0

I have a KVM single core VPS optimized for hosting static content running only Nginx 1.13.8 with SSD and 1GB RAM with a hosting provider on a package of 100 Mbit/s unmetered bandwidth.

OS in use is 3.10.0-693.17.1.el7.centos.plus.x86_64

The server is constantly at high load of Load average: 2.59 2.16 1.90

There's no PHP or MySQL services installed or running on this server.

lscpu shows:

Architecture:          x86_64
CPU op-mode(s):        32-bit, 64-bit
Byte Order:            Little Endian
CPU(s):                1
On-line CPU(s) list:   0
Thread(s) per core:    1
Core(s) per socket:    1
Socket(s):             1
NUMA node(s):          1
Vendor ID:             GenuineIntel
CPU family:            6
Model:                 13
Model name:            QEMU Virtual CPU version (cpu64-rhel6)
Stepping:              3
CPU MHz:               2266.746
BogoMIPS:              4533.49
Hypervisor vendor:     KVM
Virtualization type:   full
L1d cache:             32K
L1i cache:             32K
L2 cache:              4096K
NUMA node0 CPU(s):     0
Flags:                 fpu de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pse36 clflush mmx fxsr sse sse2 syscall nx lm nopl pni cx16 hypervisor lahf_lm

The average daily bandwidth usage is 40Mbit/s

The maximum memory usage at any given time is between 300MB ~ 350MB

The nginx error log is only less than 8KB per day.

Looking at the top command, nginx service constantly shows 20~30% at the CPU column, which I believe isn't too bad.

What could be the possible causes of this high server load?

Since nginx is pretty resource efficient for serving static content, I can't think of a reason that's causing the bottleneck.

I'm suspecting the host maching hosting the VPS is overloaded, will this reflect the high figures in load average?

Given this high load average stats, nginx is still serving the static content and pushing the bandwidth smoothly.

But it's making me worry about the stability.

I've tried the exact same server deployment with another hosting company on a dual-core setup and distribute the traffic using RRDNS for testing.

The resource usage is only at 0.05 ~ 0.30 at all time with same amount of memory / bandwidth consumption.

1
  • So what else is using CPU? You forgot to include the top output, or anything else that might be relevant. Mar 5, 2018 at 2:08

1 Answer 1

0

Please check the application that causes the High CPU Load by running this terminal command below:

ps -eo pcpu,pid,user,args | sort -k1 -r | head -10

Got this from this link

You may also run htop and send us your screenshots.

1
  • This command is helpful in that it lists the processes ordered by CPU usage. However, I've cancelled the VPS and don't have chance to test it out. But I did come to the conclusion it's the host machine at the hosting provider that's overloading. Even if I stop the nginx service, the load average remains high for an extended period of time. After stopping nginx, I didn't notice any other process with significant high CPU load in htop.
    – KDX
    Mar 5, 2018 at 8:51

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.