Merge branch 'main' into chore/spark-3.5.6

Author: razvan

CHANGELOG.md

@@ -78,6 +78,7 @@ All notable changes to this project will be documented in this file.
 - airflow: Pin Cython version ([#1116]).
 - druid: reduce docker image size by removing the recursive chown/chmods in the final image ([#1039]).
 - hadoop: reduce docker image size by removing the recursive chown/chmods in the final image ([#1029]).
+- hadoop: adapt the JMX exporter configuration to also export boolean metrics ([#1140]).
 - hbase: reduce docker image size by removing the recursive chown/chmods in the final image ([#1028]).
 - hive: reduce docker image size by removing the recursive chown/chmods in the final image ([#1040]).
 - kafka: reduce docker image size by removing the recursive chown/chmods in the final image ([#1041]).

hadoop/stackable/jmx/datanode.yaml

@@ -12,10 +12,9 @@ blacklistObjectNames:
   - 'Hadoop:service=DataNode,name=UgiMetrics'
 rules:
   # MetricsSystem
-  - pattern: 'Hadoop<service=(.*), name=MetricsSystem, sub=(.*)><>(.*): (\d+)'
+  - pattern: 'Hadoop<service=(.*), name=MetricsSystem, sub=(.*)><>(.*):'
     attrNameSnakeCase: true
     name: hadoop_$1_$3
-    value: $4
     labels:
       service: HDFS
       role: $1
@@ -24,21 +23,19 @@ rules:
     type: GAUGE
   # FSDatasetState with _total suffix (also extracts the FSDataset ID),
   # e.g. Hadoop:name=FSDatasetState,attribute=EstimatedCapacityLostTotal
-  - pattern: 'Hadoop<service=(.*), name=FSDatasetState-(.*)><>(.*_total): (\d+)'
+  - pattern: 'Hadoop<service=(.*), name=FSDatasetState-(.*)><>(.*_total):'
     attrNameSnakeCase: true
     name: hadoop_$1_$3
-    value: $4
     labels:
       service: HDFS
       role: $1
       fsdatasetid: $2
       kind: 'FSDatasetState'
     type: COUNTER
   # FSDatasetState (also extracts the FSDataset ID)
-  - pattern: 'Hadoop<service=(.*), name=FSDatasetState-(.*)><>(.*): (\d+)'
+  - pattern: 'Hadoop<service=(.*), name=FSDatasetState-(.*)><>(.*):'
     attrNameSnakeCase: true
     name: hadoop_$1_$3
-    value: $4
     labels:
       service: HDFS
       role: $1
@@ -47,21 +44,19 @@ rules:
     type: GAUGE
   # DataNodeActivity with _info suffix (also extracts hostname and port),
   # e.g. Hadoop:name=DataNodeActivity-hdfs-datanode-default-0-9866,attribute=BlocksGetLocalPathInfo
-  - pattern: 'Hadoop<service=(.*), name=DataNodeActivity-(.*)-(\d+)><>(.*_info): (\d+)'
+  - pattern: 'Hadoop<service=(.*), name=DataNodeActivity-(.*)-(\d+)><>(.*_info):'
     attrNameSnakeCase: true
     name: hadoop_$1_$4_
-    value: $5
     labels:
       service: HDFS
       role: $1
       host: $2
       port: $3
       kind: 'DataNodeActivity'
     type: GAUGE
-  - pattern: 'Hadoop<service=(.*), name=DataNodeActivity-(.*)-(\d+)><>(.*): (\d+)'
+  - pattern: 'Hadoop<service=(.*), name=DataNodeActivity-(.*)-(\d+)><>(.*):'
     attrNameSnakeCase: true
     name: hadoop_$1_$4
-    value: $5
     labels:
       service: HDFS
       role: $1
@@ -70,31 +65,28 @@ rules:
       kind: 'DataNodeActivity'
     type: GAUGE
   # Generic counter, e.g. Hadoop:name=FSDatasetState,attribute=EstimatedCapacityLostTotal
-  - pattern: 'Hadoop<service=(.*), name=(.*)><>(.*_total): (\d+)'
+  - pattern: 'Hadoop<service=(.*), name=(.*)><>(.*_total):'
     attrNameSnakeCase: true
     name: hadoop_$1_$3
-    value: $4
     labels:
       service: HDFS
       role: $1
       kind: $2
     type: COUNTER
   # Metrics suffixed with _info, e.g. Hadoop:name=JvmMetrics,attribute=LogInfo
   # The suffix _info is reserved for static information, therefore an underscore is appended.
-  - pattern: 'Hadoop<service=(.*), name=(.*)><>(.*_info): (.*)'
+  - pattern: 'Hadoop<service=(.*), name=(.*)><>(.*_info):'
     attrNameSnakeCase: true
     name: hadoop_$1_$3_
-    value: $4
     labels:
       service: HDFS
       role: $1
       kind: $2
     type: GAUGE
   # All other Hadoop metrics
-  - pattern: 'Hadoop<service=(.*), name=(.*)><>(.*): (.*)'
+  - pattern: 'Hadoop<service=(.*), name=(.*)><>(.*):'
     attrNameSnakeCase: true
     name: hadoop_$1_$3
-    value: $4
     labels:
       service: HDFS
       role: $1

hadoop/stackable/jmx/journalnode.yaml

@@ -13,10 +13,9 @@ blacklistObjectNames:
   - 'Hadoop:service=JournalNode,name=UgiMetrics'
 rules:
   # MetricsSystem
-  - pattern: 'Hadoop<service=(.*), name=MetricsSystem, sub=(.*)><>(.*): (\d+)'
+  - pattern: 'Hadoop<service=(.*), name=MetricsSystem, sub=(.*)><>(.*):'
     attrNameSnakeCase: true
     name: hadoop_$1_$3
-    value: $4
     labels:
       service: HDFS
       role: $1
@@ -25,20 +24,18 @@ rules:
     type: GAUGE
   # Metrics suffixed with _info, e.g. Hadoop:name=JvmMetrics,attribute=LogInfo
   # The suffix _info is reserved for static information, therefore an underscore is appended.
-  - pattern: 'Hadoop<service=(.*), name=(.*)><>(.*_info): (.*)'
+  - pattern: 'Hadoop<service=(.*), name=(.*)><>(.*_info):'
     attrNameSnakeCase: true
     name: hadoop_$1_$3_
-    value: $4
     labels:
       service: HDFS
       role: $1
       kind: $2
     type: GAUGE
   # All other Hadoop metrics
-  - pattern: 'Hadoop<service=(.*), name=(.*)><>(.*): (.*)'
+  - pattern: 'Hadoop<service=(.*), name=(.*)><>(.*):'
     attrNameSnakeCase: true
     name: hadoop_$1_$3
-    value: $4
     labels:
       service: HDFS
       role: $1

hadoop/stackable/jmx/namenode.yaml

@@ -13,63 +13,57 @@ blacklistObjectNames:
   - 'Hadoop:service=NameNode,name=UgiMetrics'
 rules:
   # MetricsSystem
-  - pattern: 'Hadoop<service=(.*), name=MetricsSystem, sub=(.*)><>(.*): (\d+)'
+  - pattern: 'Hadoop<service=(.*), name=MetricsSystem, sub=(.*)><>(.*):'
     attrNameSnakeCase: true
     name: hadoop_$1_$3
-    value: $4
     labels:
       service: HDFS
       role: $1
       kind: 'MetricsSystem'
       sub: $2
     type: GAUGE
   # Total raw capacity in bytes, e.g. Hadoop:name=NameNodeInfo,attribute=Total
-  - pattern: 'Hadoop<service=(.*), name=(.*)><>(total): (\d+)'
+  - pattern: 'Hadoop<service=(.*), name=(.*)><>(total):'
     attrNameSnakeCase: true
     name: hadoop_$1_$3
-    value: $4
     labels:
       service: HDFS
       role: $1
       kind: $2
     type: COUNTER
   # Generic counter, e.g. Hadoop:name=FSNamesystem,attribute=FilesTotal
-  - pattern: 'Hadoop<service=(.*), name=(.*)><>(.*_total): (\d+)'
+  - pattern: 'Hadoop<service=(.*), name=(.*)><>(.*_total):'
     attrNameSnakeCase: true
     name: hadoop_$1_$3
-    value: $4
     labels:
       service: HDFS
       role: $1
       kind: $2
     type: COUNTER
   # Metrics suffixed with _created, e.g. Hadoop:name=NameNodeActivity,attribute=FilesCreated
   # The suffix _created is reserved for timestamps, therefore an underscore is appended.
-  - pattern: 'Hadoop<service=(.*), name=(.*)><>(.*_created): (.*)'
+  - pattern: 'Hadoop<service=(.*), name=(.*)><>(.*_created):'
     attrNameSnakeCase: true
     name: hadoop_$1_$3_
-    value: $4
     labels:
       service: HDFS
       role: $1
       kind: $2
     type: GAUGE
   # Metrics suffixed with _info, e.g. Hadoop:name=JvmMetrics,attribute=LogInfo
   # The suffix _info is reserved for static information, therefore an underscore is appended.
-  - pattern: 'Hadoop<service=(.*), name=(.*)><>(.*_info): (.*)'
+  - pattern: 'Hadoop<service=(.*), name=(.*)><>(.*_info):'
     attrNameSnakeCase: true
     name: hadoop_$1_$3_
-    value: $4
     labels:
       service: HDFS
       role: $1
       kind: $2
     type: GAUGE
   # All other Hadoop metrics
-  - pattern: 'Hadoop<service=(.*), name=(.*)><>(.*): (.*)'
+  - pattern: 'Hadoop<service=(.*), name=(.*)><>(.*):'
     attrNameSnakeCase: true
     name: hadoop_$1_$3
-    value: $4
     labels:
       service: HDFS
       role: $1