In this article, I will talk about CloudWatch metrics. Like the other articles in my FinOps series, I will give you some tips about the cost-effective architecture design pattern.

Many AWS services provide metrics by default that are free of charge(cf:https://docs.aws.amazon.com/AmazonCloudWatch/latest/monitoring/aws-services-cloudwatch-metrics.html).

From AWS documentation :
"Many AWS services offer basic monitoring by publishing a default set of metrics to CloudWatch with no charge to customers."

Take care of the additional cost incure if you use external solution like DataDog or NewRelic (get metrics from APIs).

Many companies want to use a manage solution for their Observability strategies. These solutions are usually very expensive. When you make a forecast for this kind of solutions for AWS, you need to take care of the additional cost you will pay :

• The amount of API calls to GET metrics.
• The amount of Data Out from AWS to internet to upload your logs to your managed solution.

Build the dashboards you will often consult.

Every Ops needs some dashboards to consult in case of incident or performance issue. You have to define a clear strategy about this point.

When an Ops team checks the monthly cost of a dashboard, 3$
does not seem expensive. But if you have 20 members in your team and each of them creates multiple dashboards, the bill will increase.

Use some IaC tools like Terraform or CloudFormation to build your dashboards. In this case you will have the opportunity to destroy and recreate them when needed.

Use "Metrics Insights - query builder" which is free of charge.

CloudWatch Metrics Insights is a powerful SQL query engine that you can use to query your metrics. Unfortunately, for the moment it is not possible to save searches directly on it.

You can use the interactive builder view and save the SQL query generated in a git repository to share them with your team.