By ile
There was some back and forth on CPU provisioning here. Moisey let us understand that at times of high traffic peaks the customers could use more percentage of the CPU than they would be using on average.
What I would like to know is what is the upper limit that customers can utilize the underused CPU? Let’s say in the case of “1 logical core”. Is it up to 1 physical core perhaps? More than 1 physical core? Something else?
This textbox defaults to using Markdown to format your answer.
You can type !ref in this text area to quickly search our full set of tutorials, documentation & marketplace offerings and insert the link!
Hello,
There is no solid answer to this type of question. As discussed in the article you linked, it’s a very dynamic situation and the general rule is to “Play nice” with your neighbors. Generally you want to keep it so your monitoring is showing your CPU below 100%. Above these levels and you are using more than your assigned CPU usage and something you want to avoid. This is generally when it starts to cause issues both on the underlying hypervisor and likely within your server as well.
While the occasional spike isn’t generally harmful, continued use will cause problems for everyone. In the end though there is no real solid value because it’s an environment that doesn’t really provide such solid numbers on the upper and lower limits.
Become a contributor for community
Get paid to write technical tutorials and select a tech-focused charity to receive a matching donation.
DigitalOcean Documentation
Full documentation for every DigitalOcean product.
Resources for startups and SMBs
The Wave has everything you need to know about building a business, from raising funding to marketing your product.
The developer cloud
Scale up as you grow — whether you're running one virtual machine or ten thousand.
Get started for free
Sign up and get $200 in credit for your first 60 days with DigitalOcean.*
*This promotional offer applies to new accounts only.