Chapter 2. The Production Environment at Google, from the Viewpoint of an SRE

Google datacenters are very different from most conventional datacenters and small-scale server farms. These differences present both extra problems and opportunities. This chapter discusses the challenges and opportunities that characterize Google datacenters and introduces terminology that is used throughout the book.


Most of Google’s compute resources are in Google-designed datacenters with proprietary power distribution, cooling, networking, and compute hardware (see [Bar13]). Unlike “standard” colocation datacenters, the compute hardware in a Google-designed datacenter is the same across the board.1 To eliminate the confusion between server hardware and server software, we use the following terminology throughout the book:


A piece of hardware (or perhaps a VM)


A piece of software that implements a service

Machines can run any server, so we don’t dedicate specific machines to specific server programs. There’s no specific machine that runs our mail server, for example. Instead, resource allocation is handled by our cluster operating system, Borg.

We realize this use of the word server is unusual. The common use of the word conflates “binary that accepts network connection” with machine, but differentiating between the two is important when talking about computing at Google. Once you get used to our usage of server, it becomes ...

Get Site Reliability Engineering now with the O’Reilly learning platform.

O’Reilly members experience books, live events, courses curated by job role, and more from O’Reilly and nearly 200 top publishers.