Zabbix对Kafka topic积压数据监控的解决方案

# 查看消费者组的topic 消费状态
bash kafka-consumer-groups.sh --bootstrap-server 192.168.3.55:9090 --describe --group test2_consumer_group
TOPIC PARTITION CURRENT-OFFSET LOG-END-OFFSET LAG CONSUMER-ID HOST CLIENT-ID
test 0 1000000 1000000 0 consumer-1-8688633a-2f88-4c41-89ca-fd0cd6d19ec7 /127.0.0.1 consumer-1
test 1 1000000 1000000 0 consumer-1-8688633a-2f88-4c41-89ca-fd0cd6d19ec7 /127.0.0.1 consumer-1
test 2 1000000 1000000 0 consumer-1-8688633a-2f88-4c41-89ca-fd0cd6d19ec7 /127.0.0.1 consumer-1
test 3 1000000 1000000 0 consumer-1-8688633a-2f88-4c41-89ca-fd0cd6d19ec7 /127.0.0.1 consumer-1

# 自动发现
vim consumer-groups.conf
#按消费者组(Group)|Topic格式，写入自动发现配置文件
test-group|test
# 执行脚本自动发现指定消费者和topic的分区
bash consumer-groups.sh discovery
{
    "data": [
        { "{#GROUP}":"test-group", "{#TOPICP}":"test", "{#PARTITION}":"0" },
        { "{#GROUP}":"test-group", "{#TOPICP}":"test", "{#PARTITION}":"1" },
        { "{#GROUP}":"test-group", "{#TOPICP}":"test", "{#PARTITION}":"3" },
        { "{#GROUP}":"test-group", "{#TOPICP}":"test", "{#PARTITION}":"2" }
    ]
}

# 获取分区0 lag
bash consumer-groups.sh lag 0
# 获取分区1 lag
bash consumer-groups.sh lag 1
# 获取分区2 lag
bash consumer-groups.sh lag 2
# 获取分区3 lag
bash consumer-groups.sh lag 3

vim consumer-groups.sh
#!/bin/bash
#comment: 根据消费者组监控topic lag，进行监控告警
#配置文件说明
#消费者组|Topic
#test-group|test
#获取topic 信息
cal_topic() {
    if [ $# -ne 2 ]; then
        echo "parameter num error, 读取topic信息失败"
        exit 1
    else
        /usr/local/kafka/bin/kafka-consumer-groups.sh --bootstrap-server 192.168.3.55:9092 --describe --group $1 |grep -w $2
    fi
}
#topic+分区自动发现
topic_discovery() {
    printf "{\n"
    printf "\t\"data\": [\n"
    for line in `cat /data/scripts/consumer-groups.conf`
    do
        group=`echo ${line} | awk -F'|' '{print $1}'`
        topic=`echo ${line} | awk -F'|' '{print $2}'`
        cal_topic $group $topic > /tmp/consumer-group-tmp
        count=`cat /tmp/consumer-group-tmp|wc -l`
        n=0
        while read line
        do
             n=`expr  $n + 1`
             #判断最后一行
             if [ $n -eq $count ]; then
                 topicp=`echo $line | awk '{print $1}'`
                 partition=`echo $line  | awk '{print $2}'`
                 printf "\t\t{ \"{#GROUP}\":\"${group}\", \"{#TOPICP}\":\"${topicp}\", \"{#PARTITION}\":\"${partition}\" }\n"
             else
                 topicp=`echo $line | awk '{print $1}'`
                 partition=`echo $line  | awk '{print $2}'`
                 printf "\t\t{ \"{#GROUP}\":\"${group}\", \"{#TOPICP}\":\"${topicp}\", \"{#PARTITION}\":\"${partition}\" },\n"
             fi
        done < /tmp/consumer-group-tmp
    done
    printf "\t]\n"
    printf "}\n"
}


if [ $1 == "discovery" ]; then
    topic_discovery
elif [ $1 == "lag" ];then
    cat /tmp/consumer-group-tmp |awk -v p=$2 '{if($2==p){print $5}}'
else
    echo "Usage: /data/scripts/consumer-group.sh discovery | lag"
fi

告警主机：Kafka_192.168.3.55
主机IP：192.168.3.55
主机组：Kafka
告警时间：2022.03.21 00:23:10
告警等级：Average
告警信息：test-group/test/分区1:数据积压62
告警项目：topic_lag[test,1]
问题详情：
test-group/test/1: 62