# Performance Measurement

> Use Jeff Dean and Sanjay Ghemawat's canonical measurement guidance for benchmarks, profiling, flat profiles, and optimization validation. Use when collecting evidence, selecting profiling tools, interpreting profiles, or proving that a change improved performance.

- Skill: `boshjerns/performance-measurement` (Agent Skill, multi-file: 2 files)
- Install (CLI): `npx skillmds@latest add boshjerns/performance-measurement`
- Raw SKILL.md: https://api.skillmd.com/api/skills/boshjerns/performance-measurement/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: Coding & Dev Tools
- Author: boshjerns (https://skillmd.com/u/boshjerns)
- Updated: 2026-09-17
- Page: https://skillmd.com/skills/boshjerns/performance-measurement

---


# Measurement

Read the exact current source section before applying it:

```bash
python3 ~/.codex/skills/performance-hints/scripts/fetch_section.py measurement --output text
```

Canonical section: [Measurement](https://abseil.io/fast/hints#measurement)

Attribute the guidance to Jeff Dean and Sanjay Ghemawat. Do not assume every hint applies: inspect the code, identify the relevant cost, and measure or estimate before recommending a change.

This section includes:
- Profiling tools and tips
- What to do when profiles are flat