[Cherry Pick for 1.13.3] (#25)

* Fix: k8s module to create chaosengine event (#22) * Fix: k8s module to create chaosengine event Signed-off-by: udit <[email protected]> * chore (experiment) Adding vmware vm-poweroff-experiment (#24) * vm-delete-experiments-added Signed-off-by: Ubuntu <[email protected]> * Removing chaos Interval Signed-off-by: Delphine Joyneer <[email protected]> * Update README.md * Update README.md Co-authored-by: Ubuntu <[email protected]> Co-authored-by: Delphine Joyneer <[email protected]> Co-authored-by: Udit Gaurav <[email protected]> Co-authored-by: iassurewipro <[email protected]> Co-authored-by: Ubuntu <[email protected]> Co-authored-by: Delphine Joyneer <[email protected]>
litmuschaos · Apr 15, 2021 · 621671a · 621671a
1 parent 0cddede
commit 621671a
Show file tree

Hide file tree

Showing 12 changed files with 618 additions and 39 deletions.
diff --git a/.travis.yml b/.travis.yml
@@ -2,19 +2,15 @@ dist: trusty
 install: true
 language: go
 go:
-  - 1.11.2
+  - 1.14
 env:
   global:
     - GOARCH=amd64
-    - TRIVYARCH="64bit"
 
 before_install:
   - sleep 15
-  - sudo apt-get install curl
-  - export VERSION=$(curl --silent "https://api.github.com/repos/aquasecurity/trivy/releases/latest" | grep '"tag_name":' | sed -E 's/.*"v([^"]+)".*/\1/')
-  - echo ${VERSION} 
-  - wget https://github.com/aquasecurity/trivy/releases/download/v${VERSION}/trivy_${VERSION}_Linux-${TRIVYARCH}.tar.gz
-  - tar zxvf trivy_${VERSION}_Linux-${TRIVYARCH}.tar.gz
+  - wget https://github.com/aquasecurity/trivy/releases/download/v0.11.0/trivy_0.11.0_Linux-64bit.tar.gz
+  - tar zxvf trivy_0.11.0_Linux-64bit.tar.gz
 
 script:
   - make deps

diff --git a/build/ansible-runner/Dockerfile b/build/ansible-runner/Dockerfile
@@ -5,13 +5,18 @@ LABEL maintainer="LitmusChaos"
 #Installing necessary ubuntu packages
 RUN apt-get clean && \
     apt-get update --fix-missing || true && \
-    apt-get install -y --no-install-recommends python3-minimal python3-pip netcat iproute2 jq sshpass \
+    apt-get install -y --no-install-recommends python3-minimal python3-pip netcat iproute2 jq sshpass vim \
     curl openssh-client python3-setuptools && rm -rf /var/lib/apt/lists/* 
-
 RUN touch /mnt/parameters.yml
 
+
 #Installing ansible and dependencies for k8s module
-RUN pip3 install ansible==2.7.3 openshift jmespath boto boto3 ansible-lint
+RUN pip3 install cryptography==3.3.1 ansible==2.10 openshift jmespath boto boto3 
+RUN pip3 install ansible-lint==4.3.7
+RUN ansible-galaxy collection install community.kubernetes
+
+RUN file="$(ansible-lint --version)" && echo $file
+RUN file="$(pip3 --version)" && echo $file
 
 #Installing gcloud 
 RUN curl -sSL https://sdk.cloud.google.com | bash

diff --git a/chaoslib/vmware/inject_vm_failure_vm_delete.yml b/chaoslib/vmware/inject_vm_failure_vm_delete.yml
@@ -0,0 +1,86 @@
+---
+- block:
+
+    - block:
+
+        - debug:
+            msg: "***** Waiting for the ramp interval of {{ ramp_time }}s *****"
+
+        - name: "[Ramp]: Waiting for the specified ramp time before injecting chaos"
+          wait_for: timeout="{{ ramp_time }}"
+
+      when: "ramp_time is defined and ramp_time != ''"
+
+    - block:
+        - name: "[Prepare]: Generate a run id if not passed from the engine/experiment"
+          shell: echo $(mktemp) | cut -d '.' -f 2 | cut -c -6
+          register: rand_string
+
+        - set_fact:
+            run_id: "{{ rand_string.stdout | lower }}"
+      when: "run_id is not defined or run_id == ''"
+
+    - name: Getting the serviceAccountName
+      shell: >
+        kubectl get pod {{ chaos_pod_name }} -n {{ c_ns }} -o
+        custom-columns=:.spec.serviceAccountName --no-headers
+      args:
+        executable: /bin/bash
+      register: chaos_service_account
+
+    - name: "[Prepare]: Set the state of vm to stop"
+      uri:
+        url: https://{{ vcenter_server }}/rest/vcenter/vm/{{ vm_moid1 }}/power/stop
+        force_basic_auth: yes
+        validate_certs: no
+        method: POST
+        headers:
+          Cookie: "{{ login.set_cookie }}"
+      register: result1
+
+    - debug:
+        msg: "VM is powered-off"
+
+    - name: "[TimeOut]: Timeout for 1 minute"
+      pause:
+        minutes: 1
+
+    - name: "[Prepare]: Set the state of vm to start"
+      uri:
+        url: https://{{ vcenter_server }}/rest/vcenter/vm/{{ vm_moid1 }}/power/start
+        force_basic_auth: yes
+        validate_certs: no
+        method: POST
+        headers:
+          Cookie: "{{ login.set_cookie }}"
+      register: result1
+
+    - name: "[Status]: Get the current status of vm"
+      uri:
+        url: https://{{ vcenter_server }}/rest/vcenter/vm/{{ vm_moid1 }}/power/
+        force_basic_auth: yes
+        validate_certs: no
+        headers:
+          Cookie: "{{ login.set_cookie }}"
+      register: result
+      until: "'{{ result.json.value.state }}' ==  'POWERED_ON'"
+      delay: 2
+      retries: 5
+
+    - debug:
+        msg: "The state of vm is {{ result.json.value.state }}"
+
+    - fail:
+        msg: "vm-delete-chaos pod failed"
+      when: "result.json.value.state == 'POWERED_OFF'"
+
+
+    - block:
+        - debug:
+            msg: "***** Waiting for the ramp interval of {{ ramp_time }}s *****"
+
+        - name: "[Ramp]: Waiting for the specified ramp time after injecting chaos"
+          wait_for: timeout="{{ ramp_time }}"
+
+      when: "ramp_time is defined and ramp_time != ''"
+
diff --git a/experiments/vmware/vm-delete/README.md b/experiments/vmware/vm-delete/README.md
@@ -0,0 +1,229 @@
+## Experiment Metadata
+
+<table>
+  <tr>
+    <th> Type </th>
+    <th> Description  </th>
+    <th> Tested K8s Platform </th>
+  </tr>
+  <tr>
+    <td> VMWare </td>
+    <td> Stopping a VM for a certain chaos duration</td>
+    <td> EKS </td>
+  </tr>
+</table>
+
+
+## Prerequisites
+
+- Ensure that Kubernetes Version > 1.13
+- Ensure that the Litmus Chaos Operator is running by executing `kubectl get pods` in operator namespace (typically, `litmus`). If not, install from [here](https://docs.litmuschaos.io/docs/getstarted/#install-litmus)
+- Ensure that the `vm-delete` experiment resource is available in the cluster by executing `kubectl get chaosexperiments` in the desired namespace If not, install from [here](https://hub.litmuschaos.io/api/chaos/master?file=charts/vmware/vm-delete/experiment.yaml)
+- Ensure that you have sufficient Vcenter access to stop and start the vm. 
+- Ensure to create a Kubernetes secret having the Vcenter credentials in the `CHAOS_NAMESPACE`. A sample secret file looks like:
+
+```yaml
+apiVersion: v1
+kind: Secret
+metadata:
+  name: vcenter-secret
+  namespace: litmus
+type: Opaque
+stringData:
+    VCENTERSERVER: XXXXXXXXXXX
+    VCENTERUSER: XXXXXXXXXXXXX
+    VCENTERPASS: XXXXXXXXXXXXX
+```
+
+
+## Entry-Criteria
+
+-   vm is healthy before chaos injection.
+
+## Exit-Criteria
+
+-   vm is healthy post chaos injection.
+
+## Details
+
+-   Experiment uses vmware api's to start/stop the vm. 
+-   Stops a VM before bringing it back to running state after the specified chaos duration. 
+-   It helps to check the performance of the application/process running on the vmware server.
+
+
+## Integrations
+
+-   vm-delete can be effected using the chaos library: `litmus`, which makes use of vmware api's to start/stop a vm in vmware environment. 
+-   The desired chaoslib can be selected by setting the above options as value for the env variable `LIB`
+
+## Steps to Execute the Chaos Experiment
+
+- This Chaos Experiment can be triggered by creating a ChaosEngine resource on the cluster. To understand the values to provide in a ChaosEngine specification, refer [Getting Started](getstarted.md/#prepare-chaosengine)
+
+- Follow the steps in the sections below to create the chaosServiceAccount, prepare the ChaosEngine & execute the experiment.
+
+### Prepare chaosServiceAccount
+
+- Use this sample RBAC manifest to create a chaosServiceAccount in the desired (app) namespace. This example consists of the minimum necessary role permissions to execute the experiment.
+
+#### Sample Rbac Manifest
+
+[embedmd]:# (https://raw.githubusercontent.com/litmuschaos/chaos-charts/master/charts/vmware/vm-delete/rbac.yaml yaml)
+```yaml
+---
+apiVersion: v1
+kind: ServiceAccount
+metadata:
+  name: vm-delete-sa
+  namespace: default
+  labels:
+    name: vm-delete-sa
+---
+apiVersion: rbac.authorization.k8s.io/v1beta1
+kind: Role
+metadata:
+  name: vm-delete-sa
+  namespace: default
+  labels:
+    name: vm-delete-sa
+rules: [{'apiGroups': ['', 'batch', 'litmuschaos.io'], 'resources': ['jobs', 'pods', 'deployments','pods/log', 'events', 'chaosengines', 'chaosexperiments', 'chaosresults', 'secrets'], 'verbs': ['create', 'list', 'get', 'update', 'patch', 'delete','deletecollection']}]
+---
+apiVersion: rbac.authorization.k8s.io/v1beta1
+kind: RoleBinding
+metadata:
+  name: vm-delete-sa
+  namespace: default
+  labels:
+    name: vm-delete-sa
+roleRef:
+  apiGroup: rbac.authorization.k8s.io
+  kind: Role
+  name: vm-delete-sa
+subjects:
+- kind: ServiceAccount
+  name: vm-delete-sa
+  namespace: default
+```
+
+### Prepare ChaosEngine
+
+- Provide the application info in `spec.appinfo`
+- Provide the auxiliary applications info (ns & labels) in `spec.auxiliaryAppInfo`
+- Override the experiment tunables if desired in `experiments.spec.components.env`
+- To understand the values to provided in a ChaosEngine specification, refer [ChaosEngine Concepts](chaosengine-concepts.md)
+
+#### Supported Experiment Tunables
+
+<table>
+  <tr>
+    <th> Variables </th>
+    <th> Description </th>
+    <th> Specify In ChaosEngine </th>
+    <th> Notes </th>
+  </tr>
+  <tr> 
+    <td> APP_VM_MOID </td>
+    <td> Moid of the vmware instance</td>
+    <td> Required </td>
+    <td> </td>
+  </tr>
+  <tr> 
+    <td> TOTAL_CHAOS_DURATION </td>
+    <td> The time duration for chaos insertion (sec) </td>
+    <td> Optional </td>
+    <td> Defaults to 30s </td>
+  </tr>
+  <tr>
+    <td> VCENTERSERVER </td>
+    <td> IP Address of the vcenter </td>
+    <td> Required </td>
+    <td> Should be specified in secret created </td>
+  </tr>
+  <tr> 
+    <td> VCENTERUSER </td>
+    <td> Username of Vcenter </td>
+    <td> Required </td>
+    <td> Should be specified in secret created having access to start/stop the vm </td>
+  </tr>
+  <tr> 
+    <td> VCENTERPASS </td>
+    <td> Password of Vcenter </td>
+    <td> Required </td>
+    <td> Should be specified in secret created </td>
+  </tr>
+</table>
+
+#### Sample ChaosEngine Manifest
+
+[embedmd]:# (https://raw.githubusercontent.com/litmuschaos/chaos-charts/master/charts/vmware/vm-delete/engine.yaml yaml)
+```yaml
+apiVersion: litmuschaos.io/v1alpha1
+kind: ChaosEngine
+metadata:
+  name: nginx-chaos
+  namespace: default
+spec:
+  # It can be true/false
+  annotationCheck: 'false'
+  # It can be active/stop
+  engineState: 'active'
+  #ex. values: ns1:name=percona,ns2:run=nginx
+  auxiliaryAppInfo: ''
+  chaosServiceAccount: vm-delete-sa
+  monitoring: false
+  # It can be delete/retain
+  jobCleanUpPolicy: 'retain'
+  experiments:
+    - name: vm-delete
+      spec:
+        components:
+          env:
+            # set chaos duration (in sec) as desired
+            - name: TOTAL_CHAOS_DURATION
+              value: '60'
+
+            # provide the kill count
+            - name: APP_VM_MOID
+              value: ''              
+
+            - name: VCENTERSERVER
+              valueFrom:
+                secretKeyRef:
+                  name: vcenter-secret
+                  key: VCENTERSERVER
+
+            - name: VCENTERUSER
+              valueFrom:
+                secretKeyRef:
+                  name: vcenter-secret
+                  key: VCENTERUSER
+
+            - name: VCENTERPASS
+              valueFrom:
+                secretKeyRef:
+                  name: vcenter-secret
+                  key: VCENTERPASS        
+```
+
+### Create the ChaosEngine Resource
+
+- Create the ChaosEngine manifest prepared in the previous step to trigger the Chaos.
+
+  `kubectl apply -f chaosengine.yml`
+
+- If the chaos experiment is not executed, refer to the [troubleshooting](https://docs.litmuschaos.io/docs/faq-troubleshooting/) 
+  section to identify the root cause and fix the issues.
+
+### Watch Chaos progress
+
+-  You can monitor vcenter console to keep a watch over the vm state.   
+
+### Check Chaos Experiment Result
+
+- Check whether the application is resilient to the vm-delete, once the experiment (job) is completed. The ChaosResult resource name is derived like this: `<ChaosEngine-Name>-<ChaosExperiment-Name>`.
+
+  `kubectl describe chaosresult nginx-chaos-vm-delete -n <application-namespace>`
+
+### vm-delete Experiment Demo
+
+- A sample recording of this experiment execution will be added soon.
diff --git a/experiments/vmware/vm-delete/chaosutil.j2 b/experiments/vmware/vm-delete/chaosutil.j2
@@ -0,0 +1,3 @@
+{% if c_lib is defined and c_lib == 'litmus' %}
+c_util: "/chaoslib/vmware/inject_vm_failure_vm_delete.yml"
+{% endif %}
diff --git a/experiments/vmware/vm-delete/vm-delete.chartserviceversion.yaml b/experiments/vmware/vm-delete/vm-delete.chartserviceversion.yaml
@@ -0,0 +1,23 @@
+apiVersion: litmuchaos.io/v1alpha1
+kind: ChartServiceVersion
+metadata:
+  name: vm-delete 
+  version: 0.1.0
+  annotations:
+    categories: vmware
+    repository: https://github.com/litmuschaos/litmus-ansible/tree/master/vmware/vm-delete
+    support: https://kubernetes.slack.com/messages/CNXNB0ZTN
+spec:
+  displayName: vm-delete 
+  categoryDescription: >
+    stops a vm for a certain chaos duration 
+  keywords: ['pods', 'kubernetes', 'vmware','vm-delete', 'nginx'] 
+  maturity: alpha 
+  minKubeVersion: 1.12.0 
+  provider: {'name': 'Wipro'}
+  maintainers: ['[email protected]'] 
+  contributors: ['[email protected]'] 
+  links: ['https://docs.litmuschaos.io/docs/getstarted/'] 
+  icon:
+    - url: 
+      mediatype: ""