Nagios监控mongodb分片集群服务实战

时间:2022-04-21 19:21:26

1,监控插件下载

Mongodb插件下载地址为:git clone git://github.com/mzupan/nagios-plugin-mongodb.git,刚開始本人这里没有安装gitpub环境,找网友草根帮忙下载的。之后上传到了csdn资源页面,新的下载地址为:http://download.csdn.net/detail/mchdba/8019077

2,加入新的mongodb监控命令

由于mongodb服务是和mysql从库公用一台物理机。之前已经做了基础nagios以及mysql服务监控,所以这里仅仅须要在原来的基础上加入mongodb命令和服务就可以。Nagios监控mysql请參考:http://blog.itpub.net/26230597/viewspace-760141/以及http://blog.itpub.net/26230597/viewspace-1217246/。所以这里须要加入的mongodb监控命令例如以下所看到的:

[root@wgq objects]# cd /usr/local/nagios/etc/objects
[root@wgq objects]# vim commands.cfg
define command {
command_name check_mongodb
command_line $USER1$/nagios-plugin-mongodb/check_mongodb.py -H $HOSTADDRESS$ -A $ARG1$ -P $ARG2$ -W $ARG3$ -C $ARG4$
} define command {
command_name check_mongodb_database
command_line $USER1$/nagios-plugin-mongodb/check_mongodb.py -H $HOSTADDRESS$ -A $ARG1$ -P $ARG2$ -W $ARG3$ -C $ARG4$ -d $ARG5$
} define command {
command_name check_mongodb_collection
command_line $USER1$/nagios-plugin-mongodb/check_mongodb.py -H $HOSTADDRESS$ -A $ARG1$ -P $ARG2$ -W $ARG3$ -C $ARG4$ -d $ARG5$ -c $ARG6$
} define command {
command_name check_mongodb_replicaset
command_line $USER1$/nagios-plugin-mongodb/check_mongodb.py -H $HOSTADDRESS$ -A $ARG1$ -P $ARG2$ -W $ARG3$ -C $ARG4$ -r $ARG5$
} define command {
command_name check_mongodb_query
command_line $USER1$/nagios-plugin-mongodb/check_mongodb.py -H $HOSTADDRESS$ -A $ARG1$ -P $ARG2$ -W $ARG3$ -C $ARG4$ -q $ARG5$
}

3,加入mongodb监控服务

mongodb的服务也须要单独又一次加入。例如以下所看到的:

#检測mongodb服务的连接时间,超过2秒就普通报警,5秒就严重报警
define service{
host_name dbm1slave1
service_description Mongo Connect Check
check_command check_mongodb!connect!30000!2!5
max_check_attempts 5
normal_check_interval 3
retry_check_interval 2
check_period 24x7
notification_interval 10
notification_period 24x7
notification_options w,u,c,r
contact_groups ops
} #检查mongodb的连接数,超过150普通报警,200严重报警
define service{
host_name dbm1slave1
service_description Mongo Free Connections
check_command check_mongodb!connections!27017!70!80
max_check_attempts 5
normal_check_interval 3
retry_check_interval 2
check_period 24x7
notification_interval 10
notification_period 24x7
notification_options w,u,c,r
contact_groups ops
} #检查mongodb复制完毕的百分比率,确保primary和standby的time是一致的。
define service{
host_name dbm1slave1
service_description Mongo Replication Lag
check_command check_mongodb!replication_lag!27017!15!30
max_check_attempts 5
normal_check_interval 3
retry_check_interval 2
check_period 24x7
notification_interval 10
notification_period 24x7
notification_options w,u,c,r
contact_groups ops
} #检查mongodb内存使用率。阀值与mongodb所在机器的总内存数相关
define service{
host_name dbm1slave1
service_description Mongo Memory Usage
check_command check_mongodb!memory!27017!20!28
max_check_attempts 5
normal_check_interval 3
retry_check_interval 2
check_period 24x7
notification_interval 10
notification_period 24x7
notification_options w,u,c,r
contact_groups ops
} #检查mongodb Mapped的内存使用率。阀值与mongodb所在机器的总内存数相关
define service{
host_name dbm1slave1
service_description Mongo Mapped Memory Usage
check_command check_mongodb!memory_mapped!27017!20!28
max_check_attempts 5
normal_check_interval 3
retry_check_interval 2
check_period 24x7
notification_interval 10
notification_period 24x7
notification_options w,u,c,r
contact_groups ops
} #检查Lock Time的百分率。假设lock time占领mongo运行时间的5%就普通报警。假设超过10%就严重报警
define service{
host_name dbm1slave1
service_description Mongo Lock Percentage
check_command check_mongodb!lock!27017!5!10
max_check_attempts 5
normal_check_interval 3
retry_check_interval 2
check_period 24x7
notification_interval 10
notification_period 24x7
notification_options w,u,c,r
contact_groups ops
} # Check Average Flush Time,检查mongo服务器的平均flush时间,
define service{
host_name dbm1slave1
service_description Mongo Flush Average
check_command check_mongodb!flushing!27017!100!200
max_check_attempts 5
normal_check_interval 3
retry_check_interval 2
check_period 24x7
notification_interval 10
notification_period 24x7
notification_options w,u,c,r
contact_groups ops
} # Check Last Flush Time,检查最新的flush时间,假设超过200ms就普通报警。超过400ms就严重报警
define service{
host_name dbm1slave1
service_description Mongo Last Flush Time
check_command check_mongodb!last_flush_time!27017!200!400
max_check_attempts 5
normal_check_interval 3
retry_check_interval 2
check_period 24x7
notification_interval 10
notification_period 24x7
notification_options w,u,c,r
contact_groups ops
} # Check status of mongodb replicaset,检查mongo复制的状态
define service{
host_name dbm1slave1
service_description MongoDB state
check_command check_mongodb!replset_state!27017!0!0
max_check_attempts 5
normal_check_interval 3
retry_check_interval 2
check_period 24x7
notification_interval 10
notification_period 24x7
notification_options w,u,c,r
contact_groups ops
} # Check status of index miss ratio,检查索引命中率。
define service{
host_name dbm1slave1
service_description MongoDB Index Miss Ratio
check_command check_mongodb!index_miss_ratio!27017!.005!.01
max_check_attempts 5
normal_check_interval 3
retry_check_interval 2
check_period 24x7
notification_interval 10
notification_period 24x7
notification_options w,u,c,r
contact_groups ops
} # Check number of databases and number of collections
define service{
host_name dbm1slave1
service_description MongoDB Number of databases
check_command check_mongodb!databases!27017!300!500
max_check_attempts 5
normal_check_interval 3
retry_check_interval 2
check_period 24x7
notification_interval 10
notification_period 24x7
notification_options w,u,c,r
contact_groups ops
}
define service{
host_name dbm1slave1
service_description MongoDB Number of collections
check_command check_mongodb!collections!27017!300!500
max_check_attempts 5
normal_check_interval 3
retry_check_interval 2
check_period 24x7
notification_interval 10
notification_period 24x7
notification_options w,u,c,r
contact_groups ops
} # Check size of a database,检查库的大小
define service{
host_name dbm1slave1
service_description MongoDB Database size your-database
check_command check_mongodb_database!database_size!27017!300!500!your-database
max_check_attempts 5
normal_check_interval 3
retry_check_interval 2
check_period 24x7
notification_interval 10
notification_period 24x7
notification_options w,u,c,r
contact_groups ops
} # Check index size of a database,检查库索引的大小
define service{
host_name dbm1slave1
service_description MongoDB Database index size your-database
check_command check_mongodb_database!database_indexes!27017!50!100!your-database
max_check_attempts 5
normal_check_interval 3
retry_check_interval 2
check_period 24x7
notification_interval 10
notification_period 24x7
notification_options w,u,c,r
contact_groups ops
} # Check index size of a collection,检查集合collection的索引大小
define service{
host_name dbm1slave1
service_description MongoDB Database index size your-database
check_command check_mongodb_collection!collection_indexes!27017!50!100!your-database!your-collection
max_check_attempts 5
normal_check_interval 3
retry_check_interval 2
check_period 24x7
notification_interval 10
notification_period 24x7
notification_options w,u,c,r
contact_groups ops
} # Check the primary server of replicaset。检查复制的primary服务
define service{
host_name dbm1slave1
service_description MongoDB Replicaset Master Monitor: your-replicaset
check_command check_mongodb_replicaset!replica_primary!27017!0!1!your-replicaset
#演示样例:check_command check_mongodb_replicaset!replica_primary!27017!0!1!shard2
max_check_attempts 5
normal_check_interval 3
retry_check_interval 2
check_period 24x7
notification_interval 10
notification_period 24x7
notification_options w,u,c,r
contact_groups ops
} # Check the number of queries per second,检查每一秒的查询数量
define service{
host_name dbm1slave1
service_description MongoDB Updates per Second
check_command check_mongodb_query!queries_per_second!27017!200!150!update
max_check_attempts 5
normal_check_interval 3
retry_check_interval 2
check_period 24x7
notification_interval 10
notification_period 24x7
notification_options w,u,c,r
contact_groups ops
} # Check Primary Connection,检查复制中与primary库的连接时间,超过2秒就普通报警,超过4秒就严重报警
define service{
host_name dbm1slave1
service_description Mongo Connect Check
check_command check_mongodb!connect_primary!27017!2!4
max_check_attempts 5
normal_check_interval 3
retry_check_interval 2
check_period 24x7
notification_interval 10
notification_period 24x7
notification_options w,u,c,r
contact_groups ops
} # Check Collection State。检查collection状态,检查mongo服务组列表的每个主机,能够检查重要collection的高可用性(锁、超时、服务配置的可用性)。假设发现一个查询失败就会报警。
define service{
host_name dbm1slave1
service_description Mongo Collection State
check_command check_mongodb!collection_state!27017!your-database!your-collection
max_check_attempts 5
normal_check_interval 3
retry_check_interval 2
check_period 24x7
notification_interval 10
notification_period 24x7
notification_options w,u,c,r
contact_groups ops
}

4,查看部分监控项效果

配置完nagios端服务。重新启动下service nagios restart; 等上几分钟,nagios监控界面就会出现完整的mongo服务信息,例如以下所看到的:

Nagios监控mongodb分片集群服务实战

5
,从ps中确定mongodb的架构

[root@db-m1-slave-1 ~]# ps -eaf|grep mongo

mongodb   2457     1  0  2013 ?

2-03:39:08 ./mongod --configsvr --dbpath /home/data/mongodb/config --port 20000 --logpath /home/data/mongodb/config.log --logappend --fork

mongodb   2804     1  0  2013 ?        1-10:02:33 mongos --configdb 192.168.12.62:20000,192.168.12.63:20000,192.168.12.72:20000 --port 30000 --chunkSize 64 --logpath /home/data/mongodb/mongos.log --logappend --fork

mongodb   3072     1  0  2013 ?

1-10:17:20 mongod --shardsvr --replSet shard1 --port 27017 --dbpath /home/data/mongodb/shard11 --oplogSize 2048 --logpath /home/data/mongodb/shard11.log --logappend --fork

root     11179  9391  0 11:14 pts/1    00:00:00 grep mongo

mongodb  30414     1  0 Feb14 ?        1-06:20:50 mongod --shardsvr --replSet shard2 --port 27018 --dbpath /home/data/mongodb/shard21 --oplogSize 2048 --logpath /home/data/mongodb/shard21.log --logappend --fork

[root@db-m1-slave-1 ~]#

看到有4个mongo进程,

a)         启动參数有“--configdb”的就是集群入口进程;

b)         Shard Server,启动參数带“--shardsvr --replSet”的是集群分片的一个片组启动进程,用户存储实际的数据块,也就是27017port和27018port的mongodb服务实例。至于怎样推断27017port中哪个是primary哪个是secondary须要去登录27107port运行rs.status();去查看一下。

c)         Config Server:启动參数带“--configsvr”的进程,存储了整个Cluster Metadata,当中包含chunk信息,也就是20000port的mongodb服务实例。

d)         Route Server:启动參数带“mongos --configdb”的进程,前端路由,client由此接入。且让整个集群看上去像单一数据库,前端应用能够透明使用。也就是30000port的mongodb实例。


6,调试中出现过的错误

错误1:

[root@wgq nagios ~]# tail -f /usr/local/nagios/var/nagios.log

[1412819956] Warning: Return code of 13 for check of service 'Mongo Memory Usage' on host 'dbm1slave1' was out of bounds.

[1412819956] SERVICE ALERT: dbm1slave1;Mongo Memory Usage;CRITICAL;SOFT;1;(Return code of 13 is out of bounds)

[1412819975] Warning: Return code of 13 for check of service 'Mongodb Connect Check' on host 'dbm1slave1' was out of bounds.

[1412819975] SERVICE ALERT: dbm1slave1;Mongodb Connect Check;CRITICAL;SOFT;1;(Return code of 13 is out of bounds)

[1412820058] Warning: Return code of 13 for check of service 'Mongo Free Connections' on host 'dbm1slave1' was out of bounds.

须要赋值nagios用户全部权限以及r运行权限

chmod 770 /usr/lib/nagios/plugins/check_mongodb.py

chown -R nagios.nagios /usr/lib/nagios/plugins/check_mongodb.py

错误2:

监控界面Status Information一栏出现 No module named pymongo报错提示信息:

出现这个提示是由于须要安装pymongo模块,运行easy_install pymongo命令安装就可以。例如以下所看到的:

[root@wgq objects]# easy_install pymongo

Searching for pymongo

Reading http://pypi.python.org/simple/pymongo/

Best match: pymongo 2.7.2

......

zip_safe flag not set; analyzing archive contents...

Adding pymongo 2.7.2 to easy-install.pth file

Installed /usr/lib/python2.6/site-packages/pymongo-2.7.2-py2.6-linux-x86_64.egg

Processing dependencies for pymongo

Finished processing dependencies for pymongo

Nagios监控mongodb分片集群服务实战----------------------------------------------------------------------------------------------------------------

<版权全部,文章同意转载,但必须以链接方式注明源地址,否则追究法律责任!>
原博客地址:http://blog.itpub.net/26230597/viewspace-1293589/
原作者:黄杉 (mchdba)

Nagios监控mongodb分片集群服务实战----------------------------------------------------------------------------------------------------------------

參考文章:https://github.com/mzupan/nagios-plugin-mongodb/blob/master/README.md