Introduction
Efficient CI pipelines are critical to smooth development workflows, and caching plays a significant role in reducing build times. As CI workflows increasingly leverage Docker, understanding how Docker build caching works is essential for optimizing performance, especially in complex projects. In this post, we’ll dive into the fundamentals of Docker build caching, explore the components needed for effective caching with GitHub Actions, and walk through practical examples.
Docker’s v23 update introduced a significant shift in its build architecture, standardizing the use of Buildx as the build client and BuildKit as the backend. This change provides developers with the power to optimize their build processes, yet caching in CI still requires a deliberate setup, particularly when working with Docker Compose. Here, we’ll break down the basics, explain the necessary tooling, and demonstrate how to implement build caching in CI using GitHub Actions.
Docker Build in v23 and Beyond
As of Docker v23, which was released in February 2023, the traditional build system transitioned to a new architecture. The docker build
command now defaults to using Buildx as the client and BuildKit as the backend for managing the build process.
This shift is important because BuildKit significantly enhances the performance of Docker builds by allowing parallel execution, efficient layer caching, and better resource utilization. To benefit from these improvements, it is crucial to understand how to use Buildx and configure caching effectively, particularly in CI environments.
Why Docker Compose Does Not Automatically Use BuildKit
While the standard docker build
command has adopted Buildx and BuildKit, Docker Compose continues to use the traditional build system by default. When running docker compose build
, neither Buildx nor BuildKit is utilized unless explicitly configured.
This is important because Docker Compose, a tool frequently used for defining and running multi-container Docker applications, does not take advantage of the caching optimizations offered by BuildKit out of the box. To leverage caching in a CI pipeline, you must configure Docker Compose to use Buildx and BuildKit manually.
Specifying Build Cache Inputs and Outputs
To enable caching, the build cache must be inputted and outputted to a specific location in the file system. Docker provides options for specifying external cache sources and destinations via --cache-from
and --cache-to
:
docker build --cache-from type=local,src=/path/to/dir --cache-to type=local,dest=/path/to/dir ...
-
--cache-from
: Specifies the source of the build cache. -
--cache-to
: Defines where the cache should be exported after the build.
By using these flags, you can share and store cache layers between builds, ensuring faster rebuilds by skipping already cached layers. This setup is especially useful in CI environments where each build typically starts from scratch.
The Need for Buildx and docker-container Driver
However, when running the above command in a local environment, you might encounter the following error:
Cache export is not supported for the docker driver.
Switch to a different driver, or turn on the containerd image store.
This happens because the legacy Docker driver (docker
) does not support BuildKit’s cache export features. To resolve this, you need to use the docker-container
driver, which fully supports BuildKit’s advanced features. (docs)
To create a new builder that uses the docker-container
driver, run:
docker buildx create --name mybuilder --driver docker-container
docker buildx use mybuilder
This sets up a Buildx builder that uses the docker-container
driver. Now, you can use the --cache-from
and --cache-to
options to cache Docker layers effectively.
Example: Building with Buildx and Caching
Once the new builder is created, you can use the following command to build and cache your image:
docker buildx build --builder mybuilder \
--cache-from=type=local,src=/path/to/dir \
--cache-to=type=local,dest=/path/to/dir ...
Caching with Docker Compose
As mentioned earlier, Docker Compose does not automatically utilize BuildKit. To achieve caching with Docker Compose, you need to use the docker buildx bake
command. Bake is a tool in Buildx that allows multi-step orchestration of Docker builds, including advanced caching options.
Here’s how you can set up Docker Compose to leverage BuildKit caching:
docker buildx bake --file docker-compose.yml \
--builder mybuilder \
--cache-from=type=local,src=/path/to/cache \
--cache-to=type=local,dest=/path/to/cache,mode=max
This approach bypasses the default docker compose build
command and uses Buildx’s bake
to handle the build process with caching.
Implementing Caching in GitHub Actions
To use Docker build caching in GitHub Actions, you’ll need to set up caching for the build directory, configure Buildx, and run docker buildx bake
as part of the CI workflow. Here’s a sample workflow file that illustrates this:
name: CI Build
on:
push:
branches:
- main
jobs:
build:
runs-on: ubuntu-latest
<span class="na">steps</span><span class="pi">:</span>
<span class="pi">-</span> <span class="na">name</span><span class="pi">:</span> <span class="s">Checkout code</span>
<span class="na">uses</span><span class="pi">:</span> <span class="s">actions/checkout@692973e3d937129bcbf40652eb9f2f61becf3332</span>
<span class="pi">-</span> <span class="na">name</span><span class="pi">:</span> <span class="s">Setup Docker Buildx</span>
<span class="na">id</span><span class="pi">:</span> <span class="s">buildx</span>
<span class="na">uses</span><span class="pi">:</span> <span class="s">docker/setup-buildx-action@988b5a0280414f521da01fcc63a27aeeb4b104db</span>
<span class="pi">-</span> <span class="na">name</span><span class="pi">:</span> <span class="s">Cache Docker layers</span>
<span class="na">uses</span><span class="pi">:</span> <span class="s">actions/cache@v3</span>
<span class="na">with</span><span class="pi">:</span>
<span class="na">path</span><span class="pi">:</span> <span class="s">/tmp/.buildx-cache</span>
<span class="na">key</span><span class="pi">:</span> <span class="s">docker-build-cache-${{ github.ref }}-${{ github.sha }}</span>
<span class="na">restore-keys</span><span class="pi">:</span> <span class="pi">|</span>
<span class="s">docker-build-cache-${{ github.ref }}</span>
<span class="s">docker-build-cache-</span>
<span class="pi">-</span> <span class="na">name</span><span class="pi">:</span> <span class="s">Build with caching</span>
<span class="na">run</span><span class="pi">:</span> <span class="pi">|</span>
<span class="s">docker buildx bake --file docker-compose.yml \</span>
<span class="s">--builder="${{ steps.buildx.outputs.name }}" \</span>
<span class="s">--cache-from=type=local,src=/tmp/.buildx-cache \</span>
<span class="s">--cache-to=type=local,dest=/tmp/.buildx-cache,mode=max</span>
Verifying the Cache
Once the workflow completes, you can inspect the contents of the build cache stored in /tmp/.buildx-cache
. The cache is typically stored in OCI (Open Container Initiative) image format, with each image layer cached in the blobs
directory. The index.json
file in the cache contains metadata about the cached layers.
Here’s a snippet of what the index.json
file might look like:
{
"schemaVersion": 2,
"mediaType": "application/vnd.oci.image.index.v1+json",
"manifests": [
{
"mediaType": "application/vnd.oci.image.index.v1+json",
"digest": "sha256:c6fc9d593e92059b058b0b147be8e51...",
"size": 4193,
"annotations": {
"org.opencontainers.image.ref.name": "latest"
}
}
]
}
Conclusion
In this guide, we covered the essentials of setting up Docker build caching in CI, focusing on Buildx, BuildKit, and GitHub Actions. Docker Compose doesn’t use BuildKit by default, but by utilizing the buildx bake
command, you can implement effective caching strategies. While caching might not always result in significant performance improvements depending on the use case, understanding and leveraging Docker’s build architecture will put you in a better position to optimize your CI pipelines.
By following these steps, you can make sure your builds are faster, more efficient, and consistent across environments.
Thank you for reading, and happy optimizing!
For more tips and insights on security and log analysis, follow me on Twitter @Siddhant_K_code and stay updated with the latest & detailed tech content like this.
Top comments (0)