d482aa76af
* adds metadata.annotation in chaosengine and replaces install-chaos-faults step to use artifacts.data.raw manifests Signed-off-by: neelanjan00 <neelanjan.manna@harness.io> * fixes annotation -> annotations Signed-off-by: neelanjan00 <neelanjan.manna@harness.io> * updates labels Signed-off-by: neelanjan00 <neelanjan.manna@harness.io> --------- Signed-off-by: neelanjan00 <neelanjan.manna@harness.io>
1139 lines
50 KiB
YAML
1139 lines
50 KiB
YAML
apiVersion: argoproj.io/v1alpha1
|
|
kind: CronWorkflow
|
|
metadata:
|
|
name: argowf-chaos-sock-shop-resiliency-cron-wf
|
|
namespace: litmus
|
|
labels:
|
|
subject: "{{workflow.parameters.appNamespace}}_sock-shop"
|
|
spec:
|
|
schedule: "0 * * * *"
|
|
concurrencyPolicy: "Forbid"
|
|
startingDeadlineSeconds: 0
|
|
workflowSpec:
|
|
entrypoint: argowf-chaos
|
|
serviceAccountName: argo-chaos
|
|
securityContext:
|
|
runAsUser: 1000
|
|
runAsNonRoot: true
|
|
arguments:
|
|
parameters:
|
|
- name: adminModeNamespace
|
|
value: "litmus"
|
|
- name: appNamespace
|
|
value: "sock-shop"
|
|
templates:
|
|
- name: argowf-chaos
|
|
steps:
|
|
- - name: install-application
|
|
template: install-application
|
|
- - name: install-chaos-faults
|
|
template: install-chaos-faults
|
|
- name: load-test
|
|
template: load-test
|
|
- - name: pod-cpu-hog
|
|
template: pod-cpu-hog
|
|
- - name: pod-delete
|
|
template: pod-delete
|
|
- - name: pod-network-loss
|
|
template: pod-network-loss
|
|
- - name: pod-memory-hog
|
|
template: pod-memory-hog
|
|
- - name: disk-fill
|
|
template: disk-fill
|
|
- - name: cleanup-chaos-resources
|
|
template: cleanup-chaos-resources
|
|
# - name: delete-application
|
|
# template: delete-application
|
|
- name: delete-loadtest
|
|
template: delete-loadtest
|
|
|
|
- name: install-application
|
|
container:
|
|
image: litmuschaos/litmus-app-deployer:latest
|
|
args: ["-namespace=sock-shop","-typeName=resilient","-operation=apply","-timeout=400", "-app=sock-shop","-scope=cluster"] #for weak provide type flagName as resilient(-typeName=weak)
|
|
|
|
- name: install-chaos-faults
|
|
inputs:
|
|
artifacts:
|
|
- name: pod-cpu-hog-2sf
|
|
path: /tmp/pod-cpu-hog-2sf.yaml
|
|
raw:
|
|
data: |
|
|
apiVersion: litmuschaos.io/v1alpha1
|
|
description:
|
|
message: |
|
|
Injects CPU consumption on pods belonging to an app deployment
|
|
kind: ChaosExperiment
|
|
metadata:
|
|
name: pod-cpu-hog
|
|
labels:
|
|
name: pod-cpu-hog
|
|
app.kubernetes.io/part-of: litmus
|
|
app.kubernetes.io/component: chaosexperiment
|
|
app.kubernetes.io/version: latest
|
|
spec:
|
|
definition:
|
|
scope: Namespaced
|
|
permissions:
|
|
# Create and monitor the experiment & helper pods
|
|
- apiGroups: [""]
|
|
resources: ["pods"]
|
|
verbs:
|
|
[
|
|
"create",
|
|
"delete",
|
|
"get",
|
|
"list",
|
|
"patch",
|
|
"update",
|
|
"deletecollection",
|
|
]
|
|
# Performs CRUD operations on the events inside chaosengine and chaosresult
|
|
- apiGroups: [""]
|
|
resources: ["events"]
|
|
verbs: ["create", "get", "list", "patch", "update"]
|
|
# Fetch configmaps details and mount it to the experiment pod (if specified)
|
|
- apiGroups: [""]
|
|
resources: ["configmaps"]
|
|
verbs: ["get", "list"]
|
|
# Track and get the runner, experiment, and helper pods log
|
|
- apiGroups: [""]
|
|
resources: ["pods/log"]
|
|
verbs: ["get", "list", "watch"]
|
|
# for creating and managing to execute 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: "litmuschaos/go-runner:latest"
|
|
imagePullPolicy: Always
|
|
args:
|
|
- -c
|
|
- ./experiments -name pod-cpu-hog
|
|
command:
|
|
- /bin/bash
|
|
env:
|
|
- name: TOTAL_CHAOS_DURATION
|
|
value: "60"
|
|
|
|
## Number of CPU cores to stress
|
|
- name: CPU_CORES
|
|
value: "1"
|
|
|
|
## LOAD CPU WITH GIVEN PERCENT LOADING FOR THE CPU STRESS WORKERS.
|
|
## 0 IS EFFECTIVELY A SLEEP (NO LOAD) AND 100 IS FULL LOADING
|
|
- name: CPU_LOAD
|
|
value: "100"
|
|
|
|
## Percentage of total pods to target
|
|
- name: PODS_AFFECTED_PERC
|
|
value: ""
|
|
|
|
## Period to wait before and after injection of chaos in sec
|
|
- name: RAMP_TIME
|
|
value: ""
|
|
|
|
## It is used in pumba lib only
|
|
- name: LIB_IMAGE
|
|
value: "litmuschaos/go-runner:latest"
|
|
|
|
## It is used in pumba lib only
|
|
- name: STRESS_IMAGE
|
|
value: "alexeiled/stress-ng:latest-ubuntu"
|
|
|
|
## provide the cluster runtime
|
|
- name: CONTAINER_RUNTIME
|
|
value: "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: latest
|
|
- name: pod-delete-rm5
|
|
path: /tmp/pod-delete-rm5.yaml
|
|
raw:
|
|
data: |
|
|
apiVersion: litmuschaos.io/v1alpha1
|
|
description:
|
|
message: |
|
|
Deletes a pod belonging to a deployment/statefulset/daemonset
|
|
kind: ChaosExperiment
|
|
metadata:
|
|
name: pod-delete
|
|
labels:
|
|
name: pod-delete
|
|
app.kubernetes.io/part-of: litmus
|
|
app.kubernetes.io/component: chaosexperiment
|
|
app.kubernetes.io/version: latest
|
|
spec:
|
|
definition:
|
|
scope: Namespaced
|
|
permissions:
|
|
# Create and monitor the experiment & helper pods
|
|
- apiGroups: [""]
|
|
resources: ["pods"]
|
|
verbs:
|
|
[
|
|
"create",
|
|
"delete",
|
|
"get",
|
|
"list",
|
|
"patch",
|
|
"update",
|
|
"deletecollection",
|
|
]
|
|
# Performs CRUD operations on the events inside chaosengine and chaosresult
|
|
- apiGroups: [""]
|
|
resources: ["events"]
|
|
verbs: ["create", "get", "list", "patch", "update"]
|
|
# Fetch configmaps details and mount it to the experiment pod (if specified)
|
|
- apiGroups: [""]
|
|
resources: ["configmaps"]
|
|
verbs: ["get", "list"]
|
|
# Track and get the runner, experiment, and helper pods log
|
|
- apiGroups: [""]
|
|
resources: ["pods/log"]
|
|
verbs: ["get", "list", "watch"]
|
|
# for creating and managing to execute 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: "litmuschaos/go-runner:latest"
|
|
imagePullPolicy: Always
|
|
args:
|
|
- -c
|
|
- ./experiments -name pod-delete
|
|
command:
|
|
- /bin/bash
|
|
env:
|
|
- name: TOTAL_CHAOS_DURATION
|
|
value: "15"
|
|
|
|
# Period to wait before and after injection of chaos in sec
|
|
- name: RAMP_TIME
|
|
value: ""
|
|
|
|
- name: FORCE
|
|
value: "true"
|
|
|
|
- name: CHAOS_INTERVAL
|
|
value: "5"
|
|
|
|
## percentage of total pods to target
|
|
- name: PODS_AFFECTED_PERC
|
|
value: ""
|
|
|
|
- name: 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: latest
|
|
- name: pod-network-loss-x1w
|
|
path: /tmp/pod-network-loss-x1w.yaml
|
|
raw:
|
|
data: |
|
|
apiVersion: litmuschaos.io/v1alpha1
|
|
description:
|
|
message: |
|
|
Injects network packet loss on pods belonging to an app deployment
|
|
kind: ChaosExperiment
|
|
metadata:
|
|
name: pod-network-loss
|
|
labels:
|
|
name: pod-network-loss
|
|
app.kubernetes.io/part-of: litmus
|
|
app.kubernetes.io/component: chaosexperiment
|
|
app.kubernetes.io/version: latest
|
|
spec:
|
|
definition:
|
|
scope: Namespaced
|
|
permissions:
|
|
# Create and monitor the experiment & helper pods
|
|
- apiGroups: [""]
|
|
resources: ["pods"]
|
|
verbs:
|
|
[
|
|
"create",
|
|
"delete",
|
|
"get",
|
|
"list",
|
|
"patch",
|
|
"update",
|
|
"deletecollection",
|
|
]
|
|
# Performs CRUD operations on the events inside chaosengine and chaosresult
|
|
- apiGroups: [""]
|
|
resources: ["events"]
|
|
verbs: ["create", "get", "list", "patch", "update"]
|
|
# Fetch configmaps details and mount it to the experiment pod (if specified)
|
|
- apiGroups: [""]
|
|
resources: ["configmaps"]
|
|
verbs: ["get", "list"]
|
|
# Track and get the runner, experiment, and helper pods log
|
|
- apiGroups: [""]
|
|
resources: ["pods/log"]
|
|
verbs: ["get", "list", "watch"]
|
|
# for creating and managing to execute 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: "litmuschaos/go-runner:latest"
|
|
imagePullPolicy: Always
|
|
args:
|
|
- -c
|
|
- ./experiments -name pod-network-loss
|
|
command:
|
|
- /bin/bash
|
|
env:
|
|
- name: TARGET_CONTAINER
|
|
value: ""
|
|
|
|
# provide lib image
|
|
- name: LIB_IMAGE
|
|
value: "litmuschaos/go-runner:latest"
|
|
|
|
- name: NETWORK_INTERFACE
|
|
value: "eth0"
|
|
|
|
- name: TC_IMAGE
|
|
value: "gaiadocker/iproute2"
|
|
|
|
- name: NETWORK_PACKET_LOSS_PERCENTAGE
|
|
value: "100" #in PERCENTAGE
|
|
|
|
- name: TOTAL_CHAOS_DURATION
|
|
value: "60" # in seconds
|
|
|
|
# time period to wait before and after injection of chaos in sec
|
|
- name: RAMP_TIME
|
|
value: ""
|
|
|
|
## percentage of total pods to target
|
|
- name: PODS_AFFECTED_PERC
|
|
value: ""
|
|
|
|
- name: DEFAULT_HEALTH_CHECK
|
|
value: "false"
|
|
|
|
- name: TARGET_PODS
|
|
value: ""
|
|
|
|
# To select pods on specific node(s)
|
|
- name: NODE_LABEL
|
|
value: ""
|
|
|
|
# provide the name of container runtime
|
|
# for litmus LIB, it supports docker, containerd, crio
|
|
# for pumba LIB, it supports docker only
|
|
- name: CONTAINER_RUNTIME
|
|
value: "containerd"
|
|
|
|
# provide the destination ips
|
|
# chaos injection will be triggered for these destination ips
|
|
- name: DESTINATION_IPS
|
|
value: ""
|
|
|
|
# provide the destination hosts
|
|
# chaos injection will be triggered for these destination hosts
|
|
- name: DESTINATION_HOSTS
|
|
value: ""
|
|
|
|
# provide the socket file path
|
|
- name: SOCKET_PATH
|
|
value: "/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-network-loss
|
|
app.kubernetes.io/part-of: litmus
|
|
app.kubernetes.io/component: experiment-job
|
|
app.kubernetes.io/runtime-api-usage: "true"
|
|
app.kubernetes.io/version: latest
|
|
- name: pod-memory-hog-49a
|
|
path: /tmp/pod-memory-hog-49a.yaml
|
|
raw:
|
|
data: |
|
|
apiVersion: litmuschaos.io/v1alpha1
|
|
description:
|
|
message: |
|
|
Injects memory consumption on pods belonging to an app deployment
|
|
kind: ChaosExperiment
|
|
metadata:
|
|
name: pod-memory-hog
|
|
labels:
|
|
name: pod-memory-hog
|
|
app.kubernetes.io/part-of: litmus
|
|
app.kubernetes.io/component: chaosexperiment
|
|
app.kubernetes.io/version: latest
|
|
spec:
|
|
definition:
|
|
scope: Namespaced
|
|
permissions:
|
|
# 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: "litmuschaos/go-runner:latest"
|
|
imagePullPolicy: Always
|
|
args:
|
|
- -c
|
|
- ./experiments -name pod-memory-hog
|
|
command:
|
|
- /bin/bash
|
|
env:
|
|
- name: TOTAL_CHAOS_DURATION
|
|
value: "60"
|
|
|
|
## enter the amount of memory in megabytes to be consumed by the application pod
|
|
- name: MEMORY_CONSUMPTION
|
|
value: "500"
|
|
|
|
## Number of workers to perform stress
|
|
- name: NUMBER_OF_WORKERS
|
|
value: "1"
|
|
|
|
## percentage of total pods to target
|
|
- name: PODS_AFFECTED_PERC
|
|
value: ""
|
|
|
|
## Period to wait before and after injection of chaos in sec
|
|
- name: RAMP_TIME
|
|
value: ""
|
|
|
|
## It is used in pumba lib only
|
|
- name: LIB_IMAGE
|
|
value: "litmuschaos/go-runner:latest"
|
|
|
|
## It is used in pumba lib only
|
|
- name: STRESS_IMAGE
|
|
value: "alexeiled/stress-ng:latest-ubuntu"
|
|
|
|
## provide the cluster runtime
|
|
- name: CONTAINER_RUNTIME
|
|
value: "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"
|
|
|
|
- name: DEFAULT_HEALTH_CHECK
|
|
value: "false"
|
|
|
|
- name: TARGET_CONTAINER
|
|
value: ""
|
|
|
|
- name: TARGET_PODS
|
|
value: ""
|
|
|
|
# To select pods on specific node(s)
|
|
- name: NODE_LABEL
|
|
value: ""
|
|
|
|
labels:
|
|
name: pod-memory-hog
|
|
app.kubernetes.io/part-of: litmus
|
|
app.kubernetes.io/component: experiment-job
|
|
app.kubernetes.io/runtime-api-usage: "true"
|
|
app.kubernetes.io/version: latest
|
|
- name: disk-fill-h7d
|
|
path: /tmp/disk-fill-h7d.yaml
|
|
raw:
|
|
data: |
|
|
apiVersion: litmuschaos.io/v1alpha1
|
|
description:
|
|
message: |
|
|
Fillup Ephemeral Storage of a Resource
|
|
kind: ChaosExperiment
|
|
metadata:
|
|
name: disk-fill
|
|
labels:
|
|
name: disk-fill
|
|
app.kubernetes.io/part-of: litmus
|
|
app.kubernetes.io/component: chaosexperiment
|
|
app.kubernetes.io/version: latest
|
|
spec:
|
|
definition:
|
|
scope: Namespaced
|
|
permissions:
|
|
# Create and monitor the experiment & helper pods
|
|
- apiGroups: [""]
|
|
resources: ["pods"]
|
|
verbs:
|
|
[
|
|
"create",
|
|
"delete",
|
|
"get",
|
|
"list",
|
|
"patch",
|
|
"update",
|
|
"deletecollection",
|
|
]
|
|
# Performs CRUD operations on the events inside chaosengine and chaosresult
|
|
- apiGroups: [""]
|
|
resources: ["events"]
|
|
verbs: ["create", "get", "list", "patch", "update"]
|
|
# Fetch configmaps details and mount it to the experiment pod (if specified)
|
|
- apiGroups: [""]
|
|
resources: ["configmaps"]
|
|
verbs: ["get", "list"]
|
|
# Track and get the runner, experiment, and helper pods log
|
|
- apiGroups: [""]
|
|
resources: ["pods/log"]
|
|
verbs: ["get", "list", "watch"]
|
|
# for creating and managing to execute 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: "litmuschaos/go-runner:latest"
|
|
imagePullPolicy: Always
|
|
args:
|
|
- -c
|
|
- ./experiments -name disk-fill
|
|
command:
|
|
- /bin/bash
|
|
env:
|
|
- name: TARGET_CONTAINER
|
|
value: ""
|
|
|
|
- name: FILL_PERCENTAGE
|
|
value: "80"
|
|
|
|
- name: TOTAL_CHAOS_DURATION
|
|
value: "60"
|
|
|
|
# Period to wait before and after injection of chaos in sec
|
|
- name: RAMP_TIME
|
|
value: ""
|
|
|
|
# provide the 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: "litmuschaos/go-runner:latest"
|
|
|
|
# Provide the container runtime path
|
|
# Default set to docker container path
|
|
- name: CONTAINER_PATH
|
|
value: "/var/lib/docker/containers"
|
|
|
|
## it defines the sequence of chaos execution for multiple target pods
|
|
## supported values: serial, parallel
|
|
- name: SEQUENCE
|
|
value: "parallel"
|
|
|
|
labels:
|
|
name: disk-fill
|
|
app.kubernetes.io/part-of: litmus
|
|
app.kubernetes.io/component: experiment-job
|
|
app.kubernetes.io/host-path-usage: "true"
|
|
app.kubernetes.io/version: latest
|
|
outputs: {}
|
|
metadata: {}
|
|
container:
|
|
name: ""
|
|
image: litmuschaos/k8s:latest
|
|
command:
|
|
- sh
|
|
- "-c"
|
|
args:
|
|
- kubectl apply -f /tmp/ -n {{workflow.parameters.adminModeNamespace}} && sleep 30
|
|
resources: {}
|
|
|
|
- name: pod-cpu-hog
|
|
inputs:
|
|
artifacts:
|
|
- name: pod-cpu-hog
|
|
path: /tmp/chaosengine.yaml
|
|
raw:
|
|
data: |
|
|
apiVersion: litmuschaos.io/v1alpha1
|
|
kind: ChaosEngine
|
|
metadata:
|
|
name: pod-cpu-hog-chaos
|
|
namespace: {{workflow.parameters.adminModeNamespace}}
|
|
labels:
|
|
context: "{{workflow.parameters.appNamespace}}_carts"
|
|
annotations: {}
|
|
spec:
|
|
appinfo:
|
|
appns: 'sock-shop'
|
|
applabel: 'name=carts'
|
|
appkind: 'deployment'
|
|
jobCleanUpPolicy: retain
|
|
engineState: 'active'
|
|
chaosServiceAccount: litmus-admin
|
|
experiments:
|
|
- name: pod-cpu-hog
|
|
spec:
|
|
probe:
|
|
- name: "check-frontend-access-url"
|
|
type: "httpProbe"
|
|
httpProbe/inputs:
|
|
url: "http://front-end.sock-shop.svc.cluster.local:80"
|
|
insecureSkipVerify: false
|
|
responseTimeout: 100
|
|
method:
|
|
get:
|
|
criteria: "=="
|
|
responseCode: "200"
|
|
mode: "Continuous"
|
|
runProperties:
|
|
probeTimeout: 1s
|
|
interval: 100ms
|
|
attempt: 2
|
|
probePollingInterval: 1s
|
|
- name: "check-probe-success"
|
|
type: "promProbe"
|
|
promProbe/inputs:
|
|
endpoint: "http://prometheus-k8s.monitoring.svc.cluster.local:9090"
|
|
query: "sum(rate(request_duration_seconds_count{job='sock-shop/front-end',route='/',status_code='200'}[20s]))*100"
|
|
comparator:
|
|
criteria: ">=" #supports >=,<=,>,<,==,!= comparision
|
|
value: "100"
|
|
mode: "Edge"
|
|
runProperties:
|
|
probeTimeout: 1s
|
|
interval: 100ms
|
|
attempt: 2
|
|
components:
|
|
env:
|
|
#number of cpu cores to be consumed
|
|
#verify the resources the app has been launched with
|
|
- name: CPU_CORES
|
|
value: '1'
|
|
- name: TOTAL_CHAOS_DURATION
|
|
value: '30' # in seconds
|
|
- name: CHAOS_KILL_COMMAND
|
|
value: "kill -9 $(ps afx | grep \"[md5sum] /dev/zero\" | awk '{print$1}' | tr '\n' ' ')"
|
|
|
|
container:
|
|
image: litmuschaos/litmus-checker:latest
|
|
args: ["-file=/tmp/chaosengine.yaml","-saveName=/tmp/engine-name"]
|
|
|
|
- name: pod-memory-hog
|
|
inputs:
|
|
artifacts:
|
|
- name: pod-memory-hog
|
|
path: /tmp/chaosengine.yaml
|
|
raw:
|
|
data: |
|
|
apiVersion: litmuschaos.io/v1alpha1
|
|
kind: ChaosEngine
|
|
metadata:
|
|
name: pod-memory-hog-chaos
|
|
namespace: {{workflow.parameters.adminModeNamespace}}
|
|
labels:
|
|
context: "{{workflow.parameters.appNamespace}}_orders"
|
|
annotations: {}
|
|
spec:
|
|
appinfo:
|
|
appns: 'sock-shop'
|
|
applabel: 'name=orders'
|
|
appkind: 'deployment'
|
|
jobCleanUpPolicy: retain
|
|
engineState: 'active'
|
|
chaosServiceAccount: litmus-admin
|
|
experiments:
|
|
- name: pod-memory-hog
|
|
spec:
|
|
probe:
|
|
- name: "check-frontend-access-url"
|
|
type: "httpProbe"
|
|
httpProbe/inputs:
|
|
url: "http://front-end.sock-shop.svc.cluster.local:80"
|
|
insecureSkipVerify: false
|
|
responseTimeout: 100
|
|
method:
|
|
get:
|
|
criteria: "=="
|
|
responseCode: "200"
|
|
mode: "Continuous"
|
|
runProperties:
|
|
probeTimeout: 1s
|
|
interval: 100ms
|
|
attempt: 2
|
|
probePollingInterval: 1s
|
|
- name: "check-probe-success"
|
|
type: "promProbe"
|
|
promProbe/inputs:
|
|
endpoint: "http://prometheus-k8s.monitoring.svc.cluster.local:9090"
|
|
query: "sum(rate(request_duration_seconds_count{job='sock-shop/front-end',route='/',status_code='200'}[20s]))*100"
|
|
comparator:
|
|
criteria: ">=" #supports >=,<=,>,<,==,!= comparision
|
|
value: "100"
|
|
mode: "Edge"
|
|
runProperties:
|
|
probeTimeout: 1s
|
|
interval: 100ms
|
|
attempt: 2
|
|
components:
|
|
env:
|
|
- name: MEMORY_CONSUMPTION
|
|
value: '500'
|
|
- name: TOTAL_CHAOS_DURATION
|
|
value: '30' # in seconds
|
|
- name: CHAOS_KILL_COMMAND
|
|
value: "kill -9 $(ps afx | grep \"[dd] if /dev/zero\" | awk '{print $1}' | tr '\n' ' ')"
|
|
|
|
container:
|
|
image: litmuschaos/litmus-checker:latest
|
|
args: ["-file=/tmp/chaosengine.yaml","-saveName=/tmp/engine-name"]
|
|
|
|
- name: pod-delete
|
|
inputs:
|
|
artifacts:
|
|
- name: pod-delete
|
|
path: /tmp/chaosengine.yaml
|
|
raw:
|
|
data: |
|
|
apiVersion: litmuschaos.io/v1alpha1
|
|
kind: ChaosEngine
|
|
metadata:
|
|
name: catalogue-pod-delete-chaos
|
|
namespace: {{workflow.parameters.adminModeNamespace}}
|
|
labels:
|
|
context: "{{workflow.env.appNamespace}}_catalogue"
|
|
annotations: {}
|
|
spec:
|
|
appinfo:
|
|
appns: 'sock-shop'
|
|
applabel: 'name=catalogue'
|
|
appkind: 'deployment'
|
|
engineState: 'active'
|
|
chaosServiceAccount: litmus-admin
|
|
jobCleanUpPolicy: 'retain'
|
|
components:
|
|
runner:
|
|
imagePullPolicy: Always
|
|
experiments:
|
|
- name: pod-delete
|
|
spec:
|
|
probe:
|
|
- name: "check-catalogue-access-url"
|
|
type: "httpProbe"
|
|
httpProbe/inputs:
|
|
url: "http://front-end.sock-shop.svc.cluster.local:80/catalogue"
|
|
insecureSkipVerify: false
|
|
responseTimeout: 100
|
|
method:
|
|
get:
|
|
criteria: "=="
|
|
responseCode: "200"
|
|
mode: "Continuous"
|
|
runProperties:
|
|
probeTimeout: 1s
|
|
interval: 100ms
|
|
attempt: 3
|
|
probePollingInterval: 1s
|
|
- name: "check-probe-success"
|
|
type: "promProbe"
|
|
promProbe/inputs:
|
|
endpoint: "http://prometheus-k8s.monitoring.svc.cluster.local:9090"
|
|
query: "sum(rate(request_duration_seconds_count{job='sock-shop/front-end',route='/',status_code='200'}[20s]))*100"
|
|
comparator:
|
|
criteria: ">=" #supports >=,<=,>,<,==,!= comparision
|
|
value: "100"
|
|
mode: "Edge"
|
|
runProperties:
|
|
probeTimeout: 1s
|
|
interval: 100ms
|
|
attempt: 2
|
|
components:
|
|
env:
|
|
- 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'
|
|
container:
|
|
image: litmuschaos/litmus-checker:latest
|
|
args: ["-file=/tmp/chaosengine.yaml","-saveName=/tmp/engine-name"]
|
|
|
|
- name: pod-network-loss
|
|
inputs:
|
|
artifacts:
|
|
- name: pod-network-loss
|
|
path: /tmp/chaosengine.yaml
|
|
raw:
|
|
data: |
|
|
apiVersion: litmuschaos.io/v1alpha1
|
|
kind: ChaosEngine
|
|
metadata:
|
|
name: pod-network-loss-chaos
|
|
namespace: {{workflow.parameters.adminModeNamespace}}
|
|
labels:
|
|
context: "{{workflow.parameters.appNamespace}}_user-db"
|
|
annotations: {}
|
|
spec:
|
|
appinfo:
|
|
appns: 'sock-shop'
|
|
applabel: 'name=user-db'
|
|
appkind: 'statefulset'
|
|
jobCleanUpPolicy: retain
|
|
engineState: 'active'
|
|
auxiliaryAppInfo: ''
|
|
chaosServiceAccount: litmus-admin
|
|
components:
|
|
runner:
|
|
imagePullPolicy: Always
|
|
experiments:
|
|
- name: pod-network-loss
|
|
spec:
|
|
probe:
|
|
- name: "check-cards-access-url"
|
|
type: "httpProbe"
|
|
httpProbe/inputs:
|
|
url: "http://front-end.sock-shop.svc.cluster.local:80/cards"
|
|
insecureSkipVerify: false
|
|
responseTimeout: 100
|
|
method:
|
|
get:
|
|
criteria: "=="
|
|
responseCode: "200"
|
|
mode: "Continuous"
|
|
runProperties:
|
|
probeTimeout: 1s
|
|
interval: 100ms
|
|
attempt: 3
|
|
probePollingInterval: 1s
|
|
- name: "check-probe-success"
|
|
type: "promProbe"
|
|
promProbe/inputs:
|
|
endpoint: "http://prometheus-k8s.monitoring.svc.cluster.local:9090"
|
|
query: "sum(rate(request_duration_seconds_count{job='sock-shop/front-end',route='/',status_code='200'}[20s]))*100"
|
|
comparator:
|
|
criteria: ">=" #supports >=,<=,>,<,==,!= comparision
|
|
value: "100"
|
|
mode: "Edge"
|
|
runProperties:
|
|
probeTimeout: 1s
|
|
interval: 100ms
|
|
attempt: 2
|
|
components:
|
|
env:
|
|
- name: TOTAL_CHAOS_DURATION
|
|
value: '30'
|
|
- name: NETWORK_INTERFACE
|
|
value: 'eth0'
|
|
- name: NETWORK_PACKET_LOSS_PERCENTAGE
|
|
value: '100'
|
|
- name: CONTAINER_RUNTIME
|
|
value: 'containerd'
|
|
- name: SOCKET_PATH
|
|
value: '/run/containerd/containerd.sock'
|
|
container:
|
|
image: litmuschaos/litmus-checker:latest
|
|
args: ["-file=/tmp/chaosengine.yaml","-saveName=/tmp/engine-name"]
|
|
|
|
- name: disk-fill
|
|
inputs:
|
|
artifacts:
|
|
- name: disk-fill
|
|
path: /tmp/chaosengine.yaml
|
|
raw:
|
|
data: |
|
|
apiVersion: litmuschaos.io/v1alpha1
|
|
kind: ChaosEngine
|
|
metadata:
|
|
name: catalogue-disk-fill
|
|
namespace: {{workflow.parameters.adminModeNamespace}}
|
|
labels:
|
|
context: "{{workflow.parameters.appNamespace}}_catalogue-db"
|
|
annotations: {}
|
|
spec:
|
|
appinfo:
|
|
appns: 'sock-shop'
|
|
applabel: 'name=catalogue-db'
|
|
appkind: 'statefulset'
|
|
engineState: 'active'
|
|
chaosServiceAccount: litmus-admin
|
|
jobCleanUpPolicy: 'retain'
|
|
components:
|
|
runner:
|
|
imagePullPolicy: Always
|
|
experiments:
|
|
- name: disk-fill
|
|
spec:
|
|
probe:
|
|
- name: "check-catalogue-db-cr-status"
|
|
type: "k8sProbe"
|
|
k8sProbe/inputs:
|
|
group: ""
|
|
version: "v1"
|
|
resource: "pods"
|
|
namespace: "sock-shop"
|
|
fieldSelector: "status.phase=Running"
|
|
labelSelector: "name=catalogue-db"
|
|
operation: "present"
|
|
mode: "Continuous"
|
|
runProperties:
|
|
probeTimeout: 1s
|
|
interval: 100ms
|
|
attempt: 1
|
|
probePollingInterval: 1s
|
|
- name: "check-probe-success"
|
|
type: "promProbe"
|
|
promProbe/inputs:
|
|
endpoint: "http://prometheus-k8s.monitoring.svc.cluster.local:9090"
|
|
query: "sum(rate(request_duration_seconds_count{job='sock-shop/front-end',route='/',status_code='200'}[20s]))*100"
|
|
comparator:
|
|
criteria: ">=" #supports >=,<=,>,<,==,!= comparision
|
|
value: "100"
|
|
mode: "Edge"
|
|
runProperties:
|
|
probeTimeout: 1s
|
|
interval: 100ms
|
|
attempt: 2
|
|
components:
|
|
env:
|
|
- name: FILL_PERCENTAGE
|
|
value: '100'
|
|
- name: TARGET_CONTAINER
|
|
value: ''
|
|
- name: TOTAL_CHAOS_DURATION
|
|
value: '30'
|
|
container:
|
|
image: litmuschaos/litmus-checker:latest
|
|
args: ["-file=/tmp/chaosengine.yaml","-saveName=/tmp/engine-name"]
|
|
|
|
- name: delete-application
|
|
container:
|
|
image: litmuschaos/litmus-app-deployer:latest
|
|
args: ["-namespace=sock-shop","-typeName=resilient","-operation=delete", "-app=sock-shop"]
|
|
|
|
- name: load-test
|
|
container:
|
|
image: litmuschaos/litmus-app-deployer:latest
|
|
args: ["-namespace=loadtest", "-app=loadtest"]
|
|
|
|
- name: delete-loadtest
|
|
container:
|
|
image: litmuschaos/litmus-app-deployer:latest
|
|
args: ["-namespace=loadtest","-operation=delete", "-app=loadtest"]
|
|
|
|
- name: cleanup-chaos-resources
|
|
container:
|
|
image: litmuschaos/k8s:latest
|
|
command: [sh, -c]
|
|
args:
|
|
[
|
|
"kubectl delete chaosengine pod-memory-hog-chaos pod-cpu-hog-chaos catalogue-pod-delete-chaos pod-network-loss-chaos -n {{workflow.parameters.adminModeNamespace}}",
|
|
]
|