Skip to content

Use GKE workload identity federation in composer #4023

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
wants to merge 1 commit into
base: main
Choose a base branch
from
Open

Use GKE workload identity federation in composer #4023

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
5 changes: 0 additions & 5 deletions airflow/dags/publish_open_data/publish_california_open_data.yml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -14,15 +14,10 @@ is_delete_operator_pod: true
get_logs: true

env_vars:
GOOGLE_APPLICATION_CREDENTIALS: /secrets/jobs-data/service_account.json
CALITP_BUCKET__DBT_ARTIFACTS: "{{ env_var('CALITP_BUCKET__DBT_ARTIFACTS') }}"
CALITP_BUCKET__PUBLISH: "{{ env_var('CALITP_BUCKET__PUBLISH') }}"

secrets:
- deploy_type: volume
deploy_target: /secrets/jobs-data/
secret: jobs-data
key: service-account.json
- deploy_type: env
deploy_target: CALITP_CKAN_GTFS_SCHEDULE_KEY
secret: jobs-data
Expand Down
7 changes: 0 additions & 7 deletions airflow/dags/unzip_and_validate_gtfs_schedule_hourly/validate_gtfs_schedule.yml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -17,19 +17,12 @@ is_delete_operator_pod: true
get_logs: true

env_vars:
GOOGLE_APPLICATION_CREDENTIALS: /secrets/jobs-data/service_account.json
AIRFLOW_ENV: "{{ env_var('AIRFLOW_ENV') }}"
CALITP_USER: "{{ env_var('CALITP_USER') }}"
CALITP_BUCKET__GTFS_SCHEDULE_RAW: "{{ env_var('CALITP_BUCKET__GTFS_SCHEDULE_RAW') }}"
CALITP_BUCKET__GTFS_SCHEDULE_VALIDATION_HOURLY: "{{ env_var('CALITP_BUCKET__GTFS_SCHEDULE_VALIDATION_HOURLY') }}"
GRAAS_SERVER_URL: "{{ env_var('GRAAS_SERVER_URL') }}"

secrets:
- deploy_type: volume
deploy_target: /secrets/jobs-data/
secret: jobs-data
key: service_account.json

k8s_resources:
request_memory: 5.0Gi
request_cpu: 1
Expand Down
2 changes: 1 addition & 1 deletion iac/cal-itp-data-infra-staging/composer/us/environment.tf
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -61,7 +61,7 @@ resource "google_composer_environment" "calitp-staging-composer" {
"POD_LOCATION" = "us-west2",
"POD_CLUSTER_NAME" = data.terraform_remote_state.gke.outputs.google_container_cluster_airflow-jobs-staging_name,
"POD_SECRETS_NAMESPACE" = local.namespace,
"SERVICE_ACCOUNT_NAME" = local.service_account_name,
"SERVICE_ACCOUNT_NAME" = local.kubernetes_service_account,
"CALITP_BUCKET__AGGREGATOR_SCRAPER" = "gs://${data.terraform_remote_state.gcs.outputs.google_storage_bucket_calitp-staging-aggregator-scraper_name}",
"CALITP_BUCKET__AIRTABLE" = "gs://${data.terraform_remote_state.gcs.outputs.google_storage_bucket_calitp-staging-airtable_name}",
"CALITP_BUCKET__AMPLITUDE_BENEFITS_EVENTS" = "gs://${data.terraform_remote_state.gcs.outputs.google_storage_bucket_calitp-staging-amplitude-benefits-events_name}",
Expand Down
5 changes: 2 additions & 3 deletions iac/cal-itp-data-infra-staging/composer/us/kubernetes.tf
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -22,8 +22,7 @@ resource "kubernetes_secret" "composer" {
namespace = local.namespace
}
data = {
"service_account.json" = base64decode(google_service_account_key.composer.private_key)
transitland-api-key = data.kubernetes_secret.composer.data.transitland-api-key
transitland-api-key = data.kubernetes_secret.composer.data.transitland-api-key
}
}

Expand All @@ -38,7 +37,7 @@ resource "kubernetes_priority_class" "dbt-high-priority" {

resource "kubernetes_service_account" "composer-service-account" {
metadata {
name = local.service_account_name
name = local.kubernetes_service_account
namespace = local.namespace
annotations = {
"iam.gke.io/gcp-service-account" = data.terraform_remote_state.iam.outputs.google_service_account_composer-service-account_email
Expand Down
6 changes: 3 additions & 3 deletions iac/cal-itp-data-infra-staging/composer/us/variables.tf
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,7 +1,7 @@
locals {
namespace = "airflow-jobs"
secret = "jobs-data"
service_account_name = "composer-service-account"
namespace = "airflow-jobs"
secret = "jobs-data"
kubernetes_service_account = "composer-service-account"

# This regular expression corresponds to the Python package name specification
# https://packaging.python.org/en/latest/specifications/name-normalization/
Expand Down
2 changes: 1 addition & 1 deletion iac/cal-itp-data-infra/composer/us/environment.tf
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -61,7 +61,7 @@ resource "google_composer_environment" "calitp-composer" {
"POD_LOCATION" = "us-west2",
"POD_CLUSTER_NAME" = data.terraform_remote_state.gke.outputs.google_container_cluster_airflow-jobs_name,
"POD_SECRETS_NAMESPACE" = local.namespace,
"SERVICE_ACCOUNT_NAME" = local.service_account_name,
"SERVICE_ACCOUNT_NAME" = local.kubernetes_service_account,
"CALITP_BUCKET__AGGREGATOR_SCRAPER" = "gs://${data.terraform_remote_state.gcs.outputs.google_storage_bucket_calitp-aggregator-scraper_name}",
"CALITP_BUCKET__AIRTABLE" = "gs://${data.terraform_remote_state.gcs.outputs.google_storage_bucket_calitp-airtable_name}",
"CALITP_BUCKET__AMPLITUDE_BENEFITS_EVENTS" = "gs://${data.terraform_remote_state.gcs.outputs.google_storage_bucket_calitp-amplitude-benefits-events_name}",
Expand Down
3 changes: 1 addition & 2 deletions iac/cal-itp-data-infra/composer/us/kubernetes.tf
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -24,7 +24,6 @@ resource "kubernetes_secret" "composer" {

data = {
calitp-ckan-gtfs-schedule-key = data.kubernetes_secret.composer.data.calitp-ckan-gtfs-schedule-key
"service_account.json" = base64decode(google_service_account_key.composer.private_key)
transitland-api-key = data.kubernetes_secret.composer.data.transitland-api-key
}
}
Expand All @@ -40,7 +39,7 @@ resource "kubernetes_priority_class" "dbt-high-priority" {

resource "kubernetes_service_account" "composer-service-account" {
metadata {
name = local.service_account_name
name = local.kubernetes_service_account
namespace = local.namespace
annotations = {
"iam.gke.io/gcp-service-account" = data.terraform_remote_state.iam.outputs.google_service_account_composer-service-account_email
Expand Down
7 changes: 4 additions & 3 deletions iac/cal-itp-data-infra/composer/us/variables.tf
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,7 +1,8 @@
locals {
namespace = "airflow-jobs"
secret = "jobs-data"
service_account_name = "composer-service-account"
namespace = "airflow-jobs"
secret = "jobs-data"
kubernetes_service_account = "composer-service-account"

# This regular expression corresponds to the Python package name specification
# https://packaging.python.org/en/latest/specifications/name-normalization/
python_package_regex = "(?P<name>[a-zA-Z0-9][a-zA-Z0-9._-]*[a-zA-Z0-9])(?P<version>.*)"
Expand Down
8 changes: 0 additions & 8 deletions warehouse/profiles.yml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -26,18 +26,10 @@ calitp_warehouse:
spark.executor.instances: "4" # dbt defaults to 2
spark.executor.memory: 4g
spark.dynamicAllocation.maxExecutors: "16"
prod_service_account:
<<: *prod
method: service-account
keyfile: "{{ env_var('BIGQUERY_KEYFILE_LOCATION', '/secrets/jobs-data/service-account.json') }}"
staging:
&staging
<<: *prod
execution_project: cal-itp-data-infra-staging
database: cal-itp-data-infra-staging
schema: staging
gcs_bucket: test-calitp-dbt-python-models
staging_service_account:
<<: *staging
method: service-account
keyfile: "{{ env_var('BIGQUERY_KEYFILE_LOCATION', '/secrets/jobs-data/service-account.json') }}"