We want it to be easy to figure out what’s happening with infrastructure and operations! So, you can read about our progress last week over on the infra-log
Here’s a summary:
- We had three incidents that impacted subsets of users. One of these was related to tokens, and two impacted specific edges of our network.
- We began rolling out a corrosion upgrade
- We worked towards a more complete picture of inter-region network traffic
- We continued to migrate Fly Machines from old servers while making improvements to the tooling we’re using
- We improved the tracking of deployments to our internal components
- We discovered and fixed some I/O performance issues in Mumbai
- We published a writeup that provided (me) some closure around recent NATS (on which we’ve built our log-shipping system) instability.