fix: re-enable the jmx exporter

CHANGELOG.md

@@ -23,7 +23,7 @@ All notable changes to this project will be documented in this file.
     by `FILE_LOG_DIRECTORY` (or via `--file-log-directory <DIRECTORY>`).
   - Replace stackable-operator `print_startup_string` with `tracing::info!` with fields.
 - BREAKING: Inject the vector aggregator address into the vector config using the env var `VECTOR_AGGREGATOR_ADDRESS` instead
-    of having the operator write it to the vector config ([#551]).
+  of having the operator write it to the vector config ([#551]).
 - Document that Spark Connect doesn't integrate with the history server ([#559])
 - test: Bump to Vector `0.46.1` ([#565]).
 - Use versioned common structs ([#572]).
@@ -33,7 +33,7 @@ All notable changes to this project will be documented in this file.
   - The `runAsUser` and `runAsGroup` fields will not be set anymore by the operator
   - The defaults from the docker images itself will now apply, which will be different from 1000/0 going forward
   - This is marked as breaking because tools and policies might exist, which require these fields to be set
-- BREAKING: the JMX exporter has been an replaced with the built-in Prometheus servlet. The history server pods do not expose metrics anymore ([#584])
+- Enable the built-in Prometheus servlet. The jmx exporter was removed in ([#584]) but added back in ([#585]).
 
 ### Fixed
 
@@ -61,6 +61,7 @@ All notable changes to this project will be documented in this file.
 [#580]: https://github.com/stackabletech/spark-k8s-operator/pull/580
 [#575]: https://github.com/stackabletech/spark-k8s-operator/pull/575
 [#584]: https://github.com/stackabletech/spark-k8s-operator/pull/584
+[#585]: https://github.com/stackabletech/spark-k8s-operator/pull/585
 
 ## [25.3.0] - 2025-03-21
 
@@ -111,7 +112,7 @@ All notable changes to this project will be documented in this file.
 - BREAKING: The fields `connection` and `host` on `S3Connection` as well as `bucketName` on `S3Bucket`are now mandatory ([#472]).
 - Fix `envOverrides` for SparkApplication and SparkHistoryServer ([#451]).
 - Ensure SparkApplications can only create a single submit Job. Fix for #457 ([#460]).
-- Invalid `SparkApplication`/`SparkHistoryServer`  objects don't cause the operator to stop functioning (#[482]).
+- Invalid `SparkApplication`/`SparkHistoryServer` objects don't cause the operator to stop functioning (#[482]).
 
 ### Removed
 
@@ -186,7 +187,7 @@ All notable changes to this project will be documented in this file.
 - Support PodDisruptionBudgets for HistoryServer ([#288]).
 - Support for versions 3.4.1, 3.5.0 ([#291]).
 - History server now exports metrics via jmx exporter (port 18081) ([#291]).
-- Document graceful shutdown  ([#306]).
+- Document graceful shutdown ([#306]).
 
 ### Changed
 

docs/modules/spark-k8s/pages/usage-guide/history-server.adoc

@@ -161,6 +161,6 @@ image::history-server-ui.png[History Server Console]
 
 [NOTE]
 ====
-Up to version 25.3 of the Stackable Data Platform, the history server used the JMX exporter to expose metrics on a separate port.
-Starting with version 25.7 the JMX exporter has been removed and the history server doesn't expose metrics as of Spark version 3.5.6.
+Starting with version 25.7, the built-in Prometheus servlet is enabled in addition to the existing JMX exporter.
+The JMX exporter is still available but it is deprecated and will be removed in a future release.
 ====

docs/modules/spark-k8s/pages/usage-guide/operations/applications.adoc

@@ -13,8 +13,8 @@ To resubmit an application, a new SparkApplication resource must be created.
 
 [NOTE]
 ====
-Up to version 25.3 of the Stackable Data Platform, Spark applications used the JMX exporter to expose metrics on a separate port.
-Starting with version 25.7, the built-in Prometheus servlet is used instead.
+Starting with version 25.7, the built-in Prometheus servlet is enabled.
+The JMX exporter is available but not used for applications. It has never been used automatically for applications and now it is deprecated.
 ====
 
 Application driver pods expose Prometheus metrics at the following endpoints:

rust/operator-binary/src/crd/constants.rs

@@ -86,6 +86,7 @@ pub const SPARK_DEFAULTS_FILE_NAME: &str = "spark-defaults.conf";
 pub const SPARK_ENV_SH_FILE_NAME: &str = "spark-env.sh";
 
 pub const SPARK_CLUSTER_ROLE: &str = "spark-k8s-clusterrole";
+pub const METRICS_PORT: u16 = 18081;
 pub const HISTORY_UI_PORT: u16 = 18080;
 
 pub const LISTENER_VOLUME_NAME: &str = "listener";

rust/operator-binary/src/history/config/jvm.rs

@@ -5,8 +5,9 @@ use stackable_operator::role_utils::{
 
 use crate::crd::{
     constants::{
-        JVM_SECURITY_PROPERTIES_FILE, LOG4J2_CONFIG_FILE, STACKABLE_TLS_STORE_PASSWORD,
-        STACKABLE_TRUST_STORE, VOLUME_MOUNT_PATH_CONFIG, VOLUME_MOUNT_PATH_LOG_CONFIG,
+        JVM_SECURITY_PROPERTIES_FILE, LOG4J2_CONFIG_FILE, METRICS_PORT,
+        STACKABLE_TLS_STORE_PASSWORD, STACKABLE_TRUST_STORE, VOLUME_MOUNT_PATH_CONFIG,
+        VOLUME_MOUNT_PATH_LOG_CONFIG,
     },
     history::HistoryConfigFragment,
     logdir::ResolvedLogDir,
@@ -32,6 +33,9 @@ pub fn construct_history_jvm_args(
         format!(
             "-Djava.security.properties={VOLUME_MOUNT_PATH_CONFIG}/{JVM_SECURITY_PROPERTIES_FILE}"
         ),
+        format!(
+            "-javaagent:/stackable/jmx/jmx_prometheus_javaagent.jar={METRICS_PORT}:/stackable/jmx/config.yaml"
+        ),
     ];
 
     if logdir.tls_enabled() {
@@ -82,7 +86,8 @@ mod tests {
         assert_eq!(
             jvm_config,
             "-Dlog4j.configurationFile=/stackable/log_config/log4j2.properties \
-            -Djava.security.properties=/stackable/spark/conf/security.properties"
+            -Djava.security.properties=/stackable/spark/conf/security.properties \
+            -javaagent:/stackable/jmx/jmx_prometheus_javaagent.jar=18081:/stackable/jmx/config.yaml"
         );
     }
 
@@ -125,6 +130,7 @@ mod tests {
             jvm_config,
             "-Dlog4j.configurationFile=/stackable/log_config/log4j2.properties \
             -Djava.security.properties=/stackable/spark/conf/security.properties \
+            -javaagent:/stackable/jmx/jmx_prometheus_javaagent.jar=18081:/stackable/jmx/config.yaml \
             -Dhttps.proxyHost=proxy.my.corp \
             -Djava.net.preferIPv4Stack=true \
             -Dhttps.proxyPort=1234"

rust/operator-binary/src/history/history_controller.rs

@@ -56,11 +56,11 @@ use crate::{
         constants::{
             ACCESS_KEY_ID, HISTORY_APP_NAME, HISTORY_CONTROLLER_NAME, HISTORY_ROLE_NAME,
             HISTORY_UI_PORT, JVM_SECURITY_PROPERTIES_FILE, LISTENER_VOLUME_DIR,
-            LISTENER_VOLUME_NAME, MAX_SPARK_LOG_FILES_SIZE, OPERATOR_NAME, SECRET_ACCESS_KEY,
-            SPARK_DEFAULTS_FILE_NAME, SPARK_ENV_SH_FILE_NAME, SPARK_IMAGE_BASE_NAME,
-            STACKABLE_TRUST_STORE, VOLUME_MOUNT_NAME_CONFIG, VOLUME_MOUNT_NAME_LOG,
-            VOLUME_MOUNT_NAME_LOG_CONFIG, VOLUME_MOUNT_PATH_CONFIG, VOLUME_MOUNT_PATH_LOG,
-            VOLUME_MOUNT_PATH_LOG_CONFIG,
+            LISTENER_VOLUME_NAME, MAX_SPARK_LOG_FILES_SIZE, METRICS_PORT, OPERATOR_NAME,
+            SECRET_ACCESS_KEY, SPARK_DEFAULTS_FILE_NAME, SPARK_ENV_SH_FILE_NAME,
+            SPARK_IMAGE_BASE_NAME, STACKABLE_TRUST_STORE, VOLUME_MOUNT_NAME_CONFIG,
+            VOLUME_MOUNT_NAME_LOG, VOLUME_MOUNT_NAME_LOG_CONFIG, VOLUME_MOUNT_PATH_CONFIG,
+            VOLUME_MOUNT_PATH_LOG, VOLUME_MOUNT_PATH_LOG_CONFIG,
         },
         history::{self, HistoryConfig, SparkHistoryServerContainer, v1alpha1},
         listener_ext,
@@ -574,6 +574,7 @@ fn build_stateful_set(
         ])
         .args(command_args(log_dir))
         .add_container_port("http", HISTORY_UI_PORT.into())
+        .add_container_port("metrics", METRICS_PORT.into())
         .add_env_vars(merged_env)
         .add_volume_mounts(log_dir.volume_mounts())
         .context(AddVolumeMountSnafu)?