# Amazon's Distributed Computing Manifesto

DevFeed: [Amazon's Distributed Computing Manifesto](<https://devfeed.tech/articles/amazon-s-distributed-computing-manifesto-12528.md>)

Original publisher: [Read original article](<http://brooker.co.za/blog/2022/11/22/manifesto.html>)

Author: Marc Brooker

Published: 2022-11-22T00:00:00Z

Content type: article

Language: en

Sources: [Marc Brooker's](<https://devfeed.tech/sources/marc-brooker-s-blog.md>)

Topics: [distributed-systems](<https://devfeed.tech/topics/distributed-systems.md>), [service](<https://devfeed.tech/topics/service.md>), [decoupling](<https://devfeed.tech/topics/decoupling.md>), [interface](<https://devfeed.tech/topics/interface.md>), [amazon](<https://devfeed.tech/topics/amazon.md>), [Back end](<https://devfeed.tech/topics/backend.md>), [P2P](<https://devfeed.tech/topics/p2p.md>)

Tags: [amazon](<https://devfeed.tech/tags/amazon.md>), [api](<https://devfeed.tech/tags/api.md>), [architecture](<https://devfeed.tech/tags/architecture.md>), [based](<https://devfeed.tech/tags/based.md>), [business-logic](<https://devfeed.tech/tags/business-logic.md>), [data](<https://devfeed.tech/tags/data.md>), [database](<https://devfeed.tech/tags/database.md>), [distributed-computing](<https://devfeed.tech/tags/distributed-computing.md>), [distributed-system](<https://devfeed.tech/tags/distributed-system.md>), [interfaces](<https://devfeed.tech/tags/interfaces.md>), [processing](<https://devfeed.tech/tags/processing.md>)

## AI overview

Amazon's 1998 manifesto argued that direct database access tied application code to the data model, making change and distributing work difficult as the business grew. It proposed a three-tier, service-based architecture: clients call well-defined interfaces that encapsulate business logic, keeping the underlying data model private. The article emphasizes that this required a developer mindset shift from designing around database schemas to designing client-service interfaces. The manifesto also identified centralized database workflows as a scaling bottleneck and proposed distributing workflow processing so data travels to the process. The excerpt presents these ideas as historically relevant while noting that later two-tier approaches are returning; it offers no detailed evaluation of those newer systems.

## Source excerpt

Amazon's Distributed Computing Manifesto Manifesto made manifest. In the Johannesburg of 1998, I was rocking a middle parting, my friend group was abuzz about the news that there was water (and therefore monsters) on Europa, and all the cool kids were getting satellite TV at home1. Over in Seattle, the folks at Amazon.com had started to notice that their architecture was in need of rethinking. $147 million in sales in 1997, and over $600 million in 1998, were proving to be challenging to deal with. In 1998, as Werner Vogels recently shared folks at Amazon wrote a distributed computing manifesto describing the problems they were seeing and the solutions they saw to those problems. The document itself, which you can (and should!) read in full over on Werner's blog is both something of a time capsule, and surprisingly relevant to many of the systems architecture debates going on today, and the challenges that nearly all growing architectures inevitably face. From the manifesto: The applications that run the business access the database directly and have knowledge of the data model embedded in them. This means that there is a very tight coupling between the applications and the data model, and data model changes have to be accompanied by application changes even if functionality remains the same. Despite being called a distributed computing manifesto, the Amazon of 1997 was already a distributed system by any reasonable measure. The problem was one of interfaces: the data store was serving as the interface between components and concerns, leading to tight coupling between storage and business logic. The architecture was difficult to scale, not in requests per second, but to adapt to new lines of business and the rate of overall change. This approach does not scale well and makes distributing and segregating processing based on where data is located difficult since the applications are sensitive to the interdependent relationships between data elements. The proposed solu