A debate in the research community has buzzed in the background for years: should large-scale Internet services be centralized or decentralized? Now-common centralized cloud and web services have downsides---user lock-in and loss of privacy and data control---that are increasingly apparent. However, their decentralized counterparts have struggled to gain adoption, suffer from their own problems of scalability and trust, and eventually may result in the exact same lock-in they intended to prevent. In this paper, we explore the design of a pluralist cloud architecture, Stencil, one that can serve as a narrow waist for user-facing services such as social media. We aim to enable pluralism via a unifying set of abstractions that support migration from one service to a competing service. We find that migrating linked data introduces many challenges in both source and destination services as links are severed. We show how Stencil enables correct and efficient data migration between services, how it supports the deployment of new services, and how Stencil could be incrementally deployed.

翻译：研究界多年来一直在争论:如果大规模互联网服务是集中化还是分散化的呢?现在的中央云和网络服务有越来越明显的下层-用户锁住和失去隐私和数据控制。然而,分散化的对口部门在争取被采纳方面挣扎不已,遭受着其自身的缩放和信任问题,最终可能导致他们想要防止的完全一样的锁定。在本文中,我们探讨了多元云结构的设计,即斯滕西尔,它可以作为社交媒体等用户美化服务的窄腰。我们的目标是通过一套统一的抽象概念,实现多元化,支持从一个服务向竞争性服务迁移。我们发现,随着连接的断开,迁移链接的数据在源服务和目的地服务中都带来了许多挑战。我们展示了Stencil如何在服务之间进行正确而有效的数据迁移,它如何支持新服务的部署,以及Stencil是如何逐步部署的。