A rate limiter that works on a single process is easy. A rate limiter that works when the service behind
Continue readingRate Limiting Beyond One Server: Token Buckets, Sliding Windows, and Redis
Every composite literal in Go looks like a heap allocation. Every new in Java looks like a heap allocation. In
Continue readingEscape Analysis: Why Your Allocation Never Lands on the Heap
Traces are the most expensive observability signal you collect. A single request through a microservice stack can produce hundreds of
Continue readingTail-Based Sampling: Paying Only for the Traces Worth Keeping
Generating text from a large language model is an inherently serial process. The model produces one token, appends it to
Pagination looks like the least interesting problem in backend engineering — until the page that took 30 ms at depth
Continue readingPagination at Depth: Why OFFSET Falls Over and How to Build Cursors That Don’t
Ask an inference server to answer one question and you get one GPU doing something odd: running a matrix multiplication
Continue readingContinuous Batching: The Scheduling Model Behind Every LLM Serving Stack
Every slow query investigation eventually arrives at the same place: the EXPLAIN output. It is the single most information-dense tool
Continue readingReading the Plan: What EXPLAIN ANALYZE Is Actually Telling You
When people picture a software supply chain attack, they usually imagine malicious code sneaking into a dependency. In practice, most
Continue readingYour Build Pipeline Is the Attack Surface: Practical Software Supply Chain Defense
Every conversation with a chatbot hides a growing accounting problem. Each token the model generates must attend to every token
Continue readingThe KV Cache: The Memory Bill Behind Every Token Your Model Generates
Most SLO programs die the same way. A team writes “99.9% availability” on a slide, everyone nods, and six months
Continue readingError Budgets in Practice: Burn-Rate Alerts That Fire When It Matters