August 19, 2021
Here is the link.
ABSTRACT
This book describes warehouse-scale computers (WSCs), the computing platforms that power cloud computing and all the great web services we use every day. It discusses how these new systems treat the datacenter itself as one massive computer designed at warehouse scale, with hardware and software working in concert to deliver good levels of internet service performance. The book details the architecture of WSCs and covers the main factors influencing their design, operation, and cost structure, and the characteristics of their software base. Each chapter contains multiple real-world examples, including detailed case studies and previously unpublished details of the infrastructure used to power Google’s online services. Targeted at the architects and programmers of today’s WSCs, this book provides a great foundation for those looking to innovate in this fascinating and important area, but the material will also be broadly interesting to those who just want to understand the infrastructure powering the internet.
Introduction
The ARPANET is nearly 50 years old, and the World Wide Web is close to 3 decades old. Yet the internet technologies that emerged from these two remarkable milestones continue to transform industries and cultures today and show no signs of slowing down. The widespread use of such popular internet services as web-based email, search, social networks, online maps, and video streaming, plus the increased worldwide availability of high-speed connectivity, have accelerated a trend toward server-side or “cloud” computing. With such trends now embraced by mainline enterprise workloads, the cloud computing market is projected to reach close to half a trillion dollars in the next few years [Col17].
In the last few decades, computing and storage have moved from PC-like clients to smaller, often mobile, devices, combined with large internet services. While early internet services were mostly informational, today, many web applications offer services that previously resided in the client, including email, photo and video storage, and office applications. Increasingly, traditional enterprise workloads are also shifting to cloud computing. This shift is driven not only by the need for user experience improvements, such as ease of management (no configuration or backups needed) and ubiquity of access, but also by the advantages it provides to vendors. Specifically, software as a service allows faster application development because it is simpler for software vendors to make changes and improvements. Instead of updating many millions of clients (with a myriad of peculiar hardware and software configurations), vendors need to only coordinate improvements and fixes inside their data centers and can restrict their hardware deployment to a few well-tested configurations. Similarly, server-side computing allows for faster introduction of new hardware innovations, such as accelerators that can be encapsulated under well-defined interfaces and APIs. Moreover, data center economics allow many application services to run at a low cost per user. For example, servers may be shared among thousands of active users (and many more inactive ones), resulting in better utilization. Similarly, the computation and storage itself may become cheaper in a shared service (for example, an email attachment received by multiple users can be stored once rather than many times, or a video can be converted to a client format once and streamed to multiple devices). Finally, servers and storage in a data center can be easier to manage than the desktop or laptop equivalent because they are under control of a single, knowledgeable entity. Security, in particular, is an important differentiator for the cloud.
Some workloads require so much computing capability that they are a more natural fit for a massive computing infrastructure than for client-side computing. Search services (web, images, and so on) are a prime example of this class of workloads, but applications such as language translation
No comments:
Post a Comment