Add back docker caching, simplify docker builds (#3546)

* fix multiarch

* remove extra push

* add back tag file

* fix cache tag

* add login step

* fix login

* try to fix save

* fix output maybe

* rm outputs

* remove tars

* fix refs

* fix runtime dep

* force rebuild

* lowercase image

* add suffix to build tags for runtime

* update matrix

* fix cut

* fix cut again

* add back matrix

* Update containers/build.sh

Co-authored-by: Xingyao Wang <xingyao6@illinois.edu>

---------

Co-authored-by: Xingyao Wang <xingyao6@illinois.edu>
This commit is contained in:
Robert Brennan 2024-08-23 13:01:18 -04:00 committed by GitHub
parent bf534a90b7
commit b63dec4b2e
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
4 changed files with 75 additions and 341 deletions

View File

@ -25,16 +25,9 @@ jobs:
ghcr_build:
name: Build App Image
runs-on: ubuntu-latest
outputs:
tags: ${{ steps.capture-tags.outputs.tags }}
last_tag: ${{ steps.capture-last-tag.outputs.last_tag }}
permissions:
contents: read
packages: write
strategy:
matrix:
image: ['openhands']
platform: ['amd64', 'arm64']
steps:
- name: Checkout
uses: actions/checkout@v4
@ -54,105 +47,15 @@ jobs:
swap-storage: true
- name: Set up QEMU
uses: docker/setup-qemu-action@v3
- name: Login to GHCR
uses: docker/login-action@v3
with:
registry: ghcr.io
username: ${{ github.repository_owner }}
password: ${{ secrets.GITHUB_TOKEN }}
- name: Set up Docker Buildx
id: buildx
uses: docker/setup-buildx-action@v3
- name: Build and export image
id: build
run: ./containers/build.sh ${{ matrix.image }} ${{ github.repository_owner }} ${{ matrix.platform }}
- name: Capture tags
id: capture-tags
run: |
tags=$(cat tags.txt)
echo "tags=$tags"
echo "tags=$tags" >> $GITHUB_OUTPUT
- name: Capture last tag
id: capture-last-tag
run: |
last_tag=$(cat tags.txt | awk '{print $NF}')
echo "last_tag=$last_tag"
echo "last_tag=$last_tag" >> $GITHUB_OUTPUT
- name: Upload Docker image as artifact
uses: actions/upload-artifact@v4
with:
name: ${{ matrix.image }}_${{ steps.capture-last-tag.outputs.last_tag }}_${{ matrix.platform }}
path: /tmp/${{ matrix.image }}_${{ steps.capture-last-tag.outputs.last_tag }}_${{ matrix.platform }}.tar
retention-days: 14
# Push the OpenHands Docker images to the ghcr.io repository
ghcr_push:
name: Push App Image
runs-on: ubuntu-latest
needs: [ghcr_build]
if: github.ref == 'refs/heads/main' || startsWith(github.ref, 'refs/tags/') || (github.event_name == 'pull_request' && github.event.pull_request.merged == true && github.event.pull_request.base.ref == 'main')
env:
tags: ${{ needs.ghcr_build.outputs.tags }}
permissions:
contents: read
packages: write
strategy:
matrix:
image: ['openhands']
last_tag: ['${{ needs.ghcr_build.outputs.last_tag }}']
platform: ['amd64', 'arm64']
steps:
- name: Checkout code
uses: actions/checkout@v4
- name: Login to GHCR
uses: docker/login-action@v3
with:
registry: ghcr.io
username: ${{ github.repository_owner }}
password: ${{ secrets.GITHUB_TOKEN }}
- name: Download Docker images
uses: actions/download-artifact@v4
with:
name: ${{ matrix.image }}_${{ matrix.last_tag }}_${{ matrix.platform }}
path: /tmp
- name: Load images and push to registry
run: |
mv /tmp/${{ matrix.image }}_${{ matrix.last_tag }}_${{ matrix.platform }}.tar .
loaded_image=$(docker load -i ${{ matrix.image }}_${{ matrix.last_tag }}_${{ matrix.platform }}.tar | grep "Loaded image:" | head -n 1 | awk '{print $3}')
echo "loaded image = $loaded_image"
tags=$(echo ${tags} | tr ' ' '\n')
image_name=$(echo "ghcr.io/${{ github.repository_owner }}/${{ matrix.image }}" | tr '[:upper:]' '[:lower:]')
echo "image name = $image_name"
for tag in $tags; do
echo "tag = $tag"
docker tag $loaded_image $image_name:${tag}_${{ matrix.platform }}
docker push $image_name:${tag}_${{ matrix.platform }}
done
# Creates and pushes the OpenHands Docker image manifests
create_manifest:
name: Create Manifest
runs-on: ubuntu-latest
needs: [ghcr_build, ghcr_push]
if: github.ref == 'refs/heads/main' || startsWith(github.ref, 'refs/tags/') || (github.event_name == 'pull_request' && github.event.pull_request.merged == true && github.event.pull_request.base.ref == 'main')
env:
tags: ${{ needs.ghcr_build.outputs.tags }}
strategy:
matrix:
image: ['openhands']
permissions:
contents: read
packages: write
steps:
- name: Checkout code
uses: actions/checkout@v4
- name: Login to GHCR
uses: docker/login-action@v3
with:
registry: ghcr.io
username: ${{ github.repository_owner }}
password: ${{ secrets.GITHUB_TOKEN }}
- name: Create and push multi-platform manifest
run: |
image_name=$(echo "ghcr.io/${{ github.repository_owner }}/${{ matrix.image }}" | tr '[:upper:]' '[:lower:]')
echo "image name = $image_name"
tags=$(echo ${tags} | tr ' ' '\n')
for tag in $tags; do
echo 'tag = $tag'
docker buildx imagetools create --tag $image_name:$tag \
$image_name:${tag}_amd64 \
$image_name:${tag}_arm64
done
run: ./containers/build.sh openhands ${{ github.repository_owner }} --push

View File

@ -31,11 +31,7 @@ jobs:
packages: write
strategy:
matrix:
image: ['runtime']
base_image: ['nikolaik/python-nodejs:python3.11-nodejs22', 'python:3.11-bookworm', 'node:22-bookworm']
platform: ['amd64', 'arm64']
outputs:
tags: ${{ steps.capture-tags.outputs.tags }}
steps:
- name: Checkout
uses: actions/checkout@v4
@ -55,6 +51,12 @@ jobs:
swap-storage: true
- name: Set up QEMU
uses: docker/setup-qemu-action@v3
- name: Login to GHCR
uses: docker/login-action@v3
with:
registry: ghcr.io
username: ${{ github.repository_owner }}
password: ${{ secrets.GITHUB_TOKEN }}
- name: Set up Docker Buildx
id: buildx
uses: docker/setup-buildx-action@v3
@ -72,77 +74,17 @@ jobs:
- name: Build and export image
id: build
run: |
if [ -f 'containers/runtime/Dockerfile' ]; then
echo 'Dockerfile detected, building runtime image...'
./containers/build.sh ${{ matrix.image }} ${{ github.repository_owner }} ${{ matrix.platform }}
# Capture the last tag to use in the artifact name
last_tag=$(cat tags.txt | awk '{print $NF}')
else
echo 'No Dockerfile detected which means an exact image is already built. Pulling the image and saving it to a tar file...'
source containers/runtime/config.sh
echo "$DOCKER_IMAGE_HASH_TAG $DOCKER_IMAGE_TAG" >> tags.txt
export last_tag=$DOCKER_IMAGE_TAG
echo "Pulling image $DOCKER_REGISTRY/$DOCKER_ORG/$DOCKER_IMAGE:$DOCKER_IMAGE_HASH_TAG to /tmp/${{ matrix.image }}_${last_tag}_${{ matrix.platform }}.tar"
docker pull $DOCKER_REGISTRY/$DOCKER_ORG/$DOCKER_IMAGE:$DOCKER_IMAGE_HASH_TAG
docker save $DOCKER_REGISTRY/$DOCKER_ORG/$DOCKER_IMAGE:$DOCKER_IMAGE_HASH_TAG -o /tmp/${{ matrix.image }}_${last_tag}_${{ matrix.platform }}.tar
fi
echo "last_tag=${last_tag}" >> $GITHUB_OUTPUT
- name: Capture tags
id: capture-tags
run: |
tags=$(cat tags.txt)
echo "tags=$tags"
echo "tags=$tags" >> $GITHUB_OUTPUT
- name: Upload Docker image as artifact
uses: actions/upload-artifact@v4
with:
name: ${{ matrix.image }}_${{ steps.build.outputs.last_tag }}_${{ matrix.platform }}
path: /tmp/${{ matrix.image }}_${{ steps.build.outputs.last_tag }}_${{ matrix.platform }}.tar
retention-days: 14
- name: Capture last tag
id: capture-last-tag
run: |
last_tag=$(cat tags.txt | awk '{print $NF}')
echo "$last_tag" > /tmp/last-tag-${{ matrix.image }}-${{ matrix.platform }}-${{ steps.build.outputs.last_tag }}.txt
echo "Saved last tag to /tmp/last-tag-${{ matrix.image }}-${{ matrix.platform }}-${{ steps.build.outputs.last_tag }}.txt"
- name: Upload last tag as artifact
uses: actions/upload-artifact@v4
with:
name: last-tag-${{ matrix.image }}-${{ matrix.platform }}-${{ steps.build.outputs.last_tag }}
path: /tmp/last-tag-${{ matrix.image }}-${{ matrix.platform }}-${{ steps.build.outputs.last_tag }}.txt
retention-days: 1
prepare_test_image_tags:
name: Prepare Test Images Tags
needs: ghcr_build_runtime
runs-on: ubuntu-latest
outputs:
test_image_tags: ${{ steps.set-matrix.outputs.test_image_tags }}
steps:
- name: Download last tags
uses: actions/download-artifact@v4
with:
pattern: last-tag-*
path: /tmp/
merge-multiple: true
- name: Set up test matrix
id: set-matrix
run: |
matrix=$(cat /tmp/last-tag-*.txt | sort -u | jq -R -s -c 'split("\n") | map(select(length > 0))')
echo "test_image_tags=$matrix" >> $GITHUB_OUTPUT
echo "Generated test_image_tags: $matrix"
suffix=$(echo "${{ matrix.base_image }}" | cut -d ':' -f 1 | cut -d '/' -f 1)
./containers/build.sh runtime ${{ github.repository_owner }} --push $suffix
# Run unit tests with the EventStream runtime Docker images
test_runtime:
name: Test Runtime
runs-on: ubuntu-latest
needs: prepare_test_image_tags
needs: [ghcr_build_runtime]
strategy:
matrix:
image: ['runtime']
runtime_type: ['eventstream']
platform: ['amd64']
last_tag: ${{ fromJson(needs.prepare_test_image_tags.outputs.test_image_tags) }}
base_image: ['nikolaik', 'python', 'node']
steps:
- uses: actions/checkout@v4
- name: Free Disk Space (Ubuntu)
@ -163,35 +105,17 @@ jobs:
cache: 'poetry'
- name: Install Python dependencies using Poetry
run: make install-python-dependencies
- name: Download Runtime Docker image
uses: actions/download-artifact@v4
with:
name: ${{ matrix.image }}_${{ matrix.last_tag }}_${{ matrix.platform }}
path: /tmp/
- name: Load Runtime image and run runtime tests
- name: Run runtime tests
run: |
image_file=$(find /tmp -name "${{ matrix.image }}_${{ matrix.last_tag }}_${{ matrix.platform }}.tar" | head -n 1)
git_hash=$(git rev-parse --short "$GITHUB_SHA")
image_name=ghcr.io/${{ github.repository_owner }}/runtime:$git_hash-${{ matrix.base_image }}
image_name=$(echo $image_name | tr '[:upper:]' '[:lower:]')
if [ -z "$image_file" ]; then
echo "No matching image file found for tag: ${{ matrix.last_tag }}"
exit 1
fi
echo "Loading image from file: $image_file"
output=$(docker load -i "$image_file")
# Extract the image name from the output
# Print all tags
echo "All tags:"
all_tags=$(echo "$output" | grep -oP 'Loaded image: \K.*')
echo "$all_tags"
# Choose the last tag
image_name=$(echo "$all_tags" | tail -n 1)
# Print the full name of the image
echo "Loaded Docker image: $image_name"
TEST_RUNTIME=${{ matrix.runtime_type }} SANDBOX_USER_ID=$(id -u) SANDBOX_CONTAINER_IMAGE=$image_name TEST_IN_CI=true poetry run pytest --cov=agenthub --cov=openhands --cov-report=xml -s ./tests/runtime
TEST_RUNTIME=eventstream \
SANDBOX_USER_ID=$(id -u) \
SANDBOX_CONTAINER_IMAGE=$image_name \
TEST_IN_CI=true \
poetry run pytest --cov=agenthub --cov=openhands --cov-report=xml -s ./tests/runtime
- name: Upload coverage to Codecov
uses: codecov/codecov-action@v4
env:
@ -201,14 +125,11 @@ jobs:
runtime_integration_tests_on_linux:
name: Runtime Integration Tests on Linux
runs-on: ubuntu-latest
needs: prepare_test_image_tags
needs: [ghcr_build_runtime]
strategy:
fail-fast: false
matrix:
image: ['runtime']
runtime_type: ['eventstream']
platform: ['amd64']
last_tag: ${{ fromJson(needs.prepare_test_image_tags.outputs.test_image_tags) }}
base_image: ['nikolaik', 'python', 'node']
steps:
- uses: actions/checkout@v4
- name: Install poetry via pipx
@ -220,30 +141,18 @@ jobs:
cache: 'poetry'
- name: Install Python dependencies using Poetry
run: make install-python-dependencies
- name: Download Runtime Docker image
uses: actions/download-artifact@v4
with:
name: ${{ matrix.image }}_${{ matrix.last_tag }}_${{ matrix.platform }}
path: /tmp/
- name: Load runtime image and run integration tests
- name: Run integration tests
run: |
image_file=$(find /tmp -name "${{ matrix.image }}_${{ matrix.last_tag }}_${{ matrix.platform }}.tar" | head -n 1)
git_hash=$(git rev-parse --short "$GITHUB_SHA")
image_name=ghcr.io/${{ github.repository_owner }}/runtime:$git_hash-${{ matrix.base_image }}
image_name=$(echo $image_name | tr '[:upper:]' '[:lower:]')
if [ -z "$image_file" ]; then
echo "No matching image file found for tag: ${{ matrix.last_tag }}"
exit 1
fi
echo "Loading image from file: $image_file"
output=$(docker load -i "$image_file")
# Extract the image name from the output
image_name=$(echo "$output" | grep -oP 'Loaded image: \K.*' | head -n 1)
# Print the full name of the image
echo "Loaded Docker image: $image_name"
TEST_RUNTIME=${{ matrix.runtime_type }} SANDBOX_USER_ID=$(id -u) SANDBOX_CONTAINER_IMAGE=$image_name TEST_IN_CI=true TEST_ONLY=true ./tests/integration/regenerate.sh
TEST_RUNTIME=eventstream \
SANDBOX_USER_ID=$(id -u) \
SANDBOX_CONTAINER_IMAGE=$image_name \
TEST_IN_CI=true \
TEST_ONLY=true \
./tests/integration/regenerate.sh
- name: Upload coverage to Codecov
uses: codecov/codecov-action@v4
env:
@ -257,105 +166,3 @@ jobs:
steps:
- name: All tests passed
run: echo "All runtime tests have passed successfully!"
# Push the runtime Docker images to the ghcr.io repository
ghcr_push_runtime:
name: Push Image
runs-on: ubuntu-latest
needs: [ghcr_build_runtime, prepare_test_image_tags, all_runtime_tests_passed]
if: github.ref == 'refs/heads/main' || startsWith(github.ref, 'refs/tags/') || (github.event_name == 'pull_request' && github.event.pull_request.merged == true && github.event.pull_request.base.ref == 'main')
env:
RUNTIME_TAGS: ${{ needs.ghcr_build_runtime.outputs.tags }}
permissions:
contents: read
packages: write
strategy:
matrix:
image: ['runtime']
runtime_type: ['eventstream']
platform: ['amd64', 'arm64']
last_tag: ${{ fromJson(needs.prepare_test_image_tags.outputs.test_image_tags) }}
steps:
- name: Checkout code
uses: actions/checkout@v4
- name: Free Disk Space (Ubuntu)
uses: jlumbroso/free-disk-space@main
with:
tool-cache: true
android: true
dotnet: true
haskell: true
large-packages: true
docker-images: false
swap-storage: true
- name: Login to GHCR
uses: docker/login-action@v3
with:
registry: ghcr.io
username: ${{ github.repository_owner }}
password: ${{ secrets.GITHUB_TOKEN }}
- name: Download Docker images
uses: actions/download-artifact@v4
with:
name: ${{ matrix.image }}_${{ matrix.last_tag }}_${{ matrix.platform }}
path: /tmp/
- name: Load images and push to registry
run: |
image_file=$(find /tmp -name "${{ matrix.image }}_${{ matrix.last_tag }}_${{ matrix.platform }}.tar" | head -n 1)
if [ -z "$image_file" ]; then
echo "No matching image file found for tag: ${{ matrix.last_tag }}"
exit 1
fi
echo "Loading image from file: $image_file"
if ! loaded_image=$(docker load -i "$image_file" | grep "Loaded image:" | head -n 1 | awk '{print $3}'); then
echo "Failed to load Docker image"
exit 1
fi
echo "loaded image = $loaded_image"
image_name=$(echo "ghcr.io/${{ github.repository_owner }}/${{ matrix.image }}" | tr '[:upper:]' '[:lower:]')
echo "image name = $image_name"
echo "$RUNTIME_TAGS" | tr ' ' '\n' | while read -r tag; do
echo "tag = $tag"
if [ -n "$image_name" ] && [ -n "$tag" ]; then
docker tag $loaded_image $image_name:${tag}_${{ matrix.platform }}
docker push $image_name:${tag}_${{ matrix.platform }}
else
echo "Skipping tag and push due to empty image_name or tag"
fi
done
# Creates and pushes the runtime Docker image manifest
create_manifest_runtime:
name: Create Manifest
runs-on: ubuntu-latest
needs: [ghcr_build_runtime, prepare_test_image_tags, ghcr_push_runtime]
if: github.ref == 'refs/heads/main' || startsWith(github.ref, 'refs/tags/') || (github.event_name == 'pull_request' && github.event.pull_request.merged == true && github.event.pull_request.base.ref == 'main')
env:
tags: ${{ needs.ghcr_build_runtime.outputs.tags }}
strategy:
matrix:
image: ['runtime']
permissions:
contents: read
packages: write
steps:
- name: Checkout code
uses: actions/checkout@v4
- name: Login to GHCR
uses: docker/login-action@v3
with:
registry: ghcr.io
username: ${{ github.repository_owner }}
password: ${{ secrets.GITHUB_TOKEN }}
- name: Create and push multi-platform manifest
run: |
image_name=$(echo "ghcr.io/${{ github.repository_owner }}/${{ matrix.image }}" | tr '[:upper:]' '[:lower:]')
echo "image name = $image_name"
tags=$(echo ${tags} | tr ' ' '\n')
for tag in $tags; do
echo 'tag = $tag'
docker buildx imagetools create --tag $image_name:$tag \
$image_name:${tag}_amd64 \
$image_name:${tag}_arm64
done

View File

@ -3,13 +3,25 @@ set -eo pipefail
image_name=$1
org_name=$2
platform=$3
push=0
if [[ $3 == "--push" ]]; then
push=1
fi
tag_suffix=$4
echo "Building: $image_name for platform: $platform"
echo "Building: $image_name"
tags=()
OPENHANDS_BUILD_VERSION="dev"
cache_tag_base="buildcache"
cache_tag="$cache_tag_base"
if [[ -n $GITHUB_SHA ]]; then
git_hash=$(git rev-parse --short "$GITHUB_SHA")
tags+=("$git_hash")
fi
if [[ -n $GITHUB_REF_NAME ]]; then
# check if ref name is a version number
if [[ $GITHUB_REF_NAME =~ ^[0-9]+\.[0-9]+\.[0-9]+$ ]]; then
@ -18,11 +30,20 @@ if [[ -n $GITHUB_REF_NAME ]]; then
tags+=("$major_version" "$minor_version")
tags+=("latest")
fi
sanitized=$(echo "$GITHUB_REF_NAME" | sed 's/[^a-zA-Z0-9.-]\+/-/g')
OPENHANDS_BUILD_VERSION=$sanitized
tag=$(echo "$sanitized" | tr '[:upper:]' '[:lower:]') # lower case is required in tagging
tags+=("$tag")
sanitized_ref_name=$(echo "$GITHUB_REF_NAME" | sed 's/[^a-zA-Z0-9.-]\+/-/g')
OPENHANDS_BUILD_VERSION=$sanitized_ref_name
sanitized_ref_name=$(echo "$sanitized_ref_name" | tr '[:upper:]' '[:lower:]') # lower case is required in tagging
tags+=("$sanitized_ref_name")
cache_tag+="-${sanitized_ref_name}"
fi
if [[ -n $tag_suffix ]]; then
cache_tag+="-${tag_suffix}"
for i in "${!tags[@]}"; do
tags[$i]="${tags[$i]}-$tag_suffix"
done
fi
echo "Tags: ${tags[@]}"
if [[ "$image_name" == "openhands" ]]; then
@ -68,16 +89,19 @@ for tag in "${tags[@]}"; do
args+=" -t $DOCKER_REPOSITORY:$tag"
done
output_image="/tmp/${image_name}_${tags[-1]}_${platform}.tar"
echo "Output image will be saved to: $output_image"
if [[ $push -eq 1 ]]; then
args+=" --push"
args+=" --cache-to=type=registry,ref=$DOCKER_REPOSITORY:$cache_tag,mode=max"
fi
echo "Args: $args"
docker buildx build \
$args \
--build-arg OPENHANDS_BUILD_VERSION="$OPENHANDS_BUILD_VERSION" \
--platform linux/$platform \
--cache-from=type=registry,ref=$DOCKER_REPOSITORY:$cache_tag \
--cache-from=type=registry,ref=$DOCKER_REPOSITORY:$cache_tag_base-main \
--platform linux/amd64,linux/arm64 \
--provenance=false \
-f "$dir/Dockerfile" \
--output type=docker,dest="$output_image" \
"$DOCKER_BASE_DIR"
echo "${tags[*]}" > tags.txt

View File

@ -243,7 +243,7 @@ def build_runtime_image(
# Scenario 1: If we already have an image with the exact same hash, then it means the image is already built
# with the exact same source code and Dockerfile, so we will reuse it. Building it is not required.
if runtime_builder.image_exists(hash_runtime_image_name):
if not force_rebuild and runtime_builder.image_exists(hash_runtime_image_name):
logger.info(
f'Image [{hash_runtime_image_name}] already exists so we will reuse it.'
)