Our previous post describes how we have implemented a Dynamic Feature Environment that would allow engineers at Prenetics to spin up/down a fully functional independent K8s cluster that runs our full set of microservices, offering an internal Environment as a Service (EaaS). The aim is to provide the necessary tools for our engineers to easily build and test locally.
At Prenetics Engineering we also look at improving our delivery efficiency. Lead Time for Changes (LT) is a one of the four DORA metrics and it measures the amount of time a commit would take to get into production. Reducing LT would mean faster Time to market.
We split our LT improvements into the following phases:
- Provision
- Build
- Deploy
- Test
- Release
In the following we look at how we have been optimising the provision phase.
Provision
We use CodeBuild to execute build and test steps, and to deploy our digital assets
- k8s changes via AWS Cli and kubectl,
- web changes via AWS Cli to S3
- mobile changes via Expo Cli
- infrastructure changes via Terraform
Each of our CodeBuild projects executes the required steps inside its specified Docker container. AWS offers a number of standard Docker images. However, these images do not have a number of applications needed in our build, deploy and test steps. We have therefore defined our own CodeBuild Docker image (see https://gist.github.com/peteryhwong/7bbbe461b028f5040c81cdcea2f256af is a snippet of the Dockerfile), Our custom Docker image defines from an Linux Alpine based "Docker in Docker" image and pre-installed the tools such as jq, terraform, kubectl, and AWS Cli that are needed in our build, deploy and test steps. This custom image is smaller in size and it means our steps do not need to download the same external dependencies in every execution.
This image is stored in our AWS ECR and is provisioned when CodeBuild projects execute.
Note that unlike the AWS standard images, containers created from our custom image would not the Docker daemon (dockerd) running by default, hence we would need to start Docker daemon manually when the container starts. See https://gist.github.com/peteryhwong/a51c39d69647c233808339c62d7b8f28 for details.
On average we see a reduction of up to a minute during the provision phase of our CodeBuild projects and our typical microservice's build phase is normally less than 5 minutes.
In our next post we will look at how we have been optimising the build phase.
Top comments (1)
improving your content day by day will enhance your writing skills . mantra to convince parents for love marriage