feat: Collect the containerdebug logs

CHANGELOG.md

@@ -9,6 +9,8 @@ All notable changes to this project will be documented in this file.
 - Support floating tags for product images via the new `spec.image.stackableVersionPolicy` field
   ([#876]).
 - Add `/ready` endpoint to the operator Deployment, which reports the CRD installation status ([#880]).
+- The logs of the `containerdebug` process are now collected by the Vector agent and forwarded to
+  the Vector aggregator ([#894]).
 
 ### Changed
 
@@ -48,6 +50,10 @@ All notable changes to this project will be documented in this file.
   See [our internal issue](https://github.com/stackabletech/hdfs-operator/issues/626) and [the fix](https://github.com/kube-rs/kube/pull/2042) for details ([#860]).
 - The operator now watches all resources that it creates and early-exits the reconcile action when the
   cluster is marked for deletion ([#867]).
+- The `containerdebug` process writes its log file again. The operator set
+  `CONTAINERDEBUG_LOG_DIRECTORY`, which containerdebug stopped reading in its version 0.2.0 when it
+  moved to `stackable-telemetry`; the directory is now set via `FILE_LOG_DIRECTORY`. The file is
+  rotated hourly and at most two files are kept, because rotation is opt-in ([#894]).
 
 ### Remove
 
@@ -71,6 +77,7 @@ All notable changes to this project will be documented in this file.
 [#889]: https://github.com/stackabletech/druid-operator/pull/889
 [#891]: https://github.com/stackabletech/druid-operator/pull/891
 [#892]: https://github.com/stackabletech/druid-operator/pull/892
+[#894]: https://github.com/stackabletech/druid-operator/pull/894
 
 ## [26.7.0] - 2026-07-21
 

docs/modules/druid/pages/usage-guide/logging.adoc

@@ -30,4 +30,12 @@ spec:
         enableVectorAgent: true
 ----
 
+NOTE: The logs of the xref:concepts:observability/containerdebug.adoc[`containerdebug` process] are collected as well.
+They are labelled `container: containerdebug`, although no such Kubernetes container exists.
+The process runs in the background of the `druid` container.
+The label comes from `/stackable/log/containerdebug`, the directory which the operator sets with the `FILE_LOG_DIRECTORY` environment variable and from which the Vector agent derives the container name.
+Overriding `FILE_LOG_DIRECTORY` with `envOverrides` therefore changes how these logs are aggregated.
+The agent only collects files one level below `/stackable/log`, so a sibling directory such as `/stackable/log/druid` relabels the events instead of dropping them, while any deeper or shallower path stops the aggregation.
+A path outside `/stackable/log` also leaves the size-capped log volume.
+
 Further information on how to configure logging, can be found in xref:concepts:logging.adoc[].

rust/operator-binary/src/controller/build/container.rs

@@ -7,6 +7,7 @@
 
 use std::str::FromStr;
 
+use const_format::concatcp;
 use snafu::{ResultExt, Snafu};
 use stackable_operator::{
     builder::pod::{
@@ -17,7 +18,7 @@ use stackable_operator::{
     },
     product_logging,
     v2::{
-        builder::pod::container::{EnvVarName, EnvVarSet, new_container_builder},
+        builder::pod::container::{EnvVarSet, new_container_builder},
         product_logging::framework::{
             STACKABLE_LOG_DIR, ValidatedContainerLogConfigChoice, vector_container,
         },
@@ -39,8 +40,9 @@ use crate::{
         },
     },
     crd::{
-        Container, DRUID_CONFIG_DIRECTORY, DeepStorageSpec, HDFS_CONFIG_DIRECTORY,
-        LOG_CONFIG_DIRECTORY, METRICS_PORT, METRICS_PORT_NAME, RW_CONFIG_DIRECTORY,
+        Container, DRUID_CONFIG_DIRECTORY, DeepStorageSpec, FILE_LOG_DIRECTORY, FILE_LOG_MAX_FILES,
+        FILE_LOG_ROTATION_PERIOD, HDFS_CONFIG_DIRECTORY, LOG_CONFIG_DIRECTORY, METRICS_PORT,
+        METRICS_PORT_NAME, RW_CONFIG_DIRECTORY,
     },
 };
 
@@ -51,9 +53,6 @@ stackable_operator::constant!(pub(crate) LOG_CONFIG_VOLUME_NAME: VolumeName = "l
 stackable_operator::constant!(pub(crate) LOG_VOLUME_NAME: VolumeName = "log");
 stackable_operator::constant!(pub(crate) RW_CONFIG_VOLUME_NAME: VolumeName = "rwconfig");
 
-// Needed for the `containerdebug` process to log its tracing information to.
-stackable_operator::constant!(pub(crate) CONTAINERDEBUG_LOG_DIRECTORY: EnvVarName = "CONTAINERDEBUG_LOG_DIRECTORY");
-
 // volume mount directory (not a volume name)
 const USERDATA_MOUNTPOINT: &str = "/stackable/userdata";
 
@@ -269,10 +268,20 @@ pub(crate) fn containers_and_volumes(inputs: &RoleGroupInputs) -> Result<Contain
         ));
     }
 
-    env_vars = env_vars.with_value(
-        &CONTAINERDEBUG_LOG_DIRECTORY,
-        format!("{STACKABLE_LOG_DIR}/containerdebug"),
-    );
+    // Let the `containerdebug` process write its tracing information to a file. These are the
+    // generic `stackable-telemetry` variables and apply to the whole Druid container, so any
+    // other telemetry-based process in it would log into the same directory and the Vector
+    // agent would label its events with `container: containerdebug`.
+    env_vars = env_vars
+        // The directory must be exactly one level below the log directory, because the Vector
+        // agent derives the container name from that path segment.
+        .with_value(
+            &FILE_LOG_DIRECTORY,
+            concatcp!(STACKABLE_LOG_DIR, "/containerdebug"),
+        )
+        // Rotation is opt-in, so without these the file would grow unbounded.
+        .with_value(&FILE_LOG_ROTATION_PERIOD, "hourly")
+        .with_value(&FILE_LOG_MAX_FILES, "2");
 
     // Environment variable overrides (highest precedence), merged from role and role group.
     // They are merged in last so that they override any operator-set environment variable.
@@ -453,6 +462,9 @@ fn add_log_volume_and_volume_mounts(
         VolumeBuilder::new(&*LOG_VOLUME_NAME)
             .with_empty_dir(
                 Some(""),
+                // Only the Druid log files are budgeted. The `containerdebug` files in this
+                // volume are rotated by time, not by size, so they have no budget; raising
+                // `FILE_LOG_LEVEL` via `envOverrides` can therefore evict the Pod.
                 Some(product_logging::framework::calculate_log_volume_size_limit(
                     &[MAX_DRUID_LOG_FILES_SIZE],
                 )),
@@ -473,6 +485,5 @@ mod tests {
         let _ = *LOG_CONFIG_VOLUME_NAME;
         let _ = *LOG_VOLUME_NAME;
         let _ = *RW_CONFIG_VOLUME_NAME;
-        let _ = *CONTAINERDEBUG_LOG_DIRECTORY;
     }
 }

rust/operator-binary/src/controller/build/properties/product_logging/mod.rs

@@ -66,5 +66,7 @@ mod tests {
         let content = vector_config_file_content();
         assert!(!content.is_empty());
         assert!(content.contains("files_log4j2"));
+        assert!(content.contains("files_tracing_rs"));
+        assert!(content.contains("*.tracing-rs.json"));
     }
 }