Question

Can ScyllaDB cluster be deployed to DO without performance bottleneck?

According to ScyllaDB hardware requirements it needs network interface speed of 10 - 56 GB/s for production work loads, but as far as I know currently all droplets have 2 GB/s network interfaces which is too slow for ScyllaDB production requirements.

There is already request to support high bandwidth network interfaces here.

Is there any way we can overcome this network interface limitation on DO? Does droplets like CPU / memory / storage optimized have high bandwidth network interfaces? If so how much?


Submit an answer
Answer a question...

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!

Sign In or Sign Up to Answer

These answers are provided by our Community. If you find them useful, show some love by clicking the heart. If you run into issues leave a comment, or add your own answer to help others.

Chris Shih
DigitalOcean Employee
DigitalOcean Employee badge
February 8, 2021
Accepted Answer

Hi! I’m honestly am not very familiar with ScyllaDB, but do know that our network speed is 2 GB/s for both Basic droplets and Dedicated droplets (General Purpose, CPU optimized, Mem optimized, Storage optimized).

Scylla can run with lower requirements, it depends on the workload and the size of your droplet. A small VM can be just fine with 2 GB/s. Always use the grafana monitoring stack and you can observe the network utilization and check it isn’t the bottleneck