adhorn

def corrupt_statuscode(func):
    def wrapper(*args, **kwargs):
        result = func(*args, **kwargs)
        error_code, rate = get_config('error_code')
        if not error_code:
            return result
        print("Error from config {0} at a rate of {1}".format(error_code, rate))
        # add injection approx rate% of the time
        if random.random() <= rate:
            print("corrupting now")

adhorn

import boto3
import random

def getconfig(key):
    return {
        'api-delay-services': ['ec2'],
        'api-delay-range': [0, 3],
        'api-delay-rate': 10,        
        'aws-fault-services': ['s3', 'dynamodb'],
        'api-fault-rate': 10

adhorn

---
schemaVersion: '2.2'
description: Run a CPU stress on an instance
parameters:
  duration:
    type: String
    description: 'Specify the duration - in seconds - of the CPU burn. (Required) '
    default: "60"
  cpu:
    type: String

adhorn

import boto3
import random

REGION = 'eu-west-1'


def stop_random_instance(az, tag_name, tag_value, region=REGION):
    '''
    >>> stop_random_instance(az="eu-west-1a", tag_name='chaos', tag_value="chaos-ready", region='eu-west-1')
    ['i-0ddce3c81bc836560']

adhorn

{
    "version": "1.0.0",
    "title": "What is the impact of randomly terminating an instance in an AZ",
    "description": "terminating EC2 instance at random should not impact my app from running",
    "tags": ["ec2"],
    "configuration": {
        "aws_region": "eu-west-1"
    },
    "steady-state-hypothesis": {
        "title": "more than 0 instance in region",

adhorn

{
    "Version": "2012-10-17",
    "Statement": [
        {
            "Effect": "Allow",
            "Action": [
                "ssm:DescribeAssociation",
                "ssm:GetDeployablePatchSnapshotForInstance",
                "ssm:GetDocument",
                "ssm:DescribeDocument",

adhorn

{
    "version": "1.0.0",
    "title": "What is the impact of an terminating the database master",
    "description": "terminating the master database should not prevent the application from running",
    "tags": ["db"],
    "configuration": {
        "endpoint_url": {
            "type": "env",
            "key": "ELEANOR_URL"
        }

adhorn

---
schemaVersion: '0.3'
description: Execute CPU stress via Run Command
assumeRole: "{{AutomationAssumeRole}}"
parameters:
  AutomationAssumeRole:
    type: String
    description: "The ARN of the role that allows Automation to perform the actions on your behalf."
    default: ''
  InstanceIds:

adhorn

---
description: Stop instances in a particular AZ with tag filter
schemaVersion: '0.3'
assumeRole: "{{ AutomationAssumeRole }}"
parameters:
  AvailabilityZone:
    type: String
    description: "(Required) The Availability Zone to impact"
  TagName:
    type: String

adhorn

import boto3
import random
import time


def stop_random_instance(ec2_client, az_name, tag):
    paginator = ec2_client.get_paginator('describe_instances')
    pages = paginator.paginate(
        Filters=[
            {