Revert "remove jmx agent and metrics ports"

This reverts commit 3f0d9a3.

Author: razvan

CHANGELOG.md

@@ -21,14 +21,13 @@ 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 ([#671]).
+    of having the operator write it to the vector config ([#671]).
 - test: Bump to Vector `0.46.1` ([#677]).
 - BREAKING: Previously this operator would hardcode the UID and GID of the Pods being created to 1000/0, this has changed now ([#683])
   - 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
 - Use versioned common structs ([#684]).
-- BREAKING: the JMX exporter has been an replaced with the built-in Prometheus servlet ([#694]).
 
 ### Fixed
 
@@ -49,7 +48,6 @@ All notable changes to this project will be documented in this file.
 [#683]: https://github.com/stackabletech/hdfs-operator/pull/683
 [#684]: https://github.com/stackabletech/hdfs-operator/pull/684
 [#693]: https://github.com/stackabletech/hdfs-operator/pull/693
-[#694]: https://github.com/stackabletech/hdfs-operator/pull/694
 
 ## [25.3.0] - 2025-03-21
 

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

@@ -56,6 +56,7 @@ pub fn construct_role_specific_jvm_args(
     kerberos_enabled: bool,
     resources: Option<&ResourceRequirements>,
     config_dir: &str,
+    metrics_port: u16,
 ) -> Result<String, Error> {
     let mut jvm_args = Vec::new();
 
@@ -76,9 +77,10 @@ pub fn construct_role_specific_jvm_args(
         jvm_args.push(format!("-Xmx{heap}"));
     }
 
-    jvm_args.extend([format!(
-        "-Djava.security.properties={config_dir}/{JVM_SECURITY_PROPERTIES_FILE}"
-    )]);
+    jvm_args.extend([
+        format!("-Djava.security.properties={config_dir}/{JVM_SECURITY_PROPERTIES_FILE}"),
+        format!("-javaagent:/stackable/jmx/jmx_prometheus_javaagent.jar={metrics_port}:/stackable/jmx/{hdfs_role}.yaml")
+    ]);
     if kerberos_enabled {
         jvm_args.push(format!(
             "-Djava.security.krb5.conf={KERBEROS_CONTAINER_PATH}/krb5.conf"
@@ -99,7 +101,7 @@ pub fn construct_role_specific_jvm_args(
 mod tests {
 
     use super::*;
-    use crate::container::ContainerConfig;
+    use crate::{container::ContainerConfig, crd::constants::DEFAULT_NAME_NODE_METRICS_PORT};
 
     #[test]
     fn test_global_jvm_args() {
@@ -133,7 +135,8 @@ mod tests {
             jvm_config,
             "-Xms819m \
             -Xmx819m \
-            -Djava.security.properties=/stackable/config/security.properties"
+            -Djava.security.properties=/stackable/config/security.properties \
+            -javaagent:/stackable/jmx/jmx_prometheus_javaagent.jar=8183:/stackable/jmx/namenode.yaml"
         );
     }
 
@@ -178,6 +181,7 @@ mod tests {
             format!(
                 "-Xms34406m \
                 -Djava.security.properties=/stackable/config/security.properties \
+                -javaagent:/stackable/jmx/jmx_prometheus_javaagent.jar=8183:/stackable/jmx/namenode.yaml \
                 -Djava.security.krb5.conf={KERBEROS_CONTAINER_PATH}/krb5.conf \
                 -Dhttps.proxyHost=proxy.my.corp \
                 -Djava.net.preferIPv4Stack=true \
@@ -203,6 +207,7 @@ mod tests {
             kerberos_enabled,
             resources.as_ref(),
             "/stackable/config",
+            DEFAULT_NAME_NODE_METRICS_PORT,
         )
         .unwrap()
     }

rust/operator-binary/src/container.rs

@@ -61,12 +61,14 @@ use crate::{
         AnyNodeConfig, DataNodeContainer, HdfsNodeRole, HdfsPodRef, NameNodeContainer,
         UpgradeState,
         constants::{
-            DATANODE_ROOT_DATA_DIR_PREFIX, LISTENER_VOLUME_DIR, LISTENER_VOLUME_NAME,
-            LIVENESS_PROBE_FAILURE_THRESHOLD, LIVENESS_PROBE_INITIAL_DELAY_SECONDS,
-            LIVENESS_PROBE_PERIOD_SECONDS, LOG4J_PROPERTIES, NAMENODE_ROOT_DATA_DIR,
-            READINESS_PROBE_FAILURE_THRESHOLD, READINESS_PROBE_INITIAL_DELAY_SECONDS,
-            READINESS_PROBE_PERIOD_SECONDS, SERVICE_PORT_NAME_HTTP, SERVICE_PORT_NAME_HTTPS,
-            SERVICE_PORT_NAME_IPC, SERVICE_PORT_NAME_RPC, STACKABLE_ROOT_DATA_DIR,
+            DATANODE_ROOT_DATA_DIR_PREFIX, DEFAULT_DATA_NODE_METRICS_PORT,
+            DEFAULT_JOURNAL_NODE_METRICS_PORT, DEFAULT_NAME_NODE_METRICS_PORT, LISTENER_VOLUME_DIR,
+            LISTENER_VOLUME_NAME, LIVENESS_PROBE_FAILURE_THRESHOLD,
+            LIVENESS_PROBE_INITIAL_DELAY_SECONDS, LIVENESS_PROBE_PERIOD_SECONDS, LOG4J_PROPERTIES,
+            NAMENODE_ROOT_DATA_DIR, READINESS_PROBE_FAILURE_THRESHOLD,
+            READINESS_PROBE_INITIAL_DELAY_SECONDS, READINESS_PROBE_PERIOD_SECONDS,
+            SERVICE_PORT_NAME_HTTP, SERVICE_PORT_NAME_HTTPS, SERVICE_PORT_NAME_IPC,
+            SERVICE_PORT_NAME_RPC, STACKABLE_ROOT_DATA_DIR,
         },
         storage::DataNodeStorageConfig,
         v1alpha1,
@@ -162,6 +164,8 @@ pub enum ContainerConfig {
         web_ui_http_port_name: &'static str,
         /// Port name of the web UI HTTPS port, used for the liveness probe.
         web_ui_https_port_name: &'static str,
+        /// The JMX Exporter metrics port.
+        metrics_port: u16,
     },
     Zkfc {
         /// The provided custom container name.
@@ -1222,7 +1226,9 @@ wait_for_termination $!
         resources: Option<&ResourceRequirements>,
     ) -> Result<String, Error> {
         match self {
-            ContainerConfig::Hdfs { role, .. } => {
+            ContainerConfig::Hdfs {
+                role, metrics_port, ..
+            } => {
                 let cvd = ContainerVolumeDirs::from(role);
                 let config_dir = cvd.final_config();
                 construct_role_specific_jvm_args(
@@ -1232,6 +1238,7 @@ wait_for_termination $!
                     hdfs.has_kerberos_enabled(),
                     resources,
                     config_dir,
+                    *metrics_port,
                 )
                 .with_context(|_| ConstructJvmArgumentsSnafu {
                     role: role.to_string(),
@@ -1372,6 +1379,7 @@ impl From<HdfsNodeRole> for ContainerConfig {
                 ipc_port_name: SERVICE_PORT_NAME_RPC,
                 web_ui_http_port_name: SERVICE_PORT_NAME_HTTP,
                 web_ui_https_port_name: SERVICE_PORT_NAME_HTTPS,
+                metrics_port: DEFAULT_NAME_NODE_METRICS_PORT,
             },
             HdfsNodeRole::Data => Self::Hdfs {
                 role,
@@ -1380,6 +1388,7 @@ impl From<HdfsNodeRole> for ContainerConfig {
                 ipc_port_name: SERVICE_PORT_NAME_IPC,
                 web_ui_http_port_name: SERVICE_PORT_NAME_HTTP,
                 web_ui_https_port_name: SERVICE_PORT_NAME_HTTPS,
+                metrics_port: DEFAULT_DATA_NODE_METRICS_PORT,
             },
             HdfsNodeRole::Journal => Self::Hdfs {
                 role,
@@ -1388,6 +1397,7 @@ impl From<HdfsNodeRole> for ContainerConfig {
                 ipc_port_name: SERVICE_PORT_NAME_RPC,
                 web_ui_http_port_name: SERVICE_PORT_NAME_HTTP,
                 web_ui_https_port_name: SERVICE_PORT_NAME_HTTPS,
+                metrics_port: DEFAULT_JOURNAL_NODE_METRICS_PORT,
             },
         }
     }

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

@@ -19,18 +19,22 @@ pub const SERVICE_PORT_NAME_IPC: &str = "ipc";
 pub const SERVICE_PORT_NAME_HTTP: &str = "http";
 pub const SERVICE_PORT_NAME_HTTPS: &str = "https";
 pub const SERVICE_PORT_NAME_DATA: &str = "data";
+pub const SERVICE_PORT_NAME_METRICS: &str = "metrics";
 
 pub const DEFAULT_LISTENER_CLASS: &str = "cluster-internal";
 
+pub const DEFAULT_NAME_NODE_METRICS_PORT: u16 = 8183;
 pub const DEFAULT_NAME_NODE_HTTP_PORT: u16 = 9870;
 pub const DEFAULT_NAME_NODE_HTTPS_PORT: u16 = 9871;
 pub const DEFAULT_NAME_NODE_RPC_PORT: u16 = 8020;
 
+pub const DEFAULT_DATA_NODE_METRICS_PORT: u16 = 8082;
 pub const DEFAULT_DATA_NODE_HTTP_PORT: u16 = 9864;
 pub const DEFAULT_DATA_NODE_HTTPS_PORT: u16 = 9865;
 pub const DEFAULT_DATA_NODE_DATA_PORT: u16 = 9866;
 pub const DEFAULT_DATA_NODE_IPC_PORT: u16 = 9867;
 
+pub const DEFAULT_JOURNAL_NODE_METRICS_PORT: u16 = 8081;
 pub const DEFAULT_JOURNAL_NODE_HTTP_PORT: u16 = 8480;
 pub const DEFAULT_JOURNAL_NODE_HTTPS_PORT: u16 = 8481;
 pub const DEFAULT_JOURNAL_NODE_RPC_PORT: u16 = 8485;

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

@@ -53,14 +53,16 @@ use crate::crd::{
     constants::{
         APP_NAME, CORE_SITE_XML, DEFAULT_DATA_NODE_DATA_PORT,
         DEFAULT_DATA_NODE_GRACEFUL_SHUTDOWN_TIMEOUT, DEFAULT_DATA_NODE_HTTP_PORT,
-        DEFAULT_DATA_NODE_HTTPS_PORT, DEFAULT_DATA_NODE_IPC_PORT, DEFAULT_DFS_REPLICATION_FACTOR,
-        DEFAULT_JOURNAL_NODE_GRACEFUL_SHUTDOWN_TIMEOUT, DEFAULT_JOURNAL_NODE_HTTP_PORT,
-        DEFAULT_JOURNAL_NODE_HTTPS_PORT, DEFAULT_JOURNAL_NODE_RPC_PORT, DEFAULT_LISTENER_CLASS,
+        DEFAULT_DATA_NODE_HTTPS_PORT, DEFAULT_DATA_NODE_IPC_PORT, DEFAULT_DATA_NODE_METRICS_PORT,
+        DEFAULT_DFS_REPLICATION_FACTOR, DEFAULT_JOURNAL_NODE_GRACEFUL_SHUTDOWN_TIMEOUT,
+        DEFAULT_JOURNAL_NODE_HTTP_PORT, DEFAULT_JOURNAL_NODE_HTTPS_PORT,
+        DEFAULT_JOURNAL_NODE_METRICS_PORT, DEFAULT_JOURNAL_NODE_RPC_PORT, DEFAULT_LISTENER_CLASS,
         DEFAULT_NAME_NODE_GRACEFUL_SHUTDOWN_TIMEOUT, DEFAULT_NAME_NODE_HTTP_PORT,
-        DEFAULT_NAME_NODE_HTTPS_PORT, DEFAULT_NAME_NODE_RPC_PORT, DFS_REPLICATION,
-        HADOOP_POLICY_XML, HDFS_SITE_XML, JVM_SECURITY_PROPERTIES_FILE, LISTENER_VOLUME_NAME,
-        SERVICE_PORT_NAME_DATA, SERVICE_PORT_NAME_HTTP, SERVICE_PORT_NAME_HTTPS,
-        SERVICE_PORT_NAME_IPC, SERVICE_PORT_NAME_RPC, SSL_CLIENT_XML, SSL_SERVER_XML,
+        DEFAULT_NAME_NODE_HTTPS_PORT, DEFAULT_NAME_NODE_METRICS_PORT, DEFAULT_NAME_NODE_RPC_PORT,
+        DFS_REPLICATION, HADOOP_POLICY_XML, HDFS_SITE_XML, JVM_SECURITY_PROPERTIES_FILE,
+        LISTENER_VOLUME_NAME, SERVICE_PORT_NAME_DATA, SERVICE_PORT_NAME_HTTP,
+        SERVICE_PORT_NAME_HTTPS, SERVICE_PORT_NAME_IPC, SERVICE_PORT_NAME_METRICS,
+        SERVICE_PORT_NAME_RPC, SSL_CLIENT_XML, SSL_SERVER_XML,
     },
     security::{AuthenticationConfig, KerberosConfig},
     storage::{
@@ -665,6 +667,10 @@ impl v1alpha1::HdfsCluster {
     pub fn ports(&self, role: &HdfsNodeRole) -> Vec<(String, u16)> {
         match role {
             HdfsNodeRole::Name => vec![
+                (
+                    String::from(SERVICE_PORT_NAME_METRICS),
+                    DEFAULT_NAME_NODE_METRICS_PORT,
+                ),
                 (
                     String::from(SERVICE_PORT_NAME_RPC),
                     DEFAULT_NAME_NODE_RPC_PORT,
@@ -682,6 +688,10 @@ impl v1alpha1::HdfsCluster {
                 },
             ],
             HdfsNodeRole::Data => vec![
+                (
+                    String::from(SERVICE_PORT_NAME_METRICS),
+                    DEFAULT_DATA_NODE_METRICS_PORT,
+                ),
                 (
                     String::from(SERVICE_PORT_NAME_DATA),
                     DEFAULT_DATA_NODE_DATA_PORT,
@@ -703,6 +713,10 @@ impl v1alpha1::HdfsCluster {
                 },
             ],
             HdfsNodeRole::Journal => vec![
+                (
+                    String::from(SERVICE_PORT_NAME_METRICS),
+                    DEFAULT_JOURNAL_NODE_METRICS_PORT,
+                ),
                 (
                     String::from(SERVICE_PORT_NAME_RPC),
                     DEFAULT_JOURNAL_NODE_RPC_PORT,