Skip to content

Commit

Permalink
ref(workflow): use a single job to run GCP tests
Browse files Browse the repository at this point in the history
  • Loading branch information
@gustavovalverde
gustavovalverde committed Oct 5, 2023
1 parent f3426d7 commit 3dce369
Showing 1 changed file with 32 additions and 229 deletions.
261 changes: 32 additions & 229 deletions .github/workflows/sub-deploy-integration-tests-gcp.yml
View file
Original file line number Diff line number Diff line change
Expand Up @@ -104,127 +104,14 @@ env:
CACHED_STATE_UPDATE_LIMIT: 576

jobs:
# set up and launch the test, if it doesn't use any cached state
# each test runs one of the *-with/without-cached-state job series, and skips the other
launch-without-cached-state:
name: Launch ${{ inputs.test_id }} test
if: ${{ !inputs.needs_zebra_state }}
runs-on: zfnd-runners
permissions:
contents: 'read'
id-token: 'write'
steps:
- uses: actions/checkout@v4.0.0
with:
persist-credentials: false
fetch-depth: '2'
- uses: r7kamura/rust-problem-matchers@v1.4.0

- name: Inject slug/short variables
uses: rlespinasse/github-slug-action@v4
with:
short-length: 7

# Makes the Zcash network name lowercase.
#
# Labels in GCP are required to be in lowercase, but the blockchain network
# uses sentence case, so we need to downcase ${{ inputs.network }}.
#
# Passes ${{ inputs.network }} to subsequent steps using $NETWORK env variable.
- name: Downcase network name for labels
run: |
NETWORK_CAPS="${{ inputs.network }}"
echo "NETWORK=${NETWORK_CAPS,,}" >> "$GITHUB_ENV"
# Install our SSH secret
- name: Install private SSH key
uses: shimataro/ssh-key-action@v2.5.1
with:
key: ${{ secrets.GCP_SSH_PRIVATE_KEY }}
name: google_compute_engine
known_hosts: unnecessary

- name: Generate public SSH key
run: |
sudo apt-get update && sudo apt-get -qq install -y --no-install-recommends openssh-client
ssh-keygen -y -f ~/.ssh/google_compute_engine > ~/.ssh/google_compute_engine.pub
# Setup gcloud CLI
- name: Authenticate to Google Cloud
id: auth
uses: google-github-actions/auth@v1.1.1
with:
retries: '3'
workload_identity_provider: '${{ vars.GCP_WIF }}'
service_account: '${{ vars.GCP_DEPLOYMENTS_SA }}'

- name: Set up Cloud SDK
uses: google-github-actions/setup-gcloud@v1.1.1

# Create a Compute Engine virtual machine
- name: Create ${{ inputs.test_id }} GCP compute instance
id: create-instance
run: |
gcloud compute instances create-with-container "${{ inputs.test_id }}-${{ env.GITHUB_REF_SLUG_URL }}-${{ env.GITHUB_SHA_SHORT }}" \
--boot-disk-size 300GB \
--boot-disk-type pd-ssd \
--image-project=cos-cloud \
--image-family=cos-stable \
--create-disk=name="${{ inputs.test_id }}-${{ env.GITHUB_SHA_SHORT }}",device-name="${{ inputs.test_id }}-${{ env.GITHUB_SHA_SHORT }}",size=300GB,type=pd-ssd \
--container-image=gcr.io/google-containers/busybox \
--machine-type ${{ vars.GCP_LARGE_MACHINE }} \
--network-interface=subnet=${{ vars.GCP_SUBNETWORK }} \
--scopes cloud-platform \
--metadata=google-monitoring-enabled=TRUE,google-logging-enabled=TRUE \
--metadata-from-file=startup-script=.github/workflows/scripts/gcp-vm-startup-script.sh \
--labels=app=${{ inputs.app_name }},environment=test,network=${NETWORK},github_ref=${{ env.GITHUB_REF_SLUG_URL }},test=${{ inputs.test_id }} \
--tags ${{ inputs.app_name }} \
--zone ${{ vars.GCP_ZONE }}
sleep 60
# Create a docker volume with the new disk we just created.
#
# SSH into the just created VM, and create a docker volume with the newly created disk.
- name: Create ${{ inputs.test_id }} Docker volume
run: |
gcloud compute ssh ${{ inputs.test_id }}-${{ env.GITHUB_REF_SLUG_URL }}-${{ env.GITHUB_SHA_SHORT }} \
--zone ${{ vars.GCP_ZONE }} \
--ssh-flag="-o ServerAliveInterval=5" \
--ssh-flag="-o ConnectionAttempts=20" \
--ssh-flag="-o ConnectTimeout=5" \
--command \
"\
sudo mkfs.ext4 -v /dev/sdb \
&& \
sudo docker volume create --driver local --opt type=ext4 --opt device=/dev/sdb \
${{ inputs.test_id }}-${{ env.GITHUB_SHA_SHORT }} \
"
# Launch the test without any cached state
- name: Launch ${{ inputs.test_id }} test
run: |
gcloud compute ssh ${{ inputs.test_id }}-${{ env.GITHUB_REF_SLUG_URL }}-${{ env.GITHUB_SHA_SHORT }} \
--zone ${{ vars.GCP_ZONE }} \
--ssh-flag="-o ServerAliveInterval=5" \
--ssh-flag="-o ConnectionAttempts=20" \
--ssh-flag="-o ConnectTimeout=5" \
--command \
"\
sudo docker run \
--name ${{ inputs.test_id }} \
--tty \
--detach \
${{ inputs.test_variables }} \
--mount type=volume,src=${{ inputs.test_id }}-${{ env.GITHUB_SHA_SHORT }},dst=${{ inputs.root_state_path }}/${{ inputs.zebra_state_dir }} \
${{ vars.GAR_BASE }}/${{ vars.CI_IMAGE_NAME }}:sha-${{ env.GITHUB_SHA_SHORT }} \
"
# set up and launch the test, if it uses cached state
# each test runs one of the *-with/without-cached-state job series, and skips the other
launch-with-cached-state:
name: Launch ${{ inputs.test_id }} test
if: ${{ inputs.needs_zebra_state }}
# Show all the test logs, then follow the logs of the test we just launched, until it finishes.
# Then check the result of the test.
#
# If `inputs.is_long_test` is `true`, the timeout is 5 days, otherwise it's 3 hours.
test-result:
name: Run ${{ inputs.test_id }} test
runs-on: zfnd-runners
timeout-minutes: ${{ inputs.is_long_test && 7200 || 180 }}
outputs:
cached_disk_name: ${{ steps.get-disk-name.outputs.cached_disk_name }}
permissions:
Expand Down Expand Up @@ -295,6 +182,7 @@ jobs:
# TODO: move this script into a file, and call it from manual-find-cached-disks.yml as well.
- name: Find ${{ inputs.test_id }} cached state disk
id: get-disk-name
if: ${{ inputs.needs_zebra_state || inputs.needs_lwd_state }}
run: |
LOCAL_STATE_VERSION=$(grep -oE "DATABASE_FORMAT_VERSION: .* [0-9]+" "$GITHUB_WORKSPACE/zebra-state/src/constants.rs" | grep -oE "[0-9]+" | tail -n1)
echo "STATE_VERSION: $LOCAL_STATE_VERSION"
Expand Down Expand Up @@ -361,18 +249,21 @@ jobs:
echo "STATE_VERSION=$LOCAL_STATE_VERSION" >> "$GITHUB_ENV"
echo "CACHED_DISK_NAME=$CACHED_DISK_NAME" >> "$GITHUB_ENV"
echo "DISK_OPTION=image=$CACHED_DISK_NAME," >> "$GITHUB_ENV"
# Create a Compute Engine virtual machine and attach a cached state disk using the
# $CACHED_DISK_NAME variable as the source image to populate the disk cached state
# if the test needs it.
- name: Create ${{ inputs.test_id }} GCP compute instance
id: create-instance
run: |
DISK_OPTION=${{ steps.get-disk-name.outputs.disk_option }}
gcloud compute instances create-with-container "${{ inputs.test_id }}-${{ env.GITHUB_REF_SLUG_URL }}-${{ env.GITHUB_SHA_SHORT }}" \
--boot-disk-size 300GB \
--boot-disk-type pd-ssd \
--image-project=cos-cloud \
--image-family=cos-stable \
--create-disk=image=${{ env.CACHED_DISK_NAME }},name="${{ inputs.test_id }}-${{ env.GITHUB_SHA_SHORT }}",device-name="${{ inputs.test_id }}-${{ env.GITHUB_SHA_SHORT }}",size=300GB,type=pd-ssd \
--create-disk=${DISK_OPTION}name="${{ inputs.test_id }}-${{ env.GITHUB_SHA_SHORT }}",device-name="${{ inputs.test_id }}-${{ env.GITHUB_SHA_SHORT }}",size=300GB,type=pd-ssd \
--container-image=gcr.io/google-containers/busybox \
--machine-type ${{ vars.GCP_LARGE_MACHINE }} \
--network-interface=subnet=${{ vars.GCP_SUBNETWORK }} \
Expand All @@ -382,9 +273,8 @@ jobs:
--labels=app=${{ inputs.app_name }},environment=test,network=${NETWORK},github_ref=${{ env.GITHUB_REF_SLUG_URL }},test=${{ inputs.test_id }} \
--tags ${{ inputs.app_name }} \
--zone ${{ vars.GCP_ZONE }}
sleep 60
# Create a docker volume with the selected cached state.
# Create a docker volume with the new disk we just created or the cached state.
#
# SSH into the just created VM and create a docker volume with the recently attached disk.
# (The cached state and disk are usually the same size,
Expand All @@ -398,53 +288,16 @@ jobs:
--ssh-flag="-o ConnectTimeout=5" \
--command \
"\
sudo mkfs.ext4 -v /dev/sdb \
&& \
sudo docker volume create --driver local --opt type=ext4 --opt device=/dev/sdb \
${{ inputs.test_id }}-${{ env.GITHUB_SHA_SHORT }} \
"
# Launch the test with the previously created Zebra-only cached state.
# Each test runs one of the "Launch test" steps, and skips the other.
#
# SSH into the just created VM, and create a Docker container to run the incoming test
# from ${{ inputs.test_id }}, then mount the sudo docker volume created in the previous job.
#
# The disk mounted in the VM is located at /dev/sdb, we mount the root `/` of this disk to the docker
# container in one path:
# - /var/cache/zebrad-cache -> ${{ inputs.root_state_path }}/${{ inputs.zebra_state_dir }} -> $ZEBRA_CACHED_STATE_DIR
# Launch the test with the previously created disk or cached state.
#
# This path must match the variable used by the tests in Rust, which are also set in
# `ci-unit-tests-docker.yml` to be able to run this tests.
#
# Although we're mounting the disk root, Zebra will only respect the values from
# $ZEBRA_CACHED_STATE_DIR. The inputs like ${{ inputs.zebra_state_dir }} are only used
# to match that variable paths.
- name: Launch ${{ inputs.test_id }} test
# This step only runs for tests that just read or write a Zebra state.
#
# lightwalletd-full-sync reads Zebra and writes lwd, so it is handled specially.
# TODO: we should find a better logic for this use cases
if: ${{ (inputs.needs_zebra_state && !inputs.needs_lwd_state) && inputs.test_id != 'lwd-full-sync' }}
run: |
gcloud compute ssh ${{ inputs.test_id }}-${{ env.GITHUB_REF_SLUG_URL }}-${{ env.GITHUB_SHA_SHORT }} \
--zone ${{ vars.GCP_ZONE }} \
--ssh-flag="-o ServerAliveInterval=5" \
--ssh-flag="-o ConnectionAttempts=20" \
--ssh-flag="-o ConnectTimeout=5" \
--command \
"\
# Wait for the disk to be attached
while [[ ! -e /dev/sdb ]]; do sleep 1; done && \
sudo docker run \
--name ${{ inputs.test_id }} \
--tty \
--detach \
${{ inputs.test_variables }} \
--mount type=volume,src=${{ inputs.test_id }}-${{ env.GITHUB_SHA_SHORT }},dst=${{ inputs.root_state_path }}/${{ inputs.zebra_state_dir }} \
${{ vars.GAR_BASE }}/${{ vars.CI_IMAGE_NAME }}:sha-${{ env.GITHUB_SHA_SHORT }} \
"
# Launch the test with the previously created Lightwalletd and Zebra cached state.
# Each test runs one of the "Launch test" steps, and skips the other.
# This step uses a $MOUNT_FLAGS variable to mount the disk to the docker container.
# If the test needs Lightwalletd state, we add the Lightwalletd state mount to the $MOUNT_FLAGS variable.
#
# SSH into the just created VM, and create a Docker container to run the incoming test
# from ${{ inputs.test_id }}, then mount the sudo docker volume created in the previous job.
Expand All @@ -454,27 +307,30 @@ jobs:
# considerations.
#
# The disk mounted in the VM is located at /dev/sdb, we mount the root `/` of this disk to the docker
# container in two different paths:
# container, and might have two different paths (if lightwalletd state is needed):
# - /var/cache/zebrad-cache -> ${{ inputs.root_state_path }}/${{ inputs.zebra_state_dir }} -> $ZEBRA_CACHED_STATE_DIR
# - /var/cache/lwd-cache -> ${{ inputs.root_state_path }}/${{ inputs.lwd_state_dir }} -> $LIGHTWALLETD_DATA_DIR
#
# This doesn't cause any path conflicts, because Zebra and lightwalletd create different
# subdirectories for their data. (But Zebra, lightwalletd, and the test harness must not
# delete the whole cache directory.)
#
# This paths must match the variables used by the tests in Rust, which are also set in
# This path must match the variable used by the tests in Rust, which are also set in
# `ci-unit-tests-docker.yml` to be able to run this tests.
#
# Although we're mounting the disk root to both directories, Zebra and Lightwalletd
# will only respect the values from $ZEBRA_CACHED_STATE_DIR and $LIGHTWALLETD_DATA_DIR,
# the inputs like ${{ inputs.lwd_state_dir }} are only used to match those variables paths.
# the inputs like ${{ inputs.zebra_state_dir }} and ${{ inputs.lwd_state_dir }}
# are only used to match those variables paths.
- name: Launch ${{ inputs.test_id }} test
# This step only runs for tests that read or write Lightwalletd and Zebra states.
#
# lightwalletd-full-sync reads Zebra and writes lwd, so it is handled specially.
# TODO: we should find a better logic for this use cases
if: ${{ (inputs.needs_zebra_state && inputs.needs_lwd_state) || inputs.test_id == 'lwd-full-sync' }}
run: |
MOUNT_FLAGS="--mount type=volume,src=${{ inputs.test_id }}-${{ env.GITHUB_SHA_SHORT }},dst=${{ inputs.root_state_path }}/${{ inputs.zebra_state_dir }}"
# Check if we need to mount for Lightwalletd state
if [[ "${{ inputs.needs_lwd_state }}" == "true" || "${{ inputs.test_id }}" == "lwd-full-sync" ]]; then
MOUNT_FLAGS="$MOUNT_FLAGS --mount type=volume,src=${{ inputs.test_id }}-${{ env.GITHUB_SHA_SHORT }},dst=${{ inputs.root_state_path }}/${{ inputs.lwd_state_dir }}"
fi
gcloud compute ssh ${{ inputs.test_id }}-${{ env.GITHUB_REF_SLUG_URL }}-${{ env.GITHUB_SHA_SHORT }} \
--zone ${{ vars.GCP_ZONE }} \
--ssh-flag="-o ServerAliveInterval=5" \
Expand All @@ -489,63 +345,10 @@ jobs:
--tty \
--detach \
${{ inputs.test_variables }} \
--mount type=volume,src=${{ inputs.test_id }}-${{ env.GITHUB_SHA_SHORT }},dst=${{ inputs.root_state_path }}/${{ inputs.zebra_state_dir }} \
--mount type=volume,src=${{ inputs.test_id }}-${{ env.GITHUB_SHA_SHORT }},dst=${{ inputs.root_state_path }}/${{ inputs.lwd_state_dir }} \
$MOUNT_FLAGS \
${{ vars.GAR_BASE }}/${{ vars.CI_IMAGE_NAME }}:sha-${{ env.GITHUB_SHA_SHORT }} \
"
# Show all the test logs, then follow the logs of the test we just launched, until it finishes.
# Then check the result of the test.
#
# If `inputs.is_long_test` is `true`, the timeout is 5 days, otherwise it's 3 hours.
test-result:
name: Run ${{ inputs.test_id }} test
# We run exactly one of without-cached-state or with-cached-state, and we always skip the other one.
needs: [ launch-with-cached-state, launch-without-cached-state ]
# If the previous job fails, we also want to run and fail this job,
# so that the branch protection rule fails in Mergify and GitHub.
if: ${{ !cancelled() }}
timeout-minutes: ${{ inputs.is_long_test && 7200 || 180 }}
runs-on: zfnd-runners
permissions:
contents: 'read'
id-token: 'write'
steps:
- uses: actions/checkout@v4.0.0
with:
persist-credentials: false
fetch-depth: '2'

- name: Inject slug/short variables
uses: rlespinasse/github-slug-action@v4
with:
short-length: 7

# Install our SSH secret
- name: Install private SSH key
uses: shimataro/ssh-key-action@v2.5.1
with:
key: ${{ secrets.GCP_SSH_PRIVATE_KEY }}
name: google_compute_engine
known_hosts: unnecessary

- name: Generate public SSH key
run: |
sudo apt-get update && sudo apt-get -qq install -y --no-install-recommends openssh-client
ssh-keygen -y -f ~/.ssh/google_compute_engine > ~/.ssh/google_compute_engine.pub
# Setup gcloud CLI
- name: Authenticate to Google Cloud
id: auth
uses: google-github-actions/auth@v1.1.1
with:
retries: '3'
workload_identity_provider: '${{ vars.GCP_WIF }}'
service_account: '${{ vars.GCP_DEPLOYMENTS_SA }}'

- name: Set up Cloud SDK
uses: google-github-actions/setup-gcloud@v1.1.1

# Show all the logs since the container launched,
# following until we see zebrad startup messages.
#
Expand Down Expand Up @@ -621,7 +424,7 @@ jobs:
create-state-image:
name: Create ${{ inputs.test_id }} cached state image
runs-on: ubuntu-latest
needs: [ test-result, launch-with-cached-state ]
needs: [ test-result ]
# We run exactly one of without-cached-state or with-cached-state, and we always skip the other one.
# Normally, if a job is skipped, all the jobs that depend on it are also skipped.
# So we need to override the default success() check to make this job run.
Expand Down Expand Up @@ -864,7 +667,7 @@ jobs:
- name: Get original cached state height from google cloud
run: |
ORIGINAL_HEIGHT="0"
ORIGINAL_DISK_NAME="${{ format('{0}', needs.launch-with-cached-state.outputs.cached_disk_name) }}"
ORIGINAL_DISK_NAME="${{ format('{0}', needs.test-result.outputs.cached_disk_name) }}"
if [[ -n "$ORIGINAL_DISK_NAME" ]]; then
ORIGINAL_HEIGHT=$(gcloud compute images list --filter="status=READY AND name=$ORIGINAL_DISK_NAME" --format="value(labels.height)")
Expand Down

0 comments on commit 3dce369

Please sign in to comment.