自定义nagios监控脚本画图不连续

chengchow

最近在给公司做个监控，用nagios监控交换机是H3C 5120S的，监控脚本自己写的
发现个问题，所有通过这个脚本监控的数据，rrdtool画出来的图是不连续的，
下面是其中内存监控模块的写法

1. 
   
2. check_mem(){
   
3.     MEM_USE=`$SNMP_WALK -v$SNMP_VERSION -c $SNMP_COMMUNITY $ARG_HOST $SNMP_MEM_OID | awk '{print $NF}'`
   
4.     if [ $MEM_USE -le $ARG_WARN ];then
   
5.         echo "`echo $MEM_USE | awk '{printf "OK - The MEM use: %-0s%\n",$0}'` | mem_use=$MEM_USE;80;90;0;100; "
   
6.         exit $STAT_OK
   
7.     elif [ $MEM_USE -le $ARG_CRIT ];then
   
8.         echo "`echo $MEM_USE | awk '{printf "WARNING - The MEM use: %-0s%\n",$0}'` | mem_use=$MEM_USE;80;90;0;100; "
   
9.         exit $STAT_WARNING
   
10.     else
    
11.         echo "`echo $MEM_USE | awk '{printf "CRITICAL - The MEM use: %-0s%\n",$0}'` | mem_use=$MEM_USE;80;90;0;100 "
    
12.         exit $STAT_CRITICAL
    
13.     fi
    
14. }
    
15. 
    

复制代码

请大家帮忙分析下，什么问题造成的！

chengchow

如果需要提供更多信息，请留贴说明！谢谢！

chengchow

要沉了

qq5910225

grep 'TIMEOUT:' /usr/local/pnp4nagios/var/perfdata.log
看看超时多不多，还有就是服务监控项目有多少？

zl624867243

13年注册 徽章居然这么多

chengchow

回复 6# zl624867243
去年上的多，基本白天都在线

chengchow

回复 5# qq5910225
监控服务大约400个
你说的我也想到了，我将npcd获取数据时间从15改成30，没多大效果
nagios.cfg中perdata也改了30

   

chengchow

回复 5# qq5910225
这是nagios.cfg 配置
log_file=/server/website/wwwroot/nagios/var/nagios.log
cfg_file=/server/website/wwwroot/nagios/etc/objects/commands.cfg
cfg_file=/server/website/wwwroot/nagios/etc/objects/contacts.cfg
cfg_file=/server/website/wwwroot/nagios/etc/objects/timeperiods.cfg
cfg_file=/server/website/wwwroot/nagios/etc/objects/templates.cfg
cfg_file=/server/website/wwwroot/nagios/etc/objects/hostgroups.cfg
cfg_file=/server/website/wwwroot/nagios/etc/objects/servicegroups.cfg
cfg_dir=/server/website/wwwroot/nagios/etc/servers/linux
cfg_dir=/server/website/wwwroot/nagios/etc/servers/windows
cfg_dir=/server/website/wwwroot/nagios/etc/networks/switches
cfg_dir=/server/website/wwwroot/nagios/etc/networks/virtualgw
object_cache_file=/server/website/wwwroot/nagios/var/objects.cache
precached_object_file=/server/website/wwwroot/nagios/var/objects.precache
resource_file=/server/website/wwwroot/nagios/etc/resource.cfg
status_file=/server/website/wwwroot/nagios/var/status.dat
status_update_interval=5
nagios_user=www
nagios_group=www
check_external_commands=1
command_file=/server/website/wwwroot/nagios/var/rw/nagios.cmd
lock_file=/server/website/wwwroot/nagios/var/nagios.lock
temp_file=/server/website/wwwroot/nagios/var/nagios.tmp
temp_path=/tmp
event_broker_options=-1
log_rotation_method=d
log_archive_path=/server/website/wwwroot/nagios/var/archives
use_syslog=1
log_notifications=1
log_service_retries=1
log_host_retries=1
log_event_handlers=1
log_initial_states=0
log_current_states=1
log_external_commands=1
log_passive_checks=1
service_inter_check_delay_method=s
max_service_check_spread=30
service_interleave_factor=s
host_inter_check_delay_method=s
max_host_check_spread=30
max_concurrent_checks=0
check_result_reaper_frequency=10
max_check_result_reaper_time=30
check_result_path=/server/website/wwwroot/nagios/var/spool/checkresults
max_check_result_file_age=3600
cached_host_check_horizon=15
cached_service_check_horizon=15
enable_predictive_host_dependency_checks=1
enable_predictive_service_dependency_checks=1
soft_state_dependencies=0
auto_reschedule_checks=0
auto_rescheduling_interval=30
auto_rescheduling_window=180
service_check_timeout=60
host_check_timeout=30
event_handler_timeout=30
notification_timeout=30
ocsp_timeout=5
perfdata_timeout=5
retain_state_information=1
state_retention_file=/server/website/wwwroot/nagios/var/retention.dat
retention_update_interval=60
use_retained_program_state=1
use_retained_scheduling_info=1
retained_host_attribute_mask=0
retained_service_attribute_mask=0
retained_process_host_attribute_mask=0
retained_process_service_attribute_mask=0
retained_contact_host_attribute_mask=0
retained_contact_service_attribute_mask=0
interval_length=60
check_for_updates=1
bare_update_check=0
use_aggressive_host_checking=0
execute_service_checks=1
accept_passive_service_checks=1
execute_host_checks=1
accept_passive_host_checks=1
enable_notifications=1
enable_event_handlers=1
obsess_over_services=0
obsess_over_hosts=0
translate_passive_host_checks=0
passive_host_checks_are_soft=0
check_for_orphaned_services=1
check_for_orphaned_hosts=1
check_service_freshness=1
service_freshness_check_interval=60
service_check_timeout_state=c
check_host_freshness=0
host_freshness_check_interval=60
additional_freshness_latency=15
enable_flap_detection=1
low_service_flap_threshold=5.0
high_service_flap_threshold=20.0
low_host_flap_threshold=5.0
high_host_flap_threshold=20.0
date_format=us
illegal_object_name_chars=`~!$%^&*|'"<>?,()=
illegal_macro_output_chars=`~$&|'"<>
use_regexp_matching=0
use_true_regexp_matching=0
admin_email=www@localhost
admin_pager=pagewww@localhost
daemon_dumps_core=0
use_large_installation_tweaks=0
enable_environment_macros=0
debug_level=-1
debug_verbosity=1
debug_file=/server/website/wwwroot/nagios/var/nagios.debug
max_debug_file_size=1000000
allow_empty_hostgroup_assignment=0
process_performance_data=1
service_perfdata_command=process-service-perfdata-file
host_perfdata_command=process-host-perfdata-file
service_perfdata_file=/server/website/wwwroot/pnp4nagios/var/service-perfdata
service_perfdata_file_template=DATATYPE::SERVICEPERFDATA\tTIMET:TIMET$\tHOSTNAME:HOSTNAME$\tSERVICEDESC:SERVICEDESC$\tSERVICEPERFDATA:SERVICEPERFDATA$\tSERVICECHECKCOMMAND:SERVICECHECKCOMMAND$\tHOSTSTATE:HOSTSTATE$\tHOSTSTATETYPE:HOSTSTATETYPE$\tSERVICESTATE:SERVICESTATE$\tSERVICESTATETYPE:SERVICESTATETYPE$
service_perfdata_file_mode=a
service_perfdata_file_processing_interval=30
service_perfdata_file_processing_command=process-service-perfdata-file
host_perfdata_file=/server/website/wwwroot/pnp4nagios/var/host-perfdata
host_perfdata_file_template=DATATYPE::HOSTPERFDATA\tTIMET:TIMET$\tHOSTNAME::$HOSTNAME$\tHOSTPERFDATA::$HOSTPERFDATA$\tHOSTCHECKCOMMAND::$HOSTCHECKCOMMAND$\tHOSTSTATE::$HOSTSTATE$\tHOSTSTATETYPE::$HOSTSTATETYPE$
host_perfdata_file_mode=a
host_perfdata_file_processing_interval=30
host_perfdata_file_processing_command=process-host-perfdata-file
event_broker_options=-1 # minimum 4+8=12

   

chengchow

NPCD.CFG配置
user = www
group = www
log_type = file
log_file = /server/website/wwwroot/nagios/var/npcd.log
max_logfile_size = 10485760
log_level = -1
perfdata_spool_dir = /server/website/wwwroot/pnp4nagios/var/spool
perfdata_file_run_cmd = /server/website/wwwroot/pnp4nagios/libexec/process_perfdata.pl
perfdata_file_run_cmd_args = --bulk
identify_npcd = 1
npcd_max_threads = 8
sleep_time = 30
load_threshold = 0.0
pid_file=/var/run/npcd.pid
perfdata_file = /server/website/wwwroot/pnp4nagios/var/perfdata.dump
perfdata_spool_filename = perfdata
perfdata_file_processing_interval = 30

chengchow

npcd debug信息
[root@192 var]# tail -20 npcd.log
[06-17-2015 16:35:36] NPCD: Found 2 files in /server/website/wwwroot/pnp4nagios/var/spool
[06-17-2015 16:35:36] NPCD: ThreadCounter 0/8 File is .
[06-17-2015 16:35:36] NPCD: ThreadCounter 0/8 File is ..
[06-17-2015 16:35:36] NPCD: No more files to process... waiting for 30 seconds
[06-17-2015 16:36:06] NPCD: Found 2 files in /server/website/wwwroot/pnp4nagios/var/spool
[06-17-2015 16:36:06] NPCD: ThreadCounter 0/8 File is .
[06-17-2015 16:36:06] NPCD: ThreadCounter 0/8 File is ..
[06-17-2015 16:36:06] NPCD: No more files to process... waiting for 30 seconds
[06-17-2015 16:36:36] NPCD: Found 2 files in /server/website/wwwroot/pnp4nagios/var/spool
[06-17-2015 16:36:36] NPCD: ThreadCounter 0/8 File is .
[06-17-2015 16:36:36] NPCD: ThreadCounter 0/8 File is ..
[06-17-2015 16:36:36] NPCD: No more files to process... waiting for 30 seconds
[06-17-2015 16:37:06] NPCD: Found 2 files in /server/website/wwwroot/pnp4nagios/var/spool
[06-17-2015 16:37:06] NPCD: ThreadCounter 0/8 File is .
[06-17-2015 16:37:06] NPCD: ThreadCounter 0/8 File is ..
[06-17-2015 16:37:06] NPCD: No more files to process... waiting for 30 seconds
[06-17-2015 16:37:36] NPCD: Found 2 files in /server/website/wwwroot/pnp4nagios/var/spool
[06-17-2015 16:37:36] NPCD: ThreadCounter 0/8 File is .
[06-17-2015 16:37:36] NPCD: ThreadCounter 0/8 File is ..
[06-17-2015 16:37:36] NPCD: No more files to process... waiting for 30 seconds