fix: Remote logging in Airflow 3.x (#683)

* adapt custom logging to resolve RemoteLogIO handler

* switch logic branches so that change extends beyond 3.x

* fixed version match

* integration test

* changelog, cleaned up minio install

Author: adwk67

CHANGELOG.md

@@ -13,11 +13,13 @@
 - Allow multiple Airflows in the same namespace to use Kubernetes executors.
   Previously, the operator would always use the same name for the executor Pod template ConfigMap.
   Thus when deploying multiple Airflow instances in the same namespace, there would be a conflict over the contents of that ConfigMap ([#678]).
+- For versions >= 3 custom logging initializes the RemoteLogIO handler to fix remote logging ([#683]).
 
 [#667]: https://github.com/stackabletech/airflow-operator/pull/667
 [#668]: https://github.com/stackabletech/airflow-operator/pull/668
 [#669]: https://github.com/stackabletech/airflow-operator/pull/669
 [#678]: https://github.com/stackabletech/airflow-operator/pull/678
+[#683]: https://github.com/stackabletech/airflow-operator/pull/683
 
 ## [25.7.0] - 2025-07-23
 

rust/operator-binary/src/airflow_controller.rs

@@ -806,6 +806,7 @@ fn build_rolegroup_config_map(
         container,
         &Container::Vector,
         &mut cm_builder,
+        resolved_product_image,
     )
     .context(InvalidLoggingConfigSnafu {
         cm_name: rolegroup.object_name(),

rust/operator-binary/src/product_logging.rs

@@ -3,6 +3,7 @@ use std::fmt::{Display, Write};
 use snafu::Snafu;
 use stackable_operator::{
     builder::configmap::ConfigMapBuilder,
+    commons::product_image_selection::ResolvedProductImage,
     kube::Resource,
     product_logging::{
         self,
@@ -43,6 +44,7 @@ pub fn extend_config_map_with_log_config<C, K>(
     main_container: &C,
     vector_container: &C,
     cm_builder: &mut ConfigMapBuilder,
+    resolved_product_image: &ResolvedProductImage,
 ) -> Result<()>
 where
     C: Clone + Ord + Display,
@@ -53,7 +55,10 @@ where
     }) = logging.containers.get(main_container)
     {
         let log_dir = format!("{STACKABLE_LOG_DIR}/{main_container}");
-        cm_builder.add_data(LOG_CONFIG_FILE, create_airflow_config(log_config, &log_dir));
+        cm_builder.add_data(
+            LOG_CONFIG_FILE,
+            create_airflow_config(log_config, &log_dir, resolved_product_image),
+        );
     }
 
     let vector_log_config = if let Some(ContainerLogConfig {
@@ -75,7 +80,11 @@ where
     Ok(())
 }
 
-fn create_airflow_config(log_config: &AutomaticContainerLogConfig, log_dir: &str) -> String {
+fn create_airflow_config(
+    log_config: &AutomaticContainerLogConfig,
+    log_dir: &str,
+    resolved_product_image: &ResolvedProductImage,
+) -> String {
     let loggers_config = log_config
         .loggers
         .iter()
@@ -92,18 +101,28 @@ LOGGING_CONFIG['loggers']['{name}']['level'] = {level}
             output
         });
 
+    let remote_task_log = if resolved_product_image.product_version.starts_with("2.") {
+        ""
+    } else {
+        "
+# This will cause the relevant RemoteLogIO handler to be initialized
+REMOTE_TASK_LOG = airflow_local_settings.REMOTE_TASK_LOG
+log = logging.getLogger(__name__)
+log.info('Custom logging remote task log %s', REMOTE_TASK_LOG)
+"
+    };
+
     format!(
         "\
 import logging
 import os
 from copy import deepcopy
-from airflow.config_templates.airflow_local_settings import DEFAULT_LOGGING_CONFIG
+from airflow.config_templates import airflow_local_settings
 
 os.makedirs('{log_dir}', exist_ok=True)
 
-LOGGING_CONFIG = deepcopy(DEFAULT_LOGGING_CONFIG)
-
-REMOTE_TASK_LOG = None
+LOGGING_CONFIG = deepcopy(airflow_local_settings.DEFAULT_LOGGING_CONFIG)
+{remote_task_log}
 
 LOGGING_CONFIG.setdefault('loggers', {{}})
 for logger_name, logger_config in LOGGING_CONFIG['loggers'].items():

tests/templates/kuttl/remote-logging/00-patch-ns.yaml.j2

@@ -0,0 +1,9 @@
+{% if test_scenario['values']['openshift'] == 'true' %}
+# see https://github.com/stackabletech/issues/issues/566
+---
+apiVersion: kuttl.dev/v1beta1
+kind: TestStep
+commands:
+  - script: kubectl patch namespace $NAMESPACE -p '{"metadata":{"labels":{"pod-security.kubernetes.io/enforce":"privileged"}}}'
+    timeout: 120
+{% endif %}

tests/templates/kuttl/remote-logging/00-range-limit.yaml.j2

@@ -0,0 +1,13 @@
+{% if test_scenario['values']['executor'] == 'celery' %}
+---
+apiVersion: v1
+kind: LimitRange
+metadata:
+  name: limit-request-ratio
+spec:
+  limits:
+  - type: "Container"
+    maxLimitRequestRatio:
+      cpu: 5
+      memory: 1
+{% endif %}

tests/templates/kuttl/remote-logging/02-s3-secret.yaml

@@ -0,0 +1,25 @@
+---
+apiVersion: v1
+kind: Secret
+metadata:
+  name: minio-credentials
+  labels:
+    secrets.stackable.tech/class: spark-pi-private-s3-credentials-class
+timeout: 240
+stringData:
+  accessKey: minioAccessKey
+  secretKey: minioSecretKey
+  # The following two entries are used by the Bitnami chart for MinIO to
+  # set up credentials for accessing buckets managed by the MinIO tenant.
+  root-user: minioAccessKey
+  root-password: minioSecretKey
+---
+apiVersion: secrets.stackable.tech/v1alpha1
+kind: SecretClass
+metadata:
+  name: spark-pi-private-s3-credentials-class
+spec:
+  backend:
+    k8sSearch:
+      searchNamespace:
+        pod: {}

tests/templates/kuttl/remote-logging/03-assert.yaml

@@ -0,0 +1,11 @@
+---
+apiVersion: kuttl.dev/v1beta1
+kind: TestAssert
+timeout: 900
+---
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: test-minio
+status:
+  readyReplicas: 1

tests/templates/kuttl/remote-logging/03-setup-minio.yaml

@@ -0,0 +1,11 @@
+---
+apiVersion: kuttl.dev/v1beta1
+kind: TestStep
+commands:
+  - script: >-
+      helm install test-minio
+      --namespace $NAMESPACE
+      --version 17.0.19
+      -f helm-bitnami-minio-values.yaml
+      oci://registry-1.docker.io/bitnamicharts/minio
+    timeout: 240

tests/templates/kuttl/remote-logging/10-assert.yaml

@@ -0,0 +1,14 @@
+---
+apiVersion: kuttl.dev/v1beta1
+kind: TestAssert
+metadata:
+  name: test-airflow-postgresql
+timeout: 480
+---
+apiVersion: apps/v1
+kind: StatefulSet
+metadata:
+  name: airflow-postgresql
+status:
+  readyReplicas: 1
+  replicas: 1

tests/templates/kuttl/remote-logging/10-install-postgresql.yaml

@@ -0,0 +1,12 @@
+---
+apiVersion: kuttl.dev/v1beta1
+kind: TestStep
+commands:
+  - script: >-
+      helm install airflow-postgresql
+      --namespace $NAMESPACE
+      --version 16.4.2
+      -f helm-bitnami-postgresql-values.yaml
+      oci://registry-1.docker.io/bitnamicharts/postgresql
+      --wait
+    timeout: 600