feat: Support multi-platform build

[marcozabel]

This PR

Currently the flagd-testbed docker image cannot be run on arm64 machines, as go returns an error. To be able to build the docker image across multiple platforms a parameter was introduced to build the docker image for different architectures.

Follow-up Tasks

Automate the pipeline to build a docker image for both amd64 and arm64.

How to test

docker build --build-arg TARGETARCH=amd64 -t flagd-testbed:latest -f flagd/Dockerfile .
docker build --build-arg TARGETARCH=arm64 -t flagd-testbed:latest -f flagd/Dockerfile .

[gemini-code-assist]

Summary of Changes

Hello @marcozabel, I'm Gemini Code Assist¹! I'm currently reviewing this pull request and will post my feedback shortly. In the meantime, here's a summary to help you and other reviewers quickly get up to speed!

This pull request enhances the flagd-testbed Docker image's build process by enabling multi-platform support. It resolves a previous limitation where the image could not be built or run on arm64 architectures, ensuring broader compatibility by allowing the target architecture to be specified during the Docker build.

Highlights

• Multi-platform Docker builds: Introduced support for building the flagd-testbed Docker image for multiple architectures, specifically addressing an issue preventing it from running on arm64 machines.
• Dockerfile build argument: Added a TARGETARCH build argument to the Dockerfile to allow specifying the target architecture during the build process.
• Go build command update: Modified the go build command within the Dockerfile to utilize the new TARGETARCH argument, enabling cross-compilation for the specified architecture.

Using Gemini Code Assist

The full guide for Gemini Code Assist can be found on our documentation page, here are some quick tips.

Invoking Gemini

You can request assistance from Gemini at any point by creating a comment using either /gemini <command> or @gemini-code-assist <command>. Below is a summary of the supported commands on the current page.

Feature	Command	Description
Code Review	/gemini review	Performs a code review for the current pull request in its current state.
Pull Request Summary	/gemini summary	Provides a summary of the current pull request in its current state.
Comment	@gemini-code-assist	Responds in comments when explicitly tagged, both in pull request comments and review comments.
Help	/gemini help	Displays a list of available commands.

Customization

To customize Gemini Code Assist for GitHub experience, repository maintainers can create a configuration file and/or provide a custom code review style guide (such as PEP-8 for Python) by creating and adding files to a .gemini/ folder in the base of the repository. Detailed instructions can be found here.

Limitations & Feedback

Gemini Code Assist may make mistakes. Please leave feedback on any instances where its feedback is incorrect or counter productive. You can react with 👍 and 👎 on @gemini-code-assist comments. If you're interested in giving your feedback about your experience with Gemini Code Assist for Github and other Google products, sign up here.

You can also get AI-powered code generation, chat, as well as code reviews directly in the IDE at no cost with the Gemini Code Assist IDE Extension.

Footnotes

1. Review the Privacy Notices, Generative AI Prohibited Use Policy, Terms of Service, and learn how to configure Gemini Code Assist in GitHub here. Gemini can make mistakes, so double check it and use code with caution. ↩

[gemini-code-assist]

Code Review

This pull request introduces a TARGETARCH build argument to support multi-platform Docker builds, which is a great addition. My review focuses on improving the default behavior of this new argument to make it more robust and intuitive for developers on different architectures. Specifically, I'm suggesting a change to avoid hardcoding a default architecture, which will prevent building non-runnable images on non-amd64 platforms by default.

[gemini-code-assist]

Code Review

This pull request introduces support for multi-platform builds in the Dockerfile by using a TARGETARCH build argument. The approach is sound. My review includes one suggestion to make the build process more explicit and robust by providing a clear fallback for the target architecture when it's not specified.