zebra/.github/workflows/deploy-gcp-tests.yml

1019 lines
41 KiB
YAML

name: Deploy GCP tests
on:
workflow_call:
inputs:
# Status and logging
test_id:
required: true
type: string
description: 'Unique identifier for the test'
test_description:
required: true
type: string
description: 'Explains what the test does'
# Test selection and parameters
test_variables:
required: true
type: string
description: 'Environmental variables used to select and configure the test'
network:
required: false
type: string
default: Mainnet
description: 'Zcash network to test against'
# Cached state
#
# TODO: find a better name
root_state_path:
required: false
type: string
default: '/zebrad-cache'
description: 'Cached state base directory path'
# TODO: find a better name
zebra_state_dir:
required: false
type: string
default: ''
description: 'Zebra cached state directory and input image prefix to search in GCP'
# TODO: find a better name
lwd_state_dir:
required: false
type: string
default: ''
description: 'Lightwalletd cached state directory and input image prefix to search in GCP'
disk_prefix:
required: false
type: string
default: 'zebrad-cache'
description: 'Image name prefix, and `zebra_state_dir` name for newly created cached states'
disk_suffix:
required: false
type: string
description: 'Image name suffix'
needs_zebra_state:
required: true
type: boolean
description: 'Does the test use Zebra cached state?'
needs_lwd_state:
required: false
type: boolean
description: 'Does the test use Lightwalletd and Zebra cached state?'
saves_to_disk:
required: true
type: boolean
description: 'Does the test create a new cached state disk?'
# Metadata
height_grep_text:
required: false
type: string
description: 'Regular expression to find the tip height in test logs, and add it to newly created cached state image metadata'
app_name:
required: false
type: string
default: 'zebra'
description: 'Application name for Google Cloud instance metadata'
env:
# where we get the Docker image from
IMAGE_NAME: zebrad-test
GAR_BASE: us-docker.pkg.dev/zealous-zebra/zebra
# what kind of Google Cloud instance we want to launch
ZONE: us-central1-a
MACHINE_TYPE: c2d-standard-16
# How many previous log lines we show at the start of each new log job.
# Increase this number if some log lines are skipped between jobs
#
# We want to show all the logs since the last job finished,
# but we don't know how long it will be between jobs.
# 200 lines is about 6-15 minutes of sync logs, or one panic log.
EXTRA_LOG_LINES: 200
jobs:
# set up 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
setup-without-cached-state:
name: Setup ${{ inputs.test_id }} test
if: ${{ !inputs.needs_zebra_state }}
runs-on: ubuntu-latest
permissions:
contents: 'read'
id-token: 'write'
steps:
- uses: actions/checkout@v3.0.2
with:
persist-credentials: false
fetch-depth: '2'
- name: Inject slug/short variables
uses: rlespinasse/github-slug-action@v4
with:
short-length: 7
- name: Downcase network name for disks
run: |
NETWORK_CAPS=${{ inputs.network }}
echo "NETWORK=${NETWORK_CAPS,,}" >> $GITHUB_ENV
# Setup gcloud CLI
- name: Authenticate to Google Cloud
id: auth
uses: google-github-actions/auth@v0.8.0
with:
retries: '3'
workload_identity_provider: 'projects/143793276228/locations/global/workloadIdentityPools/github-actions/providers/github-oidc'
service_account: 'github-service-account@zealous-zebra.iam.gserviceaccount.com'
token_format: 'access_token'
# 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 100GB \
--boot-disk-type pd-ssd \
--create-disk name="${{ inputs.test_id }}-${{ env.GITHUB_SHA_SHORT }}",device-name="${{ inputs.test_id }}-${{ env.GITHUB_SHA_SHORT }}",size=100GB,type=pd-ssd \
--container-image debian:buster \
--container-restart-policy=never \
--machine-type ${{ env.MACHINE_TYPE }} \
--scopes cloud-platform \
--metadata=google-monitoring-enabled=true,google-logging-enabled=true \
--tags ${{ inputs.app_name }} \
--zone ${{ env.ZONE }}
sleep 60
- name: Create ${{ inputs.test_id }} Docker volume
run: |
gcloud compute ssh \
${{ inputs.test_id }}-${{ env.GITHUB_REF_SLUG_URL }}-${{ env.GITHUB_SHA_SHORT }} \
--zone ${{ env.ZONE }} \
--quiet \
--ssh-flag="-o ServerAliveInterval=5" \
--command \
"\
sudo mkfs.ext4 /dev/sdb \
&& \
docker volume create --driver local --opt type=ext4 --opt device=/dev/sdb \
${{ inputs.test_id }}-${{ env.GITHUB_SHA_SHORT }} \
"
# launch the test, if it doesn't use any cached state
launch-without-cached-state:
name: Launch ${{ inputs.test_id }} test
needs: [ setup-without-cached-state ]
# If creating the Google Cloud instance fails, we don't want to launch another docker instance.
if: ${{ !cancelled() && !failure() && !inputs.needs_zebra_state }}
runs-on: ubuntu-latest
permissions:
contents: 'read'
id-token: 'write'
steps:
- uses: actions/checkout@v3.0.2
with:
persist-credentials: false
fetch-depth: '2'
- name: Inject slug/short variables
uses: rlespinasse/github-slug-action@v4
with:
short-length: 7
- name: Downcase network name for disks
run: |
NETWORK_CAPS=${{ inputs.network }}
echo "NETWORK=${NETWORK_CAPS,,}" >> $GITHUB_ENV
# Setup gcloud CLI
- name: Authenticate to Google Cloud
id: auth
uses: google-github-actions/auth@v0.8.0
with:
retries: '3'
workload_identity_provider: 'projects/143793276228/locations/global/workloadIdentityPools/github-actions/providers/github-oidc'
service_account: 'github-service-account@zealous-zebra.iam.gserviceaccount.com'
token_format: 'access_token'
# 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 ${{ env.ZONE }} \
--quiet \
--ssh-flag="-o ServerAliveInterval=5" \
--command \
"\
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 }} \
${{ env.GAR_BASE }}/${{ env.IMAGE_NAME }}:sha-${{ env.GITHUB_SHA_SHORT }} \
"
# set up the test, if it uses cached state
# each test runs one of the *-with/without-cached-state job series, and skips the other
setup-with-cached-state:
name: Setup ${{ inputs.test_id }} test
if: ${{ inputs.needs_zebra_state }}
runs-on: ubuntu-latest
permissions:
contents: 'read'
id-token: 'write'
steps:
- uses: actions/checkout@v3.0.2
with:
persist-credentials: false
fetch-depth: '2'
- name: Inject slug/short variables
uses: rlespinasse/github-slug-action@v4
with:
short-length: 7
- name: Downcase network name for disks
run: |
NETWORK_CAPS=${{ inputs.network }}
echo "NETWORK=${NETWORK_CAPS,,}" >> $GITHUB_ENV
# Setup gcloud CLI
- name: Authenticate to Google Cloud
id: auth
uses: google-github-actions/auth@v0.8.0
with:
retries: '3'
workload_identity_provider: 'projects/143793276228/locations/global/workloadIdentityPools/github-actions/providers/github-oidc'
service_account: 'github-service-account@zealous-zebra.iam.gserviceaccount.com'
token_format: 'access_token'
# Find a cached state disk for this job, matching all of:
# - disk cached state (lwd_state_dir/zebra_state_dir or disk_prefix) - zebrad-cache or lwd-cache
# - state version (from the source code) - v{N}
# - network (network) - mainnet or testnet
# - disk target height kind (disk_suffix) - checkpoint or tip
#
# If the test needs a lightwalletd state (needs_lwd_state) set the variable DISK_PREFIX accordingly
# - To ${{ inputs.lwd_state_dir }}" if needed
# - To ${{ inputs.zebra_state_dir || inputs.disk_prefix }} if not
#
# If there are multiple disks:
# - prefer images generated from this branch, then the `main` branch, then any other branch
# - prefer newer images to older images
#
# Passes the disk name to subsequent steps using $CACHED_DISK_NAME env variable
# Passes the state version to subsequent steps using $STATE_VERSION env variable
- name: Find ${{ inputs.test_id }} cached state disk
id: get-disk-name
run: |
LOCAL_STATE_VERSION=$(grep -oE "DATABASE_FORMAT_VERSION: .* [0-9]+" "$GITHUB_WORKSPACE/zebra-state/src/constants.rs" | grep -oE "[0-9]+" | tail -n1)
echo "STATE_VERSION: $LOCAL_STATE_VERSION"
if [[ "${{ inputs.needs_lwd_state }}" == "true" ]]; then
DISK_PREFIX=${{ inputs.lwd_state_dir }}
else
DISK_PREFIX=${{ inputs.zebra_state_dir || inputs.disk_prefix }}
fi
# Try to find an image generated from this branch and commit
# Fields are listed in the "Create image from state disk" step
BRANCH_DISK_NAME="${DISK_PREFIX}-${GITHUB_REF_SLUG_URL}-${GITHUB_SHA_SHORT}-v${LOCAL_STATE_VERSION}-${NETWORK}-${{ inputs.disk_suffix }}"
CACHED_DISK_NAME=$(gcloud compute images list --filter="name~${BRANCH_DISK_NAME}" --format="value(NAME)" --sort-by=~creationTimestamp --limit=1)
echo "${GITHUB_REF_SLUG_URL}-${GITHUB_SHA_SHORT} Disk: $CACHED_DISK_NAME"
if [[ -z "$CACHED_DISK_NAME" ]]; then
# Try to find an image generated from the main branch
CACHED_DISK_NAME=$(gcloud compute images list --filter="name~${DISK_PREFIX}-main-[0-9a-f]+-v${LOCAL_STATE_VERSION}-${NETWORK}-${{ inputs.disk_suffix }}" --format="value(NAME)" --sort-by=~creationTimestamp --limit=1)
echo "main Disk: $CACHED_DISK_NAME"
fi
if [[ -z "$CACHED_DISK_NAME" ]]; then
# Try to find an image generated from any other branch
CACHED_DISK_NAME=$(gcloud compute images list --filter="name~${DISK_PREFIX}-.+-[0-9a-f]+-v${LOCAL_STATE_VERSION}-${NETWORK}-${{ inputs.disk_suffix }}" --format="value(NAME)" --sort-by=~creationTimestamp --limit=1)
echo "any branch Disk: $CACHED_DISK_NAME"
fi
if [[ -z "$CACHED_DISK_NAME" ]]; then
echo "No cached state disk available"
echo "Expected ${BRANCH_DISK_NAME}"
echo "Also searched for any commit on main, and any commit on any branch"
echo "Cached state test jobs must depend on the cached state rebuild job"
exit 1
fi
echo "Description: $(gcloud compute images describe $CACHED_DISK_NAME --format='value(DESCRIPTION)')"
echo "STATE_VERSION=$LOCAL_STATE_VERSION" >> $GITHUB_ENV
echo "CACHED_DISK_NAME=$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
- 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 100GB \
--boot-disk-type pd-ssd \
--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=100GB,type=pd-ssd \
--container-image debian:buster \
--container-restart-policy=never \
--machine-type ${{ env.MACHINE_TYPE }} \
--scopes cloud-platform \
--metadata=google-monitoring-enabled=true,google-logging-enabled=true \
--tags ${{ inputs.app_name }} \
--zone ${{ env.ZONE }}
sleep 60
# Create a docker volume with the selected cached state.
#
# SSH into the just created VM, and create a docker volume with the recently attached 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 ${{ env.ZONE }} \
--quiet \
--ssh-flag="-o ServerAliveInterval=5" \
--command \
"\
docker volume create --driver local --opt type=ext4 --opt device=/dev/sdb \
${{ inputs.test_id }}-${{ env.GITHUB_SHA_SHORT }} \
"
# launch the test, if it uses cached state
launch-with-cached-state:
name: Launch ${{ inputs.test_id }} test
needs: [ setup-with-cached-state ]
# If creating the Google Cloud instance fails, we don't want to launch another docker instance.
if: ${{ !cancelled() && !failure() && inputs.needs_zebra_state }}
runs-on: ubuntu-latest
permissions:
contents: 'read'
id-token: 'write'
steps:
- uses: actions/checkout@v3.0.2
with:
persist-credentials: false
fetch-depth: '2'
- name: Inject slug/short variables
uses: rlespinasse/github-slug-action@v4
with:
short-length: 7
- name: Downcase network name for disks
run: |
NETWORK_CAPS=${{ inputs.network }}
echo "NETWORK=${NETWORK_CAPS,,}" >> $GITHUB_ENV
# Setup gcloud CLI
- name: Authenticate to Google Cloud
id: auth
uses: google-github-actions/auth@v0.8.0
with:
retries: '3'
workload_identity_provider: 'projects/143793276228/locations/global/workloadIdentityPools/github-actions/providers/github-oidc'
service_account: 'github-service-account@zealous-zebra.iam.gserviceaccount.com'
token_format: 'access_token'
# 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 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
#
# This path must match the variable used by the tests in Rust, which are also set in
# `continous-integration-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 ${{ env.ZONE }} \
--quiet \
--ssh-flag="-o ServerAliveInterval=5" \
--command \
"\
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 }} \
${{ env.GAR_BASE }}/${{ env.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.
#
# SSH into the just created VM, and create a Docker container to run the incoming test
# from ${{ inputs.test_id }}, then mount the docker volume created in the previous job.
#
# In this step we're using the same disk for simplicity, as mounting multiple disks to the
# VM and to the container might require more steps in this workflow, and additional
# 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:
# - /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
# `continous-integration-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.
- 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: |
gcloud compute ssh \
${{ inputs.test_id }}-${{ env.GITHUB_REF_SLUG_URL }}-${{ env.GITHUB_SHA_SHORT }} \
--zone ${{ env.ZONE }} \
--quiet \
--ssh-flag="-o ServerAliveInterval=5" \
--command \
"\
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 }}/${{ inputs.zebra_state_dir }} \
--mount type=volume,src=${{ inputs.test_id }}-${{ env.GITHUB_SHA_SHORT }},dst=${{ inputs.root_state_path }}/${{ inputs.lwd_state_dir }} \
${{ env.GAR_BASE }}/${{ env.IMAGE_NAME }}:sha-${{ env.GITHUB_SHA_SHORT }} \
"
# follow the logs of the test we just launched, up to Sapling activation (or the test finishing)
logs-sprout:
name: Log ${{ inputs.test_id }} test (sprout)
# 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 still want to show the logs.
if: ${{ !cancelled() }}
runs-on: ubuntu-latest
permissions:
contents: 'read'
id-token: 'write'
steps:
- uses: actions/checkout@v3.0.2
with:
persist-credentials: false
fetch-depth: '2'
- name: Inject slug/short variables
uses: rlespinasse/github-slug-action@v4
with:
short-length: 7
- name: Downcase network name for disks
run: |
NETWORK_CAPS=${{ inputs.network }}
echo "NETWORK=${NETWORK_CAPS,,}" >> $GITHUB_ENV
# Setup gcloud CLI
- name: Authenticate to Google Cloud
id: auth
uses: google-github-actions/auth@v0.8.0
with:
retries: '3'
workload_identity_provider: 'projects/143793276228/locations/global/workloadIdentityPools/github-actions/providers/github-oidc'
service_account: 'github-service-account@zealous-zebra.iam.gserviceaccount.com'
token_format: 'access_token'
# Show all the logs since the container launched,
# following until Sapling activation (or the test finishes).
#
# The log pipeline ignores the exit status of `docker logs`.
# Errors in the tests are caught by the final test status job.
- name: Show logs for ${{ inputs.test_id }} test (sprout)
run: |
gcloud compute ssh \
${{ inputs.test_id }}-${{ env.GITHUB_REF_SLUG_URL }}-${{ env.GITHUB_SHA_SHORT }} \
--zone ${{ env.ZONE }} \
--quiet \
--ssh-flag="-o ServerAliveInterval=5" \
--command \
"\
docker logs \
--tail all \
--follow \
${{ inputs.test_id }} | \
tee --output-error=exit /dev/stderr | \
grep --max-count=1 --extended-regexp --color=always \
'(estimated progress.*network_upgrade.*=.*Sapling)|(estimated progress.*network_upgrade.*=.*Blossom)|(estimated progress.*network_upgrade.*=.*Heartwood)|(estimated progress.*network_upgrade.*=.*Canopy)|(estimated progress.*network_upgrade.*=.*Nu5)|(test result:.*finished in)' \
"
# follow the logs of the test we just launched, up to Canopy activation (or the test finishing)
logs-heartwood:
name: Log ${{ inputs.test_id }} test (heartwood)
needs: [ logs-sprout ]
# If the previous job fails, we still want to show the logs.
if: ${{ !cancelled() }}
runs-on: ubuntu-latest
permissions:
contents: 'read'
id-token: 'write'
steps:
- uses: actions/checkout@v3.0.2
with:
persist-credentials: false
fetch-depth: '2'
- name: Inject slug/short variables
uses: rlespinasse/github-slug-action@v4
with:
short-length: 7
- name: Downcase network name for disks
run: |
NETWORK_CAPS=${{ inputs.network }}
echo "NETWORK=${NETWORK_CAPS,,}" >> $GITHUB_ENV
# Setup gcloud CLI
- name: Authenticate to Google Cloud
id: auth
uses: google-github-actions/auth@v0.8.0
with:
retries: '3'
workload_identity_provider: 'projects/143793276228/locations/global/workloadIdentityPools/github-actions/providers/github-oidc'
service_account: 'github-service-account@zealous-zebra.iam.gserviceaccount.com'
token_format: 'access_token'
# Show recent logs, following until Canopy activation (or the test finishes)
- name: Show logs for ${{ inputs.test_id }} test (heartwood)
run: |
gcloud compute ssh \
${{ inputs.test_id }}-${{ env.GITHUB_REF_SLUG_URL }}-${{ env.GITHUB_SHA_SHORT }} \
--zone ${{ env.ZONE }} \
--quiet \
--ssh-flag="-o ServerAliveInterval=5" \
--command \
"\
docker logs \
--tail all \
--follow \
${{ inputs.test_id }} | \
tee --output-error=exit /dev/stderr | \
grep --max-count=1 --extended-regexp --color=always \
'(estimated progress.*network_upgrade.*=.*Canopy)|(estimated progress.*network_upgrade.*=.*Nu5)|(test result:.*finished in)' \
"
# follow the logs of the test we just launched, up to NU5 activation (or the test finishing)
logs-canopy:
name: Log ${{ inputs.test_id }} test (canopy)
needs: [ logs-heartwood ]
# If the previous job fails, we still want to show the logs.
if: ${{ !cancelled() }}
runs-on: ubuntu-latest
permissions:
contents: 'read'
id-token: 'write'
steps:
- uses: actions/checkout@v3.0.2
with:
persist-credentials: false
fetch-depth: '2'
- name: Inject slug/short variables
uses: rlespinasse/github-slug-action@v4
with:
short-length: 7
- name: Downcase network name for disks
run: |
NETWORK_CAPS=${{ inputs.network }}
echo "NETWORK=${NETWORK_CAPS,,}" >> $GITHUB_ENV
# Setup gcloud CLI
- name: Authenticate to Google Cloud
id: auth
uses: google-github-actions/auth@v0.8.0
with:
retries: '3'
workload_identity_provider: 'projects/143793276228/locations/global/workloadIdentityPools/github-actions/providers/github-oidc'
service_account: 'github-service-account@zealous-zebra.iam.gserviceaccount.com'
token_format: 'access_token'
# Show recent logs, following until NU5 activation (or the test finishes)
- name: Show logs for ${{ inputs.test_id }} test (canopy)
run: |
gcloud compute ssh \
${{ inputs.test_id }}-${{ env.GITHUB_REF_SLUG_URL }}-${{ env.GITHUB_SHA_SHORT }} \
--zone ${{ env.ZONE }} \
--quiet \
--ssh-flag="-o ServerAliveInterval=5" \
--command \
"\
docker logs \
--tail all \
--follow \
${{ inputs.test_id }} | \
tee --output-error=exit /dev/stderr | \
grep --max-count=1 --extended-regexp --color=always \
'(estimated progress.*network_upgrade.*=.*Nu5)|(test result:.*finished in)' \
"
# follow the logs of the test we just launched, up to block 1,740,000 or later
# (or the test finishing)
#
# We chose this height because it was about 5 hours into the NU5 sync, at the end of July 2022.
# This is a temporary workaround until we improve sync speeds.
logs-1740k:
name: Log ${{ inputs.test_id }} test (1740k)
needs: [ logs-canopy ]
# If the previous job fails, we still want to show the logs.
if: ${{ !cancelled() }}
runs-on: ubuntu-latest
permissions:
contents: 'read'
id-token: 'write'
steps:
- uses: actions/checkout@v3.0.2
with:
persist-credentials: false
fetch-depth: '2'
- name: Inject slug/short variables
uses: rlespinasse/github-slug-action@v4
with:
short-length: 7
- name: Downcase network name for disks
run: |
NETWORK_CAPS=${{ inputs.network }}
echo "NETWORK=${NETWORK_CAPS,,}" >> $GITHUB_ENV
# Setup gcloud CLI
- name: Authenticate to Google Cloud
id: auth
uses: google-github-actions/auth@v0.8.0
with:
retries: '3'
workload_identity_provider: 'projects/143793276228/locations/global/workloadIdentityPools/github-actions/providers/github-oidc'
service_account: 'github-service-account@zealous-zebra.iam.gserviceaccount.com'
token_format: 'access_token'
# Show recent logs, following until block 1,740,000 (or the test finishes)
- name: Show logs for ${{ inputs.test_id }} test (1740k)
run: |
gcloud compute ssh \
${{ inputs.test_id }}-${{ env.GITHUB_REF_SLUG_URL }}-${{ env.GITHUB_SHA_SHORT }} \
--zone ${{ env.ZONE }} \
--quiet \
--ssh-flag="-o ServerAliveInterval=5" \
--command \
"\
docker logs \
--tail all \
--follow \
${{ inputs.test_id }} | \
tee --output-error=exit /dev/stderr | \
grep --max-count=1 --extended-regexp --color=always \
'(estimated progress.*current_height.*=.*17[4-9][0-9][0-9][0-9][0-9].*remaining_sync_blocks)|(estimated progress.*current_height.*=.*1[8-9][0-9][0-9][0-9][0-9][0-9].*remaining_sync_blocks)||(estimated progress.*current_height.*=.*2[0-9][0-9][0-9][0-9][0-9][0-9].*remaining_sync_blocks)|(test result:.*finished in)' \
"
# follow the logs of the test we just launched, up to the last checkpoint (or the test finishing)
logs-checkpoint:
name: Log ${{ inputs.test_id }} test (checkpoint)
needs: [ logs-1740k ]
# If the previous job fails, we still want to show the logs.
if: ${{ !cancelled() }}
runs-on: ubuntu-latest
permissions:
contents: 'read'
id-token: 'write'
steps:
- uses: actions/checkout@v3.0.2
with:
persist-credentials: false
fetch-depth: '2'
- name: Inject slug/short variables
uses: rlespinasse/github-slug-action@v4
with:
short-length: 7
- name: Downcase network name for disks
run: |
NETWORK_CAPS=${{ inputs.network }}
echo "NETWORK=${NETWORK_CAPS,,}" >> $GITHUB_ENV
# Setup gcloud CLI
- name: Authenticate to Google Cloud
id: auth
uses: google-github-actions/auth@v0.8.0
with:
retries: '3'
workload_identity_provider: 'projects/143793276228/locations/global/workloadIdentityPools/github-actions/providers/github-oidc'
service_account: 'github-service-account@zealous-zebra.iam.gserviceaccount.com'
token_format: 'access_token'
# Show recent logs, following until the last checkpoint (or the test finishes)
#
# TODO: when doing obtain/extend tips, log the verifier in use, and check for full verification here
- name: Show logs for ${{ inputs.test_id }} test (checkpoint)
run: |
gcloud compute ssh \
${{ inputs.test_id }}-${{ env.GITHUB_REF_SLUG_URL }}-${{ env.GITHUB_SHA_SHORT }} \
--zone ${{ env.ZONE }} \
--quiet \
--ssh-flag="-o ServerAliveInterval=5" \
--command \
"\
docker logs \
--tail ${{ env.EXTRA_LOG_LINES }} \
--follow \
${{ inputs.test_id }} | \
tee --output-error=exit /dev/stderr | \
grep --max-count=1 --extended-regexp --color=always \
'(verified final checkpoint)|(test result:.*finished in)' \
"
# follow the logs of the test we just launched, until it finishes
logs-end:
name: Log ${{ inputs.test_id }} test (end)
needs: [ logs-checkpoint ]
# If the previous job fails, we still want to show the logs.
if: ${{ !cancelled() }}
runs-on: ubuntu-latest
permissions:
contents: 'read'
id-token: 'write'
steps:
- uses: actions/checkout@v3.0.2
with:
persist-credentials: false
fetch-depth: '2'
- name: Inject slug/short variables
uses: rlespinasse/github-slug-action@v4
with:
short-length: 7
- name: Downcase network name for disks
run: |
NETWORK_CAPS=${{ inputs.network }}
echo "NETWORK=${NETWORK_CAPS,,}" >> $GITHUB_ENV
# Setup gcloud CLI
- name: Authenticate to Google Cloud
id: auth
uses: google-github-actions/auth@v0.8.0
with:
retries: '3'
workload_identity_provider: 'projects/143793276228/locations/global/workloadIdentityPools/github-actions/providers/github-oidc'
service_account: 'github-service-account@zealous-zebra.iam.gserviceaccount.com'
token_format: 'access_token'
# Show recent logs, following until the test finishes
- name: Show logs for ${{ inputs.test_id }} test (end)
run: |
gcloud compute ssh \
${{ inputs.test_id }}-${{ env.GITHUB_REF_SLUG_URL }}-${{ env.GITHUB_SHA_SHORT }} \
--zone ${{ env.ZONE }} \
--quiet \
--ssh-flag="-o ServerAliveInterval=5" \
--command \
"\
docker logs \
--tail ${{ env.EXTRA_LOG_LINES }} \
--follow \
${{ inputs.test_id }} | \
tee --output-error=exit /dev/stderr | \
grep --max-count=1 --extended-regexp --color=always \
'test result:.*finished in' \
"
# check the results of the test
test-result:
# TODO: update the job name here, and in the branch protection rules
name: Run ${{ inputs.test_id }} test
needs: [ logs-end ]
# 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: ${{ !cancelled() }}
runs-on: ubuntu-latest
permissions:
contents: 'read'
id-token: 'write'
steps:
- uses: actions/checkout@v3.0.2
with:
persist-credentials: false
fetch-depth: '2'
- name: Inject slug/short variables
uses: rlespinasse/github-slug-action@v4
with:
short-length: 7
- name: Downcase network name for disks
run: |
NETWORK_CAPS=${{ inputs.network }}
echo "NETWORK=${NETWORK_CAPS,,}" >> $GITHUB_ENV
# Setup gcloud CLI
- name: Authenticate to Google Cloud
id: auth
uses: google-github-actions/auth@v0.8.0
with:
retries: '3'
workload_identity_provider: 'projects/143793276228/locations/global/workloadIdentityPools/github-actions/providers/github-oidc'
service_account: 'github-service-account@zealous-zebra.iam.gserviceaccount.com'
token_format: 'access_token'
# Check that the container executed at least 1 Rust test harness test, and that all tests passed.
# Then wait for the container to finish, and exit with the test's exit status.
# Also shows recent test logs.
#
# If the container has already finished, `docker wait` should return its status.
# But sometimes this doesn't work, so we use `docker inspect` as a fallback.
#
# `docker wait` prints the container exit status as a string, but we need to exit the `ssh` command
# with that status.
# (`docker wait` can also wait for multiple containers, but we only ever wait for a single container.)
- name: Result of ${{ inputs.test_id }} test
run: |
gcloud compute ssh \
${{ inputs.test_id }}-${{ env.GITHUB_REF_SLUG_URL }}-${{ env.GITHUB_SHA_SHORT }} \
--zone ${{ env.ZONE }} \
--quiet \
--ssh-flag="-o ServerAliveInterval=5" \
--command=' \
set -e;
docker logs \
--tail ${{ env.EXTRA_LOG_LINES }} \
${{ inputs.test_id }} | \
tee --output-error=exit /dev/stderr | \
grep --max-count=1 --extended-regexp --color=always \
"test result: .*ok.* [1-9][0-9]* passed.*finished in"; \
EXIT_STATUS=$( \
docker wait ${{ inputs.test_id }} || \
docker inspect --format "{{.State.ExitCode}}" ${{ inputs.test_id }} || \
echo "missing container, or missing exit status for container" \
); \
echo "docker exit status: $EXIT_STATUS"; \
exit "$EXIT_STATUS" \
'
# create a state image from the instance's state disk, if requested by the caller
create-state-image:
name: Create ${{ inputs.test_id }} cached state image
runs-on: ubuntu-latest
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.
if: ${{ !cancelled() && !failure() && inputs.saves_to_disk }}
permissions:
contents: 'read'
id-token: 'write'
steps:
- uses: actions/checkout@v3.0.2
with:
persist-credentials: false
fetch-depth: '2'
- name: Inject slug/short variables
uses: rlespinasse/github-slug-action@v4
with:
short-length: 7
# Disk images 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 $NETWORK env variable
- name: Downcase network name for disks
run: |
NETWORK_CAPS=${{ inputs.network }}
echo "NETWORK=${NETWORK_CAPS,,}" >> $GITHUB_ENV
# Setup gcloud CLI
- name: Authenticate to Google Cloud
id: auth
uses: google-github-actions/auth@v0.7.3
with:
workload_identity_provider: 'projects/143793276228/locations/global/workloadIdentityPools/github-actions/providers/github-oidc'
service_account: 'github-service-account@zealous-zebra.iam.gserviceaccount.com'
token_format: 'access_token'
# Get the state version from the local constants.rs file to be used in the image creation,
# as the state version is part of the disk image name.
#
# Passes the state version to subsequent steps using $STATE_VERSION env variable
- name: Get state version from constants.rs
run: |
LOCAL_STATE_VERSION=$(grep -oE "DATABASE_FORMAT_VERSION: .* [0-9]+" $GITHUB_WORKSPACE/zebra-state/src/constants.rs | grep -oE "[0-9]+" | tail -n1)
echo "STATE_VERSION: $LOCAL_STATE_VERSION"
echo "STATE_VERSION=$LOCAL_STATE_VERSION" >> $GITHUB_ENV
# Get the sync height from the test logs, which is later used as part of the
# disk description.
#
# The regex used to grep the sync height is provided by ${{ inputs.height_grep_text }},
# this allows to dynamically change the height as needed by different situations or
# based on the logs output from different tests
#
# Passes the sync height to subsequent steps using $SYNC_HEIGHT env variable
- name: Get sync height from logs
run: |
SYNC_HEIGHT=""
DOCKER_LOGS=$(\
gcloud compute ssh \
${{ inputs.test_id }}-${{ env.GITHUB_REF_SLUG_URL }}-${{ env.GITHUB_SHA_SHORT }} \
--zone ${{ env.ZONE }} \
--quiet \
--ssh-flag="-o ServerAliveInterval=5" \
--command="docker logs ${{ inputs.test_id }} --tail 20")
SYNC_HEIGHT=$(echo $DOCKER_LOGS | grep -oE '${{ inputs.height_grep_text }}\([0-9]+\)' | grep -oE '[0-9]+' | tail -1 || [[ $? == 1 ]])
echo "SYNC_HEIGHT=$SYNC_HEIGHT" >> $GITHUB_ENV
# Create an image from disk that will be used for following/other tests
# This image can contain:
# - Zebra cached state
# - Zebra + lightwalletd cached state
# Which cached state is being saved to the disk is defined by ${{ inputs.disk_prefix }}
#
# Force the image creation (--force) as the disk is still attached even though is not being
# used by the container
- name: Create image from state disk
run: |
gcloud compute images create ${{ inputs.disk_prefix }}-${{ env.GITHUB_REF_SLUG_URL }}-${{ env.GITHUB_SHA_SHORT }}-v${{ env.STATE_VERSION }}-${{ env.NETWORK }}-${{ inputs.disk_suffix }} \
--force \
--source-disk=${{ inputs.test_id }}-${{ env.GITHUB_SHA_SHORT }} \
--source-disk-zone=${{ env.ZONE }} \
--storage-location=us \
--description="Created from commit ${{ env.GITHUB_SHA_SHORT }} with height ${{ env.SYNC_HEIGHT }}"
# delete the Google Cloud instance for this test
delete-instance:
name: Delete ${{ inputs.test_id }} instance
runs-on: ubuntu-latest
needs: [ create-state-image ]
# If a disk generation step timeouts (+6 hours) the previous job (creating the image) will be skipped.
# Even if the instance continues running, no image will be created, so it's better to delete it.
if: always()
continue-on-error: true
permissions:
contents: 'read'
id-token: 'write'
steps:
- uses: actions/checkout@v3.0.2
with:
persist-credentials: false
fetch-depth: '2'
- name: Inject slug/short variables
uses: rlespinasse/github-slug-action@v4
with:
short-length: 7
# Setup gcloud CLI
- name: Authenticate to Google Cloud
id: auth
uses: google-github-actions/auth@v0.7.3
with:
workload_identity_provider: 'projects/143793276228/locations/global/workloadIdentityPools/github-actions/providers/github-oidc'
service_account: 'github-service-account@zealous-zebra.iam.gserviceaccount.com'
token_format: 'access_token'
# Deletes the instances that has been recently deployed in the actual commit after all
# previous jobs have run, no matter the outcome of the job.
- name: Delete test instance
continue-on-error: true
run: |
INSTANCE=$(gcloud compute instances list --filter=${{ inputs.test_id }}-${{ env.GITHUB_REF_SLUG_URL }}-${{ env.GITHUB_SHA_SHORT }} --format='value(NAME)')
if [ -z "${INSTANCE}" ]; then
echo "No instance to delete"
else
gcloud compute instances delete "${INSTANCE}" --zone "${{ env.ZONE }}" --delete-disks all --quiet
fi