what we learned from load-testing our own edge to failure sounds like a narrow topic. It turns out to touch almost every part of how an edge network behaves under attack.
The economics behind it
A booter service rents out a 100 Gbps attack for less than the price of a pizza. Defending against it with bandwidth alone is a race you lose. Defending against it by making each malicious request cost more than it earns is a race you win.
This is the entire idea behind never metering attack traffic: our costs scale with filtering, not with your invoice.
What we got wrong
Our first version challenged too eagerly on mobile networks, where thousands of real users share a handful of carrier-grade NAT addresses. Reputation that is shared is reputation that is noisy.
We now weight fingerprint consistency and session behaviour far more heavily than IP reputation for traffic from known mobile carrier ranges.
Lessons for your own runbook
Know who can change DNS at two in the morning. Know your origin IPs and who can rotate them. Know which routes are expensive, and have a rate limit ready for each of them.
Most outages during attacks are not caused by the attack itself but by rushed changes made while under pressure.
What actually happens during a flood
The first thing to fail during a layer 7 flood is almost never bandwidth. It is connection slots, worker processes or database connections on the origin — resources measured in hundreds or thousands, not gigabits. An attacker who can make each request expensive only needs a few thousand requests per second.
That is why we score requests before they are proxied. By the time a request reaches your origin, it has been attributed to a client, compared against that client’s history and weighed against the current load on the route it targets.
Observability first
Every mitigation decision is logged with its reasons, and every log line can be traced to the rule and score components that produced it. When a customer asks why a request was challenged, the answer is a link, not a guess.
Logs stream to the customer’s SIEM within seconds, which also means their security team sees attacks in the same tools they use for everything else.
Latency budget
Our budget for the whole filtering pipeline is one millisecond at the 99th percentile. Anything that cannot be decided within that budget runs asynchronously and influences the next request from the same client, not the current one.
That constraint shapes everything: data structures, where state lives and which signals we are willing to compute inline.
The numbers
Across the last quarter, 71% of challenged clients never attempted a solution, 24% solved one challenge and then behaved normally, and 5% solved challenges repeatedly while continuing to attack — the last group is where analysts spend their time.
Median added latency for legitimate visitors that were challenged was 280 ms on desktop and 410 ms on mid-range Android devices.
As always, questions and corrections are welcome at [email protected].
Would love a follow-up on how you handle HTTP/3 fingerprinting.
The billing model is what got our finance team on board, honestly.
Our auditors asked for exactly this kind of incident evidence under DORA.
Carpet bombing is nasty. Good to see a clear explanation of it.