mongodb 的 cpu 占用一直很高,长期保持在150%。准确的说是cpu时间片的占用,所用的服务器是4核的物理机,cpu占用在30%到40%之间,不知道这样是否正常。
服务读写都不是特别高
PID USER PR NI VIRT RES SHR S %CPU %MEM TIME+ COMMAND
1025 mongodb 20 0 7632304 340452 291908 S 157.8 4.2 87414:58 mongod
insert query update delete getmore command flushes mapped vsize res faults qr|qw ar|aw netIn netOut conn time
*0 *0 *0 *0 0 26181|0 0 3.5G 7.3G 334.0M 0 0|0 0|0 3m 2m 28 18:20:00
*0 *0 *0 *0 0 22740|0 0 3.5G 7.3G 334.0M 0 0|0 0|0 2m 1m 28 18:20:01
*0 *0 *0 *0 0 19667|0 1 3.5G 7.3G 334.0M 0 0|0 0|0 2m 1m 28 18:20:02
*0 *0 *0 *0 0 19194|0 0 3.5G 7.3G 334.0M 0 0|0 0|0 2m 1m 28 18:20:03
*0 *0 *0 *0 0 19212|0 0 3.5G 7.3G 334.0M 0 0|0 1|0 2m 1m 28 18:20:04
*0 *0 *0 *0 0 19168|0 0 3.5G 7.3G 334.0M 0 0|0 1|0 2m 1m 28 18:20:05
*0 *0 *0 *0 0 19205|0 0 3.5G 7.3G 334.0M 0 0|0 0|0 2m 1m 28 18:20:06
*0 *0 *0 *0 0 19207|0 0 3.5G 7.3G 334.0M 0 0|0 1|0 2m 1m 28 18:20:07
*0 *0 *0 *0 0 19218|0 0 3.5G 7.3G 334.0M 0 0|0 0|0 2m 1m 28 18:20:08
*0 *0 *0 *0 0 19206|0 0 3.5G 7.3G 334.0M 0 0|0 1|0 2m 1m 28 18:20:09
ns total read write 2015-09-16T18:21:42+08:00
log_inst.log_inst_2015_09_16 185ms 185ms 0ms
log_info.log_info_2015_09_16 164ms 164ms 0ms
log_data.log_data_2015_09_16 163ms 163ms 0ms
pprt.pprt_sub 130ms 130ms 0ms
pprt.pprt_hub 128ms 128ms 0ms
admin.system.roles 0ms 0ms 0ms
admin.system.version 0ms 0ms 0ms
local.startup_log 0ms 0ms 0ms
local.system.indexes 0ms 0ms 0ms
local.system.namespaces 0ms 0ms 0ms
曾经蜡笔没有小新2017-04-28 09:07:26
Use iostat to check whether there is a problem with the system I/O.
怪我咯2017-04-28 09:07:26
It should be that the index is missing
Look at the mongo logs and find the queries with many and slow queries
Create the index accordingly