Units of scale

One last thing to consider when thinking about Linux and the cloud is the scale of things. Jeff Dean, a prominent computer scientist at Google, gave a talk in 2002 about latency numbers every engineer should know based on research from Peter Norvig (https://norvig.com/21-days.html#answers), another very prominent computer scientist at Google.

These numbers have been updated and represented by many since then. The most recent numbers I could find are from Colin Scott (https://colin-scott.github.io/blog/2012/12/24/latency-trends/), a software engineer at Google, who has been guessing how the numbers change based on historical trends in computer hardware. I got the following numbers from Jonas Bonér, the creator of akka and the CTO of Lightbend, and modified the table (https://gist.github.com/jboner/2841832).

Action	Nanoseconds	Microseconds	Milliseconds
L1 cache reference	0.5 ns
L2 cache reference	7 ns
Mutex lock/unlock	25 ns		...