Cloudflare, the San Francisco-based security and performance services firm had an outage in its services which lasted an hour and 15 minutes due to an event which the company admit was their error. The outage affected traffic in 19 of its data centers. These 19 locations oversee a significant proportion of their global traffic and a change to the network configuration in those locations caused an accidental outage. The Cloudflare outage caused major disruptions across the internet including in popular sites such as Discord, Shopify, Grindr, Fitbit, and Peloton.

Recently Cloudflare converted 19 of its data centers to what they internally call Multi-Colo PoP (MCP). The problem occurred while company officials were deploying a change to the prefix advertisement policies leading to the outage. Read more about this story on our LinkedIn page