2 posts tagged with "redis"

This week Kahuna crossed a line I did not expect to cross this year. A single node served 290k get requests per second for ephemeral keys. On the same machine, with the same number of clients, Valkey 9.1 served 247k plain GET requests per second.

The rate limiter is the number I care about more. Kahuna ran the fixed-window counter script from the rate-limiting recipe at about 200k requests per second. Valkey ran the same counter as a Lua script at 161k with EVAL and 175k with EVALSHA.

Before this work the same rate limiter ran at 84k. Nothing about the storage engine changed. What changed is how requests travel over the wire, and how a script that touches one key runs inside the node.

Last Sunday, I was having lunch with a friend and talking about Kahuna, CamusDB, and all the time I've been putting into these projects lately. He didn't really understand why I would build Kahuna when most of what it does could probably be achieved with some combination of Redis and Postgres.

My explanation may not have been very convincing, and I understand why. Every business has a different tolerance for durability, availability, and consistency. Not every business operates 24/7, and not every business suffers significantly if its systems are down for a few minutes or even a few hours. In many operations, problems and mistakes can be fixed manually by people, or sometimes with an apology to the customer.

My story is very different. For some reason, I've spent almost my entire career working in industries that operate 24/7: airline reservations, hospitality, and video games. There is always a customer or user somewhere interacting with the system, whether it's just a few people or hundreds of thousands at the same time. That changed the way my brain works and the kinds of failure modes I instinctively try to avoid.

Building systems where performance is high and consistency is non-negotiable gradually became part of my DNA.