线上zabbix监控redis和redis集群
2018-10-31 15:25:46公司最近网站改版，增加了redis服务器，现领导要求需要测试redis的监控，于是从网上找了个redis的监控脚本，简单的修改了一下，测试中没出现任何问题。生产环境中，可根据实际要监控的参数值修改脚本内容，并添加相应的触发器。
Redis有自带的redis-cli客户端，通过info命令可以查询到redis的运行情况，我们可以写个shell脚本，通过zabbix来调用这个脚本实现redis的监控。
一、info命令的使用
要获得redis的当前情况，可以使用info命令。
命令格式：
redis-cli -h -p -a info [参数]
redis-cli -h -p -c[参数]
1、查询server信息
redis-cli -h 127.0.0.1 -p 6379 -a 'password' info server
http://i2.运维网.com/images/blog/201811/15/0dd0ed2e87f8d6357609636f6d7ca34e.png
2、查询客户端连接情况
redis-cli -h 127.0.0.1 -p 6379 -a 'password' info clients
http://i2.运维网.com/images/blog/201811/15/b13d93fec7d59f82541926585e307fb8.png
3、查询内存使用情况
redis-cli -h 127.0.0.1 -p 6379 -a 'password' info memory
http://i2.运维网.com/images/blog/201811/15/20a9951885d6d6bd019c195e596aa753.png
4、查询CPU使用情况
redis-cli -h 127.0.0.1 -p 6379 -a 'password' info cpu
http://i2.运维网.com/images/blog/201811/15/2d787a77254dce917787dd6c51c47a9b.png
5、查询redis集群情况
redis-cli -h 127.0.0.1 -p 6379 -c cluster nodes
redis-cli -h 127.0.0.1 -p 6379 -c info server
http://i2.运维网.com/images/blog/201811/15/52556d842037ac9fa8505ee1d1e482d9.png
http://i2.运维网.com/images/blog/201811/15/cafb609a1c6b700a8b2306f9d234c0fd.png
二、创建redis监控脚本
1、编写监控脚本（第一个脚本是参考网上的，第二个脚本是根据系统实际情况改编的。）
第一个网上参考脚本：
vim /etc/zabbix/zabbix_agentd.d/redis_status.sh
#!/bin/bash
REDISCLI="/usr/local/bin/redis-cli"
HOST="127.0.0.1"
PORT=6379
PASS="password"
if [[ $# == 1 ]];then
case $1 in
version)
result=$REDISCLI -h $HOST -a $PASS -p $PORT info server | grep -w "redis_version" | awk -F':' '{print $2}'
echo $result
;;
uptime)
result=$REDISCLI -h $HOST -a $PASS -p $PORT info server | grep -w "uptime_in_seconds" | awk -F':' '{print $2}'
echo $result
;;
connected_clients)
result=$REDISCLI -h $HOST -a $PASS -p $PORT info clients | grep -w "connected_clients" | awk -F':' '{print $2}'
echo $result
;;
blocked_clients)
result=$REDISCLI -h $HOST -a $PASS -p $PORT info clients | grep -w "blocked_clients" | awk -F':' '{print $2}'
echo $result
;;
used_memory)
result=$REDISCLI -h $HOST -a $PASS -p $PORT info memory | grep -w "used_memory" | awk -F':' '{print $2}'
echo $result
;;
used_memory_rss)
result=$REDISCLI -h $HOST -a $PASS -p $PORT info memory | grep -w "used_memory_rss" | awk -F':' '{print $2}'
echo $result
;;
used_memory_peak)
result=$REDISCLI -h $HOST -a $PASS -p $PORT info memory | grep -w "used_memory_peak" | awk -F':' '{print $2}'
echo $result
;;
used_memory_lua)
result=$REDISCLI -h $HOST -a $PASS -p $PORT info memory | grep -w "used_memory_lua" | awk -F':' '{print $2}'
echo $result
;;
used_cpu_sys)
result=$REDISCLI -h $HOST -a $PASS -p $PORT info cpu | grep -w "used_cpu_sys" | awk -F':' '{print $2}'
echo $result
;;
used_cpu_user)
result=$REDISCLI -h $HOST -a $PASS -p $PORT info cpu | grep -w "used_cpu_user" | awk -F':' '{print $2}'
echo $result
;;
used_cpu_sys_children)
result=$REDISCLI -h $HOST -a $PASS -p $PORT info cpu | grep -w "used_cpu_sys_children" | awk -F':' '{print $2}'
echo $result
;;
used_cpu_user_children)
result=$REDISCLI -h $HOST -a $PASS -p $PORT info cpu | grep -w "used_cpu_user_children" | awk -F':' '{print $2}'
echo $result
;;
rdb_last_bgsave_status)
result=$REDISCLI -h $HOST -a $PASS -p $PORT info Persistence | grep -w "rdb_last_bgsave_status" | awk -F':' '{print $2}' | grep -c ok
echo $result
;;
aof_last_bgrewrite_status)
result=$REDISCLI -h $HOST -a $PASS -p $PORT info Persistence | grep -w "aof_last_bgrewrite_status" | awk -F':' '{print $2}' | grep -c ok
echo $result
;;
aof_last_write_status)
result=$REDISCLI -h $HOST -a $PASS -p $PORT info Persistence | grep -w "aof_last_write_status" | awk -F':' '{print $2}' | grep -c ok
echo $result
;;
)
echo -e "\033[33mUsage: $0 {connected_clients|blocked_clients|used_memory|used_memory_rss|used_memory_peak|used_memory_lua|used_cpu_sys|used_cpu_user|used_cpu_sys_children|used_cpu_user_children|rdb_last_bgsave_status|aof_last_bgrewrite_status|aof_last_write_status}\033[0m"
;;
esac
elif [[ $# == 2 ]];then
case $2 in
keys)
result=$REDISCLI -h $HOST -a $PASS -p $PORT info | grep -w "$1" | grep -w "keys" | awk -F'=|,' '{print $2}'
echo $result
;;
expires)
result=$REDISCLI -h $HOST -a $PASS -p $PORT info | grep -w "$1" | grep -w "keys" | awk -F'=|,' '{print $4}'
echo $result
;;
avg_ttl)
result=$REDISCLI -h $HOST -a $PASS -p $PORT info | grep -w "$1" | grep -w "avg_ttl" | awk -F'=|,' '{print $6}'
echo $result
;;
)
echo -e "\033[33mUsage: $0 {db0 keys|db0 expires|db0 avg_ttl}\033[0m"
;;
esac
fi
第二个根据自己系统环境改编的脚本：
vim /etc/zabbix/zabbix_agentd.d/redis_status.sh
#!/bin/bash
REDISCLI="/usr/bin/redis-cli"
HOST="127.0.0.1"
PORT=6379
if [[ $# == 1 ]];then
case $1 in
cluster_state)
result=$REDISCLI -h $HOST-p $PORT -c cluster info| grep -w "cluster_state" | awk -F':' '{print $2}'| grep -c ok
echo $result
;;
cluster_slots_assigned)
result=$REDISCLI -h $HOST-p $PORT -c cluster info| grep -w "cluster_slots_assigned" | awk -F':' '{print $2}'
echo $result
;;
cluster_slots_ok)
result=$REDISCLI -h $HOST-p $PORT -c cluster info| grep -w "cluster_slots_ok" | awk -F':' '{print $2}'
echo $result
;;
cluster_slots_pfail)
result=$REDISCLI -h $HOST-p $PORT -c cluster info| grep -w "cluster_slots_pfail" | awk -F':' '{print $2}'
echo $result
;;
cluster_slots_fail)
result=$REDISCLI -h $HOST-p $PORT -c cluster info| grep -w "cluster_slots_fail" | awk -F':' '{print $2}'
echo $result
;;
cluster_known_nodes)
result=$REDISCLI -h $HOST-p $PORT -c cluster info| grep -w "cluster_known_nodes" | awk -F':' '{print $2}'
echo $result
;;
cluster_size)
result=$REDISCLI -h $HOST-p $PORT -c cluster info| grep -w "cluster_size" | awk -F':' '{print $2}'
echo $result
;;
cluster_current_epoch)
result=$REDISCLI -h $HOST-p $PORT -c cluster info| grep -w "cluster_current_epoch" | awk -F':' '{print $2}'
echo $result
;;
cluster_my_epoch)
result=$REDISCLI -h $HOST-p $PORT -c cluster info| grep -w "cluster_my_epoch" | awk -F':' '{print $2}'
echo $result
;;
cluster_stats_messages_ping_sent)
result=$REDISCLI -h $HOST-p $PORT -c cluster info| grep -w "cluster_stats_messages_ping_sent" | awk -F':' '{print $2}'
echo $result
;;
cluster_stats_messages_pong_sent)
result=$REDISCLI -h $HOST-p $PORT -c cluster info| grep -w "cluster_stats_messages_pong_sent" | awk -F':' '{print $2}'
echo $result
;;
cluster_stats_messages_sent)
result=$REDISCLI -h $HOST-p $PORT -c cluster info| grep -w "cluster_stats_messages_sent" | awk -F':' '{print $2}'
echo $result
;;
cluster_stats_messages_ping_received)
result=$REDISCLI -h $HOST-p $PORT -c cluster info| grep -w "cluster_stats_messages_ping_received" | awk -F':' '{print $2}'
echo $result
;;
cluster_stats_messages_pong_received)
result=$REDISCLI -h $HOST-p $PORT -c cluster info| grep -w "cluster_stats_messages_pong_received" | awk -F':' '{print $2}'
echo $result
;;
cluster_stats_messages_received)
result=$REDISCLI -h $HOST-p $PORT -c cluster info| grep -w "cluster_stats_messages_received" | awk -F':' '{print $2}'
echo $result
;;
*)
echo -e "\033[33mUsage: $0 {cluster_state|cluster_slots_assigned|cluster_slots_ok|cluster_slots_pfail|cluster_slots_fail|cluster_known_nodes|cluster_size|cluster_current_epoch|cluster_known_nodes|cluster_size|cluster_current_epoch|cluster_my_epoch|cluster_stats_messages_ping_sent|cluster_stats_messages_pong_sent|cluster_stats_messages_sent|cluster_stats_messages_ping_received|cluster_stats_messages_pong_received|cluster_stats_messages_received}\033[0m"
;;
esac
fi
好接下来继续：
2、赋予脚本可执行权限
chmod +x /etc/zabbix/zabbix_agentd.d/redis_status.sh
3、脚本测试
查看redis的客户端连接数
/etc/zabbix/zabbix_agentd.d/redis_status.sh connected_clients
http://i2.运维网.com/images/blog/201811/15/ec41e65c692c0f5eed12954f52248a55.png
三、创建redis监控配置文件
1、编写redis监控配置文件
vim /etc/zabbix/zabbix_agentd.d/redis.conf
UserParameter=Redis.status
[*],/data/zabbix/scripts/redis_status.sh $1
UserParameter=Redisfile,redis-cli -h 127.0.0.1 -p 6379 -c cluster nodes | awk -F ',' '{print $2}' | grep -c 'fail'
2、重启zabbix-agent
ps -ef | grep zabbix_agentd
kill -9 进程
/data/zabbix/sbin/zabbix_agentd -c /data/zabbix/etc/zabbix_agentd.conf
或者：
systemctl restart zabbix-agent
3、在zabbix server端测试
zabbix_get -s 192.168.2.235 -p 10050 -k "Redis.Info"
http://i2.运维网.com/images/blog/201811/15/32ff6742b65c954e7811d1ed1e2bdf82.png
四、创建并导入监控模板
1、创建监控模板文件
redis-template.xml文件内容如下
2.0
2014-08-07T10:04:35Z
RedisMontior
Templates
RedisMontior
RedisMontior
RedisMontior
Templates
Redis Clients
Redis CPU
Redis DbKey
Redis Memory
Redis WriteStatus
Redis.Info
0
0
Redis.Info
30
90
365
0
3
0
0
0
0
1
0
0
0
Redis WriteStatus
Redis.Info
0
0
Redis.Info
30
90
365
0
3
0
0
0
0
1
0
0
0
Redis WriteStatus
Redis.Info
0
0
Redis.Info
30
90
365
0
3
0
0
0
0
1
0
0
0
Redis Clients
Redis.Info
0
0
Redis.Info
30
90
365
0
3
0
0
0
0
1
0
0
0
Redis Clients
Redis.Info
0
0
Redis.Info
30
90
365
0
3
0
0
0
0
1
0
0
0
Redis DbKey
Redis.Info
0
0
Redis.Info
30
90
365
0
3
0
0
0
0
1
0
0
0
Redis DbKey
Redis.Info
0
0
Redis.Info
30
90
365
0
3
0
0
0
0
1
0
0
0
Redis DbKey
Redis.Info
0
0
Redis.Info
30
90
365
0
3
0
0
0
0
1
0
0
0
Redis WriteStatus
Redis.Info
0
0
Redis.Info
30
90
365
0
3
uptime
0
0
0
0
1
0
0
0
Redis.Info
0
0
Redis.Info
30
90
365
0
0
0
0
0
0
1
0
0
0
Redis CPU
Redis.Info
0
0
Redis.Info
30
90
365
0
0
0
0
0
0
1
0
0
0
Redis CPU
Redis.Info
0
0
Redis.Info
30
90
365
0
0
0
0
0
0
1
0
0
0
Redis CPU
Redis.Info
0
0
Redis.Info
30
90
365
0
0
0
0
0
0
1
0
0
0
Redis CPU
Redis.Info
0
0
Redis.Info
30
90
365
0
3
0
0
0
0
1
0
0
0
Redis Memory
Redis.Info
0
0
Redis.Info
30
90
365
0
3
0
0
0
0
1
0
0
0
Redis Memory
Redis.Info
0
0
Redis.Info
30
90
365
0
3
0
0
0
0
1
0
0
0
Redis Memory
Redis.Info
0
0
Redis.Info
30
90
365
0
3
0
0
0
0
1
0
0
0
Redis Memory
Redis.Info
0
0
Redis.Info
30
90
365
0
1
0
0
0
0
1
0
0
0
Redis Status
0
0
Redis.Status
30
90
365
0
3
0
0
0
0
1
0
0
0
{RedisMontior:Redis.Status.last(0)}=0
Redis is down
0
5
0
Redis Client
900
200
0.0000
100.0000
1
1
0
1
0
0.0000
0.0000
0
0
0
0
0
0
C80000
0
2
0
RedisMontior
Redis.Info
1
0
00C800
0
2
0
RedisMontior
Redis.Info
Redis CPU
900
200
0.0000
100.0000
1
1
0
1
0
0.0000
0.0000
0
0
0
0
0
2
C80000
0
2
0
RedisMontior
Redis.Info
1
2
00C800
0
2
0
RedisMontior
Redis.Info
2
2
0000C8
0
2
0
RedisMontior
Redis.Info
3
2
C800C8
0
2
0
RedisMontior
Redis.Info
Redis DbKeys
900
200
0.0000
100.0000
1
1
0
1
0
0.0000
0.0000
0
0
0
0
0
2
C80000
0
2
0
RedisMontior
Redis.Info
1
2
00C800
0
2
0
RedisMontior
Redis.Info
2
2
0000C8
0
2
0
RedisMontior
Redis.Info
Redis Memory
900
200
0.0000
100.0000
1
1
0
1
0
0.0000
0.0000
0
0
0
0
0
2
C80000
0
2
0
RedisMontior
Redis.Info
1
2
00C800
0
2
0
RedisMontior
Redis.Info
2
2
0000C8
0
2
0
RedisMontior
Redis.Info
3
2
C800C8
0
2
0
RedisMontior
Redis.Info
Redis WriteStatus
900
200
0.0000
100.0000
1
1
0
1
0
0.0000
0.0000
0
0
0
0
0
2
C80000
0
2
0
RedisMontior
Redis.Info
1
2
0000C8
0
2
0
RedisMontior
Redis.Info
2
2
00C800
0
2
0
RedisMontior
Redis.Info
模板下载地址：
https://pan.baidu.com/s/1Iqqr_ad1V_Vzt9H4DyDoeA
密码：m15h
2、导入监控模板
配置—模板—导入
http://i2.运维网.com/images/blog/201811/15/4aa7436dafab086041dfddc8f7fbb269.png
点击“选择文件”，找到redis-template.xml文件，将其导入
http://i2.运维网.com/images/blog/201811/15/e5705ad1497e00413223d199579569d3.png
五、给主机添加监控模板
http://i2.运维网.com/images/blog/201811/15/4eccc58b30d763ae0923dd227949b7c3.png
http://i2.运维网.com/images/blog/201811/15/a716c9745f97099528076689a99db89e.png
六、监控效果图
http://i2.运维网.com/images/blog/201811/15/111e208c513365948da056b599856bd9.png
http://i2.运维网.com/images/blog/201811/15/820e16b1d915c2480576aa13c666549d.png
http://i2.运维网.com/images/blog/201811/15/ee02f8253debc7e97527032f3957627e.png
脚本、模板下载地址：
https://pan.baidu.com/s/1UnS4e4FFv1rZW-ctdrdQHA
密码：1glw
以上内容，如有问题 随时沟通
QQ: 936172842
页:
[1]