pods log
|
||||
- apiGroups: [""]
|
||||
resources: ["pods/log"]
|
||||
verbs: ["get", "list", "watch"]
|
||||
# for creating and managing to execute commands inside target container
|
||||
- apiGroups: [""]
|
||||
resources: ["pods/exec", "pods/eviction"]
|
||||
verbs: ["get", "list", "create"]
|
||||
# ignore daemonsets while draining the node
|
||||
- apiGroups: ["apps"]
|
||||
resources: ["daemonsets"]
|
||||
verbs: ["list", "get", "delete"]
|
||||
# for configuring and monitor the experiment job by the chaos-runner pod
|
||||
- apiGroups: ["batch"]
|
||||
resources: ["jobs"]
|
||||
verbs: ["create", "list", "get", "delete", "deletecollection"]
|
||||
# for creation, status polling and deletion of litmus chaos resources used within a chaos workflow
|
||||
- apiGroups: ["litmuschaos.io"]
|
||||
resources: ["chaosengines", "chaosexperiments", "chaosresults"]
|
||||
verbs: ["create", "list", "get", "patch", "update", "delete"]
|
||||
# for experiment to perform node status checks
|
||||
- apiGroups: [""]
|
||||
resources: ["nodes"]
|
||||
verbs: ["get", "list", "patch"]
|
||||
image: "chaosnative/go-runner:ci"
|
||||
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'
|
||||
|
||||
# Period to wait before and after injection of chaos in sec
|
||||
- name: RAMP_TIME
|
||||
value: ''
|
||||
|
||||
- name: DEFAULT_HEALTH_CHECK
|
||||
value: 'false'
|
||||
|
||||
labels:
|
||||
name: node-drain
|
||||
app.kubernetes.io/part-of: litmus
|
||||
app.kubernetes.io/component: experiment-job
|
||||
app.kubernetes.io/version: ci
|
||||
@@ -0,0 +1,33 @@
|
||||
---
|
||||
apiVersion: litmuschaos.io/v1alpha1
|
||||
kind: ChartServiceVersion
|
||||
metadata:
|
||||
name: node-drain
|
||||
version: 0.1.0
|
||||
annotations:
|
||||
categories: Kubernetes
|
||||
vendor: Harness
|
||||
spec:
|
||||
displayName: Node Drain
|
||||
categoryDescription: >
|
||||
Drain the node where application pod is scheduled.
|
||||
keywords:
|
||||
- Kubernetes
|
||||
platforms:
|
||||
- GKE
|
||||
- AWS(KOPS)
|
||||
- Packet(Kubeadm)
|
||||
- Konvoy
|
||||
- EKS
|
||||
- AKS
|
||||
chaosType: infra
|
||||
minKubeVersion: 1.12.0
|
||||
labels:
|
||||
app.kubernetes.io/component: chartserviceversion
|
||||
app.kubernetes.io/version: ci
|
||||
links:
|
||||
- name: Documentation
|
||||
url: https://docs.harness.io/category/kl0mxwpfw1-hce-category
|
||||
icon:
|
||||
- url: ""
|
||||
mediatype: ""
|
||||
40
faults/kubernetes/node-io-stress/engine.yaml
Normal file
40
faults/kubernetes/node-io-stress/engine.yaml
Normal file
@@ -0,0 +1,40 @@
|
||||
---
|
||||
apiVersion: litmuschaos.io/v1alpha1
|
||||
kind: ChaosEngine
|
||||
metadata:
|
||||
name: nginx-chaos
|
||||
namespace: default
|
||||
spec:
|
||||
# It can be active/stop
|
||||
engineState: 'active'
|
||||
#ex. values: ns1:name=percona,ns2:run=nginx
|
||||
auxiliaryAppInfo: ''
|
||||
chaosServiceAccount: node-io-stress-sa
|
||||
experiments:
|
||||
- name: node-io-stress
|
||||
spec:
|
||||
components:
|
||||
env:
|
||||
# set chaos duration (in sec) as desired
|
||||
- name: TOTAL_CHAOS_DURATION
|
||||
value: '120'
|
||||
|
||||
## specify the size as percentage of free space on the file system
|
||||
- name: FILESYSTEM_UTILIZATION_PERCENTAGE
|
||||
value: '10'
|
||||
|
||||
## Number of core of CPU
|
||||
- name: CPU
|
||||
value: '1'
|
||||
|
||||
## Total number of workers default value is 4
|
||||
- name: NUMBER_OF_WORKERS
|
||||
value: '4'
|
||||
|
||||
## percentage of total nodes to target
|
||||
- name: NODES_AFFECTED_PERC
|
||||
value: ''
|
||||
|
||||
# provide the comma separated target node names
|
||||
- name: TARGET_NODES
|
||||
value: ''
|
||||
114
faults/kubernetes/node-io-stress/fault.yaml
Normal file
114
faults/kubernetes/node-io-stress/fault.yaml
Normal file
@@ -0,0 +1,114 @@
|
||||
---
|
||||
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: ci
|
||||
spec:
|
||||
definition:
|
||||
scope: Cluster
|
||||
permissions:
|
||||
# Create and monitor the experiment & helper pods
|
||||
- apiGroups: [""]
|
||||
resources: ["pods"]
|
||||
verbs: ["create", "delete", "get", "list", "patch", "update", "deletecollection"]
|
||||
# Performs CRUD operations on the events inside chaosengine and chaosresult
|
||||
- apiGroups: [""]
|
||||
resources: ["events"]
|
||||
verbs: ["create", "get", "list", "patch", "update"]
|
||||
# Fetch configmaps details and mount it to the experiment pod (if specified)
|
||||
- apiGroups: [""]
|
||||
resources: ["configmaps"]
|
||||
verbs: ["get", "list"]
|
||||
# Track and get the runner, experiment, and helper pods log
|
||||
- apiGroups: [""]
|
||||
resources: ["pods/log"]
|
||||
verbs: ["get", "list", "watch"]
|
||||
# for creating and managing to execute commands inside target container
|
||||
- apiGroups: [""]
|
||||
resources: ["pods/exec"]
|
||||
verbs: ["get", "list", "create"]
|
||||
# for configuring and monitor the experiment job by the chaos-runner pod
|
||||
- apiGroups: ["batch"]
|
||||
resources: ["jobs"]
|
||||
verbs: ["create", "list", "get", "delete", "deletecollection"]
|
||||
# for creation, status polling and deletion of litmus chaos resources used within a chaos workflow
|
||||
- apiGroups: ["litmuschaos.io"]
|
||||
resources: ["chaosengines", "chaosexperiments", "chaosresults"]
|
||||
verbs: ["create", "list", "get", "patch", "update", "delete"]
|
||||
# for experiment to perform node status checks
|
||||
- apiGroups: [""]
|
||||
resources: ["nodes"]
|
||||
verbs: ["get", "list"]
|
||||
image: "chaosnative/go-runner:ci"
|
||||
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 lib image
|
||||
- name: LIB_IMAGE
|
||||
value: 'chaosnative/go-runner:ci'
|
||||
|
||||
## percentage of total nodes to target
|
||||
- name: NODES_AFFECTED_PERC
|
||||
value: ''
|
||||
|
||||
- name: DEFAULT_HEALTH_CHECK
|
||||
value: 'false'
|
||||
|
||||
## 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: ci
|
||||
@@ -0,0 +1,32 @@
|
||||
---
|
||||
apiVersion: litmuschaos.io/v1alpha1
|
||||
kind: ChartServiceVersion
|
||||
metadata:
|
||||
name: node-io-stress
|
||||
version: 0.1.0
|
||||
annotations:
|
||||
categories: Kubernetes
|
||||
vendor: Harness
|
||||
spec:
|
||||
displayName: Node IO Stress
|
||||
categoryDescription: |
|
||||
This fault causes disk stress on the Kubernetes node. This fault aims to verify the resiliency of applications that share this disk resource for ephemeral or persistent storage purposes..
|
||||
- Disk stress on a particular node filesystem where the application deployment is available.
|
||||
- The amount of disk stress can be either specifed as the size in percentage of the total free space on the file system or simply in Gigabytes(GB)
|
||||
keywords:
|
||||
- Kubernetes
|
||||
platforms:
|
||||
- GKE
|
||||
- EKS
|
||||
- AKS
|
||||
chaosType: infra
|
||||
minKubeVersion: 1.12.0
|
||||
labels:
|
||||
app.kubernetes.io/component: chartserviceversion
|
||||
app.kubernetes.io/version: ci
|
||||
links:
|
||||
- name: Documentation
|
||||
url: https://docs.harness.io/category/kl0mxwpfw1-hce-category
|
||||
icon:
|
||||
- url: ""
|
||||
mediatype: ""
|
||||
38
faults/kubernetes/node-memory-hog/engine.yaml
Normal file
38
faults/kubernetes/node-memory-hog/engine.yaml
Normal file
@@ -0,0 +1,38 @@
|
||||
---
|
||||
apiVersion: litmuschaos.io/v1alpha1
|
||||
kind: ChaosEngine
|
||||
metadata:
|
||||
name: nginx-chaos
|
||||
namespace: default
|
||||
spec:
|
||||
# It can be active/stop
|
||||
engineState: 'active'
|
||||
#ex. values: ns1:name=percona,ns2:run=nginx
|
||||
auxiliaryAppInfo: ''
|
||||
chaosServiceAccount: node-memory-hog-sa
|
||||
experiments:
|
||||
- name: node-memory-hog
|
||||
spec:
|
||||
components:
|
||||
env:
|
||||
# set chaos duration (in sec) as desired
|
||||
- name: TOTAL_CHAOS_DURATION
|
||||
value: '120'
|
||||
|
||||
## percentage of total nodes to target
|
||||
- name: NODES_AFFECTED_PERC
|
||||
value: ''
|
||||
|
||||
# provide the comma separated target node names
|
||||
- name: TARGET_NODES
|
||||
value: ''
|
||||
|
||||
## 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: '0'
|
||||
|
||||
## 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: '0'
|
||||
105
faults/kubernetes/node-memory-hog/fault.yaml
Normal file
105
faults/kubernetes/node-memory-hog/fault.yaml
Normal file
@@ -0,0 +1,105 @@
|
||||
---
|
||||
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: ci
|
||||
spec:
|
||||
definition:
|
||||
scope: Cluster
|
||||
permissions:
|
||||
# Create and monitor the experiment & helper pods
|
||||
- apiGroups: [""]
|
||||
resources: ["pods"]
|
||||
verbs: ["create", "delete", "get", "list", "patch", "update", "deletecollection"]
|
||||
# Performs CRUD operations on the events inside chaosengine and chaosresult
|
||||
- apiGroups: [""]
|
||||
resources: ["events"]
|
||||
verbs: ["create", "get", "list", "patch", "update"]
|
||||
# Fetch configmaps details and mount it to the experiment pod (if specified)
|
||||
- apiGroups: [""]
|
||||
resources: ["configmaps"]
|
||||
verbs: ["get", "list"]
|
||||
# Track and get the runner, experiment, and helper pods log
|
||||
- apiGroups: [""]
|
||||
resources: ["pods/log"]
|
||||
verbs: ["get", "list", "watch"]
|
||||
# for creating and managing to execute commands inside target container
|
||||
- apiGroups: [""]
|
||||
resources: ["pods/exec"]
|
||||
verbs: ["get", "list", "create"]
|
||||
# for configuring and monitor the experiment job by the chaos-runner pod
|
||||
- apiGroups: ["batch"]
|
||||
resources: ["jobs"]
|
||||
verbs: ["create", "list", "get", "delete", "deletecollection"]
|
||||
# for creation, status polling and deletion of litmus chaos resources used within a chaos workflow
|
||||
- apiGroups: ["litmuschaos.io"]
|
||||
resources: ["chaosengines", "chaosexperiments", "chaosresults"]
|
||||
verbs: ["create", "list", "get", "patch", "update", "delete"]
|
||||
# for experiment to perform node status checks
|
||||
- apiGroups: [""]
|
||||
resources: ["nodes"]
|
||||
verbs: ["get", "list"]
|
||||
image: "chaosnative/go-runner:ci"
|
||||
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 lib image
|
||||
- name: LIB_IMAGE
|
||||
value: 'chaosnative/go-runner:ci'
|
||||
|
||||
- name: DEFAULT_HEALTH_CHECK
|
||||
value: 'false'
|
||||
|
||||
## 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: ci
|
||||
@@ -0,0 +1,37 @@
|
||||
---
|
||||
apiVersion: litmuschaos.io/v1alpha1
|
||||
kind: ChartServiceVersion
|
||||
metadata:
|
||||
name: node-memory-hog
|
||||
version: 0.1.0
|
||||
annotations:
|
||||
categories: Kubernetes
|
||||
vendor: Harness
|
||||
spec:
|
||||
displayName: Node Memory Hog
|
||||
categoryDescription: |
|
||||
Kubernetes Node memory hog fault disrupts the state of Kubernetes resources. This fault injects a memory spike on a node where the application pod is scheduled.
|
||||
- Memory hog on a particular node where the application deployment is available.
|
||||
- After the test, the recovery should be manual for the application pod and node in case they are not in an appropriate state.
|
||||
keywords:
|
||||
- Kubernetes
|
||||
platforms:
|
||||
- GKE
|
||||
- EKS
|
||||
- AKS
|
||||
- Kind
|
||||
- Rancher
|
||||
- OpenShift(OKD)
|
||||
experiments:
|
||||
- node-memory-hog
|
||||
chaosType: infra
|
||||
minKubeVersion: 1.12.0
|
||||
labels:
|
||||
app.kubernetes.io/component: chartserviceversion
|
||||
app.kubernetes.io/version: ci
|
||||
links:
|
||||
- name: Documentation
|
||||
url: https://docs.harness.io/category/kl0mxwpfw1-hce-category
|
||||
icon:
|
||||
- url: ""
|
||||
mediatype: ""
|
||||
33
faults/kubernetes/node-poweroff/engine.yaml
Normal file
33
faults/kubernetes/node-poweroff/engine.yaml
Normal file
@@ -0,0 +1,33 @@
|
||||
apiVersion: litmuschaos.io/v1alpha1
|
||||
kind: ChaosEngine
|
||||
metadata:
|
||||
name: nginx-chaos
|
||||
namespace: default
|
||||
spec:
|
||||
# It can be active/stop
|
||||
engineState: 'active'
|
||||
#ex. values: ns1:name=percona,ns2:run=nginx
|
||||
auxiliaryAppInfo: ''
|
||||
chaosServiceAccount: node-poweroff-sa
|
||||
experiments:
|
||||
- name: node-poweroff
|
||||
spec:
|
||||
components:
|
||||
# nodeSelector:
|
||||
# # provide the node labels
|
||||
# kubernetes.io/hostname: 'node02'
|
||||
env:
|
||||
- name: TOTAL_CHAOS_DURATION
|
||||
value: '60'
|
||||
|
||||
# ENTER THE TARGET NODE NAME
|
||||
- name: TARGET_NODE
|
||||
value: ''
|
||||
|
||||
# ENTER THE TARGET NODE IP
|
||||
- name: TARGET_NODE_IP
|
||||
value: ''
|
||||
|
||||
# ENTER THE USER TO BE USED FOR SSH AUTH
|
||||
- name: SSH_USER
|
||||
value: 'root'
|
||||
93
faults/kubernetes/node-poweroff/fault.yaml
Normal file
93
faults/kubernetes/node-poweroff/fault.yaml
Normal file
@@ -0,0 +1,93 @@
|
||||
---
|
||||
apiVersion: litmuschaos.io/v1alpha1
|
||||
description:
|
||||
message: |
|
||||
Poweroff a node in the cluster
|
||||
kind: ChaosExperiment
|
||||
metadata:
|
||||
name: node-poweroff
|
||||
labels:
|
||||
name: node-poweroff
|
||||
app.kubernetes.io/part-of: litmus
|
||||
app.kubernetes.io/component: chaosexperiment
|
||||
app.kubernetes.io/version: latest
|
||||
spec:
|
||||
definition:
|
||||
scope: Cluster
|
||||
permissions:
|
||||
# Create and monitor the experiment & helper pods
|
||||
- apiGroups: [""]
|
||||
resources: ["pods"]
|
||||
verbs: ["create","delete","get","list","patch","update", "deletecollection"]
|
||||
# Performs CRUD operations on the events inside chaosengine and chaosresult
|
||||
- apiGroups: [""]
|
||||
resources: ["events"]
|
||||
verbs: ["create","get","list","patch","update"]
|
||||
# Fetch configmaps & secrets details and mount it to the experiment pod (if specified)
|
||||
- apiGroups: [""]
|
||||
resources: ["configmaps","secrets"]
|
||||
verbs: ["get","list",]
|
||||
# Track and get the runner, experiment, and helper pods log
|
||||
- apiGroups: [""]
|
||||
resources: ["pods/log"]
|
||||
verbs: ["get","list","watch"]
|
||||
# for creating and managing to execute comands inside target container
|
||||
- apiGroups: [""]
|
||||
resources: ["pods/exec"]
|
||||
verbs: ["get","list","create"]
|
||||
# for configuring and monitor the experiment job by the chaos-runner pod
|
||||
- apiGroups: ["batch"]
|
||||
resources: ["jobs"]
|
||||
verbs: ["create","list","get","delete","deletecollection"]
|
||||
# for creation, status polling and deletion of litmus chaos resources used within a chaos workflow
|
||||
- apiGroups: ["litmuschaos.io"]
|
||||
resources: ["chaosengines","chaosexperiments","chaosresults"]
|
||||
verbs: ["create","list","get","patch","update","delete"]
|
||||
# for experiment to perform node status checks
|
||||
- apiGroups: [""]
|
||||
resources: ["nodes"]
|
||||
verbs: ["get","list"]
|
||||
image: "litmuschaos/go-runner:latest"
|
||||
imagePullPolicy: Always
|
||||
args:
|
||||
- -c
|
||||
- ./experiments -name node-restart
|
||||
command:
|
||||
- /bin/bash
|
||||
env:
|
||||
- name: SSH_USER
|
||||
value: 'root'
|
||||
|
||||
- name: TOTAL_CHAOS_DURATION
|
||||
value: '60'
|
||||
|
||||
- name: REBOOT_COMMAND
|
||||
value: '-o ServerAliveInterval=1 -o ServerAliveCountMax=1 "sudo systemctl poweroff --force --force" ; true'
|
||||
|
||||
# Period to wait before and after injection of chaos in sec
|
||||
- name: RAMP_TIME
|
||||
value: ''
|
||||
|
||||
# provide 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/
|
||||
@@ -0,0 +1,29 @@
|
||||
---
|
||||
apiVersion: litmuschaos.io/v1alpha1
|
||||
kind: ChartServiceVersion
|
||||
metadata:
|
||||
name: node-poweroff
|
||||
version: 0.1.0
|
||||
annotations:
|
||||
categories: Kubernetes
|
||||
vendor: Harness
|
||||
spec:
|
||||
displayName: Node Poweroff
|
||||
categoryDescription: |
|
||||
Node poweroff contains chaos experiment to poweroff a node via SSH.
|
||||
keywords:
|
||||
- Kubernetes
|
||||
platforms:
|
||||
- KVM/LibVirt based K8s
|
||||
- EKS
|
||||
chaosType: infra
|
||||
minKubeVersion: 1.12.0
|
||||
labels:
|
||||
app.kubernetes.io/component: chartserviceversion
|
||||
app.kubernetes.io/version: ci
|
||||
links:
|
||||
- name: Documentation
|
||||
url: https://docs.harness.io/category/kl0mxwpfw1-hce-category
|
||||
icon:
|
||||
- url: ""
|
||||
mediatype: ""
|
||||
37
faults/kubernetes/node-restart/engine.yaml
Normal file
37
faults/kubernetes/node-restart/engine.yaml
Normal file
@@ -0,0 +1,37 @@
|
||||
---
|
||||
apiVersion: litmuschaos.io/v1alpha1
|
||||
kind: ChaosEngine
|
||||
metadata:
|
||||
name: nginx-chaos
|
||||
namespace: default
|
||||
spec:
|
||||
# It can be active/stop
|
||||
engineState: 'active'
|
||||
#ex. values: ns1:name=percona,ns2:run=nginx
|
||||
auxiliaryAppInfo: ''
|
||||
chaosServiceAccount: litmus-admin
|
||||
experiments:
|
||||
- name: node-restart
|
||||
spec:
|
||||
components:
|
||||
# nodeSelector:
|
||||
# # provide the node labels
|
||||
# kubernetes.io/hostname: 'node02'
|
||||
env:
|
||||
- name: TOTAL_CHAOS_DURATION
|
||||
value: '60'
|
||||
|
||||
# ENTER THE TARGET NODE NAME
|
||||
- name: TARGET_NODE
|
||||
value: ''
|
||||
|
||||
# ENTER THE TARGET NODE IP
|
||||
- name: TARGET_NODE_IP
|
||||
value: ''
|
||||
|
||||
# ENTER THE USER TO BE USED FOR SSH AUTH
|
||||
- name: SSH_USER
|
||||
value: 'root'
|
||||
|
||||
- name: REBOOT_COMMAND
|
||||
value: 'sudo systemctl reboot; true'
|
||||
95
faults/kubernetes/node-restart/fault.yaml
Normal file
95
faults/kubernetes/node-restart/fault.yaml
Normal file
@@ -0,0 +1,95 @@
|
||||
---
|
||||
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: ci
|
||||
spec:
|
||||
definition:
|
||||
scope: Cluster
|
||||
permissions:
|
||||
# Create and monitor the experiment & helper pods
|
||||
- apiGroups: [""]
|
||||
resources: ["pods"]
|
||||
verbs: ["create", "delete", "get", "list", "patch", "update", "deletecollection"]
|
||||
# Performs CRUD operations on the events inside chaosengine and chaosresult
|
||||
- apiGroups: [""]
|
||||
resources: ["events"]
|
||||
verbs: ["create", "get", "list", "patch", "update"]
|
||||
# Fetch configmaps & secrets details and mount it to the experiment pod (if specified)
|
||||
- apiGroups: [""]
|
||||
resources: ["configmaps", "secrets"]
|
||||
verbs: ["get", "list"]
|
||||
# Track and get the runner, experiment, and helper pods log
|
||||
- apiGroups: [""]
|
||||
resources: ["pods/log"]
|
||||
verbs: ["get", "list", "watch"]
|
||||
# for creating and managing to execute commands inside target container
|
||||
- apiGroups: [""]
|
||||
resources: ["pods/exec"]
|
||||
verbs: ["get", "list", "create"]
|
||||
# for configuring and monitor the experiment job by the chaos-runner pod
|
||||
- apiGroups: ["batch"]
|
||||
resources: ["jobs"]
|
||||
verbs: ["create", "list", "get", "delete", "deletecollection"]
|
||||
# for creation, status polling and deletion of litmus chaos resources used within a chaos workflow
|
||||
- apiGroups: ["litmuschaos.io"]
|
||||
resources: ["chaosengines", "chaosexperiments", "chaosresults"]
|
||||
verbs: ["create", "list", "get", "patch", "update", "delete"]
|
||||
# for experiment to perform node status checks
|
||||
- apiGroups: [""]
|
||||
resources: ["nodes"]
|
||||
verbs: ["get", "list"]
|
||||
image: "chaosnative/go-runner:ci"
|
||||
imagePullPolicy: Always
|
||||
args:
|
||||
- -c
|
||||
- ./experiments -name node-restart
|
||||
command:
|
||||
- /bin/bash
|
||||
env:
|
||||
- name: SSH_USER
|
||||
value: 'root'
|
||||
- name: REBOOT_COMMAND
|
||||
value: 'sudo systemctl reboot; true'
|
||||
|
||||
- name: TOTAL_CHAOS_DURATION
|
||||
value: '60'
|
||||
|
||||
# Period to wait before and after injection of chaos in sec
|
||||
- name: RAMP_TIME
|
||||
value: ''
|
||||
|
||||
# provide lib image
|
||||
- name: LIB_IMAGE
|
||||
value: "chaosnative/go-runner:ci"
|
||||
|
||||
# ENTER THE TARGET NODE NAME
|
||||
- name: TARGET_NODE
|
||||
value: ''
|
||||
|
||||
- name: NODE_LABEL
|
||||
value: ''
|
||||
|
||||
# ENTER THE TARGET NODE IP
|
||||
- name: TARGET_NODE_IP
|
||||
value: ''
|
||||
|
||||
- name: DEFAULT_HEALTH_CHECK
|
||||
value: 'false'
|
||||
|
||||
labels:
|
||||
name: node-restart
|
||||
app.kubernetes.io/part-of: litmus
|
||||
app.kubernetes.io/component: experiment-job
|
||||
app.kubernetes.io/version: ci
|
||||
secrets:
|
||||
- name: id-rsa
|
||||
mountPath: /mnt/
|
||||
@@ -0,0 +1,25 @@
|
||||
---
|
||||
apiVersion: litmuschaos.io/v1alpha1
|
||||
kind: ChartServiceVersion
|
||||
metadata:
|
||||
name: node-restart
|
||||
version: 0.1.0
|
||||
annotations:
|
||||
categories: Kubernetes
|
||||
spec:
|
||||
displayName: Node Restart
|
||||
categoryDescription: |
|
||||
Node restart fault restarts a target node via SSH.
|
||||
keywords:
|
||||
- Kubernetes
|
||||
platforms:
|
||||
- KVM/LibVirt based K8s
|
||||
- EKS
|
||||
chaosType: infra
|
||||
minKubeVersion: 1.12.0
|
||||
links:
|
||||
- name: Documentation
|
||||
url: https://docs.harness.io/category/kl0mxwpfw1-hce-category
|
||||
icon:
|
||||
- url:
|
||||
mediatype: ""
|
||||
31
faults/kubernetes/node-taint/engine.yaml
Normal file
31
faults/kubernetes/node-taint/engine.yaml
Normal file
@@ -0,0 +1,31 @@
|
||||
---
|
||||
apiVersion: litmuschaos.io/v1alpha1
|
||||
kind: ChaosEngine
|
||||
metadata:
|
||||
name: nginx-chaos
|
||||
namespace: default
|
||||
spec:
|
||||
# It can be active/stop
|
||||
engineState: 'active'
|
||||
#ex. values: ns1:name=percona,ns2:run=nginx
|
||||
auxiliaryAppInfo: ''
|
||||
chaosServiceAccount: node-taint-sa
|
||||
experiments:
|
||||
- name: node-taint
|
||||
spec:
|
||||
components:
|
||||
# nodeSelector:
|
||||
# # provide the node labels
|
||||
# kubernetes.io/hostname: 'node02'
|
||||
env:
|
||||
- name: TOTAL_CHAOS_DURATION
|
||||
value: '60'
|
||||
|
||||
# set target node name
|
||||
- name: TARGET_NODE
|
||||
value: ''
|
||||
|
||||
# set taint label & effect
|
||||
# key=value:effect or key:effect
|
||||
- name: TAINTS
|
||||
value: 'app.hce.io/chaos=true:NoSchedule'
|
||||
87
faults/kubernetes/node-taint/fault.yaml
Normal file
87
faults/kubernetes/node-taint/fault.yaml
Normal file
@@ -0,0 +1,87 @@
|
||||
---
|
||||
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: ci
|
||||
spec:
|
||||
definition:
|
||||
scope: Cluster
|
||||
permissions:
|
||||
# Create and monitor the experiment & helper pods
|
||||
- apiGroups: [""]
|
||||
resources: ["pods"]
|
||||
verbs: ["create", "delete", "get", "list", "patch", "update", "deletecollection"]
|
||||
# Performs CRUD operations on the events inside chaosengine and chaosresult
|
||||
- apiGroups: [""]
|
||||
resources: ["events"]
|
||||
verbs: ["create", "get", "list", "patch", "update"]
|
||||
# Fetch configmaps details and mount it to the experiment pod (if specified)
|
||||
- apiGroups: [""]
|
||||
resources: ["configmaps"]
|
||||
verbs: ["get", "list"]
|
||||
# Track and get the runner, experiment, and helper pods log
|
||||
- apiGroups: [""]
|
||||
resources: ["pods/log"]
|
||||
verbs: ["get", "list", "watch"]
|
||||
# for creating and managing to execute commands inside target container
|
||||
- apiGroups: [""]
|
||||
resources: ["pods/exec", "pods/eviction"]
|
||||
verbs: ["get", "list", "create"]
|
||||
# ignore daemonsets while draining the node
|
||||
- apiGroups: ["apps"]
|
||||
resources: ["daemonsets"]
|
||||
verbs: ["list", "get", "delete"]
|
||||
# for configuring and monitor the experiment job by the chaos-runner pod
|
||||
- apiGroups: ["batch"]
|
||||
resources: ["jobs"]
|
||||
verbs: ["create", "list", "get", "delete", "deletecollection"]
|
||||
# for creation, status polling and deletion of litmus chaos resources used within a chaos workflow
|
||||
- apiGroups: ["litmuschaos.io"]
|
||||
resources: ["chaosengines", "chaosexperiments", "chaosresults"]
|
||||
verbs: ["create", "list", "get", "patch", "update", "delete"]
|
||||
# for experiment to perform node status checks
|
||||
- apiGroups: [""]
|
||||
resources: ["nodes"]
|
||||
verbs: ["get", "list", "patch", "update"]
|
||||
image: "chaosnative/go-runner:ci"
|
||||
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'
|
||||
|
||||
# Period to wait before and after injection of chaos in sec
|
||||
- name: RAMP_TIME
|
||||
value: ''
|
||||
|
||||
# set taint label & effect
|
||||
# key=value:effect or key:effect
|
||||
- name: TAINTS
|
||||
value: ''
|
||||
|
||||
- name: DEFAULT_HEALTH_CHECK
|
||||
value: 'false'
|
||||
|
||||
labels:
|
||||
name: node-taint
|
||||
app.kubernetes.io/part-of: litmus
|
||||
app.kubernetes.io/component: experiment-job
|
||||
app.kubernetes.io/version: ci
|
||||
@@ -0,0 +1,33 @@
|
||||
---
|
||||
apiVersion: litmuschaos.io/v1alpha1
|
||||
kind: ChartServiceVersion
|
||||
metadata:
|
||||
name: node-taint
|
||||
version: 0.1.0
|
||||
annotations:
|
||||
categories: Kubernetes
|
||||
vendor: Harness
|
||||
spec:
|
||||
displayName: Node Taint
|
||||
categoryDescription: >
|
||||
Taint the node where application pod is scheduled.
|
||||
keywords:
|
||||
- Kubernetes
|
||||
platforms:
|
||||
- GKE
|
||||
- AWS(KOPS)
|
||||
- Packet(Kubeadm)
|
||||
- Konvoy
|
||||
- EKS
|
||||
- AKS
|
||||
chaosType: infra
|
||||
minKubeVersion: 1.12.0
|
||||
labels:
|
||||
app.kubernetes.io/component: chartserviceversion
|
||||
app.kubernetes.io/version: ci
|
||||
links:
|
||||
- name: Documentation
|
||||
url: https://docs.harness.io/category/kl0mxwpfw1-hce-category
|
||||
icon:
|
||||
- url: ""
|
||||
mediatype: ""
|
||||
29
faults/kubernetes/pod-autoscaler/engine.yaml
Normal file
29
faults/kubernetes/pod-autoscaler/engine.yaml
Normal file
@@ -0,0 +1,29 @@
|
||||
---
|
||||
apiVersion: litmuschaos.io/v1alpha1
|
||||
kind: ChaosEngine
|
||||
metadata:
|
||||
name: nginx-chaos
|
||||
namespace: default
|
||||
spec:
|
||||
# It can be active/stop
|
||||
engineState: 'active'
|
||||
#ex. values: ns1:name=percona,ns2:run=nginx
|
||||
auxiliaryAppInfo: ''
|
||||
appinfo:
|
||||
appns: ''
|
||||
applabel: ''
|
||||
appkind: ''
|
||||
chaosServiceAccount: pod-autoscaler-sa
|
||||
experiments:
|
||||
- name: pod-autoscaler
|
||||
spec:
|
||||
components:
|
||||
env:
|
||||
# set chaos duration (in sec) as desired
|
||||
- name: TOTAL_CHAOS_DURATION
|
||||
value: '60'
|
||||
|
||||
# number of replicas to scale
|
||||
- name: REPLICA_COUNT
|
||||
value: '5'
|
||||
|
||||
76
faults/kubernetes/pod-autoscaler/fault.yaml
Normal file
76
faults/kubernetes/pod-autoscaler/fault.yaml
Normal file
@@ -0,0 +1,76 @@
|
||||
---
|
||||
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: ci
|
||||
spec:
|
||||
definition:
|
||||
scope: Cluster
|
||||
permissions:
|
||||
# Create and monitor the experiment & helper pods
|
||||
- apiGroups: [""]
|
||||
resources: ["pods"]
|
||||
verbs: ["create", "delete", "get", "list", "patch", "update", "deletecollection"]
|
||||
# Performs CRUD operations on the events inside chaosengine and chaosresult
|
||||
- apiGroups: [""]
|
||||
resources: ["events"]
|
||||
verbs: ["create", "get", "list", "patch", "update"]
|
||||
# Fetch configmaps details and mount it to the experiment pod (if specified)
|
||||
- apiGroups: [""]
|
||||
resources: ["configmaps"]
|
||||
verbs: ["get", "list"]
|
||||
# Track and get the runner, experiment, and helper pods log
|
||||
- apiGroups: [""]
|
||||
resources: ["pods/log"]
|
||||
verbs: ["get", "list", "watch"]
|
||||
# for creating and managing to execute commands inside target container
|
||||
- apiGroups: [""]
|
||||
resources: ["pods/exec"]
|
||||
verbs: ["get", "list", "create"]
|
||||
# performs CRUD operations on the deployments and statefulsets
|
||||
- apiGroups: ["apps"]
|
||||
resources: ["deployments", "statefulsets"]
|
||||
verbs: ["list", "get", "patch", "update"]
|
||||
# for configuring and monitor the experiment job by the chaos-runner pod
|
||||
- apiGroups: ["batch"]
|
||||
resources: ["jobs"]
|
||||
verbs: ["create", "list", "get", "delete", "deletecollection"]
|
||||
# for creation, status polling and deletion of litmus chaos resources used within a chaos workflow
|
||||
- apiGroups: ["litmuschaos.io"]
|
||||
resources: ["chaosengines", "chaosexperiments", "chaosresults"]
|
||||
verbs: ["create", "list", "get", "patch", "update", "delete"]
|
||||
image: "chaosnative/go-runner:ci"
|
||||
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'
|
||||
|
||||
- name: DEFAULT_HEALTH_CHECK
|
||||
value: 'false'
|
||||
|
||||
labels:
|
||||
name: pod-autoscaler
|
||||
app.kubernetes.io/part-of: litmus
|
||||
app.kubernetes.io/component: experiment-job
|
||||
app.kubernetes.io/version: ci
|
||||
@@ -0,0 +1,32 @@
|
||||
---
|
||||
apiVersion: litmuschaos.io/v1alpha1
|
||||
kind: ChartServiceVersion
|
||||
metadata:
|
||||
name: pod-autoscaler
|
||||
version: 0.1.0
|
||||
annotations:
|
||||
categories: Kubernetes
|
||||
vendor: Harness
|
||||
spec:
|
||||
displayName: Pod Autoscaler
|
||||
categoryDescription: |
|
||||
This fault aims to check the ability of nodes to accommodate the number of replicas a given application pod.
|
||||
It can be used for other cases as well, such as for checking the Node auto-scaling feature. For example, check if the pods are successfully rescheduled within a specified period in cases where the existing nodes are already running at the specified limits.
|
||||
keywords:
|
||||
- Kubernetes
|
||||
platforms:
|
||||
- GKE
|
||||
- EKS
|
||||
- Minikube
|
||||
- AKS
|
||||
chaosType: infra
|
||||
minKubeVersion: 1.12.0
|
||||
labels:
|
||||
app.kubernetes.io/component: chartserviceversion
|
||||
app.kubernetes.io/version: ci
|
||||
links:
|
||||
- name: Documentation
|
||||
url: https://docs.harness.io/category/kl0mxwpfw1-hce-category
|
||||
icon:
|
||||
- url:
|
||||
mediatype: ""
|
||||
31
faults/kubernetes/pod-cpu-hog-exec/engine.yaml
Normal file
31
faults/kubernetes/pod-cpu-hog-exec/engine.yaml
Normal file
@@ -0,0 +1,31 @@
|
||||
---
|
||||
apiVersion: litmuschaos.io/v1alpha1
|
||||
kind: ChaosEngine
|
||||
metadata:
|
||||
name: nginx-chaos
|
||||
namespace: default
|
||||
spec:
|
||||
# It can be active/stop
|
||||
engineState: 'active'
|
||||
appinfo:
|
||||
appns: ''
|
||||
applabel: ''
|
||||
appkind: ''
|
||||
chaosServiceAccount: pod-cpu-hog-exec-sa
|
||||
experiments:
|
||||
- name: pod-cpu-hog-exec
|
||||
spec:
|
||||
components:
|
||||
env:
|
||||
- name: TOTAL_CHAOS_DURATION
|
||||
value: '60' # in seconds
|
||||
|
||||
#number of CPU cores to be consumed
|
||||
#verify the resources the app has been launched with
|
||||
- name: CPU_CORES
|
||||
value: '1'
|
||||
|
||||
## Percentage of total pods to target
|
||||
- name: PODS_AFFECTED_PERC
|
||||
value: ''
|
||||
|
||||
107
faults/kubernetes/pod-cpu-hog-exec/fault.yaml
Normal file
107
faults/kubernetes/pod-cpu-hog-exec/fault.yaml
Normal file
@@ -0,0 +1,107 @@
|
||||
---
|
||||
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: ci
|
||||
spec:
|
||||
definition:
|
||||
scope: Namespaced
|
||||
permissions:
|
||||
# Create and monitor the experiment & helper pods
|
||||
- apiGroups: [""]
|
||||
resources: ["pods"]
|
||||
verbs: ["create", "delete", "get", "list", "patch", "update", "deletecollection"]
|
||||
# Performs CRUD operations on the events inside chaosengine and chaosresult
|
||||
- apiGroups: [""]
|
||||
resources: ["events"]
|
||||
verbs: ["create", "get", "list", "patch", "update"]
|
||||
# Fetch configmaps details and mount it to the experiment pod (if specified)
|
||||
- apiGroups: [""]
|
||||
resources: ["configmaps"]
|
||||
verbs: ["get", "list"]
|
||||
# Track and get the runner, experiment, and helper pods log
|
||||
- apiGroups: [""]
|
||||
resources: ["pods/log"]
|
||||
verbs: ["get", "list", "watch"]
|
||||
# for creating and managing to execute commands inside target container
|
||||
- apiGroups: [""]
|
||||
resources: ["pods/exec"]
|
||||
verbs: ["get", "list", "create"]
|
||||
# deriving the parent/owner details of the pod(if parent is anyof {deployment, statefulset, daemonsets})
|
||||
- apiGroups: ["apps"]
|
||||
resources: ["deployments", "statefulsets", "replicasets", "daemonsets"]
|
||||
verbs: ["list", "get"]
|
||||
# deriving the parent/owner details of the pod(if parent is deploymentConfig)
|
||||
- apiGroups: ["apps.openshift.io"]
|
||||
resources: ["deploymentconfigs"]
|
||||
verbs: ["list", "get"]
|
||||
# deriving the parent/owner details of the pod(if parent is deploymentConfig)
|
||||
- apiGroups: [""]
|
||||
resources: ["replicationcontrollers"]
|
||||
verbs: ["get", "list"]
|
||||
# deriving the parent/owner details of the pod(if parent is argo-rollouts)
|
||||
- apiGroups: ["argoproj.io"]
|
||||
resources: ["rollouts"]
|
||||
verbs: ["list", "get"]
|
||||
# for configuring and monitor the experiment job by the chaos-runner pod
|
||||
- apiGroups: ["batch"]
|
||||
resources: ["jobs"]
|
||||
verbs: ["create", "list", "get", "delete", "deletecollection"]
|
||||
# for creation, status polling and deletion of litmus chaos resources used within a chaos workflow
|
||||
- apiGroups: ["litmuschaos.io"]
|
||||
resources: ["chaosengines", "chaosexperiments", "chaosresults"]
|
||||
verbs: ["create", "list", "get", "patch", "update", "delete"]
|
||||
image: "chaosnative/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: ''
|
||||
|
||||
# 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_CONTAINER
|
||||
value: ''
|
||||
|
||||
- name: TARGET_PODS
|
||||
value: ''
|
||||
|
||||
- name: DEFAULT_HEALTH_CHECK
|
||||
value: 'false'
|
||||
|
||||
## 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: ci
|
||||
@@ -0,0 +1,34 @@
|
||||
---
|
||||
apiVersion: litmuschaos.io/v1alpha1
|
||||
kind: ChartServiceVersion
|
||||
metadata:
|
||||
name: pod-cpu-hog-exec
|
||||
version: 0.1.0
|
||||
annotations:
|
||||
categories: Kubernetes
|
||||
vendor: Harness
|
||||
spec:
|
||||
displayName: Pod CPU Hog Exec
|
||||
categoryDescription: |
|
||||
pod-cpu-hog-exec fault consumes CPU resources of specified containers in Kubernetes pods.
|
||||
- Causes high CPU resource consumption utilizing one or more cores by triggering md5sum commands.
|
||||
- The application pod should be healthy once chaos is stopped. Expectation is that service-requests should be served despite chaos.
|
||||
keywords:
|
||||
- Kubernetes
|
||||
platforms:
|
||||
- GKE
|
||||
- Packet(Kubeadm)
|
||||
- Minikube
|
||||
- EKS
|
||||
- AKS
|
||||
- Kind
|
||||
minKubeVersion: 1.12.0
|
||||
labels:
|
||||
app.kubernetes.io/component: chartserviceversion
|
||||
app.kubernetes.io/version: ci
|
||||
links:
|
||||
- name: Documentation
|
||||
url: https://docs.harness.io/category/kl0mxwpfw1-hce-category
|
||||
icon:
|
||||
- base64data: ""
|
||||
mediatype: ""
|
||||
36
faults/kubernetes/pod-cpu-hog/engine.yaml
Normal file
36
faults/kubernetes/pod-cpu-hog/engine.yaml
Normal file
@@ -0,0 +1,36 @@
|
||||
---
|
||||
apiVersion: litmuschaos.io/v1alpha1
|
||||
kind: ChaosEngine
|
||||
metadata:
|
||||
name: nginx-chaos
|
||||
namespace: default
|
||||
spec:
|
||||
# It can be active/stop
|
||||
engineState: 'active'
|
||||
appinfo:
|
||||
appns: ''
|
||||
applabel: ''
|
||||
appkind: ''
|
||||
chaosServiceAccount: pod-cpu-hog-sa
|
||||
experiments:
|
||||
- name: pod-cpu-hog
|
||||
spec:
|
||||
components:
|
||||
env:
|
||||
- name: TOTAL_CHAOS_DURATION
|
||||
value: '60' # in seconds
|
||||
|
||||
- name: CPU_CORES
|
||||
value: '1'
|
||||
|
||||
## Percentage of total pods to target
|
||||
- name: PODS_AFFECTED_PERC
|
||||
value: ''
|
||||
|
||||
## provide the cluster runtime
|
||||
- name: CONTAINER_RUNTIME
|
||||
value: 'containerd'
|
||||
|
||||
# provide the socket file path
|
||||
- name: SOCKET_PATH
|
||||
value: '/run/containerd/containerd.sock'
|
||||
129
faults/kubernetes/pod-cpu-hog/fault.yaml
Normal file
129
faults/kubernetes/pod-cpu-hog/fault.yaml
Normal file
@@ -0,0 +1,129 @@
|
||||
---
|
||||
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: ci
|
||||
spec:
|
||||
definition:
|
||||
scope: Namespaced
|
||||
permissions:
|
||||
# Create and monitor the experiment & helper pods
|
||||
- apiGroups: [""]
|
||||
resources: ["pods"]
|
||||
verbs: ["create", "delete", "get", "list", "patch", "update", "deletecollection"]
|
||||
# Performs CRUD operations on the events inside chaosengine and chaosresult
|
||||
- apiGroups: [""]
|
||||
resources: ["events"]
|
||||
verbs: ["create", "get", "list", "patch", "update"]
|
||||
# Fetch configmaps details and mount it to the experiment pod (if specified)
|
||||
- apiGroups: [""]
|
||||
resources: ["configmaps"]
|
||||
verbs: ["get", "list"]
|
||||
# Track and get the runner, experiment, and helper pods log
|
||||
- apiGroups: [""]
|
||||
resources: ["pods/log"]
|
||||
verbs: ["get", "list", "watch"]
|
||||
# for creating and managing to execute commands inside target container
|
||||
- apiGroups: [""]
|
||||
resources: ["pods/exec"]
|
||||
verbs: ["get", "list", "create"]
|
||||
# deriving the parent/owner details of the pod(if parent is anyof {deployment, statefulset, daemonsets})
|
||||
- apiGroups: ["apps"]
|
||||
resources: ["deployments", "statefulsets", "replicasets", "daemonsets"]
|
||||
verbs: ["list", "get"]
|
||||
# deriving the parent/owner details of the pod(if parent is deploymentConfig)
|
||||
- apiGroups: ["apps.openshift.io"]
|
||||
resources: ["deploymentconfigs"]
|
||||
verbs: ["list", "get"]
|
||||
# deriving the parent/owner details of the pod(if parent is deploymentConfig)
|
||||
- apiGroups: [""]
|
||||
resources: ["replicationcontrollers"]
|
||||
verbs: ["get", "list"]
|
||||
# deriving the parent/owner details of the pod(if parent is argo-rollouts)
|
||||
- apiGroups: ["argoproj.io"]
|
||||
resources: ["rollouts"]
|
||||
verbs: ["list", "get"]
|
||||
# for configuring and monitor the experiment job by the chaos-runner pod
|
||||
- apiGroups: ["batch"]
|
||||
resources: ["jobs"]
|
||||
verbs: ["create", "list", "get", "delete", "deletecollection"]
|
||||
# for creation, status polling and deletion of litmus chaos resources used within a chaos workflow
|
||||
- apiGroups: ["litmuschaos.io"]
|
||||
resources: ["chaosengines", "chaosexperiments", "chaosresults"]
|
||||
verbs: ["create", "list", "get", "patch", "update", "delete"]
|
||||
image: "chaosnative/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'
|
||||
|
||||
## LOAD CPU WITH GIVEN PERCENT LOADING FOR THE CPU STRESS WORKERS.
|
||||
## 0 IS EFFECTIVELY A SLEEP (NO LOAD) AND 100 IS FULL LOADING
|
||||
- name: CPU_LOAD
|
||||
value: '100'
|
||||
|
||||
## Percentage of total pods to target
|
||||
- name: PODS_AFFECTED_PERC
|
||||
value: ''
|
||||
|
||||
## Period to wait before and after injection of chaos in sec
|
||||
- name: RAMP_TIME
|
||||
value: ''
|
||||
|
||||
## It is used in pumba lib only
|
||||
- name: LIB_IMAGE
|
||||
value: 'chaosnative/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: 'containerd'
|
||||
|
||||
# provide the socket file path
|
||||
- name: SOCKET_PATH
|
||||
value: '/run/containerd/containerd.sock'
|
||||
|
||||
- name: TARGET_CONTAINER
|
||||
value: ''
|
||||
|
||||
- name: TARGET_PODS
|
||||
value: ''
|
||||
|
||||
- name: DEFAULT_HEALTH_CHECK
|
||||
value: 'false'
|
||||
|
||||
# To select pods on specific node(s)
|
||||
- name: NODE_LABEL
|
||||
value: ''
|
||||
|
||||
## it defines the sequence of chaos execution for multiple target pods
|
||||
## supported values: serial, parallel
|
||||
- name: SEQUENCE
|
||||
value: 'parallel'
|
||||
|
||||
labels:
|
||||
name: pod-cpu-hog
|
||||
app.kubernetes.io/part-of: litmus
|
||||
app.kubernetes.io/component: experiment-job
|
||||
app.kubernetes.io/runtime-api-usage: "true"
|
||||
app.kubernetes.io/version: ci
|
||||
@@ -0,0 +1,39 @@
|
||||
---
|
||||
apiVersion: litmuschaos.io/v1alpha1
|
||||
kind: ChartServiceVersion
|
||||
metadata:
|
||||
name: pod-cpu-hog
|
||||
version: 0.1.0
|
||||
annotations:
|
||||
categories: Kubernetes
|
||||
vendor: Harness
|
||||
spec:
|
||||
displayName: Pod CPU Hog
|
||||
categoryDescription: |
|
||||
Pod-CPU-Hog fault consumes the CPU resources of specified containers in Kubernetes pods.
|
||||
- Causes CPU resource consumption on specified application containers using cgroups and litmus nsutil which consume CPU resources of the given target containers.
|
||||
- It can test the application's resilience to potential slowness/unavailability of some replicas due to high CPU load.
|
||||
- The application pod should be healthy once chaos is stopped. Expectation is that service-requests should be served despite chaos.
|
||||
keywords:
|
||||
- Kubernetes
|
||||
platforms:
|
||||
- GKE
|
||||
- Packet(Kubeadm)
|
||||
- Minikube
|
||||
- EKS
|
||||
- AKS
|
||||
- Kind
|
||||
experiments:
|
||||
- pod-cpu-hog
|
||||
- sock-shop
|
||||
- sock-shop-promProbe
|
||||
minKubeVersion: 1.12.0
|
||||
labels:
|
||||
app.kubernetes.io/component: chartserviceversion
|
||||
app.kubernetes.io/version: ci
|
||||
links:
|
||||
- name: Documentation
|
||||
url: https://docs.harness.io/category/kl0mxwpfw1-hce-category
|
||||
icon:
|
||||
- base64data: ""
|
||||
mediatype: ""
|
||||
35
faults/kubernetes/pod-delete/engine.yaml
Normal file
35
faults/kubernetes/pod-delete/engine.yaml
Normal file
@@ -0,0 +1,35 @@
|
||||
---
|
||||
apiVersion: litmuschaos.io/v1alpha1
|
||||
kind: ChaosEngine
|
||||
metadata:
|
||||
name: nginx-chaos
|
||||
namespace: default
|
||||
spec:
|
||||
appinfo:
|
||||
appns: ''
|
||||
applabel: ''
|
||||
appkind: ''
|
||||
# It can be active/stop
|
||||
engineState: 'active'
|
||||
chaosServiceAccount: pod-delete-sa
|
||||
experiments:
|
||||
- name: pod-delete
|
||||
spec:
|
||||
components:
|
||||
env:
|
||||
# set chaos duration (in sec) as desired
|
||||
- name: TOTAL_CHAOS_DURATION
|
||||
value: '30'
|
||||
|
||||
# set chaos interval (in sec) as desired
|
||||
- name: CHAOS_INTERVAL
|
||||
value: '10'
|
||||
|
||||
# pod failures without '--force' & default terminationGracePeriodSeconds
|
||||
- name: FORCE
|
||||
value: 'false'
|
||||
|
||||
## percentage of total pods to target
|
||||
- name: PODS_AFFECTED_PERC
|
||||
value: ''
|
||||
|
||||
109
faults/kubernetes/pod-delete/fault.yaml
Normal file
109
faults/kubernetes/pod-delete/fault.yaml
Normal file
@@ -0,0 +1,109 @@
|
||||
---
|
||||
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: ci
|
||||
spec:
|
||||
definition:
|
||||
scope: Namespaced
|
||||
permissions:
|
||||
# Create and monitor the experiment & helper pods
|
||||
- apiGroups: [""]
|
||||
resources: ["pods"]
|
||||
verbs: ["create", "delete", "get", "list", "patch", "update", "deletecollection"]
|
||||
# Performs CRUD operations on the events inside chaosengine and chaosresult
|
||||
- apiGroups: [""]
|
||||
resources: ["events"]
|
||||
verbs: ["create", "get", "list", "patch", "update"]
|
||||
# Fetch configmaps details and mount it to the experiment pod (if specified)
|
||||
- apiGroups: [""]
|
||||
resources: ["configmaps"]
|
||||
verbs: ["get", "list"]
|
||||
# Track and get the runner, experiment, and helper pods log
|
||||
- apiGroups: [""]
|
||||
resources: ["pods/log"]
|
||||
verbs: ["get", "list", "watch"]
|
||||
# for creating and managing to execute commands inside target container
|
||||
- apiGroups: [""]
|
||||
resources: ["pods/exec"]
|
||||
verbs: ["get", "list", "create"]
|
||||
# deriving the parent/owner details of the pod(if parent is anyof {deployment, statefulset, daemonsets})
|
||||
- apiGroups: ["apps"]
|
||||
resources: ["deployments", "statefulsets", "replicasets", "daemonsets"]
|
||||
verbs: ["list", "get"]
|
||||
# deriving the parent/owner details of the pod(if parent is deploymentConfig)
|
||||
- apiGroups: ["apps.openshift.io"]
|
||||
resources: ["deploymentconfigs"]
|
||||
verbs: ["list", "get"]
|
||||
# deriving the parent/owner details of the pod(if parent is deploymentConfig)
|
||||
- apiGroups: [""]
|
||||
resources: ["replicationcontrollers"]
|
||||
verbs: ["get", "list"]
|
||||
# deriving the parent/owner details of the pod(if parent is argo-rollouts)
|
||||
- apiGroups: ["argoproj.io"]
|
||||
resources: ["rollouts"]
|
||||
verbs: ["list", "get"]
|
||||
# for configuring and monitor the experiment job by the chaos-runner pod
|
||||
- apiGroups: ["batch"]
|
||||
resources: ["jobs"]
|
||||
verbs: ["create", "list", "get", "delete", "deletecollection"]
|
||||
# for creation, status polling and deletion of litmus chaos resources used within a chaos workflow
|
||||
- apiGroups: ["litmuschaos.io"]
|
||||
resources: ["chaosengines", "chaosexperiments", "chaosresults"]
|
||||
verbs: ["create", "list", "get", "patch", "update", "delete"]
|
||||
image: "chaosnative/go-runner:ci"
|
||||
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: TARGET_CONTAINER
|
||||
value: ''
|
||||
|
||||
- name: TARGET_PODS
|
||||
value: ''
|
||||
|
||||
- name: DEFAULT_HEALTH_CHECK
|
||||
value: 'false'
|
||||
|
||||
# To select pods on specific node(s)
|
||||
- name: NODE_LABEL
|
||||
value: ''
|
||||
|
||||
## it defines the sequence of chaos execution for multiple target pods
|
||||
## supported values: serial, parallel
|
||||
- name: SEQUENCE
|
||||
value: 'parallel'
|
||||
|
||||
labels:
|
||||
name: pod-delete
|
||||
app.kubernetes.io/part-of: litmus
|
||||
app.kubernetes.io/component: experiment-job
|
||||
app.kubernetes.io/version: ci
|
||||
@@ -0,0 +1,42 @@
|
||||
---
|
||||
apiVersion: litmuschaos.io/v1alpha1
|
||||
kind: ChartServiceVersion
|
||||
metadata:
|
||||
name: pod-delete
|
||||
version: 0.1.0
|
||||
annotations:
|
||||
categories: Kubernetes
|
||||
vendor: Harness
|
||||
spec:
|
||||
displayName: Pod Delete
|
||||
categoryDescription: |
|
||||
Pod delete fault disrupts the state of Kubernetes resources. This fault injects random pod delete failures against specified application.
|
||||
- Causes (forced/graceful) pod failure of random replicas of an application deployment.
|
||||
- Tests deployment sanity (replica availability & uninterrupted service) and recovery workflows of the application pod.
|
||||
keywords:
|
||||
- Kubernetes
|
||||
platforms:
|
||||
- GKE
|
||||
- Konvoy
|
||||
- Packet(Kubeadm)
|
||||
- Minikube
|
||||
- EKS
|
||||
- AKS
|
||||
- Kind
|
||||
- Rancher
|
||||
- OpenShift(OKD)
|
||||
experiments:
|
||||
- pod-delete
|
||||
- podtato-head
|
||||
- sock-shop
|
||||
- sock-shop-promProbe
|
||||
minKubeVersion: 1.12.0
|
||||
labels:
|
||||
app.kubernetes.io/component: chartserviceversion
|
||||
app.kubernetes.io/version: ci
|
||||
links:
|
||||
- name: Documentation
|
||||
url: https://docs.harness.io/category/kl0mxwpfw1-hce-category
|
||||
icon:
|
||||
- url:
|
||||
mediatype: ""
|
||||
43
faults/kubernetes/pod-dns-error/engine.yaml
Normal file
43
faults/kubernetes/pod-dns-error/engine.yaml
Normal file
@@ -0,0 +1,43 @@
|
||||
---
|
||||
apiVersion: litmuschaos.io/v1alpha1
|
||||
kind: ChaosEngine
|
||||
metadata:
|
||||
name: nginx-chaos
|
||||
spec:
|
||||
appinfo:
|
||||
appns: ""
|
||||
applabel: ""
|
||||
appkind: ""
|
||||
# It can be active/stop
|
||||
engineState: "active"
|
||||
#ex. values: ns1:name=percona,ns2:run=nginx
|
||||
auxiliaryAppInfo: ""
|
||||
chaosServiceAccount: pod-dns-error-sa
|
||||
experiments:
|
||||
- name: pod-dns-error
|
||||
spec:
|
||||
components:
|
||||
env:
|
||||
- name: TOTAL_CHAOS_DURATION
|
||||
value: "60" # in seconds
|
||||
|
||||
# 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"
|
||||
|
||||
# provide the name of container runtime, it supports docker, containerd, crio
|
||||
- name: CONTAINER_RUNTIME
|
||||
value: 'containerd'
|
||||
|
||||
# provide the socket file path
|
||||
- name: SOCKET_PATH
|
||||
value: '/run/containerd/containerd.sock'
|
||||
|
||||
## percentage of total pods to target
|
||||
- name: PODS_AFFECTED_PERC
|
||||
value: ""
|
||||
|
||||
119
faults/kubernetes/pod-dns-error/fault.yaml
Normal file
119
faults/kubernetes/pod-dns-error/fault.yaml
Normal file
@@ -0,0 +1,119 @@
|
||||
---
|
||||
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: ci
|
||||
spec:
|
||||
definition:
|
||||
scope: Namespaced
|
||||
permissions:
|
||||
# Create and monitor the experiment & helper pods
|
||||
- apiGroups: [""]
|
||||
resources: ["pods"]
|
||||
verbs: ["create", "delete", "get", "list", "patch", "update", "deletecollection"]
|
||||
# Performs CRUD operations on the events inside chaosengine and chaosresult
|
||||
- apiGroups: [""]
|
||||
resources: ["events"]
|
||||
verbs: ["create", "get", "list", "patch", "update"]
|
||||
# Fetch configmaps details and mount it to the experiment pod (if specified)
|
||||
- apiGroups: [""]
|
||||
resources: ["configmaps"]
|
||||
verbs: ["get", "list"]
|
||||
# Track and get the runner, experiment, and helper pods log
|
||||
- apiGroups: [""]
|
||||
resources: ["pods/log"]
|
||||
verbs: ["get", "list", "watch"]
|
||||
# for creating and managing to execute commands inside target container
|
||||
- apiGroups: [""]
|
||||
resources: ["pods/exec"]
|
||||
verbs: ["get", "list", "create"]
|
||||
# deriving the parent/owner details of the pod(if parent is anyof {deployment, statefulset, daemonsets})
|
||||
- apiGroups: ["apps"]
|
||||
resources: ["deployments", "statefulsets", "replicasets", "daemonsets"]
|
||||
verbs: ["list", "get"]
|
||||
# deriving the parent/owner details of the pod(if parent is deploymentConfig)
|
||||
- apiGroups: ["apps.openshift.io"]
|
||||
resources: ["deploymentconfigs"]
|
||||
verbs: ["list", "get"]
|
||||
# deriving the parent/owner details of the pod(if parent is deploymentConfig)
|
||||
- apiGroups: [""]
|
||||
resources: ["replicationcontrollers"]
|
||||
verbs: ["get", "list"]
|
||||
# deriving the parent/owner details of the pod(if parent is argo-rollouts)
|
||||
- apiGroups: ["argoproj.io"]
|
||||
resources: ["rollouts"]
|
||||
verbs: ["list", "get"]
|
||||
# for configuring and monitor the experiment job by the chaos-runner pod
|
||||
- apiGroups: ["batch"]
|
||||
resources: ["jobs"]
|
||||
verbs: ["create", "list", "get", "delete", "deletecollection"]
|
||||
# for creation, status polling and deletion of litmus chaos resources used within a chaos workflow
|
||||
- apiGroups: ["litmuschaos.io"]
|
||||
resources: ["chaosengines", "chaosexperiments", "chaosresults"]
|
||||
verbs: ["create", "list", "get", "patch", "update", "delete"]
|
||||
image: "chaosnative/go-runner:ci"
|
||||
args:
|
||||
- -c
|
||||
- ./experiments -name pod-dns-error
|
||||
command:
|
||||
- /bin/bash
|
||||
env:
|
||||
- name: TARGET_CONTAINER
|
||||
value: ""
|
||||
|
||||
# provide lib image
|
||||
- name: LIB_IMAGE
|
||||
value: "chaosnative/go-runner:ci"
|
||||
|
||||
- name: DEFAULT_HEALTH_CHECK
|
||||
value: 'false'
|
||||
|
||||
- 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: 'containerd'
|
||||
|
||||
# provide the socket file path
|
||||
- name: SOCKET_PATH
|
||||
value: '/run/containerd/containerd.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/runtime-api-usage: "true"
|
||||
app.kubernetes.io/version: ci
|
||||
@@ -0,0 +1,24 @@
|
||||
---
|
||||
apiVersion: litmuschaos.io/v1alpha1
|
||||
kind: ChartServiceVersion
|
||||
metadata:
|
||||
name: pod-dns-error
|
||||
version: 0.1.0
|
||||
annotations:
|
||||
categories: kubernetes
|
||||
spec:
|
||||
displayName: Pod DNS Error
|
||||
categoryDescription: >
|
||||
Pod DNS Error fault injects DNS failure/error in target pod containers.
|
||||
keywords:
|
||||
- Kubernetes
|
||||
minKubeVersion: 1.12.0
|
||||
labels:
|
||||
app.kubernetes.io/component: chartserviceversion
|
||||
app.kubernetes.io/version: ci
|
||||
links:
|
||||
- name: Documentation
|
||||
url: https://docs.harness.io/category/kl0mxwpfw1-hce-category
|
||||
icon:
|
||||
- base64data: ""
|
||||
mediatype: ""
|
||||
39
faults/kubernetes/pod-dns-spoof/engine.yaml
Normal file
39
faults/kubernetes/pod-dns-spoof/engine.yaml
Normal file
@@ -0,0 +1,39 @@
|
||||
---
|
||||
apiVersion: litmuschaos.io/v1alpha1
|
||||
kind: ChaosEngine
|
||||
metadata:
|
||||
name: nginx-chaos
|
||||
spec:
|
||||
appinfo:
|
||||
appns: ""
|
||||
applabel: ""
|
||||
appkind: ""
|
||||
# It can be active/stop
|
||||
engineState: "active"
|
||||
#ex. values: ns1:name=percona,ns2:run=nginx
|
||||
auxiliaryAppInfo: ""
|
||||
chaosServiceAccount: pod-dns-spoof-sa
|
||||
experiments:
|
||||
- name: pod-dns-spoof
|
||||
spec:
|
||||
components:
|
||||
env:
|
||||
- name: TOTAL_CHAOS_DURATION
|
||||
value: "60" # in seconds
|
||||
|
||||
# map of the target hostnames eg. '{"abc.com":"spoofabc.com"}' . If empty no queries will be spoofed
|
||||
- name: SPOOF_MAP
|
||||
value: '{"google.com":"fakegoogle.com"}'
|
||||
|
||||
# provide the name of container runtime, it supports docker, containerd, crio
|
||||
- name: CONTAINER_RUNTIME
|
||||
value: 'containerd'
|
||||
|
||||
# provide the socket file path
|
||||
- name: SOCKET_PATH
|
||||
value: '/run/containerd/containerd.sock'
|
||||
|
||||
## percentage of total pods to target
|
||||
- name: PODS_AFFECTED_PERC
|
||||
value: ""
|
||||
|
||||
115
faults/kubernetes/pod-dns-spoof/fault.yaml
Normal file
115
faults/kubernetes/pod-dns-spoof/fault.yaml
Normal file
@@ -0,0 +1,115 @@
|
||||
---
|
||||
apiVersion: litmuschaos.io/v1alpha1
|
||||
description:
|
||||
message: |
|
||||
Pod DNS Spoof can spoof particular DNS requests in target pod container to desired target hostnames
|
||||
kind: ChaosExperiment
|
||||
metadata:
|
||||
name: pod-dns-spoof
|
||||
labels:
|
||||
name: pod-dns-spoof
|
||||
app.kubernetes.io/part-of: litmus
|
||||
app.kubernetes.io/component: chaosexperiment
|
||||
app.kubernetes.io/version: ci
|
||||
spec:
|
||||
definition:
|
||||
scope: Namespaced
|
||||
permissions:
|
||||
# Create and monitor the experiment & helper pods
|
||||
- apiGroups: [""]
|
||||
resources: ["pods"]
|
||||
verbs: ["create", "delete", "get", "list", "patch", "update", "deletecollection"]
|
||||
# Performs CRUD operations on the events inside chaosengine and chaosresult
|
||||
- apiGroups: [""]
|
||||
resources: ["events"]
|
||||
verbs: ["create", "get", "list", "patch", "update"]
|
||||
# Fetch configmaps details and mount it to the experiment pod (if specified)
|
||||
- apiGroups: [""]
|
||||
resources: ["configmaps"]
|
||||
verbs: ["get", "list"]
|
||||
# Track and get the runner, experiment, and helper pods log
|
||||
- apiGroups: [""]
|
||||
resources: ["pods/log"]
|
||||
verbs: ["get", "list", "watch"]
|
||||
# for creating and managing to execute commands inside target container
|
||||
- apiGroups: [""]
|
||||
resources: ["pods/exec"]
|
||||
verbs: ["get", "list", "create"]
|
||||
# deriving the parent/owner details of the pod(if parent is anyof {deployment, statefulset, daemonsets})
|
||||
- apiGroups: ["apps"]
|
||||
resources: ["deployments", "statefulsets", "replicasets", "daemonsets"]
|
||||
verbs: ["list", "get"]
|
||||
# deriving the parent/owner details of the pod(if parent is deploymentConfig)
|
||||
- apiGroups: ["apps.openshift.io"]
|
||||
resources: ["deploymentconfigs"]
|
||||
verbs: ["list", "get"]
|
||||
# deriving the parent/owner details of the pod(if parent is deploymentConfig)
|
||||
- apiGroups: [""]
|
||||
resources: ["replicationcontrollers"]
|
||||
verbs: ["get", "list"]
|
||||
# deriving the parent/owner details of the pod(if parent is argo-rollouts)
|
||||
- apiGroups: ["argoproj.io"]
|
||||
resources: ["rollouts"]
|
||||
verbs: ["list", "get"]
|
||||
# for configuring and monitor the experiment job by the chaos-runner pod
|
||||
- apiGroups: ["batch"]
|
||||
resources: ["jobs"]
|
||||
verbs: ["create", "list", "get", "delete", "deletecollection"]
|
||||
# for creation, status polling and deletion of litmus chaos resources used within a chaos workflow
|
||||
- apiGroups: ["litmuschaos.io"]
|
||||
resources: ["chaosengines", "chaosexperiments", "chaosresults"]
|
||||
verbs: ["create", "list", "get", "patch", "update", "delete"]
|
||||
image: "chaosnative/go-runner:ci"
|
||||
args:
|
||||
- -c
|
||||
- ./experiments -name pod-dns-spoof
|
||||
command:
|
||||
- /bin/bash
|
||||
env:
|
||||
- name: TARGET_CONTAINER
|
||||
value: ""
|
||||
|
||||
# provide lib image
|
||||
- name: LIB_IMAGE
|
||||
value: "chaosnative/go-runner:ci"
|
||||
|
||||
- name: DEFAULT_HEALTH_CHECK
|
||||
value: 'false'
|
||||
|
||||
- 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: 'containerd'
|
||||
|
||||
# provide the socket file path
|
||||
- name: SOCKET_PATH
|
||||
value: '/run/containerd/containerd.sock'
|
||||
|
||||
## it defines the sequence of chaos execution for multiple target pods
|
||||
## supported values: serial, parallel
|
||||
- name: SEQUENCE
|
||||
value: "parallel"
|
||||
|
||||
# map of the target hostnames eg. '{"abc.com":"spoofabc.com"}' . If empty no queries will be spoofed
|
||||
- name: SPOOF_MAP
|
||||
value: ""
|
||||
|
||||
labels:
|
||||
experiment: pod-dns-spoof
|
||||
app.kubernetes.io/part-of: litmus
|
||||
app.kubernetes.io/component: experiment-job
|
||||
app.kubernetes.io/runtime-api-usage: "true"
|
||||
app.kubernetes.io/version: ci
|
||||
@@ -0,0 +1,24 @@
|
||||
---
|
||||
apiVersion: litmuschaos.io/v1alpha1
|
||||
kind: ChartServiceVersion
|
||||
metadata:
|
||||
name: pod-dns-spoof
|
||||
version: 0.1.0
|
||||
annotations:
|
||||
categories: kubernetes
|
||||
spec:
|
||||
displayName: Pod DNS Spoof
|
||||
categoryDescription: >
|
||||
Pod DNS Spoof fault spoofs particular DNS requests in a target pod container to desired target hostnames.
|
||||
keywords:
|
||||
- Kubernetes
|
||||
minKubeVersion: 1.12.0
|
||||
labels:
|
||||
app.kubernetes.io/component: chartserviceversion
|
||||
app.kubernetes.io/version: ci
|
||||
links:
|
||||
- name: Documentation
|
||||
url: https://docs.harness.io/category/kl0mxwpfw1-hce-category
|
||||
icon:
|
||||
- base64data: ""
|
||||
mediatype: ""
|
||||
43
faults/kubernetes/pod-http-latency/engine.yaml
Normal file
43
faults/kubernetes/pod-http-latency/engine.yaml
Normal file
@@ -0,0 +1,43 @@
|
||||
---
|
||||
apiVersion: litmuschaos.io/v1alpha1
|
||||
kind: ChaosEngine
|
||||
metadata:
|
||||
name: nginx-http-chaos
|
||||
namespace: default
|
||||
spec:
|
||||
# It can be active/stop
|
||||
engineState: 'active'
|
||||
appinfo:
|
||||
appns: ''
|
||||
# FYI, To see app label, apply kubectl get pods --show-labels
|
||||
applabel: ''
|
||||
appkind: ''
|
||||
chaosServiceAccount: pod-http-latency-sa
|
||||
experiments:
|
||||
- name: pod-http-latency
|
||||
spec:
|
||||
components:
|
||||
env:
|
||||
- name: TOTAL_CHAOS_DURATION
|
||||
value: '60' # in seconds
|
||||
|
||||
- name: LATENCY
|
||||
value: '2000' #in ms
|
||||
|
||||
# port of the target service
|
||||
- name: TARGET_SERVICE_PORT
|
||||
value: "80"
|
||||
|
||||
# provide the name of container runtime
|
||||
# it supports docker, containerd, crio
|
||||
- name: CONTAINER_RUNTIME
|
||||
value: 'containerd'
|
||||
|
||||
# provide the socket file path
|
||||
- name: SOCKET_PATH
|
||||
value: '/run/containerd/containerd.sock'
|
||||
|
||||
## percentage of total pods to target
|
||||
- name: PODS_AFFECTED_PERC
|
||||
value: ''
|
||||
|
||||
139
faults/kubernetes/pod-http-latency/fault.yaml
Normal file
139
faults/kubernetes/pod-http-latency/fault.yaml
Normal file
@@ -0,0 +1,139 @@
|
||||
---
|
||||
apiVersion: litmuschaos.io/v1alpha1
|
||||
description:
|
||||
message: |
|
||||
Injects HTTP request latency on pods belonging to an app deployment
|
||||
kind: ChaosExperiment
|
||||
metadata:
|
||||
name: pod-http-latency
|
||||
labels:
|
||||
name: pod-http-latency
|
||||
app.kubernetes.io/part-of: litmus
|
||||
app.kubernetes.io/component: chaosexperiment
|
||||
app.kubernetes.io/version: ci
|
||||
spec:
|
||||
definition:
|
||||
scope: Namespaced
|
||||
permissions:
|
||||
# Create and monitor the experiment & helper pods
|
||||
- apiGroups: [""]
|
||||
resources: ["pods"]
|
||||
verbs: ["create", "delete", "get", "list", "patch", "update", "deletecollection"]
|
||||
# Performs CRUD operations on the events inside chaosengine and chaosresult
|
||||
- apiGroups: [""]
|
||||
resources: ["events"]
|
||||
verbs: ["create", "get", "list", "patch", "update"]
|
||||
# Fetch configmaps details and mount it to the experiment pod (if specified)
|
||||
- apiGroups: [""]
|
||||
resources: ["configmaps"]
|
||||
verbs: ["get", "list"]
|
||||
# Track and get the runner, experiment, and helper pods log
|
||||
- apiGroups: [""]
|
||||
resources: ["pods/log"]
|
||||
verbs: ["get", "list", "watch"]
|
||||
# for creating and managing to execute commands inside target container
|
||||
- apiGroups: [""]
|
||||
resources: ["pods/exec"]
|
||||
verbs: ["get", "list", "create"]
|
||||
# deriving the parent/owner details of the pod(if parent is anyof {deployment, statefulset, daemonsets})
|
||||
- apiGroups: ["apps"]
|
||||
resources: ["deployments", "statefulsets", "replicasets", "daemonsets"]
|
||||
verbs: ["list", "get"]
|
||||
# deriving the parent/owner details of the pod(if parent is deploymentConfig)
|
||||
- apiGroups: ["apps.openshift.io"]
|
||||
resources: ["deploymentconfigs"]
|
||||
verbs: ["list", "get"]
|
||||
# deriving the parent/owner details of the pod(if parent is deploymentConfig)
|
||||
- apiGroups: [""]
|
||||
resources: ["replicationcontrollers"]
|
||||
verbs: ["get", "list"]
|
||||
# deriving the parent/owner details of the pod(if parent is argo-rollouts)
|
||||
- apiGroups: ["argoproj.io"]
|
||||
resources: ["rollouts"]
|
||||
verbs: ["list", "get"]
|
||||
# for configuring and monitor the experiment job by the chaos-runner pod
|
||||
- apiGroups: ["batch"]
|
||||
resources: ["jobs"]
|
||||
verbs: ["create", "list", "get", "delete", "deletecollection"]
|
||||
# for creation, status polling and deletion of litmus chaos resources used within a chaos workflow
|
||||
- apiGroups: ["litmuschaos.io"]
|
||||
resources: ["chaosengines", "chaosexperiments", "chaosresults"]
|
||||
verbs: ["create", "list", "get", "patch", "update", "delete"]
|
||||
image: "chaosnative/go-runner:ci"
|
||||
imagePullPolicy: Always
|
||||
args:
|
||||
- -c
|
||||
- ./experiments -name pod-http-latency
|
||||
command:
|
||||
- /bin/bash
|
||||
env:
|
||||
- name: TARGET_CONTAINER
|
||||
value: ''
|
||||
|
||||
# provide lib image
|
||||
- name: LIB_IMAGE
|
||||
value: 'chaosnative/go-runner:ci'
|
||||
|
||||
- name: LATENCY
|
||||
value: '2000' #in ms
|
||||
|
||||
# port of the target service
|
||||
- name: TARGET_SERVICE_PORT
|
||||
value: "80"
|
||||
|
||||
# toxicity is the probability of the request to be affected
|
||||
# provide the percentage value in the range of 0-100
|
||||
# 0 means no request will be affected and 100 means all request will be affected
|
||||
- name: TOXICITY
|
||||
value: "100"
|
||||
|
||||
# port on which the proxy will listen
|
||||
- name: PROXY_PORT
|
||||
value: "20000"
|
||||
|
||||
# network interface on which the proxy will listen
|
||||
- name: NETWORK_INTERFACE
|
||||
value: "eth0"
|
||||
|
||||
- name: TOTAL_CHAOS_DURATION
|
||||
value: '60' # in seconds
|
||||
|
||||
# Time period to wait before and after injection of chaos in sec
|
||||
- name: RAMP_TIME
|
||||
value: ''
|
||||
|
||||
- name: DEFAULT_HEALTH_CHECK
|
||||
value: 'false'
|
||||
|
||||
# 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: 'containerd'
|
||||
|
||||
# provide the socket file path
|
||||
- name: SOCKET_PATH
|
||||
value: '/run/containerd/containerd.sock'
|
||||
|
||||
# To select pods on specific node(s)
|
||||
- name: NODE_LABEL
|
||||
value: ''
|
||||
|
||||
## it defines the sequence of chaos execution for multiple target pods
|
||||
## supported values: serial, parallel
|
||||
- name: SEQUENCE
|
||||
value: 'parallel'
|
||||
|
||||
labels:
|
||||
name: pod-http-latency
|
||||
app.kubernetes.io/part-of: litmus
|
||||
app.kubernetes.io/component: experiment-job
|
||||
app.kubernetes.io/runtime-api-usage: "true"
|
||||
app.kubernetes.io/version: ci
|
||||
@@ -0,0 +1,31 @@
|
||||
---
|
||||
apiVersion: litmuschaos.io/v1alpha1
|
||||
kind: ChartServiceVersion
|
||||
metadata:
|
||||
name: pod-http-latency
|
||||
version: 0.1.0
|
||||
annotations:
|
||||
categories: Kubernetes
|
||||
vendor: Harness
|
||||
spec:
|
||||
displayName: Pod HTTP Latency
|
||||
categoryDescription: |
|
||||
Pod-http-latency fault disrupts HTTP requests of kubernetes pods. This fault can inject random HTTP response delays on the app replica pods.
|
||||
- Causes flaky access to application replica by injecting HTTP response delay using toxiproxy.
|
||||
- The application pod should be healthy once chaos is stopped. Service-requests should be served despite chaos.
|
||||
keywords:
|
||||
- Kubernetes
|
||||
platforms:
|
||||
- GKE
|
||||
- Minikube
|
||||
- EKS
|
||||
minKubeVersion: 1.12.0
|
||||
labels:
|
||||
app.kubernetes.io/component: chartserviceversion
|
||||
app.kubernetes.io/version: ci
|
||||
links:
|
||||
- name: Documentation
|
||||
url: https://docs.harness.io/category/kl0mxwpfw1-hce-category
|
||||
icon:
|
||||
- base64data: ""
|
||||
mediatype: ""
|
||||
43
faults/kubernetes/pod-http-modify-body/engine.yaml
Normal file
43
faults/kubernetes/pod-http-modify-body/engine.yaml
Normal file
@@ -0,0 +1,43 @@
|
||||
---
|
||||
apiVersion: litmuschaos.io/v1alpha1
|
||||
kind: ChaosEngine
|
||||
metadata:
|
||||
name: nginx-chaos
|
||||
spec:
|
||||
# It can be active/stop
|
||||
engineState: 'active'
|
||||
appinfo:
|
||||
appns: ''
|
||||
applabel: ''
|
||||
appkind: ''
|
||||
chaosServiceAccount: pod-http-modify-body-sa
|
||||
experiments:
|
||||
- name: pod-http-modify-body
|
||||
spec:
|
||||
components:
|
||||
env:
|
||||
# set chaos duration (in sec) as desired
|
||||
- name: TOTAL_CHAOS_DURATION
|
||||
value: '60' # in seconds
|
||||
|
||||
# provide the body string to overwrite the response body
|
||||
- name: RESPONSE_BODY
|
||||
value: ''
|
||||
|
||||
# port of the target service
|
||||
- name: TARGET_SERVICE_PORT
|
||||
value: "80"
|
||||
|
||||
# provide the name of container runtime
|
||||
# it supports docker, containerd, crio
|
||||
- name: CONTAINER_RUNTIME
|
||||
value: 'containerd'
|
||||
|
||||
# provide the socket file path
|
||||
- name: SOCKET_PATH
|
||||
value: '/run/containerd/containerd.sock'
|
||||
|
||||
## percentage of total pods to target
|
||||
- name: PODS_AFFECTED_PERC
|
||||
value: ''
|
||||
|
||||
150
faults/kubernetes/pod-http-modify-body/fault.yaml
Normal file
150
faults/kubernetes/pod-http-modify-body/fault.yaml
Normal file
@@ -0,0 +1,150 @@
|
||||
---
|
||||
apiVersion: litmuschaos.io/v1alpha1
|
||||
description:
|
||||
message: |
|
||||
It injects the chaos inside the pod which modifies the body of the response from the provided application server to the body string provided by the user and reverts after a specified duration
|
||||
kind: ChaosExperiment
|
||||
metadata:
|
||||
name: pod-http-modify-body
|
||||
labels:
|
||||
name: pod-http-modify-body
|
||||
app.kubernetes.io/part-of: litmus
|
||||
app.kubernetes.io/component: chaosexperiment
|
||||
app.kubernetes.io/version: ci
|
||||
spec:
|
||||
definition:
|
||||
scope: Namespaced
|
||||
permissions:
|
||||
# Create and monitor the experiment & helper pods
|
||||
- apiGroups: [""]
|
||||
resources: ["pods"]
|
||||
verbs: ["create", "delete", "get", "list", "patch", "update", "deletecollection"]
|
||||
# Performs CRUD operations on the events inside chaosengine and chaosresult
|
||||
- apiGroups: [""]
|
||||
resources: ["events"]
|
||||
verbs: ["create", "get", "list", "patch", "update"]
|
||||
# Fetch configmaps details and mount it to the experiment pod (if specified)
|
||||
- apiGroups: [""]
|
||||
resources: ["configmaps"]
|
||||
verbs: ["get", "list"]
|
||||
# Track and get the runner, experiment, and helper pods log
|
||||
- apiGroups: [""]
|
||||
resources: ["pods/log"]
|
||||
verbs: ["get", "list", "watch"]
|
||||
# for creating and managing to execute commands inside target container
|
||||
- apiGroups: [""]
|
||||
resources: ["pods/exec"]
|
||||
verbs: ["get", "list", "create"]
|
||||
# deriving the parent/owner details of the pod(if parent is anyof {deployment, statefulset, daemonsets})
|
||||
- apiGroups: ["apps"]
|
||||
resources: ["deployments", "statefulsets", "replicasets", "daemonsets"]
|
||||
verbs: ["list", "get"]
|
||||
# deriving the parent/owner details of the pod(if parent is deploymentConfig)
|
||||
- apiGroups: ["apps.openshift.io"]
|
||||
resources: ["deploymentconfigs"]
|
||||
verbs: ["list", "get"]
|
||||
# deriving the parent/owner details of the pod(if parent is deploymentConfig)
|
||||
- apiGroups: [""]
|
||||
resources: ["replicationcontrollers"]
|
||||
verbs: ["get", "list"]
|
||||
# deriving the parent/owner details of the pod(if parent is argo-rollouts)
|
||||
- apiGroups: ["argoproj.io"]
|
||||
resources: ["rollouts"]
|
||||
verbs: ["list", "get"]
|
||||
# for configuring and monitor the experiment job by the chaos-runner pod
|
||||
- apiGroups: ["batch"]
|
||||
resources: ["jobs"]
|
||||
verbs: ["create", "list", "get", "delete", "deletecollection"]
|
||||
# for creation, status polling and deletion of litmus chaos resources used within a chaos workflow
|
||||
- apiGroups: ["litmuschaos.io"]
|
||||
resources: ["chaosengines", "chaosexperiments", "chaosresults"]
|
||||
verbs: ["create", "list", "get", "patch", "update", "delete"]
|
||||
image: "chaosnative/go-runner:ci"
|
||||
imagePullPolicy: Always
|
||||
args:
|
||||
- -c
|
||||
- ./experiments -name pod-http-modify-body
|
||||
command:
|
||||
- /bin/bash
|
||||
env:
|
||||
- name: TARGET_CONTAINER
|
||||
value: ''
|
||||
|
||||
# provide lib image
|
||||
- name: LIB_IMAGE
|
||||
value: 'chaosnative/go-runner:ci'
|
||||
|
||||
# provide the body string to overwrite the response body
|
||||
# if no value is provided, response will be an empty body.
|
||||
- name: RESPONSE_BODY
|
||||
value: ''
|
||||
|
||||
# provide the encoding type for the response body
|
||||
# currently supported value are gzip, deflate
|
||||
# if empty no encoding will be applied
|
||||
- name: CONTENT_ENCODING
|
||||
value: ''
|
||||
|
||||
# provide the content type for the response body
|
||||
- name: CONTENT_TYPE
|
||||
value: 'text/plain'
|
||||
|
||||
# port of the target service
|
||||
- name: TARGET_SERVICE_PORT
|
||||
value: "80"
|
||||
|
||||
# toxicity is the probability of the request to be affected
|
||||
# provide the percentage value in the range of 0-100
|
||||
# 0 means no request will be affected and 100 means all request will be affected
|
||||
- name: TOXICITY
|
||||
value: "100"
|
||||
|
||||
# port on which the proxy will listen
|
||||
- name: PROXY_PORT
|
||||
value: "20000"
|
||||
|
||||
# network interface on which the proxy will listen
|
||||
- name: NETWORK_INTERFACE
|
||||
value: "eth0"
|
||||
|
||||
- name: TOTAL_CHAOS_DURATION
|
||||
value: '60' # in seconds
|
||||
|
||||
# Time period to wait before and after injection of chaos in sec
|
||||
- name: RAMP_TIME
|
||||
value: ''
|
||||
|
||||
- name: DEFAULT_HEALTH_CHECK
|
||||
value: 'false'
|
||||
|
||||
# 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: 'containerd'
|
||||
|
||||
# provide the socket file path
|
||||
- name: SOCKET_PATH
|
||||
value: '/run/containerd/containerd.sock'
|
||||
|
||||
# To select pods on specific node(s)
|
||||
- name: NODE_LABEL
|
||||
value: ''
|
||||
|
||||
## it defines the sequence of chaos execution for multiple target pods
|
||||
## supported values: serial, parallel
|
||||
- name: SEQUENCE
|
||||
value: 'parallel'
|
||||
|
||||
labels:
|
||||
name: pod-http-modify-body
|
||||
app.kubernetes.io/part-of: litmus
|
||||
app.kubernetes.io/component: experiment-job
|
||||
app.kubernetes.io/version: ci
|
||||
@@ -0,0 +1,28 @@
|
||||
---
|
||||
apiVersion: litmuschaos.io/v1alpha1
|
||||
kind: ChartServiceVersion
|
||||
metadata:
|
||||
name: pod-http-modify-body
|
||||
version: 0.1.0
|
||||
annotations:
|
||||
categories: kubernetes
|
||||
spec:
|
||||
displayName: Pod HTTP Modify Body
|
||||
categoryDescription: >
|
||||
Pod-http-modify-body fault disrupts HTTP requests of kubernetes pods. This fault can modify the body of the response from the service targetted.
|
||||
- Causes modification of response body of the HTTP request.
|
||||
- The application pod should be healthy once chaos is stopped. Service-requests should be served despite chaos.
|
||||
keywords:
|
||||
- kubernetes
|
||||
platforms:
|
||||
- "Minikube"
|
||||
minKubeVersion: 1.12.0
|
||||
labels:
|
||||
app.kubernetes.io/component: chartserviceversion
|
||||
app.kubernetes.io/version: ci
|
||||
links:
|
||||
- name: Documentation
|
||||
url: https://docs.harness.io/category/kl0mxwpfw1-hce-category
|
||||
icon:
|
||||
- base64data: ""
|
||||
mediatype: ""
|
||||
49
faults/kubernetes/pod-http-modify-header/engine.yaml
Normal file
49
faults/kubernetes/pod-http-modify-header/engine.yaml
Normal file
@@ -0,0 +1,49 @@
|
||||
---
|
||||
apiVersion: litmuschaos.io/v1alpha1
|
||||
kind: ChaosEngine
|
||||
metadata:
|
||||
name: nginx-http-chaos
|
||||
namespace: default
|
||||
spec:
|
||||
# It can be active/stop
|
||||
engineState: 'active'
|
||||
appinfo:
|
||||
appns: ''
|
||||
# FYI, To see app label, apply kubectl get pods --show-labels
|
||||
applabel: ''
|
||||
appkind: ''
|
||||
chaosServiceAccount: pod-http-modify-header-sa
|
||||
experiments:
|
||||
- name: pod-http-modify-header
|
||||
spec:
|
||||
components:
|
||||
env:
|
||||
- name: TOTAL_CHAOS_DURATION
|
||||
value: '60' # in seconds
|
||||
|
||||
# port of the target service
|
||||
- name: TARGET_SERVICE_PORT
|
||||
value: "80"
|
||||
|
||||
# map of headers to modify/add; Eg: {"X-Litmus-Test-Header": "X-Litmus-Test-Value"}
|
||||
# to remove a header, just set the value to ""; Eg: {"X-Litmus-Test-Header": ""}
|
||||
- name: HEADERS_MAP
|
||||
value: '{}'
|
||||
|
||||
# whether to modify response headers or request headers. Accepted values: request, response
|
||||
- name: HEADER_MODE
|
||||
value: 'response'
|
||||
|
||||
# provide the name of container runtime
|
||||
# it supports docker, containerd, crio
|
||||
- name: CONTAINER_RUNTIME
|
||||
value: 'containerd'
|
||||
|
||||
# provide the socket file path
|
||||
- name: SOCKET_PATH
|
||||
value: '/run/containerd/containerd.sock'
|
||||
|
||||
## percentage of total pods to target
|
||||
- name: PODS_AFFECTED_PERC
|
||||
value: ''
|
||||
|
||||
145
faults/kubernetes/pod-http-modify-header/fault.yaml
Normal file
145
faults/kubernetes/pod-http-modify-header/fault.yaml
Normal file
@@ -0,0 +1,145 @@
|
||||
---
|
||||
apiVersion: litmuschaos.io/v1alpha1
|
||||
description:
|
||||
message: |
|
||||
It injects the chaos inside the pod which modifies the header of the request/response from the provided application server to the headers provided by the user and reverts after a specified duration
|
||||
kind: ChaosExperiment
|
||||
metadata:
|
||||
name: pod-http-modify-header
|
||||
labels:
|
||||
name: pod-http-modify-header
|
||||
app.kubernetes.io/part-of: litmus
|
||||
app.kubernetes.io/component: chaosexperiment
|
||||
app.kubernetes.io/version: ci
|
||||
spec:
|
||||
definition:
|
||||
scope: Namespaced
|
||||
permissions:
|
||||
# Create and monitor the experiment & helper pods
|
||||
- apiGroups: [""]
|
||||
resources: ["pods"]
|
||||
verbs: ["create", "delete", "get", "list", "patch", "update", "deletecollection"]
|
||||
# Performs CRUD operations on the events inside chaosengine and chaosresult
|
||||
- apiGroups: [""]
|
||||
resources: ["events"]
|
||||
verbs: ["create", "get", "list", "patch", "update"]
|
||||
# Fetch configmaps details and mount it to the experiment pod (if specified)
|
||||
- apiGroups: [""]
|
||||
resources: ["configmaps"]
|
||||
verbs: ["get", "list"]
|
||||
# Track and get the runner, experiment, and helper pods log
|
||||
- apiGroups: [""]
|
||||
resources: ["pods/log"]
|
||||
verbs: ["get", "list", "watch"]
|
||||
# for creating and managing to execute commands inside target container
|
||||
- apiGroups: [""]
|
||||
resources: ["pods/exec"]
|
||||
verbs: ["get", "list", "create"]
|
||||
# deriving the parent/owner details of the pod(if parent is anyof {deployment, statefulset, daemonsets})
|
||||
- apiGroups: ["apps"]
|
||||
resources: ["deployments", "statefulsets", "replicasets", "daemonsets"]
|
||||
verbs: ["list", "get"]
|
||||
# deriving the parent/owner details of the pod(if parent is deploymentConfig)
|
||||
- apiGroups: ["apps.openshift.io"]
|
||||
resources: ["deploymentconfigs"]
|
||||
verbs: ["list", "get"]
|
||||
# deriving the parent/owner details of the pod(if parent is deploymentConfig)
|
||||
- apiGroups: [""]
|
||||
resources: ["replicationcontrollers"]
|
||||
verbs: ["get", "list"]
|
||||
# deriving the parent/owner details of the pod(if parent is argo-rollouts)
|
||||
- apiGroups: ["argoproj.io"]
|
||||
resources: ["rollouts"]
|
||||
verbs: ["list", "get"]
|
||||
# for configuring and monitor the experiment job by the chaos-runner pod
|
||||
- apiGroups: ["batch"]
|
||||
resources: ["jobs"]
|
||||
verbs: ["create", "list", "get", "delete", "deletecollection"]
|
||||
# for creation, status polling and deletion of litmus chaos resources used within a chaos workflow
|
||||
- apiGroups: ["litmuschaos.io"]
|
||||
resources: ["chaosengines", "chaosexperiments", "chaosresults"]
|
||||
verbs: ["create", "list", "get", "patch", "update", "delete"]
|
||||
image: "chaosnative/go-runner:ci"
|
||||
imagePullPolicy: Always
|
||||
args:
|
||||
- -c
|
||||
- ./experiments -name pod-http-modify-header
|
||||
command:
|
||||
- /bin/bash
|
||||
env:
|
||||
- name: TARGET_CONTAINER
|
||||
value: ''
|
||||
|
||||
# provide lib image
|
||||
- name: LIB_IMAGE
|
||||
value: 'chaosnative/go-runner:ci'
|
||||
|
||||
# map of headers to modify/add; Eg: {"X-Litmus-Test-Header": "X-Litmus-Test-Value"}
|
||||
# to remove a header, just set the value to ""; Eg: {"X-Litmus-Test-Header": ""}
|
||||
- name: HEADERS_MAP
|
||||
value: '{}'
|
||||
|
||||
# whether to modify response headers or request headers. Accepted values: request, response
|
||||
- name: HEADER_MODE
|
||||
value: 'response'
|
||||
|
||||
# port of the target service
|
||||
- name: TARGET_SERVICE_PORT
|
||||
value: "80"
|
||||
|
||||
# toxicity is the probability of the request to be affected
|
||||
# provide the percentage value in the range of 0-100
|
||||
# 0 means no request will be affected and 100 means all request will be affected
|
||||
- name: TOXICITY
|
||||
value: "100"
|
||||
|
||||
# port on which the proxy will listen
|
||||
- name: PROXY_PORT
|
||||
value: "20000"
|
||||
|
||||
# network interface on which the proxy will listen
|
||||
- name: NETWORK_INTERFACE
|
||||
value: "eth0"
|
||||
|
||||
- name: TOTAL_CHAOS_DURATION
|
||||
value: '60' # in seconds
|
||||
|
||||
# Time period to wait before and after injection of chaos in sec
|
||||
- name: RAMP_TIME
|
||||
value: ''
|
||||
|
||||
- name: DEFAULT_HEALTH_CHECK
|
||||
value: 'false'
|
||||
|
||||
# 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: 'containerd'
|
||||
|
||||
# provide the socket file path
|
||||
- name: SOCKET_PATH
|
||||
value: '/run/containerd/containerd.sock'
|
||||
|
||||
# To select pods on specific node(s)
|
||||
- name: NODE_LABEL
|
||||
value: ''
|
||||
|
||||
## it defines the sequence of chaos execution for multiple target pods
|
||||
## supported values: serial, parallel
|
||||
- name: SEQUENCE
|
||||
value: 'parallel'
|
||||
|
||||
labels:
|
||||
name: pod-http-modify-header
|
||||
app.kubernetes.io/part-of: litmus
|
||||
app.kubernetes.io/component: experiment-job
|
||||
app.kubernetes.io/runtime-api-usage: "true"
|
||||
app.kubernetes.io/version: ci
|
||||
@@ -0,0 +1,31 @@
|
||||
---
|
||||
apiVersion: litmuschaos.io/v1alpha1
|
||||
kind: ChartServiceVersion
|
||||
metadata:
|
||||
name: pod-http-modify-header
|
||||
version: 0.1.0
|
||||
annotations:
|
||||
categories: Kubernetes
|
||||
vendor: CNCF
|
||||
spec:
|
||||
displayName: Pod HTTP Modify Header
|
||||
categoryDescription: |
|
||||
Pod-http-modify-header fault disrupts HTTP requests of kubernetes pods. This fault can modify headers of incoming requests or the response from the service targetted.
|
||||
- Causes modification of request/response headers of the HTTP request.
|
||||
- The application pod should be healthy once chaos is stopped. Service-requests should be served despite chaos.
|
||||
keywords:
|
||||
- Kubernetes
|
||||
platforms:
|
||||
- GKE
|
||||
- Minikube
|
||||
- EKS
|
||||
minKubeVersion: 1.12.0
|
||||
labels:
|
||||
app.kubernetes.io/component: chartserviceversion
|
||||
app.kubernetes.io/version: ci
|
||||
icon:
|
||||
- base64data: ""
|
||||
mediatype: ""
|
||||
links:
|
||||
- name: Documentation
|
||||
url: https://docs.harness.io/category/kl0mxwpfw1-hce-category
|
||||
49
faults/kubernetes/pod-http-reset-peer/engine.yaml
Normal file
49
faults/kubernetes/pod-http-reset-peer/engine.yaml
Normal file
@@ -0,0 +1,49 @@
|
||||
---
|
||||
apiVersion: litmuschaos.io/v1alpha1
|
||||
kind: ChaosEngine
|
||||
metadata:
|
||||
name: nginx-chaos
|
||||
namespace: default
|
||||
spec:
|
||||
# It can be active/stop
|
||||
engineState: 'active'
|
||||
appinfo:
|
||||
appns: ''
|
||||
# FYI, To see app label, apply kubectl get pods --show-labels
|
||||
applabel: ''
|
||||
appkind: ''
|
||||
chaosServiceAccount: pod-http-reset-peer-sa
|
||||
experiments:
|
||||
- name: pod-http-reset-peer
|
||||
spec:
|
||||
components:
|
||||
env:
|
||||
# set chaos duration (in sec) as desired
|
||||
- name: TOTAL_CHAOS_DURATION
|
||||
value: '60' # in seconds
|
||||
|
||||
# reset timeout specifies after how much duration to reset the connection
|
||||
- name: RESET_TIMEOUT
|
||||
value: '0' #in ms
|
||||
|
||||
# port of the target service
|
||||
- name: TARGET_SERVICE_PORT
|
||||
value: "80"
|
||||
|
||||
- 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: 'containerd'
|
||||
|
||||
# provide the socket file path
|
||||
- name: SOCKET_PATH
|
||||
value: '/run/containerd/containerd.sock'
|
||||
|
||||
## percentage of total pods to target
|
||||
- name: PODS_AFFECTED_PERC
|
||||
value: ''
|
||||
|
||||
139
faults/kubernetes/pod-http-reset-peer/fault.yaml
Normal file
139
faults/kubernetes/pod-http-reset-peer/fault.yaml
Normal file
@@ -0,0 +1,139 @@
|
||||
---
|
||||
apiVersion: litmuschaos.io/v1alpha1
|
||||
description:
|
||||
message: |
|
||||
it injects chaos into the pod which stops outgoing HTTP requests by resetting the TCP connection and then reverts back to the original state after a specified duration
|
||||
kind: ChaosExperiment
|
||||
metadata:
|
||||
name: pod-http-reset-peer
|
||||
labels:
|
||||
name: pod-http-reset-peer
|
||||
app.kubernetes.io/part-of: litmus
|
||||
app.kubernetes.io/component: chaosexperiment
|
||||
app.kubernetes.io/version: ci
|
||||
spec:
|
||||
definition:
|
||||
scope: Namespaced
|
||||
permissions:
|
||||
# Create and monitor the experiment & helper pods
|
||||
- apiGroups: [""]
|
||||
resources: ["pods"]
|
||||
verbs: ["create", "delete", "get", "list", "patch", "update", "deletecollection"]
|
||||
# Performs CRUD operations on the events inside chaosengine and chaosresult
|
||||
- apiGroups: [""]
|
||||
resources: ["events"]
|
||||
verbs: ["create", "get", "list", "patch", "update"]
|
||||
# Fetch configmaps details and mount it to the experiment pod (if specified)
|
||||
- apiGroups: [""]
|
||||
resources: ["configmaps"]
|
||||
verbs: ["get", "list"]
|
||||
# Track and get the runner, experiment, and helper pods log
|
||||
- apiGroups: [""]
|
||||
resources: ["pods/log"]
|
||||
verbs: ["get", "list", "watch"]
|
||||
# for creating and managing to execute commands inside target container
|
||||
- apiGroups: [""]
|
||||
resources: ["pods/exec"]
|
||||
verbs: ["get", "list", "create"]
|
||||
# deriving the parent/owner details of the pod(if parent is anyof {deployment, statefulset, daemonsets})
|
||||
- apiGroups: ["apps"]
|
||||
resources: ["deployments", "statefulsets", "replicasets", "daemonsets"]
|
||||
verbs: ["list", "get"]
|
||||
# deriving the parent/owner details of the pod(if parent is deploymentConfig)
|
||||
- apiGroups: ["apps.openshift.io"]
|
||||
resources: ["deploymentconfigs"]
|
||||
verbs: ["list", "get"]
|
||||
# deriving the parent/owner details of the pod(if parent is deploymentConfig)
|
||||
- apiGroups: [""]
|
||||
resources: ["replicationcontrollers"]
|
||||
verbs: ["get", "list"]
|
||||
# deriving the parent/owner details of the pod(if parent is argo-rollouts)
|
||||
- apiGroups: ["argoproj.io"]
|
||||
resources: ["rollouts"]
|
||||
verbs: ["list", "get"]
|
||||
# for configuring and monitor the experiment job by the chaos-runner pod
|
||||
- apiGroups: ["batch"]
|
||||
resources: ["jobs"]
|
||||
verbs: ["create", "list", "get", "delete", "deletecollection"]
|
||||
# for creation, status polling and deletion of litmus chaos resources used within a chaos workflow
|
||||
- apiGroups: ["litmuschaos.io"]
|
||||
resources: ["chaosengines", "chaosexperiments", "chaosresults"]
|
||||
verbs: ["create", "list", "get", "patch", "update", "delete"]
|
||||
image: "chaosnative/go-runner:ci"
|
||||
imagePullPolicy: Always
|
||||
args:
|
||||
- -c
|
||||
- ./experiments -name pod-http-reset-peer
|
||||
command:
|
||||
- /bin/bash
|
||||
env:
|
||||
- name: TARGET_CONTAINER
|
||||
value: ''
|
||||
|
||||
# provide lib image
|
||||
- name: LIB_IMAGE
|
||||
value: 'chaosnative/go-runner:ci'
|
||||
|
||||
# reset timeout specifies after how much duration to reset the connection
|
||||
- name: RESET_TIMEOUT
|
||||
value: '0' #in ms
|
||||
|
||||
# port of the target service
|
||||
- name: TARGET_SERVICE_PORT
|
||||
value: "80"
|
||||
|
||||
# toxicity is the probability of the request to be affected
|
||||
# provide the percentage value in the range of 0-100
|
||||
# 0 means no request will be affected and 100 means all request will be affected
|
||||
- name: TOXICITY
|
||||
value: "100"
|
||||
|
||||
# port on which the proxy will listen
|
||||
- name: PROXY_PORT
|
||||
value: "20000"
|
||||
|
||||
# network interface on which the proxy will listen
|
||||
- name: NETWORK_INTERFACE
|
||||
value: "eth0"
|
||||
|
||||
- name: TOTAL_CHAOS_DURATION
|
||||
value: '60' # in seconds
|
||||
|
||||
# Time period to wait before and after injection of chaos in sec
|
||||
- name: RAMP_TIME
|
||||
value: ''
|
||||
|
||||
- name: DEFAULT_HEALTH_CHECK
|
||||
value: 'false'
|
||||
|
||||
# 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: 'containerd'
|
||||
|
||||
# provide the socket file path
|
||||
- name: SOCKET_PATH
|
||||
value: '/run/containerd/containerd.sock'
|
||||
|
||||
# To select pods on specific node(s)
|
||||
- name: NODE_LABEL
|
||||
value: ''
|
||||
|
||||
## it defines the sequence of chaos execution for multiple target pods
|
||||
## supported values: serial, parallel
|
||||
- name: SEQUENCE
|
||||
value: 'parallel'
|
||||
|
||||
labels:
|
||||
name: pod-http-reset-peer
|
||||
app.kubernetes.io/part-of: litmus
|
||||
app.kubernetes.io/component: experiment-job
|
||||
app.kubernetes.io/version: ci
|
||||
@@ -0,0 +1,28 @@
|
||||
---
|
||||
apiVersion: litmuschaos.io/v1alpha1
|
||||
kind: ChartServiceVersion
|
||||
metadata:
|
||||
name: pod-http-reset-peer
|
||||
version: 0.1.0
|
||||
annotations:
|
||||
categories: kubernetes
|
||||
spec:
|
||||
displayName: Pod HTTP Reset Peer
|
||||
categoryDescription: >
|
||||
pod-http-reset-peer fault disrupts HTTP requests of kubernetes pods. This fault can stop outgoing HTTP requests by resetting the TCP connection on the service targetted.
|
||||
- Causes connection failure (connection reset by peer) of the HTTP request.
|
||||
- The application pod should be healthy once chaos is stopped. Service-requests should be served despite chaos.
|
||||
keywords:
|
||||
- kubernetes
|
||||
platforms:
|
||||
- "Minikube"
|
||||
minKubeVersion: 1.12.0
|
||||
labels:
|
||||
app.kubernetes.io/component: chartserviceversion
|
||||
app.kubernetes.io/version: ci
|
||||
links:
|
||||
- name: Documentation
|
||||
url: https://docs.harness.io/category/kl0mxwpfw1-hce-category
|
||||
icon:
|
||||
- base64data: ""
|
||||
mediatype: ""
|
||||
54
faults/kubernetes/pod-http-status-code/engine.yaml
Normal file
54
faults/kubernetes/pod-http-status-code/engine.yaml
Normal file
@@ -0,0 +1,54 @@
|
||||
---
|
||||
apiVersion: litmuschaos.io/v1alpha1
|
||||
kind: ChaosEngine
|
||||
metadata:
|
||||
name: nginx-chaos
|
||||
spec:
|
||||
# It can be active/stop
|
||||
engineState: 'active'
|
||||
appinfo:
|
||||
appns: ''
|
||||
applabel: ''
|
||||
appkind: ''
|
||||
chaosServiceAccount: pod-http-status-code-sa
|
||||
experiments:
|
||||
- name: pod-http-status-code
|
||||
spec:
|
||||
components:
|
||||
env:
|
||||
# set chaos duration (in sec) as desired
|
||||
- name: TOTAL_CHAOS_DURATION
|
||||
value: '30'
|
||||
|
||||
# set chaos interval (in sec) as desired
|
||||
- name: CHAOS_INTERVAL
|
||||
value: '10'
|
||||
|
||||
# modified status code for the HTTP response
|
||||
# if no value is provided, a random status code from the supported code list will selected
|
||||
# if an invalid status code is provided, the experiment will fail
|
||||
# supported status code list: [200, 201, 202, 204, 300, 301, 302, 304, 307, 400, 401, 403, 404, 500, 501, 502, 503, 504
|
||||
- name: STATUS_CODE
|
||||
value: ''
|
||||
|
||||
# whether to modify the body as per the status code provided
|
||||
- name: "MODIFY_RESPONSE_BODY"
|
||||
value: "true"
|
||||
|
||||
# port of the target service
|
||||
- name: TARGET_SERVICE_PORT
|
||||
value: "80"
|
||||
|
||||
# provide the name of container runtime
|
||||
# it supports docker, containerd, crio
|
||||
- name: CONTAINER_RUNTIME
|
||||
value: 'containerd'
|
||||
|
||||
# provide the socket file path
|
||||
- name: SOCKET_PATH
|
||||
value: '/run/containerd/containerd.sock'
|
||||
|
||||
## percentage of total pods to target
|
||||
- name: PODS_AFFECTED_PERC
|
||||
value: ''
|
||||
|
||||
160
faults/kubernetes/pod-http-status-code/fault.yaml
Normal file
160
faults/kubernetes/pod-http-status-code/fault.yaml
Normal file
@@ -0,0 +1,160 @@
|
||||
---
|
||||
apiVersion: litmuschaos.io/v1alpha1
|
||||
description:
|
||||
message: |
|
||||
It injects chaos inside the pod which modifies the status code of the response from the provided application server to desired status code provided by the user and reverts after a specified duration
|
||||
kind: ChaosExperiment
|
||||
metadata:
|
||||
name: pod-http-status-code
|
||||
labels:
|
||||
name: pod-http-status-code
|
||||
app.kubernetes.io/part-of: litmus
|
||||
app.kubernetes.io/component: chaosexperiment
|
||||
app.kubernetes.io/version: ci
|
||||
spec:
|
||||
definition:
|
||||
scope: Namespaced
|
||||
permissions:
|
||||
# Create and monitor the experiment & helper pods
|
||||
- apiGroups: [""]
|
||||
resources: ["pods"]
|
||||
verbs: ["create", "delete", "get", "list", "patch", "update", "deletecollection"]
|
||||
# Performs CRUD operations on the events inside chaosengine and chaosresult
|
||||
- apiGroups: [""]
|
||||
resources: ["events"]
|
||||
verbs: ["create", "get", "list", "patch", "update"]
|
||||
# Fetch configmaps details and mount it to the experiment pod (if specified)
|
||||
- apiGroups: [""]
|
||||
resources: ["configmaps"]
|
||||
verbs: ["get", "list"]
|
||||
# Track and get the runner, experiment, and helper pods log
|
||||
- apiGroups: [""]
|
||||
resources: ["pods/log"]
|
||||
verbs: ["get", "list", "watch"]
|
||||
# for creating and managing to execute commands inside target container
|
||||
- apiGroups: [""]
|
||||
resources: ["pods/exec"]
|
||||
verbs: ["get", "list", "create"]
|
||||
# deriving the parent/owner details of the pod(if parent is anyof {deployment, statefulset, daemonsets})
|
||||
- apiGroups: ["apps"]
|
||||
resources: ["deployments", "statefulsets", "replicasets", "daemonsets"]
|
||||
verbs: ["list", "get"]
|
||||
# deriving the parent/owner details of the pod(if parent is deploymentConfig)
|
||||
- apiGroups: ["apps.openshift.io"]
|
||||
resources: ["deploymentconfigs"]
|
||||
verbs: ["list", "get"]
|
||||
# deriving the parent/owner details of the pod(if parent is deploymentConfig)
|
||||
- apiGroups: [""]
|
||||
resources: ["replicationcontrollers"]
|
||||
verbs: ["get", "list"]
|
||||
# deriving the parent/owner details of the pod(if parent is argo-rollouts)
|
||||
- apiGroups: ["argoproj.io"]
|
||||
resources: ["rollouts"]
|
||||
verbs: ["list", "get"]
|
||||
# for configuring and monitor the experiment job by the chaos-runner pod
|
||||
- apiGroups: ["batch"]
|
||||
resources: ["jobs"]
|
||||
verbs: ["create", "list", "get", "delete", "deletecollection"]
|
||||
# for creation, status polling and deletion of litmus chaos resources used within a chaos workflow
|
||||
- apiGroups: ["litmuschaos.io"]
|
||||
resources: ["chaosengines", "chaosexperiments", "chaosresults"]
|
||||
verbs: ["create", "list", "get", "patch", "update", "delete"]
|
||||
image: "chaosnative/go-runner:ci"
|
||||
imagePullPolicy: Always
|
||||
args:
|
||||
- -c
|
||||
- ./experiments -name pod-http-status-code
|
||||
command:
|
||||
- /bin/bash
|
||||
env:
|
||||
- name: TARGET_CONTAINER
|
||||
value: ''
|
||||
|
||||
# provide lib image
|
||||
- name: LIB_IMAGE
|
||||
value: 'chaosnative/go-runner:ci'
|
||||
|
||||
# modified status code for the HTTP response
|
||||
# if no value is provided, a random status code from the supported code list will selected
|
||||
# if an invalid status code is provided, the experiment will fail
|
||||
# supported status code list: [200, 201, 202, 204, 300, 301, 302, 304, 307, 400, 401, 403, 404, 500, 501, 502, 503, 504]
|
||||
- name: STATUS_CODE
|
||||
value: ''
|
||||
|
||||
# whether to modify the body as per the status code provided
|
||||
- name: "MODIFY_RESPONSE_BODY"
|
||||
value: "true"
|
||||
|
||||
# provide the body string to overwrite the response body. This will be used only if MODIFY_RESPONSE_BODY is set to true
|
||||
- name: RESPONSE_BODY
|
||||
value: ''
|
||||
|
||||
# provide the encoding type for the response body
|
||||
# currently supported value are gzip, deflate
|
||||
# if empty no encoding will be applied
|
||||
- name: CONTENT_ENCODING
|
||||
value: ''
|
||||
|
||||
# provide the content type for the response body
|
||||
- name: CONTENT_TYPE
|
||||
value: 'text/plain'
|
||||
|
||||
# port of the target service
|
||||
- name: TARGET_SERVICE_PORT
|
||||
value: "80"
|
||||
|
||||
# toxicity is the probability of the request to be affected
|
||||
# provide the percentage value in the range of 0-100
|
||||
# 0 means no request will be affected and 100 means all request will be affected
|
||||
- name: TOXICITY
|
||||
value: "100"
|
||||
|
||||
# port on which the proxy will listen
|
||||
- name: PROXY_PORT
|
||||
value: "20000"
|
||||
|
||||
# network interface on which the proxy will listen
|
||||
- name: NETWORK_INTERFACE
|
||||
value: "eth0"
|
||||
|
||||
- name: TOTAL_CHAOS_DURATION
|
||||
value: '60' # in seconds
|
||||
|
||||
# Time period to wait before and after injection of chaos in sec
|
||||
- name: RAMP_TIME
|
||||
value: ''
|
||||
|
||||
- name: DEFAULT_HEALTH_CHECK
|
||||
value: 'false'
|
||||
|
||||
# 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: 'containerd'
|
||||
|
||||
# provide the socket file path
|
||||
- name: SOCKET_PATH
|
||||
value: '/run/containerd/containerd.sock'
|
||||
|
||||
# To select pods on specific node(s)
|
||||
- name: NODE_LABEL
|
||||
value: ''
|
||||
|
||||
## it defines the sequence of chaos execution for multiple target pods
|
||||
## supported values: serial, parallel
|
||||
- name: SEQUENCE
|
||||
value: 'parallel'
|
||||
|
||||
labels:
|
||||
name: pod-http-status-code
|
||||
app.kubernetes.io/part-of: litmus
|
||||
app.kubernetes.io/component: experiment-job
|
||||
app.kubernetes.io/version: ci
|
||||
@@ -0,0 +1,28 @@
|
||||
---
|
||||
apiVersion: litmuschaos.io/v1alpha1
|
||||
kind: ChartServiceVersion
|
||||
metadata:
|
||||
name: pod-http-status-code
|
||||
version: 0.1.0
|
||||
annotations:
|
||||
categories: kubernetes
|
||||
spec:
|
||||
displayName: Pod HTTP Status Code
|
||||
categoryDescription: >
|
||||
pod-http-status-code fault disrupts HTTP requests of kubernetes pods. This fault can modify the status code of the response on the service targetted.
|
||||
- Causes modification of status code of the HTTP request.
|
||||
- The application pod should be healthy once chaos is stopped. Service-requests should be served despite chaos.
|
||||
keywords:
|
||||
- kubernetes
|
||||
platforms:
|
||||
- "Minikube"
|
||||
minKubeVersion: 1.12.0
|
||||
labels:
|
||||
app.kubernetes.io/component: chartserviceversion
|
||||
app.kubernetes.io/version: ci
|
||||
links:
|
||||
- name: Documentation
|
||||
url: https://docs.harness.io/category/kl0mxwpfw1-hce-category
|
||||
icon:
|
||||
- base64data: ""
|
||||
mediatype: ""
|
||||
39
faults/kubernetes/pod-io-stress/engine.yaml
Normal file
39
faults/kubernetes/pod-io-stress/engine.yaml
Normal file
@@ -0,0 +1,39 @@
|
||||
---
|
||||
apiVersion: litmuschaos.io/v1alpha1
|
||||
kind: ChaosEngine
|
||||
metadata:
|
||||
name: nginx-chaos
|
||||
namespace: default
|
||||
spec:
|
||||
# It can be active/stop
|
||||
engineState: 'active'
|
||||
appinfo:
|
||||
appns: ''
|
||||
applabel: ''
|
||||
appkind: ''
|
||||
chaosServiceAccount: pod-io-stress-sa
|
||||
experiments:
|
||||
- name: pod-io-stress
|
||||
spec:
|
||||
components:
|
||||
env:
|
||||
# set chaos duration (in sec) as desired
|
||||
- name: TOTAL_CHAOS_DURATION
|
||||
value: '120'
|
||||
|
||||
## specify the size as percentage of free space on the file system
|
||||
- name: FILESYSTEM_UTILIZATION_PERCENTAGE
|
||||
value: '10'
|
||||
|
||||
## Percentage of total pods to target
|
||||
- name: PODS_AFFECTED_PERC
|
||||
value: ''
|
||||
|
||||
## provide the cluster runtime
|
||||
- name: CONTAINER_RUNTIME
|
||||
value: 'containerd'
|
||||
|
||||
# provide the socket file path
|
||||
- name: SOCKET_PATH
|
||||
value: '/run/containerd/containerd.sock'
|
||||
|
||||
135
faults/kubernetes/pod-io-stress/fault.yaml
Normal file
135
faults/kubernetes/pod-io-stress/fault.yaml
Normal file
@@ -0,0 +1,135 @@
|
||||
---
|
||||
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: ci
|
||||
spec:
|
||||
definition:
|
||||
scope: Namespaced
|
||||
permissions:
|
||||
# Create and monitor the experiment & helper pods
|
||||
- apiGroups: [""]
|
||||
resources: ["pods"]
|
||||
verbs: ["create", "delete", "get", "list", "patch", "update", "deletecollection"]
|
||||
# Performs CRUD operations on the events inside chaosengine and chaosresult
|
||||
- apiGroups: [""]
|
||||
resources: ["events"]
|
||||
verbs: ["create", "get", "list", "patch", "update"]
|
||||
# Fetch configmaps details and mount it to the experiment pod (if specified)
|
||||
- apiGroups: [""]
|
||||
resources: ["configmaps"]
|
||||
verbs: ["get", "list"]
|
||||
# Track and get the runner, experiment, and helper pods log
|
||||
- apiGroups: [""]
|
||||
resources: ["pods/log"]
|
||||
verbs: ["get", "list", "watch"]
|
||||
# for creating and managing to execute commands inside target container
|
||||
- apiGroups: [""]
|
||||
resources: ["pods/exec"]
|
||||
verbs: ["get", "list", "create"]
|
||||
# deriving the parent/owner details of the pod(if parent is anyof {deployment, statefulset, daemonsets})
|
||||
- apiGroups: ["apps"]
|
||||
resources: ["deployments", "statefulsets", "replicasets", "daemonsets"]
|
||||
verbs: ["list", "get"]
|
||||
# deriving the parent/owner details of the pod(if parent is deploymentConfig)
|
||||
- apiGroups: ["apps.openshift.io"]
|
||||
resources: ["deploymentconfigs"]
|
||||
verbs: ["list", "get"]
|
||||
# deriving the parent/owner details of the pod(if parent is deploymentConfig)
|
||||
- apiGroups: [""]
|
||||
resources: ["replicationcontrollers"]
|
||||
verbs: ["get", "list"]
|
||||
# deriving the parent/owner details of the pod(if parent is argo-rollouts)
|
||||
- apiGroups: ["argoproj.io"]
|
||||
resources: ["rollouts"]
|
||||
verbs: ["list", "get"]
|
||||
# for configuring and monitor the experiment job by the chaos-runner pod
|
||||
- apiGroups: ["batch"]
|
||||
resources: ["jobs"]
|
||||
verbs: ["create", "list", "get", "delete", "deletecollection"]
|
||||
# for creation, status polling and deletion of litmus chaos resources used within a chaos workflow
|
||||
- apiGroups: ["litmuschaos.io"]
|
||||
resources: ["chaosengines", "chaosexperiments", "chaosresults"]
|
||||
verbs: ["create", "list", "get", "patch", "update", "delete"]
|
||||
image: "chaosnative/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: ''
|
||||
|
||||
- name: TARGET_CONTAINER
|
||||
value: ''
|
||||
|
||||
## specify the comma separated target pods
|
||||
- name: TARGET_PODS
|
||||
value: ''
|
||||
|
||||
# To select pods on specific node(s)
|
||||
- name: NODE_LABEL
|
||||
value: ''
|
||||
|
||||
# Period to wait before and after injection of chaos in sec
|
||||
- name: RAMP_TIME
|
||||
value: ''
|
||||
|
||||
# provide lib image
|
||||
- name: LIB_IMAGE
|
||||
value: 'chaosnative/go-runner:ci'
|
||||
|
||||
- name: DEFAULT_HEALTH_CHECK
|
||||
value: 'false'
|
||||
|
||||
## provide the cluster runtime
|
||||
- name: CONTAINER_RUNTIME
|
||||
value: 'containerd'
|
||||
|
||||
# provide the socket file path
|
||||
- name: SOCKET_PATH
|
||||
value: '/run/containerd/containerd.sock'
|
||||
|
||||
## it defines the sequence of chaos execution for multiple target pods
|
||||
## supported values: serial, parallel
|
||||
- name: SEQUENCE
|
||||
value: 'parallel'
|
||||
|
||||
labels:
|
||||
name: pod-io-stress
|
||||
app.kubernetes.io/part-of: litmus
|
||||
app.kubernetes.io/component: experiment-job
|
||||
app.kubernetes.io/runtime-api-usage: "true"
|
||||
app.kubernetes.io/version: ci
|
||||
Some files were not shown because too many files have changed in this diff Show More
Reference in New Issue
Block a user