Website Performance Timing Metrics

9/24/2019

This post introduces Cloudflare's Browser Insights product, which leverages the browser's Performance API (specifically Navigation Timing) to collect and analyze real user performance metrics. It details how the JavaScript beacon injects into web pages to gather data on DNS lookup, TCP connection, request, response, and processing times, presenting this aggregated data in the Cloudflare dashboard. The post also outlines future plans to incorporate Resource Timing and Paint Timing metrics, JavaScript error tracking, and A/B performance measurement.

9/24/2019

Introduced Browser Insights, a new tool for Real User Monitoring (RUM) that measures website performance from the perspective of end-users. It works by injecting a JavaScript snippet that uses the browser's Performance API to collect timing information. The tool provides request-level and page-level metrics, and allows filtering by dimensions like URL and Country. Future plans include more metrics, subresource analytics, A/B testing integration, error collection, alerting, and AI-powered insights.

10/17/2018

This post details the timing measurements provided by cURL and Chrome, explaining what each metric represents (e.g., time_namelookup, time_connect, time_appconnect, time_starttransfer, Stalled, Initial connection, Request sent). It illustrates these timings with diagrams against HTTP over TLS 1.2 connections and discusses how to interpret them to estimate server processing time versus network latency. The post concludes by questioning the sufficiency of TTFB for reflecting real user experience and hints at future discussions on measuring page usefulness.

7/5/2012

This post argues that Time To First Byte (TTFB) is a misleading metric for end-user experience. It demonstrates through experiments with a custom Go server and analysis of WebPageTest and Gomez that TTFB often measures the first byte of the HTTP response headers, not the first byte of the page content. It also shows how gzip compression, while improving total download time, can negatively impact TTFB. The post concludes that TTFB is only useful as a trend measured at the server and that Cloudflare focuses on optimizing the real end-user page visibility time.