Part 3 of the Scaling CouchDB to 1 Million Requests Per Minute series - A config line about connection counts pinned our TCP receive window to 8,192 bytes, turning a single write into thousands of round trips.
Read more →
One of our production subnets sat at 99% IP utilization. The IPs were there, just held hostage by the VPC CNI's defaults.
Read more →
Part 2 of the Scaling CouchDB to 1 Million Requests Per Minute series - The story of how a 64 KiB pipe between CouchDB and containerd led to OOM a production node.
Read more →
The Argo CD scaling problem we only noticed after 2,000+ Applications started sharing the same GitOps monorepo.
Read more →
A post where I detail the different challenges I've faced while scaling CouchDB.
Read more →