Scale up as you grow — whether you're running one virtual machine or ten thousand.

From GPU-powered inference and Kubernetes to managed databases and storage, get everything you need to build, scale, and deploy intelligent applications.

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!
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.
I’ve found similar.
After some investigation (and reading up) I think the problem is that DO’s hypervisors do not use battery backed RAID controllers [would be nice if they verified this]. This means an fsync has to pysically flush to disk which is slow even on SSDs.
I see an average of about 20ms which matches your 50/sec. However, I am measuring from within the app which requires a localhost network round trip too… and I’m actually committing real data.
In a previous incarnation I used to manage database RAID arrays and one problem is that once the battery goes (which shows up as a tiny light on the controller and happens every year or two) the performance drops away.