zabbix 监控Storage Manager for DM Series zabbix 监控goldendb

转载

mob64ca1410eb61 2024-04-19 18:52:33

文章标签 运维数据库 shell mongodb 客户端 文章分类 运维

**Zabbix 监控mongodb做后整理**

系统运维工程师李超因为我安全问题我们只能呢个通过mongo客户端去远程监控mongo服务端。1、如果你不是在mongo服务器上操作请参考我下边的部分，如果是直接在mongodb服务器上安装的zabbix_agnetd请参考网上其他文章。（直接在mongodb服务端安装zabbix客户端的文档非常多）。2、下边首先安装mongo客户端：我的系统是：ubuntu16.04，安装mongo客户端直接apt-get安装即可（这里不多做介绍，但是要注意apt一般都是较低的版本，要4.0版本的可以更新apt这里不做介绍，网上可以搜索到相关内容）。3、当mongodb客户端安装完毕以后我们执行下边命令/bin/echo "db.serverStatus()" |/usr/bin/mongo 192.168.16.111:20001/admin -ulichao -plichao通过这个命令可以测试知道mongo的系统参数，我们根据这些系统参数进行监控，执行结果如下：

MongoDB shell version v4.0.0
connecting to: mongodb://192.168.16.111:20001/admin
MongoDB server version: 3.4.9
WARNING: shell and server versions do not match
{
"host" : "iZ2zeem1uivcbfbr01nmnrZ:20000",
"version" : "3.4.9",
"process" : "mongos",
"pid" : NumberLong(10828),
"uptime" : 24441734,
"uptimeMillis" : NumberLong("24441733680"),
"uptimeEstimate" : NumberLong(24441733),
"localTime" : ISODate("2018-08-02T09:34:54.400Z"),
"asserts" : {
"regular" : 0,
"warning" : 0,
"msg" : 0,
"user" : 1763423,
"rollovers" : 0
},
"connections" : {
"current" : 86,
"available" : 52342,
"totalCreated" : 118672
},
"extra_info" : {
"note" : "fields vary by platform",
"page_faults" : 14
},
"network" : {
"bytesIn" : NumberLong("467536962787"),
"bytesOut" : NumberLong("111369070632"),
"physicalBytesIn" : NumberLong("467536962787"),
"physicalBytesOut" : NumberLong("108213593338"),
"numRequests" : NumberLong("2582169303")
},
"opcounters" : {
"insert" : 619611,
"query" : 406777,
"update" : 122426978,
"delete" : 61,
"getmore" : 308,
"command" : 215576153
},
"sharding" : {
"configsvrConnectionString" : "config/iZ2ze7s6pfi7t4x18mx417Z:22000,iZ2ze7s6pfi7t4x18mx418Z:22000,iZ2ze7s6pfi7t4x18mx419Z:22000",
"lastSeenConfigServerOpTime" : {
"ts" : Timestamp(1533202490, 2),
"t" : NumberLong(3)
}
},
"tcmalloc" : {
"generic" : {
"current_allocated_bytes" : 4007000,
"heap_size" : NumberLong("3108966400")
},
"tcmalloc" : {
"pageheap_free_bytes" : 36864,
"pageheap_unmapped_bytes" : NumberLong("3090604032"),
"max_total_thread_cache_bytes" : NumberLong(1073741824),
"current_total_thread_cache_bytes" : 5583584,
"total_free_bytes" : 14318504,
"central_cache_free_bytes" : 3283112,
"transfer_cache_free_bytes" : 5451808,
"thread_cache_free_bytes" : 5583584,
"aggressive_memory_decommit" : 0,
"formattedString" : "------------------------------------------------\nMALLOC: 4007000 ( 3.8 MiB) Bytes in use by application\nMALLOC: + 36864 ( 0.0 MiB) Bytes in page heap freelist\nMALLOC: + 3283112 ( 3.1 MiB) Bytes in central cache freelist\nMALLOC: + 5451808 ( 5.2 MiB) Bytes in transfer cache freelist\nMALLOC: + 5583584 ( 5.3 MiB) Bytes in thread cache freelists\nMALLOC: + 8577216 ( 8.2 MiB) Bytes in malloc metadata\nMALLOC: ------------\nMALLOC: = 26939584 ( 25.7 MiB) Actual memory used (physical + swap)\nMALLOC: + 3090604032 ( 2947.4 MiB) Bytes released to OS (aka unmapped)\nMALLOC: ------------\nMALLOC: = 3117543616 ( 2973.1 MiB) Virtual address space used\nMALLOC:\nMALLOC: 2014 Spans in use\nMALLOC: 115 Thread heaps in use\nMALLOC: 4096 Tcmalloc page size\n------------------------------------------------\nCall ReleaseFreeMemory() to release freelist memory to the OS (via madvise()).\nBytes released to the OS take up virtual address space but no physical memory.\n"
}
},
"mem" : {
"bits" : 64,
"resident" : 174,
"virtual" : 3426,
"supported" : true
},
"metrics" : {
"cursor" : {
"timedOut" : NumberLong(380),
"open" : {
"multiTarget" : NumberLong(0),
"singleTarget" : NumberLong(0),
"pinned" : NumberLong(0),
"total" : NumberLong(0)
}
},
"commands" : {
"<UNKNOWN>" : NumberLong(1),
"aggregate" : {
"failed" : NumberLong(142),
"total" : NumberLong(8980)
},
"authenticate" : {
"failed" : NumberLong(12),
"total" : NumberLong(12)
},
"buildInfo" : {
"failed" : NumberLong(0),
"total" : NumberLong(635407)
},
"collStats" : {
"failed" : NumberLong(65),
"total" : NumberLong(6827)
},
"count" : {
"failed" : NumberLong(388),
"total" : NumberLong(491985789)
},
"create" : {
"failed" : NumberLong(0),
"total" : NumberLong(10)
},
"createIndexes" : {
"failed" : NumberLong(1),
"total" : NumberLong(69)
},
"createUser" : {
"failed" : NumberLong(6),
"total" : NumberLong(10)
},
"currentOp" : {
"failed" : NumberLong(0),
"total" : NumberLong(15)
},
"dbStats" : {
"failed" : NumberLong(7),
"total" : NumberLong(917)
},
"delete" : {
"failed" : NumberLong(0),
"total" : NumberLong(705)
},
"distinct" : {
"failed" : NumberLong(17),
"total" : NumberLong(5105)
},
"drop" : {
"failed" : NumberLong(0),
"total" : NumberLong(67)
},
"dropDatabase" : {
"failed" : NumberLong(0),
"total" : NumberLong(7)
},
"dropIndexes" : {
"failed" : NumberLong(7),
"total" : NumberLong(23)
},
"enableSharding" : {
"failed" : NumberLong(1),
"total" : NumberLong(2)
},
"explain" : {
"failed" : NumberLong(0),
"total" : NumberLong(13)
},
"find" : {
"failed" : NumberLong(131),
"total" : NumberLong(1764517)
},
"findAndModify" : {
"failed" : NumberLong(1),
"total" : NumberLong(772)
},
"getLastError" : {
"failed" : NumberLong(0),
"total" : NumberLong(1989)
},
"getLog" : {
"failed" : NumberLong(0),
"total" : NumberLong(2)
},
"getMore" : {
"failed" : NumberLong(17),
"total" : NumberLong(1791)
},
"getnonce" : {
"failed" : NumberLong(0),
"total" : NumberLong(38)
},
"insert" : {
"failed" : NumberLong(0),
"total" : NumberLong(207939962)
},
"isMaster" : {
"failed" : NumberLong(0),
"total" : NumberLong(35391424)
},
"killCursors" : {
"failed" : NumberLong(0),
"total" : NumberLong(79)
},
"listCollections" : {
"failed" : NumberLong(0),
"total" : NumberLong(862)
},
"listDatabases" : {
"failed" : NumberLong(0),
"total" : NumberLong(263)
},
"listIndexes" : {
"failed" : NumberLong(0),
"total" : NumberLong(8)
},
"logout" : {
"failed" : NumberLong(0),
"total" : NumberLong(8658)
},
"mapReduce" : {
"failed" : NumberLong(24),
"total" : NumberLong(64)
},
"ping" : {
"failed" : NumberLong(0),
"total" : NumberLong(5980)
},
"profile" : {
"failed" : NumberLong(4),
"total" : NumberLong(4)
},
"renameCollection" : {
"failed" : NumberLong(0),
"total" : NumberLong(2)
},
"repairDatabase" : {
"failed" : NumberLong(0),
"total" : NumberLong(1)
},
"replSetGetStatus" : {
"failed" : NumberLong(88870),
"total" : NumberLong(88870)
},
"rolesInfo" : {
"failed" : NumberLong(0),
"total" : NumberLong(491)
},
"saslContinue" : {
"failed" : NumberLong(4),
"total" : NumberLong(183362)
},
"saslStart" : {
"failed" : NumberLong(8),
"total" : NumberLong(91691)
},
"serverStatus" : {
"failed" : NumberLong(0),
"total" : NumberLong(223111)
},
"shardCollection" : {
"failed" : NumberLong(0),
"total" : NumberLong(3)
},
"update" : {
"failed" : NumberLong(0),
"total" : NumberLong(552681439)
},
"usersInfo" : {
"failed" : NumberLong(0),
"total" : NumberLong(493)
},
"whatsmyuri" : {
"failed" : NumberLong(0),
"total" : NumberLong(54513)
}
}
},
"ok" : 1
}
Bye上边是我们执行完命令从mongo服务端获取到mongo服务端的参数，下面对他进行监控。
首先建立脚本check_mongo.sh
#!/bin/bash
#mongodb status
#b.serverStatus().ok
#memory status
#Physical memory: db.serverStatus().mem.resident
#Virtual memory: db.serverStatus().mem.virtual
#opcounters status
#insert: db.serverStatus().opcounters.insert
#query: db.serverStatus().opcounters.query
#update: db.serverStatus().opcounters.update
#delete: db.serverStatus().opcounters.delete
#connections status
#current connections: db.serverStatus().connections.current
MONGODBPATH="/usr/bin/mongo"
HOST="47.94.37.221"
PORT="$1"
MONGODB_PA="$MONGODBPATH ${HOST}:${PORT}/admin -uroot -pkeytech2017"if [ $# == 3 ];then
result=$(/bin/echo "db.serverStatus().$2.$3" | $MONGODB_PA --quiet)
echo $result
elif [ $# == 2 ];then
result=$(/bin/echo "db.serverStatus().$2" | $MONGODB_PA --quiet)
echo $result
else
echo "Usage:$0 PORT mem resident"
fi

保存退出！

这里我们可以测试一下我们的脚本可用性：

zabbix 监控Storage Manager for DM Series zabbix 监控goldendb_shell

zabbix 监控Storage Manager for DM Series zabbix 监控goldendb_shell_02

我们这里的测试是结合上边第一条命令执行后显示的参数来输入的如：

zabbix 监控Storage Manager for DM Series zabbix 监控goldendb_shell_03

这下明白脚本后边跟的参数的意思了吧$1:端口 $2:主参数 $3: 你要提取的参数

然后我们建立我们想要的key

zabbix 监控Storage Manager for DM Series zabbix 监控goldendb_数据库_04

别问我这个目录时干什么的，如果不知道，请从头开始了解zabbix。

在这个目录下我监理一个.conf文件

zabbix 监控Storage Manager for DM Series zabbix 监控goldendb_shell_05

这个是我的key文件里边所有内容，但是接上边的内容我们这里只写入

UserParameter=MongoDB.totalCreated,/data/zabbix/scripts/check_mongodb.sh 20001 connections totalCreatedUserParameter=MongoDB.available,/data/zabbix/scripts/check_mongodb.sh 20001 connections available这两条

剩下的两条后边会用到（最下边会说这两条做什么用）加完那两条我们保存退出，然后去web上自定义key进行监控

zabbix 监控Storage Manager for DM Series zabbix 监控goldendb_数据库_06

zabbix 监控Storage Manager for DM Series zabbix 监控goldendb_客户端_07

保存，过一会监控图像就出来了，如图：

zabbix 监控Storage Manager for DM Series zabbix 监控goldendb_shell_08

zabbix 监控Storage Manager for DM Series zabbix 监控goldendb_运维_09

OK！监控完毕但是，但是……mongo那么多监控项我们现在只监控了两项吧，如果你觉得上边的方法你吼的住你照着上边自己慢慢的吧所有key都谢出来，下面介绍其他方法，

第二种办法就是我上边说的，直接定义key，在key文件里边加上命令如下

UserParameter=MongoDB.Status[*],/bin/echo "db.serverStatus().$1" |/usr/bin/mongo 192.168.16.111:20001/admin -ulichao -plichao | grep "\<$2\>" |awk -F : '{print $$2}' |awk -F , '{print $$1}'
UserParameter=MongoDB.byesOut,/bin/echo "db.serverStatus().network" |/usr/bin/mongo 192.168.16.111:20001/admin -ulichao -plichao | grep "bytesOut" | awk -F : '{print $2}' | awk -F , '{print $1}' | awk -F \" '{print $2}'
UserParameter=MongoDB.bytesIn,/bin/echo "db.serverStatus().network" |/usr/bin/mongo 192.168.16.111:20001/admin -ulichao -plichao | grep "bytesIn" | awk -F : '{print $2}' | awk -F , '{print $1}' | awk -F \" '{print $2}'

添加完毕保存保存退出。

然后直接导入模板监控即可。模板在这：https://pan.baidu.com/s/1PFrhealedPUejz7ACI_WVA添加到web上我么你可以在图形上看到下图

zabbix 监控Storage Manager for DM Series zabbix 监控goldendb_数据库_10