fix: revert jmx exporter removal

CHANGELOG.md

@@ -123,7 +123,6 @@ All notable changes to this project will be documented in this file.
 - nifi: Remove `2.2.0` ([#1114]).
 - kafka: Remove `3.7.1` and `3.8.0` ([#1117]).
 - spark-connect-client: Remove `3.5.5` ([#1142]).
-- spark-k8s: Remove the JMX exporter jar ([#1157]).
 
 [nifi-iceberg-bundle]: https://github.com/stackabletech/nifi-iceberg-bundle
 [#1025]: https://github.com/stackabletech/docker-images/pull/1025
@@ -185,7 +184,6 @@ All notable changes to this project will be documented in this file.
 [#1151]: https://github.com/stackabletech/docker-images/pull/1151
 [#1152]: https://github.com/stackabletech/docker-images/pull/1152
 [#1156]: https://github.com/stackabletech/docker-images/pull/1156
-[#1157]: https://github.com/stackabletech/docker-images/pull/1157
 [#1163]: https://github.com/stackabletech/docker-images/pull/1163
 [#1165]: https://github.com/stackabletech/docker-images/pull/1165
 

spark-k8s/Dockerfile

@@ -131,6 +131,7 @@ ARG AZURE_KEYVAULT_CORE
 ARG JACKSON_DATAFORMAT_XML
 ARG STAX2_API
 ARG WOODSTOX_CORE
+ARG JMX_EXPORTER
 ARG TARGETARCH
 ARG TINI
 ARG STACKABLE_USER_UID
@@ -205,6 +206,8 @@ RUN cp /stackable/spark-${PRODUCT}/connector/connect/server/target/spark-connect
     && cp /stackable/spark-${PRODUCT}/connector/connect/common/target/spark-connect-common_*-${PRODUCT}.jar . \
     && cp /stackable/spark-${PRODUCT}/connector/connect/client/jvm/target/spark-connect-client-jvm_2.12-${PRODUCT}.jar .
 
+COPY spark-k8s/stackable/jmx /stackable/jmx
+
 WORKDIR /stackable/spark-${PRODUCT}/dist/extra-jars
 
 RUN <<EOF
@@ -221,8 +224,14 @@ curl --fail "https://repo.stackable.tech/repository/packages/tini/tini-${TINI}-$
   -o /usr/bin/tini
 chmod +x /usr/bin/tini
 
+# JMX Exporter
+curl --fail "https://repo.stackable.tech/repository/packages/jmx-exporter/jmx_prometheus_javaagent-${JMX_EXPORTER}.jar" \
+  -o "/stackable/jmx/jmx_prometheus_javaagent-${JMX_EXPORTER}.jar"
+ln -s "/stackable/jmx/jmx_prometheus_javaagent-${JMX_EXPORTER}.jar" /stackable/jmx/jmx_prometheus_javaagent.jar
+
 chmod -R g=u /stackable/spark-${PRODUCT}/dist
 chmod -R g=u /stackable/spark-${PRODUCT}/assembly/target/bom.json
+chmod -R g=u /stackable/jmx
 EOF
 
 # TODO: java-base installs the Adoptium dnf repo and the Termurin jre which is not needed here.
@@ -232,6 +241,7 @@ FROM stackable/image/java-base AS final
 ARG PRODUCT
 ARG PYTHON
 ARG RELEASE
+ARG JMX_EXPORTER
 ARG HBASE_CONNECTOR
 ARG STACKABLE_USER_UID
 
@@ -257,6 +267,7 @@ COPY --chown=${STACKABLE_USER_UID}:0 --from=spark-builder /stackable/spark-${PRO
 COPY --chown=${STACKABLE_USER_UID}:0 --from=spark-source-builder /stackable/spark-${PRODUCT}-src.tar.gz /stackable
 COPY --chown=${STACKABLE_USER_UID}:0 --from=hbase-connectors-builder /stackable/hbase-connector-${HBASE_CONNECTOR}-src.tar.gz /stackable
 COPY --chown=${STACKABLE_USER_UID}:0 --from=spark-builder /stackable/spark-${PRODUCT}/assembly/target/bom.json /stackable/spark/spark-${PRODUCT}.cdx.json
+COPY --chown=${STACKABLE_USER_UID}:0 --from=spark-builder /stackable/jmx /stackable/jmx
 COPY --from=spark-builder /usr/bin/tini /usr/bin/tini
 
 COPY --chown=${STACKABLE_USER_UID}:0 spark-k8s/stackable/run-spark.sh /stackable/run-spark.sh
@@ -290,6 +301,7 @@ chown -h ${STACKABLE_USER_UID}:0 /stackable/spark/examples/jars/spark-examples.j
 
 # fix permissions
 chmod g=u /stackable/spark
+chmod g=u /stackable/jmx
 chmod g=u /stackable/run-spark.sh
 EOF
 

spark-k8s/stackable/jmx/config.yaml

@@ -0,0 +1,132 @@
+---
+rules:
+
+  # These come from the master
+  # Example: master.aliveWorkers
+  - pattern: "metrics<name=master\\.(.*), type=counters><>Value"
+    name: spark_master_$1
+
+  # These come from the worker
+  # Example: worker.coresFree
+  - pattern: "metrics<name=worker\\.(.*), type=counters><>Value"
+    name: spark_worker_$1
+
+  # These come from the application driver
+  # Example: app-20160809000059-0000.driver.DAGScheduler.stage.failedStages
+  - pattern: "metrics<name=(.*)\\.driver\\.(DAGScheduler|BlockManager|jvm)\\.(.*), type=gauges><>Value"
+    name: spark_driver_$2_$3
+    type: GAUGE
+    labels:
+      app_id: "$1"
+
+  # These come from the application driver
+  # Emulate timers for DAGScheduler like messagePRocessingTime
+  - pattern: "metrics<name=(.*)\\.driver\\.DAGScheduler\\.(.*), type=counters><>Count"
+    name: spark_driver_DAGScheduler_$2_total
+    type: COUNTER
+    labels:
+      app_id: "$1"
+
+  - pattern: "metrics<name=(.*)\\.driver\\.HiveExternalCatalog\\.(.*), type=counters><>Count"
+    name: spark_driver_HiveExternalCatalog_$2_total
+    type: COUNTER
+    labels:
+      app_id: "$1"
+
+  # These come from the application driver
+  # Emulate histograms for CodeGenerator
+  - pattern: "metrics<name=(.*)\\.driver\\.CodeGenerator\\.(.*), type=counters><>Count"
+    name: spark_driver_CodeGenerator_$2_total
+    type: COUNTER
+    labels:
+      app_id: "$1"
+
+  # These come from the application driver
+  # Emulate timer (keep only count attribute) plus counters for LiveListenerBus
+  - pattern: "metrics<name=(.*)\\.driver\\.LiveListenerBus\\.(.*), type=counters><>Count"
+    name: spark_driver_LiveListenerBus_$2_total
+    type: COUNTER
+    labels:
+      app_id: "$1"
+
+  # Get Gauge type metrics for LiveListenerBus
+  - pattern: "metrics<name=(.*)\\.driver\\.LiveListenerBus\\.(.*), type=gauges><>Value"
+    name: spark_driver_LiveListenerBus_$2
+    type: GAUGE
+    labels:
+      app_id: "$1"
+
+  # These come from the application driver if it's a streaming application
+  # Example: app-20160809000059-0000.driver.com.example.ClassName.StreamingMetrics.streaming.lastCompletedBatch_schedulingDelay
+  - pattern: "metrics<name=(.*)\\.driver\\.(.*)\\.StreamingMetrics\\.streaming\\.(.*), type=gauges><>Value"
+    name: spark_driver_streaming_$3
+    labels:
+      app_id: "$1"
+      app_name: "$2"
+
+  # These come from the application driver if it's a structured streaming application
+  # Example: app-20160809000059-0000.driver.spark.streaming.QueryName.inputRate-total
+  - pattern: "metrics<name=(.*)\\.driver\\.spark\\.streaming\\.(.*)\\.(.*), type=gauges><>Value"
+    name: spark_driver_structured_streaming_$3
+    labels:
+      app_id: "$1"
+      query_name: "$2"
+
+  # These come from the application executors
+  # Examples:
+  #  app-20160809000059-0000.0.executor.threadpool.activeTasks (value)
+  #  app-20160809000059-0000.0.executor.JvmGCtime (counter)
+
+  # filesystem metrics are declared as gauge metrics, but are actually counters
+  - pattern: "metrics<name=(.*)\\.(.*)\\.executor\\.filesystem\\.(.*), type=gauges><>Value"
+    name: spark_executor_filesystem_$3_total
+    type: COUNTER
+    labels:
+      app_id: "$1"
+      executor_id: "$2"
+
+  - pattern: "metrics<name=(.*)\\.(.*)\\.executor\\.(.*), type=gauges><>Value"
+    name: spark_executor_$3
+    type: GAUGE
+    labels:
+      app_id: "$1"
+      executor_id: "$2"
+
+  - pattern: "metrics<name=(.*)\\.(.*)\\.executor\\.(.*), type=counters><>Count"
+    name: spark_executor_$3_total
+    type: COUNTER
+    labels:
+      app_id: "$1"
+      executor_id: "$2"
+
+  - pattern: "metrics<name=(.*)\\.(.*)\\.ExecutorMetrics\\.(.*), type=gauges><>Value"
+    name: spark_executor_$3
+    type: GAUGE
+    labels:
+      app_id: "$1"
+      executor_id: "$2"
+
+  # These come from the application executors
+  # Example: app-20160809000059-0000.0.jvm.threadpool.activeTasks
+  - pattern: "metrics<name=(.*)\\.([0-9]+)\\.(jvm|NettyBlockTransfer)\\.(.*), type=gauges><>Value"
+    name: spark_executor_$3_$4
+    type: GAUGE
+    labels:
+      app_id: "$1"
+      executor_id: "$2"
+
+  - pattern: "metrics<name=(.*)\\.([0-9]+)\\.HiveExternalCatalog\\.(.*), type=counters><>Count"
+    name: spark_executor_HiveExternalCatalog_$3_total
+    type: COUNTER
+    labels:
+      app_id: "$1"
+      executor_id: "$2"
+
+  # These come from the application driver
+  # Emulate histograms for CodeGenerator
+  - pattern: "metrics<name=(.*)\\.([0-9]+)\\.CodeGenerator\\.(.*), type=counters><>Count"
+    name: spark_executor_CodeGenerator_$3_total
+    type: COUNTER
+    labels:
+      app_id: "$1"
+      executor_id: "$2"

spark-k8s/versions.py

@@ -13,6 +13,7 @@
         "stax2_api": "4.2.1",  # https://mvnrepository.com/artifact/com.fasterxml.jackson.dataformat/jackson-dataformat-xml/2.15.2
         "woodstox_core": "6.5.1",  # https://mvnrepository.com/artifact/com.fasterxml.jackson.dataformat/jackson-dataformat-xml/2.15.2
         "vector": "0.47.0",
+        "jmx_exporter": "1.3.0",
         "tini": "0.19.0",
         "hbase_connector": "1.0.1",
     },
@@ -30,6 +31,7 @@
         "stax2_api": "4.2.1",  # https://mvnrepository.com/artifact/com.fasterxml.jackson.dataformat/jackson-dataformat-xml/2.15.2
         "woodstox_core": "6.5.1",  # https://mvnrepository.com/artifact/com.fasterxml.jackson.dataformat/jackson-dataformat-xml/2.15.2
         "vector": "0.47.0",
+        "jmx_exporter": "1.3.0",
         "tini": "0.19.0",
         "hbase_connector": "1.0.1",
     },