From 6f6f2a8693a9aceb44ce82527d489ec384496ed3 Mon Sep 17 00:00:00 2001
From: Kai Moritz <kai@juplo.de>
Date: Wed, 4 Oct 2023 00:01:32 +0200
Subject: [PATCH] WIP:prometheus

---
 strimzi-kafka/cluster.yaml                    |  20 +-
 .../kafka-cruise-control-metrics.yaml         |  14 ++
 strimzi-kafka/kafka-metrics.yaml              | 183 ++++++++++++++++++
 3 files changed, 216 insertions(+), 1 deletion(-)
 create mode 100644 strimzi-kafka/kafka-cruise-control-metrics.yaml
 create mode 100644 strimzi-kafka/kafka-metrics.yaml

diff --git a/strimzi-kafka/cluster.yaml b/strimzi-kafka/cluster.yaml
index 792223f..9c10072 100644
--- a/strimzi-kafka/cluster.yaml
+++ b/strimzi-kafka/cluster.yaml
@@ -30,6 +30,12 @@ spec:
         class: local-storage
         size: 1Gi
         deleteClaim: false
+    metricsConfig:
+      type: jmxPrometheusExporter
+      valueFrom:
+        configMapKeyRef:
+          name: kafka-metrics
+          key: kafka-metrics-config.yml
   zookeeper:
     replicas: 1
     storage:
@@ -38,7 +44,19 @@ spec:
       class: local-storage
       size: 500Mi
       deleteClaim: false
+    metricsConfig:
+      type: jmxPrometheusExporter
+      valueFrom:
+        configMapKeyRef:
+          name: kafka-metrics
+          key: zookeeper-metrics-config.yml
   entityOperator:
     topicOperator: {}
-  cruiseControl: {}
+  cruiseControl:
+    metricsConfig:
+      type: jmxPrometheusExporter
+      valueFrom:
+        configMapKeyRef:
+          name: cruise-control-metrics
+          key: metrics-config.yml
   kafkaExporter: {}
diff --git a/strimzi-kafka/kafka-cruise-control-metrics.yaml b/strimzi-kafka/kafka-cruise-control-metrics.yaml
new file mode 100644
index 0000000..08c3a80
--- /dev/null
+++ b/strimzi-kafka/kafka-cruise-control-metrics.yaml
@@ -0,0 +1,14 @@
+kind: ConfigMap
+apiVersion: v1
+metadata:
+  name: cruise-control-metrics
+  labels:
+    app: strimzi
+data:
+  metrics-config.yml: |
+    # See https://github.com/prometheus/jmx_exporter for more info about JMX Prometheus Exporter metrics
+    lowercaseOutputName: true
+    rules:
+    - pattern: kafka.cruisecontrol<name=(.+)><>(\w+)
+      name: kafka_cruisecontrol_$1_$2
+      type: GAUGE
diff --git a/strimzi-kafka/kafka-metrics.yaml b/strimzi-kafka/kafka-metrics.yaml
new file mode 100644
index 0000000..979d60b
--- /dev/null
+++ b/strimzi-kafka/kafka-metrics.yaml
@@ -0,0 +1,183 @@
+kind: ConfigMap
+apiVersion: v1
+metadata:
+  name: kafka-metrics
+  labels:
+    app: strimzi
+data:
+  kafka-metrics-config.yml: |
+    # See https://github.com/prometheus/jmx_exporter for more info about JMX Prometheus Exporter metrics
+    lowercaseOutputName: true
+    rules:
+    # Special cases and very specific rules
+    - pattern: kafka.server<type=(.+), name=(.+), clientId=(.+), topic=(.+), partition=(.*)><>Value
+      name: kafka_server_$1_$2
+      type: GAUGE
+      labels:
+       clientId: "$3"
+       topic: "$4"
+       partition: "$5"
+    - pattern: kafka.server<type=(.+), name=(.+), clientId=(.+), brokerHost=(.+), brokerPort=(.+)><>Value
+      name: kafka_server_$1_$2
+      type: GAUGE
+      labels:
+       clientId: "$3"
+       broker: "$4:$5"
+    - pattern: kafka.server<type=(.+), cipher=(.+), protocol=(.+), listener=(.+), networkProcessor=(.+)><>connections
+      name: kafka_server_$1_connections_tls_info
+      type: GAUGE
+      labels:
+        cipher: "$2"
+        protocol: "$3"
+        listener: "$4"
+        networkProcessor: "$5"
+    - pattern: kafka.server<type=(.+), clientSoftwareName=(.+), clientSoftwareVersion=(.+), listener=(.+), networkProcessor=(.+)><>connections
+      name: kafka_server_$1_connections_software
+      type: GAUGE
+      labels:
+        clientSoftwareName: "$2"
+        clientSoftwareVersion: "$3"
+        listener: "$4"
+        networkProcessor: "$5"
+    - pattern: "kafka.server<type=(.+), listener=(.+), networkProcessor=(.+)><>(.+):"
+      name: kafka_server_$1_$4
+      type: GAUGE
+      labels:
+       listener: "$2"
+       networkProcessor: "$3"
+    - pattern: kafka.server<type=(.+), listener=(.+), networkProcessor=(.+)><>(.+)
+      name: kafka_server_$1_$4
+      type: GAUGE
+      labels:
+       listener: "$2"
+       networkProcessor: "$3"
+    # Some percent metrics use MeanRate attribute
+    # Ex) kafka.server<type=(KafkaRequestHandlerPool), name=(RequestHandlerAvgIdlePercent)><>MeanRate
+    - pattern: kafka.(\w+)<type=(.+), name=(.+)Percent\w*><>MeanRate
+      name: kafka_$1_$2_$3_percent
+      type: GAUGE
+    # Generic gauges for percents
+    - pattern: kafka.(\w+)<type=(.+), name=(.+)Percent\w*><>Value
+      name: kafka_$1_$2_$3_percent
+      type: GAUGE
+    - pattern: kafka.(\w+)<type=(.+), name=(.+)Percent\w*, (.+)=(.+)><>Value
+      name: kafka_$1_$2_$3_percent
+      type: GAUGE
+      labels:
+        "$4": "$5"
+    # Generic per-second counters with 0-2 key/value pairs
+    - pattern: kafka.(\w+)<type=(.+), name=(.+)PerSec\w*, (.+)=(.+), (.+)=(.+)><>Count
+      name: kafka_$1_$2_$3_total
+      type: COUNTER
+      labels:
+        "$4": "$5"
+        "$6": "$7"
+    - pattern: kafka.(\w+)<type=(.+), name=(.+)PerSec\w*, (.+)=(.+)><>Count
+      name: kafka_$1_$2_$3_total
+      type: COUNTER
+      labels:
+        "$4": "$5"
+    - pattern: kafka.(\w+)<type=(.+), name=(.+)PerSec\w*><>Count
+      name: kafka_$1_$2_$3_total
+      type: COUNTER
+    # Generic gauges with 0-2 key/value pairs
+    - pattern: kafka.(\w+)<type=(.+), name=(.+), (.+)=(.+), (.+)=(.+)><>Value
+      name: kafka_$1_$2_$3
+      type: GAUGE
+      labels:
+        "$4": "$5"
+        "$6": "$7"
+    - pattern: kafka.(\w+)<type=(.+), name=(.+), (.+)=(.+)><>Value
+      name: kafka_$1_$2_$3
+      type: GAUGE
+      labels:
+        "$4": "$5"
+    - pattern: kafka.(\w+)<type=(.+), name=(.+)><>Value
+      name: kafka_$1_$2_$3
+      type: GAUGE
+    # Emulate Prometheus 'Summary' metrics for the exported 'Histogram's.
+    # Note that these are missing the '_sum' metric!
+    - pattern: kafka.(\w+)<type=(.+), name=(.+), (.+)=(.+), (.+)=(.+)><>Count
+      name: kafka_$1_$2_$3_count
+      type: COUNTER
+      labels:
+        "$4": "$5"
+        "$6": "$7"
+    - pattern: kafka.(\w+)<type=(.+), name=(.+), (.+)=(.*), (.+)=(.+)><>(\d+)thPercentile
+      name: kafka_$1_$2_$3
+      type: GAUGE
+      labels:
+        "$4": "$5"
+        "$6": "$7"
+        quantile: "0.$8"
+    - pattern: kafka.(\w+)<type=(.+), name=(.+), (.+)=(.+)><>Count
+      name: kafka_$1_$2_$3_count
+      type: COUNTER
+      labels:
+        "$4": "$5"
+    - pattern: kafka.(\w+)<type=(.+), name=(.+), (.+)=(.*)><>(\d+)thPercentile
+      name: kafka_$1_$2_$3
+      type: GAUGE
+      labels:
+        "$4": "$5"
+        quantile: "0.$6"
+    - pattern: kafka.(\w+)<type=(.+), name=(.+)><>Count
+      name: kafka_$1_$2_$3_count
+      type: COUNTER
+    - pattern: kafka.(\w+)<type=(.+), name=(.+)><>(\d+)thPercentile
+      name: kafka_$1_$2_$3
+      type: GAUGE
+      labels:
+        quantile: "0.$4"
+    # KRaft mode: uncomment the following lines to export KRaft related metrics
+    # KRaft overall related metrics
+    # distinguish between always increasing COUNTER (total and max) and variable GAUGE (all others) metrics
+    #- pattern: "kafka.server<type=raft-metrics><>(.+-total|.+-max):"
+    #  name: kafka_server_raftmetrics_$1
+    #  type: COUNTER
+    #- pattern: "kafka.server<type=raft-metrics><>(.+):"
+    #  name: kafka_server_raftmetrics_$1
+    #  type: GAUGE
+    # KRaft "low level" channels related metrics
+    # distinguish between always increasing COUNTER (total and max) and variable GAUGE (all others) metrics
+    #- pattern: "kafka.server<type=raft-channel-metrics><>(.+-total|.+-max):"
+    #  name: kafka_server_raftchannelmetrics_$1
+    #  type: COUNTER
+    #- pattern: "kafka.server<type=raft-channel-metrics><>(.+):"
+    #  name: kafka_server_raftchannelmetrics_$1
+    #  type: GAUGE
+    # Broker metrics related to fetching metadata topic records in KRaft mode
+    #- pattern: "kafka.server<type=broker-metadata-metrics><>(.+):"
+    #  name: kafka_server_brokermetadatametrics_$1
+    #  type: GAUGE
+  zookeeper-metrics-config.yml: |
+    # See https://github.com/prometheus/jmx_exporter for more info about JMX Prometheus Exporter metrics
+    lowercaseOutputName: true
+    rules:
+    # replicated Zookeeper
+    - pattern: "org.apache.ZooKeeperService<name0=ReplicatedServer_id(\\d+)><>(\\w+)"
+      name: "zookeeper_$2"
+      type: GAUGE
+    - pattern: "org.apache.ZooKeeperService<name0=ReplicatedServer_id(\\d+), name1=replica.(\\d+)><>(\\w+)"
+      name: "zookeeper_$3"
+      type: GAUGE
+      labels:
+        replicaId: "$2"
+    - pattern: "org.apache.ZooKeeperService<name0=ReplicatedServer_id(\\d+), name1=replica.(\\d+), name2=(\\w+)><>(Packets\\w+)"
+      name: "zookeeper_$4"
+      type: COUNTER
+      labels:
+        replicaId: "$2"
+        memberType: "$3"
+    - pattern: "org.apache.ZooKeeperService<name0=ReplicatedServer_id(\\d+), name1=replica.(\\d+), name2=(\\w+)><>(\\w+)"
+      name: "zookeeper_$4"
+      type: GAUGE
+      labels:
+        replicaId: "$2"
+        memberType: "$3"
+    - pattern: "org.apache.ZooKeeperService<name0=ReplicatedServer_id(\\d+), name1=replica.(\\d+), name2=(\\w+), name3=(\\w+)><>(\\w+)"
+      name: "zookeeper_$4_$5"
+      type: GAUGE
+      labels:
+        replicaId: "$2"
+        memberType: "$3"
-- 
2.20.1