Hello,
I’m a bit astonished by the differences between CPU usage in unix top command and CPU usage in docker stats. I know that docker stats doesn’t count CPU usage of docker daemon itself, but the difference is so important.
docker stats
CONTAINER ID NAME CPU % MEM USAGE / LIMIT MEM % NET I/O BLOCK I/O PIDS
980f8197b7a4 traefik-proxy 1.50% 19.07MiB / 3.858GiB 0.48% 126MB / 130MB 19.4MB / 81.9kB 17
bbdb85d87e19 postgres_ext 0.79% 3.406MiB / 3.858GiB 0.09% 767kB / 1.87MB 2.25GB / 17.1MB 8
96875ed2751c container-php 0.00% 8.82MiB / 3.858GiB 0.22% 1.23MB / 652kB 30.4MB / 0B 3
4adbdc1f00d5 container-mediawiki 0.00% 18.23MiB / 3.858GiB 0.46% 3.97MB / 1.25MB 84.9MB / 2.11MB 7
5863404acfbe container-nginx 0.32% 1.734MiB / 3.858GiB 0.04% 31.6MB / 169MB 205MB / 0B 2
57f48d070804 container2-nginx 0.00% 2.441MiB / 3.858GiB 0.06% 2.26MB / 9.87MB 20.1MB / 0B 2
52794d154062 container-postgres 0.00% 1.625MiB / 3.858GiB 0.04% 1.85kB / 0B 16.8MB / 401kB 6
1def99fe7c92 container2-php 0.00% 7.527MiB / 3.858GiB 0.19% 1.61MB / 442kB 18.6MB / 0B 3
1ac98ea7b17c container-mariadb 0.03% 168.3MiB / 3.858GiB 4.26% 58kB / 1.1MB 213MB / 31.6MB 32
682c37718db0 container2-mariadb 0.01% 87.92MiB / 3.858GiB 2.23% 236kB / 4.53MB 90.7MB / 41.5MB 30
baaa39931a5c container2-postgres 0.01% 1.527MiB / 3.858GiB 0.04% 1.53kB / 0B 15.6MB / 401kB 6
d8f284c438af container2-php5 0.00% 21.37MiB / 3.858GiB 0.54% 4.62MB / 2.02MB 72.4MB / 0B 4
d8035fd66102 container-php5 0.28% 5.043MiB / 3.858GiB 0.13% 13.3MB / 4.17MB 9.31MB / 0B 4
d65050511747 container_vsftpd 0.00% 1.379MiB / 3.858GiB 0.03% 4.75kB / 2.61kB 50.1MB / 287kB 2
315ea21c999f logspout_logspout_1 0.03% 5.145MiB / 3.858GiB 0.13% 1.28kB / 422B 0B / 0B 8
So i have one traefik container, four PHP containers, 2 mariadb containers, 3 postgres containers. They don’t seem to use a lot of resources ! (RAM or CPU).
top
top - 15:39:31 up 2:57, 2 users, load average: 8,14, 7,71, 7,72
Tasks: 315 total, 1 running, 314 sleeping, 0 stopped, 0 zombie
%Cpu0 : 81,9 us, 4,7 sy, 0,0 ni, 13,0 id, 0,0 wa, 0,0 hi, 0,3 si, 0,0 st
%Cpu1 : 88,7 us, 2,3 sy, 0,0 ni, 9,0 id, 0,0 wa, 0,0 hi, 0,0 si, 0,0 st
%Cpu2 : 80,6 us, 6,0 sy, 0,0 ni, 13,0 id, 0,0 wa, 0,0 hi, 0,3 si, 0,0 st
%Cpu3 : 85,5 us, 2,7 sy, 0,0 ni, 11,4 id, 0,0 wa, 0,0 hi, 0,3 si, 0,0 st
%Cpu4 : 82,1 us, 4,4 sy, 0,0 ni, 13,5 id, 0,0 wa, 0,0 hi, 0,0 si, 0,0 st
%Cpu5 : 88,6 us, 3,0 sy, 0,0 ni, 8,4 id, 0,0 wa, 0,0 hi, 0,0 si, 0,0 st
%Cpu6 : 82,7 us, 5,4 sy, 0,0 ni, 11,9 id, 0,0 wa, 0,0 hi, 0,0 si, 0,0 st
%Cpu7 : 84,8 us, 3,7 sy, 0,0 ni, 11,1 id, 0,0 wa, 0,0 hi, 0,3 si, 0,0 st
KiB Mem : 4045612 total, 542052 free, 639448 used, 2864112 buff/cache
KiB Swap: 3149820 total, 3066508 free, 83312 used. 2914132 avail Mem
PID USER PR NI VIRT RES SHR S %CPU %MEM TIME+ COMMAND
15941 root 20 0 2050700 87724 29156 S 673,4 2,2 284:46.21 dockerd
15952 root 20 0 1534388 21188 3956 S 5,3 0,5 1:24.11 docker-containe
11372 root 20 0 66512 34776 15860 S 2,3 0,9 0:16.43 traefik
18314 mustsys+ 20 0 489776 25172 13888 S 2,0 0,6 0:05.56 docker
7 root 20 0 0 0 0 S 0,3 0,0 0:12.25 rcu_sched
477 root 20 0 0 0 0 S 0,3 0,0 0:01.08 jbd2/dm-0-8
8521 82 20 0 61404 6708 2800 S 0,3 0,2 0:01.33 php-fpm
8522 82 20 0 61404 6316 2408 S 0,3 0,2 0:01.32 php-fpm
18042 root 20 0 413704 3768 2356 S 0,3 0,1 0:07.01 docker-containe
18982 systemd+ 20 0 37456 2320 752 S 0,3 0,1 0:12.18 nginx
20254 mustsys+ 20 0 40656 3940 3160 R 0,3 0,1 0:00.05 top
1 root 20 0 37952 5108 3324 S 0,0 0,1 0:07.56 systemd
2 root 20 0 0 0 0 S 0,0 0,0 0:00.00 kthreadd
3 root 20 0 0 0 0 S 0,0 0,0 0:00.27 ksoftirqd/0
It’s a VM on a ESXi, with 8 CPU vCore and 4GB of RAM.VMWare ESXi tells me that my VM is using 11,3GHZ of CPU :’(
Do you have an idea what way cause this ?
I use last docker version (17.10).
Thank you a lot