liveBook · Manning

Edge computing

As explained in Fast by Default

Edge computing is the execution of application logic at geographically distributed locations close to users rather than only in centralized data centers.

Edge computing runs application logic at geographically distributed locations close to users instead of relying only on centralized data centers. It targets latency caused by distance, especially when one synchronous backend call adds hundreds of milliseconds to each request. section 5.3 section 5.3.2

Traditional CDN caching places copies of static files near users; edge computing extends that pattern by running application code at distributed edge locations. This distinction changes how interactive requests, not only downloads, reach users. section 5.3.2 section 5.3.2

Apply the architecture by separating delivery decisions:

  • Cache static assets with content-based filenames indefinitely, because changed content receives a new filename. section 5.3.2
  • Set dynamic-content lifetimes according to update frequency; cache HTML for minutes or hours when appropriate. section 5.3.2
  • Treat personalized API responses cautiously, often caching them briefly or not at all. section 5.3.2
  • Compare geographic distribution, team capability, operational capacity, simplicity, flexibility, and speed before moving computation outward. section 5.3

Retail rendering at the edge

A retailer serving primarily from United States data centers gave shoppers in Germany roughly 200ms of latency on every round trip. After tripling its points of presence and deploying the rendering engine in regions that previously cached only static files, it reduced Time to First Byte by about 50% for 20% of its traffic. section 5.3.2

Figure 5.7 CDN latency advantage

Use the latency comparison to distinguish nearby CDN delivery from longer trips to a centralized origin. section 5.3.2

How Fast by Default covers it

How deep it goes
Defines edge computation, contrasts it with CDN caching, and gives caching rules plus a measured deployment example.
Examples
Uses retailer rendering near German shoppers, Australian image delivery, and Fastly's global news-content purging.
What you can do after
Evaluate centralized and edge architectures, then choose caching and rendering placement using latency, personalization, and update frequency.
How it connects
Connects edge computing with backend architecture, CDN caching, rendering, latency, Time to First Byte, and geographic distribution.

Also explained in

Compare how 6 books explain edge computing →

Related concepts

This explainer was generated by Manning's knowledge graph from the text of Fast by Default. The section links point to the parts of the book it draws on.