From 152bb19a7cdd448941e07c3a7c23e5a16f9c6b56 Mon Sep 17 00:00:00 2001
From: Staffan Olsson <staffan@repos.se>
Date: Fri, 2 Feb 2018 12:33:27 +0100
Subject: ”In a production Kafka cluster, an offline partition
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

may be impacting the producer clients, losing messages or causing back-pressure in the application.
This is most often a “site down” type of problem and will need to be addressed immediately.”

Excerpt from: Neha Narkhede, Gwen Shapira, and Todd Palino. ”Kafka: The Definitive Guide”.

We now export kafka_controller_kafkacontroller_value{name="OfflinePartitionsCount",} and friends.
See #140 for why.
---
 prometheus/10-metrics-config.yml | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/prometheus/10-metrics-config.yml b/prometheus/10-metrics-config.yml
index 4416cce..33bed50 100644
--- a/prometheus/10-metrics-config.yml
+++ b/prometheus/10-metrics-config.yml
@@ -9,8 +9,9 @@ data:
     lowercaseOutputName: true
     jmxUrl: service:jmx:rmi:///jndi/rmi://127.0.0.1:5555/jmxrmi
     ssl: false
-    whitelistObjectNames: ["kafka.server:*","java.lang:*"]
+    whitelistObjectNames: ["kafka.controller:*","kafka.server:*","java.lang:*"]
     rules:
+      - pattern : kafka.controller<type=KafkaController, name=(.+)><>(.*)
       - pattern : kafka.server<type=ReplicaFetcherManager, name=MaxLag, clientId=(.+)><>Value
       - pattern : kafka.server<type=BrokerTopicMetrics, name=(BytesInPerSec|BytesOutPerSec|MessagesInPerSec), topic=(.+)><>OneMinuteRate
       - pattern : kafka.server<type=KafkaRequestHandlerPool, name=RequestHandlerAvgIdlePercent><>OneMinuteRate
-- 
cgit v1.2.3