Examples of Resource Estimation

Use a hypothetical Twitter-like service to work through server count, storage, and bandwidth. The objective is to trace each result back to its assumptions, compare average and concentrated traffic, and identify which values require measurement.

Introduction

We’ll now apply these resource estimation techniques to a Twitter-like service. Using baseline assumptions, we’ll estimate the required number of servers, storage capacity, and network bandwidth.

Number of servers required

These are hypothetical inputs for the exercise, not measured Twitter traffic or a deployment recommendation:

Assumptions:

• 500 million (M) daily active users (DAU)

• Average of 20 requests per user per day

• Single server capacity (64 cores): 64,000 requests per second (RPS)

Estimating the Number of Servers

| Total servers required | 2 | Ideal CPU-only lower bound |