A Byzantine failure in the real world

An analysis of the Cloudflare API availability incident on 2020-11-02When we review design documents at Cloudflare, we are always on the lookout for Single Points of Failure (SPOFs). Eliminating these is a necessary step in architecting a system you can be confident in. Ironically, when you’re designing a system with…

The Story of Two Outages

Over the last two days, Cloudflare observed two events that had effects on global Internet traffic levels. Cloudflare handles approximately 10% of all Internet requests, so we have significant visibility into traffic from countries and networks across the world. On Tuesday, September 5th, the government of Togo decided to restrict…

The Story of Two Outages

Over the last two days, Cloudflare observed two events that had effects on global Internet traffic levels. Cloudflare handles approximately 10% of all Internet requests, so we have significant visibility into traffic from countries and networks across the world. On Tuesday, September 5th, the government of Togo decided to restrict…