我已经用石墨输出服务以及标准码头服务配置了kafka-monitor的实例。码头服务可以正常工作-所有图表都是实时的。石墨报告服务没有那么多。以下监视器配置的一部分:
{
"single-cluster-monitor": {
"class.name": "com.linkedin.kmf.apps.SingleClusterMonitor",
"topic": "kafka-monitor-topic",
"zookeeper.connect": "node1:2181,node2:2181,node3:2181",
"bootstrap.servers": "node1:9092,node2:9092,node3:9092",
"produce.record.delay.ms": 100,
"topic-management.topicCreationEnabled": true,
"topic-management.replicationFactor" : 1,
"topic-management.partitionsToBrokersRatio" : 2.0,
"topic-management.rebalance.interval.ms" : 600000,
"topic-management.topicFactory.props": {
},
"topic-management.topic.props": {
"retention.ms": "3600000"
},
"produce.producer.props": {
"client.id": "kmf-client-id"
},
"consume.latency.sla.ms": "20000",
"consume.consumer.props": {
}
},
"jetty-service": {
"class.name": "com.linkedin.kmf.services.JettyService",
"jetty.port": 8000
},
"graphite-service": {
"class.name": "com.linkedin.kmf.services.GraphiteMetricsReporterService",
"report.graphite.host": "graphitenode",
"report.graphite.port": "2003",
"report.graphite.prefix": "kafka-monitor",
"report.interval.sec": 5,
"report.metrics.list": [
# "kmf:type=kafka-monitor:offline-runnable-count",
"kmf.services:type=produce-service,name=*:produce-availability-avg",
"kmf.services:type=consume-service,name=*:consume-availability-avg",
"kmf.services:type=produce-service,name=*:records-produced-total",
"kmf.services:type=consume-service,name=*:records-consumed-total",
"kmf.services:type=consume-service,name=*:records-lost-total",
"kmf.services:type=consume-service,name=*:records-duplicated-total",
"kmf.services:type=consume-service,name=*:records-delay-ms-avg",
"kmf.services:type=produce-service,name=*:records-produced-rate",
"kmf.services:type=produce-service,name=*:produce-error-rate",
"kmf.services:type=consume-service,name=*:consume-error-rate"
]
}
}
因此简而言之: -码头服务很好 -Graphite在给定端口上收集许多指标,但不包括来自Kafka监视器的指标(无法通过WebUI找到它们) -TCPDUMP实用程序帮助我确认了软件包实际上已到达给定的端口
您知道此设置可能有什么问题吗?还有其他发现问题的方法吗?