Gathering and reviewing data to obtain useful insights into your organization and assess the performance of your processes is essential. When it comes to AWS savings, it’s necessary to calculate your AWS expense and utilization performance metrics. You should do this just like you measure your operational activities. As 35% of the cloud spend is wasted, organizations need to find more effective ways to make the most out of their AWS savings.

In the previous articles of this series, we discussed the most common challenges with AWS costs, listed three reasons why organizations need AWS cost optimization, and made a short introduction to FinOps. In this article, we suggest some cost management metrics that can help you track AWS savings more effectively. Moreover, you can use them as a tool to predict future performance and make cutting decisions.

Check out our comprehensive guide on creating an AWS cost optimization strategy.

Monthly growth

Observing your monthly growth helps you to obtain a perspective of how efficiently your AWS implementation is rising in terms of the total costs. In order to conform to cyclical trends in your company, we also suggest reviewing these statistics over several periods. For example, aside from calculating one-month growth, also calculate your growth over a period of six months. This will help you understand the trends that your company follows and therefore forecast future growth.

Provisioned capacity & use

Over-provisioning, distributing services with more power than necessary, is one of the principal factors of cloud waste. Many people think of over-provisioning as a state where size did not matter from the days of on-site hosting. However, you actually pay for the capacity you provision instead of what you use. This is a warning that the environment is inefficient and that you should take remedial action to the right size and reduce your cloud expenses if your provisioned capacity is dramatically higher than the actual usage.

Amazon EC2 unit expenses

Amazon EC2 powers many AWS workloads. This means that EC2 will account for a greater portion of your expenses compared to other services. As developers usually use EC2 through a variety of workloads, we suggest that they monitor your costs at shorter instances. They can do this on a daily, or even hourly basis. These reports can also help you control pricing models more effectively. Moreover, you could understand how much EC2 does one subscriber cost you, which is a very useful metric.

Amazon EC2 instance expenses

New instance generations also support increased processing power and greater cost savings. For this purpose, it can be very effective to describe the EC2 workloads that run on older generations of instances and devise a roadmap to update to the new generations of instances. Setting a concrete goal and taking targeted actions to achieve it can be very useful in optimizing your EC2 usage efficiency and reducing your overall AWS costs.

Amazon EC2 usage coverage

There is a range of pricing models that you can use to gain greater savings. At the same time, you could be scaling up your AWS consumption. You can select between Spot instances, Savings Programs, and Reserved Instances that represent a number of different use cases for your EC2 use. Setting a threshold of how much your instance fleet should cover is useful in each case. The goal here is to choose the most optimal model for your particular case.

S3 expense per storage class

Another tool you are probably using is Amazon S3, which also plays a big role in AWS savings. This service also has a lot of built-in features to help you optimize your costs. You should evaluate the different storage groups that your company is using, similar to EC2. Then, customize policies to make an impact on them. Use lifecycle policies to automate your cost savings plan.

Expenses for unused resources

Every organization has unused resources they’re paying for. For example, recovery snapshots. But, the amount spent on them is a good indicator of how well the organization is managing finances in the cloud. There are likely hundreds, if not thousands of other unused resources in most organizations’ cloud environments. They range from idle load balances to unattached block storage volumes. However, in many cases, these are not easy to identify. Therefore, it’s a worthwhile investment to implement a cloud management platform that can bring granular visibility into your entire cloud ecosystem and can actively monitor and identify unused resources that can be terminated.

Data retrieval costs

Many companies are conscious that by keeping infrequently used data in cold storage stages, they will save a substantial amount of capital. But, when occasionally retrieved data is accessed often enough due to data retrieval costs, these costs could surpass the avoided amount by putting data in a cold storage tier.

The intelligent tiering class by AWS partially solves this problem. It can help you get an overview of how much of your object storage charges are susceptible to data retrieval. However, it doesn’t work when you have one zone storage or archived storage.

Number of cost spike notifications

As almost all billing dashboards offer a budget limit setup, this means that you’ll get a notification each time the budget is overshoot, or a similar cost rise occurs.

Sudden cost spikes can be a sign of malfunctioning assets or network breaches. This is why you need to know when they happen in real-time. Look for cloud management systems that, when designing rules, offer both flexibility and immediately warn stakeholders when policies are broken.

After you’ve created your own dashboard with the specific metrics your business needs, you should work more deeply on evaluating them. For example, metrics about spending and usage can be useful in reporting to the entire organization about the costs of your department. Metrics that refer to value can be compared to your market value drivers to produce KPIs that you can track based on your company goals. It all depends on the specific objectives you’re aiming to achieve.