CPU Load Average of 100 normal during cpbackup?

[feldon27]

Is a load average of 100 normal when running cpbackup manually with --force?

 

[feldon27]

How do people survive with their production environment server at 75-100 load for hours?

 

[Infopro]

Where are you seeing that load showing, exactly?

 

[feldon27]

top (once I got SSH to let me login after about 5 minutes of trying)

also

/http://***************:2082/cpsess4031622528/frontend/x3/status.html

 

[cPanelMichael]

Hello

You should verify it's the backup process and not additional processes running at the same time that is causing the server load. A good tutorial on troubleshooting the server load is at:

Troubleshooting High Load on Linux Systems

Note that you can also browse to the "Stats and Logs" tab in "WHM Home » Server Configuration » Tweak Settings" and modify the following option:

"Extra CPUs for server load"

Per it's description:

The load average above the number of CPUs at which cpuwatch, cpanellogd, backups, and CPU stats consider the system to be in a critical load state. For example, a server with 4 physical CPUs and a value of 2 in this field will be considered “critical” in these cases once the load reaches 6.

Thank you.

 

[feldon27]

I expected a RTFM response and you didn't disappoint.

 

[LDHosting]

I expected a RTFM response and you didn't disappoint.

I think Michael answered the best that he could, considering that he has no access to your server, or any idea what processes were running during the backup or what those processes were doing (is the server swapping? IO bound due to slow or failing disks/heavy write activity/MySQL usage? Is it CPU bound? etc etc etc). Michael tried to give you additional information to help you identify the cause, however, it seems that was unwanted.

To answer your questions specifically then:

"Is a load average of 100 normal when running cpbackup manually with --force?"
No.

"How do people survive with their production environment server at 75-100 load for hours?"
They don't. They typically resolve the issue that is causing the high load.

 

[feldon27]

I could respond with more sarcasm, but instead, I'll just let this picture speak for itself:

/http://www.feldoncentral.com/forumpics/cpbackup_server_load2.png

The part where server load was 80-120? That's cPBackup running. For over 3 hours, websites on the server were extremely unresponsive, if they were accessible at all.

I'll give cPanel staff credit for being quick to respond, but it's often a link to the most obvious section of the cPanel documentation, even when a very specific question has been posed.

I'm running a cPanel / CENTOS 5 server on a quad core Xeon with 4GB RAM. Load is typically between 1-3, until cpbackup starts. Then it buries the needle for 3-4 hours. This will obviously preclude me from using cpbackup as long as it is not able to throttle back. I cannot have 4 hours of downtime every week.

 

[cPanelPeter]

Hello,

Please open a support ticket using the link in my signature. One of our analysts will investigate this issue for you.
Once the ticket is opened, please post the ticket number here in this thread so we can update the thread accordingly.

 

[Zekeman]

Feldon... I am having a similar issue, did you resolve yours, if so how?