Files
litmus-hub/faults/kubernetes/node-poweroff/fault.yaml
Shubham Chaudhary 625df46807 Integrate the litmus images with scarf gateway (#620)
Signed-off-by: Shubham Chaudhary <shubham.chaudhary@harness.io>
2024-01-15 18:45:11 +05:30

103 lines
3.1 KiB
YAML

---
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.docker.scarf.sh/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.docker.scarf.sh/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/