What zero-downtime upgrades actually require
A field guide to sequencing control-plane, storage, and workload changes without turning maintenance into an outage.
Local previewField notes / Latest
What production is teaching us.
Engineering notes from operating open infrastructure: the failures, design decisions, and upstream work that make open infrastructure better.
Browse all field notes
Designing Ceph failure domains for the failures you really have
Why rack diagrams, recovery traffic, and operational ownership belong in the same design review.
Local preview
Upstream first is an operating model, not a slogan
How production feedback becomes a smaller patch queue, healthier upstream projects, and fewer private forks.
Local preview