feat: run containerdebug in the background (#557)

* feat: run containerdebug in the background

* add --container

Author: razvan

CHANGELOG.md

@@ -2,6 +2,10 @@
 
 ## [Unreleased]
 
+### Added
+
+- Run a `containerdebug` process in the background of each Airflow container to collect debugging information ([#557]).
+
 ### Fixed
 
 - BREAKING: Use distinct ServiceAccounts for the Stacklets, so that multiple Stacklets can be
@@ -11,6 +15,7 @@
 
 [#545]: https://github.com/stackabletech/airflow-operator/pull/545
 [#547]: https://github.com/stackabletech/airflow-operator/pull/547
+[#557]: https://github.com/stackabletech/airflow-operator/pull/557
 
 ## [24.11.0] - 2024-11-18
 

rust/crd/src/lib.rs

@@ -344,6 +344,7 @@ impl AirflowRole {
                 command.extend(Self::authentication_start_commands(auth_config));
                 command.extend(vec![
                     "prepare_signal_handlers".to_string(),
+                    format!("CONTAINERDEBUG_LOG_DIRECTORY={STACKABLE_LOG_DIR}/containerdebug containerdebug --output={STACKABLE_LOG_DIR}/containerdebug-state.json --loop &"),
                     "airflow webserver &".to_string(),
                 ]);
             }
@@ -361,10 +362,12 @@ impl AirflowRole {
                     --role \"Admin\""
                     .to_string(),
                 "prepare_signal_handlers".to_string(),
+                format!("CONTAINERDEBUG_LOG_DIRECTORY={STACKABLE_LOG_DIR}/containerdebug containerdebug --output={STACKABLE_LOG_DIR}/containerdebug-state.json --loop &"),
                 "airflow scheduler &".to_string(),
             ]),
             AirflowRole::Worker => command.extend(vec![
                 "prepare_signal_handlers".to_string(),
+                format!("CONTAINERDEBUG_LOG_DIRECTORY={STACKABLE_LOG_DIR}/containerdebug containerdebug --output={STACKABLE_LOG_DIR}/containerdebug-state.json --loop &"),
                 "airflow celery worker &".to_string(),
             ]),
         }

tests/templates/kuttl/smoke/40-assert.yaml.j2

@@ -79,3 +79,11 @@ status:
   expectedPods: 1
   currentHealthy: 1
   disruptionsAllowed: 1
+---
+# This test checks if the containerdebug-state.json file is present and valid
+apiVersion: kuttl.dev/v1beta1
+kind: TestAssert
+timeout: 600
+commands:
+  - script: kubectl exec -n $NAMESPACE --container airflow airflow-scheduler-default-0 -- cat /stackable/log/containerdebug-state.json | jq --exit-status
+  - script: kubectl exec -n $NAMESPACE --container airflow airflow-webserver-default-0 -- cat /stackable/log/containerdebug-state.json | jq --exit-status