liveBook · Manning

Throughput

As explained in Grokking Concurrency

Throughput is the number of tasks a system completes or handles during a given period of time.

Think of a transport system: throughput asks how many people reach their destination in a given time, not how quickly one person travels. In computing, throughput is the number of tasks a system handles over a period of time. section 1.2

Motorcycle versus bus

A motorcycle may complete one trip faster than a bus, giving it lower latency. Yet a bus can carry many more people per hour, giving it higher throughput. Improving throughput therefore does not necessarily make each individual task finish sooner. section 1.2

Use throughput when measuring the amount of work completed:

  • Count completed tasks per unit of time. section 1.2
  • Consider concurrency when seeking more performance from multiple processing resources. section 1.2

How Grokking Concurrency covers it

How deep it goes
Defines throughput and contrasts it with latency, stopping short of implementation or optimization procedures.
Examples
Uses motorcycle and bus transportation to contrast individual travel speed with people transported per hour.
What you can do after
Evaluate/understand performance by distinguishing completed work per time from the duration of one task.
How it connects
Connects throughput to latency, concurrency, system performance, and multiprocessor architectures.

Also explained in

Compare how 20 books explain throughput →

Related concepts

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