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，刚开始本人这里没有安装gitpub环境，找网友帮忙下载的，之后上传到了Linux公社资源网站，新的下载地址为：
------------------------------------------分割线------------------------------------------
具体下载目录在 /2014年资料/10月/10日/Nagios监控MongoDB分片集群服务实战
------------------------------------------分割线------------------------------------------
在RHEL5.3上配置基本的Nagios系统(使用Nagios-3.1.2)
CentOS 5.5+Nginx+Nagios监控端和被控端安装配置指南
Ubuntu 13.10 Server 安装 Nagios Core 网络监控运用
2，添加新的mongodb监控命令
因为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，所以这里只需要在原来的基础上添加mongodb命令和服务即可。Nagios监控mysql请参考： 以及 。所以这里需要添加的mongodb监控命令如下所示：
[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，添加mongodb监控服务
mongodb的服务也需要单独重新添加，如下所示：
#检测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复制完成的百分比率，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，如果lock time占据mongo运行时间的5%就普通报警，如果超过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，如果超过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
#示例：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服务组列表的每一个主机，可以检查重要collection的高可用性（锁、超时、服务配置的可用性），如果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
}