hegdenu.com

how big is your future?

on Thursday, 31 October 2024 I am, of course, talking about std::future::Future.

can you help?

One thing I wanted to do as part of this post was write a small utility which would allow me to scale up different memory values independently. This would be a nice tool to interactively test assumptions about what kubernetes does when the RSS or certain page caches get larger.

how did I know?

One of our backend services was having trouble with the latency of the requests, up to such a point that it was causing instability. Basically, requests were so slow they caused the pods to timeout and get killed. We'd tracked this down to a specific type of request that required an expensive filtering operation.

so it went to production, right?

Well..., no. Or, kind of. I've skipped over some details that had nothing to do with the performance optimization. Let's fill them in. This service is made up of two parts, a front-end service (Rust) which deals with HTTP requests from end users and then forwards the request onto a back-end service (C++) which contains the indexed data.

why a new meet-up?

I like meet-ups. Or rather, I like the idea of meet-ups. Get together with a group of like-minded people. Hear interesting ideas on your common topic of interest. Ask questions directly. Socialise, meet new people, enjoy yourself. But I've always found it hard to fit them into my schedule. Bad enough when I lived in Berlin and could often walk there.