Connection pooling to the origin: the numbers that surprised us

This post is about connection pooling to the origin: the numbers that surprised us. It started, as most of our posts do, with an incident that did not go the way we expected.

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.

Challenges beat blocks

Blocking lists go stale within minutes when attackers rotate through residential proxies. Proof-of-work does not care where a request comes from; it only cares whether the client is willing to pay the cost.

For a real browser that cost is a few hundred milliseconds, once per session. For a botnet sending a million requests a minute it is a million puzzles a minute — and at that point the attack stops being cheap.

Measuring success

We track three numbers for every incident: time to mitigation, the share of attack traffic that reached the origin, and the share of legitimate traffic that was challenged. The first should be under a second, the second under 0.1% and the third under 1%.

Those numbers go into every incident report, and they are the same numbers we are measured against in our SLA.

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 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.

What we changed

We moved the decision from a single threshold to a continuous score, added an explanation to every decision and made every rule testable against historical traffic before it goes live.

The result is fewer late-night pages for our analysts and — more importantly — fewer real users challenged by mistake.

{ "match": { "path": "/wp-login.php", "risk": ">= 34" }, "action": "challenge" }

If you run into any of this in your own environment, our SOC is happy to take a look — even if you are not a customer.