Terraform SRE build - unix1998/technical_notes GitHub Wiki

To set up a virtual server farm in AWS using Terraform while incorporating Site Reliability Engineering (SRE) principles like auto-scaling and auto-healing, you need to define various AWS resources and configurations in your Terraform configuration files. Here's a step-by-step guide to help you get started:

1. Set Up Your Terraform Configuration File

First, create a main configuration file, typically named main.tf. This file will define your AWS provider, VPC, subnets, security groups, EC2 instances, and auto-scaling configurations.

2. Define the AWS Provider

provider "aws" {
  region = "us-west-2"  # Replace with your preferred region
}

3. Create a VPC

resource "aws_vpc" "main" {
  cidr_block = "10.0.0.0/16"
}

resource "aws_subnet" "subnet1" {
  vpc_id     = aws_vpc.main.id
  cidr_block = "10.0.1.0/24"
  availability_zone = "us-west-2a"
}

resource "aws_subnet" "subnet2" {
  vpc_id     = aws_vpc.main.id
  cidr_block = "10.0.2.0/24"
  availability_zone = "us-west-2b"
}

4. Define Security Groups

resource "aws_security_group" "web" {
  vpc_id = aws_vpc.main.id

  ingress {
    from_port   = 80
    to_port     = 80
    protocol    = "tcp"
    cidr_blocks = ["0.0.0.0/0"]
  }

  egress {
    from_port   = 0
    to_port     = 0
    protocol    = "-1"
    cidr_blocks = ["0.0.0.0/0"]
  }
}

5. Launch Configuration and Auto Scaling Group

resource "aws_launch_configuration" "example" {
  name          = "example-launch-configuration"
  image_id      = "ami-0c55b159cbfafe1f0"  # Replace with your preferred AMI ID
  instance_type = "t2.micro"
  security_groups = [aws_security_group.web.id]

  lifecycle {
    create_before_destroy = true
  }
}

resource "aws_autoscaling_group" "example" {
  launch_configuration = aws_launch_configuration.example.id
  min_size             = 1
  max_size             = 5
  desired_capacity     = 2
  vpc_zone_identifier  = [aws_subnet.subnet1.id, aws_subnet.subnet2.id]

  tag {
    key                 = "Name"
    value               = "example-instance"
    propagate_at_launch = true
  }

  lifecycle {
    create_before_destroy = true
  }

  health_check_type = "EC2"
  health_check_grace_period = 300
}

6. Auto Healing with Auto Scaling Policies

Define auto-scaling policies to handle scaling events based on CloudWatch alarms.

resource "aws_autoscaling_policy" "scale_up" {
  name                   = "scale_up"
  scaling_adjustment     = 1
  adjustment_type        = "ChangeInCapacity"
  cooldown               = 300
  autoscaling_group_name = aws_autoscaling_group.example.name
}

resource "aws_autoscaling_policy" "scale_down" {
  name                   = "scale_down"
  scaling_adjustment     = -1
  adjustment_type        = "ChangeInCapacity"
  cooldown               = 300
  autoscaling_group_name = aws_autoscaling_group.example.name
}

resource "aws_cloudwatch_metric_alarm" "high_cpu" {
  alarm_name          = "high_cpu"
  comparison_operator = "GreaterThanOrEqualToThreshold"
  evaluation_periods  = "2"
  metric_name         = "CPUUtilization"
  namespace           = "AWS/EC2"
  period              = "120"
  statistic           = "Average"
  threshold           = "70"

  alarm_actions = [aws_autoscaling_policy.scale_up.arn]

  dimensions = {
    AutoScalingGroupName = aws_autoscaling_group.example.name
  }
}

resource "aws_cloudwatch_metric_alarm" "low_cpu" {
  alarm_name          = "low_cpu"
  comparison_operator = "LessThanOrEqualToThreshold"
  evaluation_periods  = "2"
  metric_name         = "CPUUtilization"
  namespace           = "AWS/EC2"
  period              = "120"
  statistic           = "Average"
  threshold           = "30"

  alarm_actions = [aws_autoscaling_policy.scale_down.arn]

  dimensions = {
    AutoScalingGroupName = aws_autoscaling_group.example.name
  }
}

7. Initialize and Apply Terraform Configuration

1. Initialize your Terraform workspace.

   terraform init
   

2. Validate the configuration.

   terraform validate
   

3. Apply the configuration.

   terraform apply
   

This configuration sets up a basic virtual server farm with auto-scaling and auto-healing capabilities using Terraform on AWS. Adjust the parameters as needed for your specific use case.