How we cut anycast failover to under a second
When an edge location fails, BGP alone can take tens of seconds to move traffic. Here is how we combined BFD, pre-computed withdrawals and health-driven route maps to get it under one second.
Cache.bz Engineering
How we build and run a global content delivery network: networking, performance, security and the occasional post-mortem.
Purging by cache tag at 150 ms worldwide
Cache tags let publishers purge every page that mentions an article in one call. Making that fast across 38 locations meant rethinking how we index cached objects.
AVIF at the edge: smaller images without the CPU bill
AVIF images are often 30% smaller than WebP, but encoding them is expensive. We share how we made on-the-fly AVIF practical.
Post-mortem: elevated purge latency on 28 October
For 26 minutes, purges took up to 40 seconds to reach every location. Here is what happened and what we changed.
Why we still do not enable TLS 1.3 0-RTT by default
Zero round-trip resumption shaves a full round trip off repeat visits, but it comes with replay risks. Here is how we think about the trade-off.
Origin shield: the most boring feature that saves the most money
A shield tier sounds unglamorous, but for many customers it removes over half of the remaining origin traffic. A look at why.