Load really high on Proxmox 4

[6lex]

Hello,

I notice a very high load constant on a server proxmox (OVH) : load average: 7,55

This is not normal because there is not a lot of CT...

is there a solution to optimize proxmox for not having a load so high constantly?

Serveur features :
128Gio RAM
Intel(R) Xeon(R) CPU E5-1650 v4 @ 3.60GHz 12core
SATAx2Tio

root@prox:~# pct list
VMID Status Lock Name
202 running a
203 running b
204 running c
205 running d
206 running e
207 running f
208 running g

root@prox:~# vmstat -SM 1
procs -----------memory---------- ---swap-- -----io---- -system-- ------cpu-----
r b swpd free buff cache si so bi bo in cs us sy id wa st
0 0 68 2225 4334 112242 0 0 17 124 1 0 5 1 87 8 0
1 0 68 2206 4334 112242 0 0 0 44 716 2235 3 0 96 0 0
1 0 68 2223 4334 112242 0 0 0 16 608 3268 3 0 97 0 0
0 0 68 2223 4334 112242 0 0 0 248 533 950 1 0 99 0 0
0 0 68 2222 4334 112242 0 0 0 796 858 1523 2 0 90 8 0
0 0 68 2222 4334 112242 0 0 0 84 748 1195 2 0 96 2 0
0 2 68 2207 4334 112242 0 0 0 700 1110 2856 4 1 86 8 0
1 0 68 2187 4334 112242 0 0 0 308 944 2221 4 0 90 6 0
0 0 68 2191 4334 112242 0 0 0 0 634 1169 3 0 97 0 0
0 0 68 2158 4334 112242 0 0 0 188 908 1956 5 0 91 3 0

root@prox:~# pveperf /var/lib/vz
CPU BOGOMIPS: 86393.64
REGEX/SECOND: 2942722
HD SIZE: 1809.01 GB (/dev/mapper/pve-data)
BUFFERED READS: 73.54 MB/sec
AVERAGE SEEK TIME: 61.61 ms
FSYNCS/SECOND: 11.70
DNS EXT: 19.12 ms
DNS INT: 10.65 ms (ip-149-202-201.eu)

root@prox:~# uptime
14:09:15 up 31 days, 15:20, 1 user, load average: 7,55, 3,45, 3,09

root@prox:~# cat /etc/fstab
# <file system> <mount point> <type> <options> <dump> <pass>
/dev/md2 / ext4 errors=remount-ro 0 1
/dev/pve/data /var/lib/vz ext4 defaults 1 2
/dev/sda3 swap swap defaults 0 0
/dev/sdb3 swap swap defaults 0 0
proc /proc proc defaults 0 0
sysfs /sys sysfs defaults 0 0

root@prox:~# pveversion
pve-manager/4.4-22/2728f613 (running kernel: 4.4.98-6-pve)

tx

 

[LnxBil]

is there a solution to optimize proxmox for not having a load so high constantly?

Yes, not running so much :-D

FSYNCS/SECOND: 11.70

Your fsyncs are really, really low. It it right that you run your configuration with the unsupported mdadm-based software raid? Are there problems in /proc/mdstat?

And in general: Please use CODE-Tags, the output is very hard to read otherwise.