Skip to main content
main-content

Über dieses Buch

Traditional cloud computing and the emerging edge computing have greatly promoted the development of Internet applications. But what are the key issues in these two trends and what are the differences between them?

This book systematically introduces several key procedures in both cloud computing and edge computing scenarios, with each chapter providing a detailed description of novel design. In addition, the book also discusses a series of important findings from industry collaborations, which greatly enhance our understanding of the real system of industry. This book is not only a valuable reference resource for researchers, but also provides large-scale deployment cases for real systems in industry.

In order to gain the most benefit from this book, readers should have some the basic knowledge of computer networks.

Inhaltsverzeichnis

Frontmatter

Chapter 1. Introduction

Abstract
Data center has many features such as virtualized resource environment, modular infrastructure, automated operation and maintenance management, rapid expansion capability, efficient resource utilization, and reliable redundant backup. While edge computing has advantages in the latency due to the short distance to end users, a variety of business applications have exploded, which has placed higher demands on the basic functions and service performance of the edge servers. This book will analyze these two trends in detail. This chapter introduces the research background, content summary, key contributions, and arrangements of the remaining chapters.
Yuchao Zhang, Ke Xu

Chapter 2. A Survey of Resource Management in Cloud and Edge Computing

Abstract
This chapter is to summarize the processing of the business, starting from the service access to the data center, to the data transmission control, to the server back-end communication, and the data synchronization service support, tracking the complete service flow of the data flow. And carry out comprehensive and in-depth research work for each of these links.
Yuchao Zhang, Ke Xu

Chapter 3. A Task Scheduling Scheme in the DC Access Network

Abstract
State-of-the-art microservices are starting to get more and more attention in recent years. A broad spectrum of online interactive applications are now programmed to service chains on cloud, seeking for better system scalability and lower operation cost. Different from the conventional batch jobs, most of these applications are composed of multiple stand-alone services that communicate with each other. These step-by-step operations unavoidably introduce higher latency to the delay-sensitive chained services.
In this chapter, we aim at designing an optimization approach to reduce the latency of chained services. Specifically, presenting the measurement and analysis of chained services on Baidu’s cloud platform, our real-world trace indicates that these chained services are suffering from significantly high latency because they are mostly handled by different queues on cloud servers for multiple times. Such a unique feature, however, introduces significant challenge to optimize microservice’s overall queueing delay. To address this problem, we propose a delay-guaranteed approach to accelerate the overall queueing of chained services while obtaining fairness across all the workloads. Our real-world deployments on Baidu shows that the proposed design can successfully reduce the latency of chained services by 35% with minimal affect to other workloads.
Yuchao Zhang, Ke Xu

Chapter 4. A Cross-Layer Transport Protocol Design in the Terminal Systems of DC

Abstract
Data centers are now used as the underlying infrastructure of many modern commercial operations, powering both large Internet services and a growing number of data-intensive scientific applications. The tasks in these applications always consist of rich and complex flows which require different resources at different time slots. The existing data center scheduling frameworks are however base on either task- or flow-level metrics. This simplifies the design and deployment but hardly unleashes the potentials of obtaining low task completion time for delay-sensitive applications.
In this chapter, we show that the performance (e.g., tail and average task completion time) of existing flow-aware and task-aware network scheduling is far from being optimal. To address such a problem, we carefully examine the possibility to consider both task- and flow-level metrics together and present the design of TAFA (task-aware and flow-aware) in data center networks. This approach seamlessly combines the existing flow and task metrics together while successfully avoids their problems as flow isolation and flow indiscrimination. The evaluation result shows that TAFA can obtain a near-optimal performance and reduce over 35% task completion time for the existing data center systems.
Yuchao Zhang, Ke Xu

Chapter 5. Optimization of Container Communication in DC Back-End Servers

Abstract
Containerization has been used in many applications for isolation purposes due to its lightweight, scalable, and highly portable properties. However, to apply containerization in large-scale Internet data centers faces a big challenge. Services in data centers are always instantiated as a group of containers, which often generate heavy communication workloads and therefore resulting in inefficient communications and downgraded service performance. Although assigning the containers of the same service to the same server can reduce the communication overhead, this may cause heavily imbalanced resource utilization since containers of the same service are usually intensive to the same resource.
To reduce communication cost as well as balance the resource utilization in large-scale data centers, we further explore the container distribution issues in a real industrial environment and find that such conflict lies in two phases – container placement and container reassignment. The objective of this chapter is to address the container distribution problem in these two phases. For the container placement problem, we propose an efficient Communication Aware Worst Fit Decreasing (CA-WFD) algorithm to place a set of new containers into data centers. For the container reassignment problem, we propose a two-stage algorithm called Sweep&Search to optimize a given initial distribution of containers by migrating containers among servers. We implement the proposed algorithms in Baidu’s data centers and conduct extensive evaluations. Compared with the state-of-the-art strategies, the evaluation results show that our algorithms perform better up to 70% and increase the overall service throughput up to 90% simultaneously.
Yuchao Zhang, Ke Xu

Chapter 6. The Deployment of Large-Scale Data Synchronization System for Cross-DC Networks

Abstract
Many important cloud services require replicating massive data from one datacenter (DC) to multiple DCs. While the performance of pair-wise inter-DC data transfers has been much improved, prior solutions are insufficient to optimize bulk-data multicast, as they fail to explore the rich inter-DC overlay paths that exist in geo-distributed DCs, as well as the remaining bandwidth reserved for online traffic under fixed bandwidth separation scheme. To take advantage of these opportunities, we present BDS+, a near-optimal network system for large-scale inter-DC data replication. BDS+ is an application-level multicast overlay network with a fully centralized architecture, allowing a central controller to maintain an up-to-date global view of data delivery status of intermediate servers, in order to fully utilize the available overlay paths. Furthermore, in each overlay path, it leverages dynamic bandwidth separation to make use of the remaining available bandwidth reserved for online traffic. By constantly estimating online traffic demand and rescheduling bulk-data transfers accordingly, BDS+ can further speed up the massive data multicast. Through a pilot deployment in one of the largest online service providers and large-scale real-trace simulations, we show that BDS+ can achieve 3–5× speedup over the provider’s existing system and several well-known overlay routing baselines of static bandwidth separation. Moreover, dynamic bandwidth separation can further reduce the completion time of bulk data transfers by 1.2 to 1.3 times.
Yuchao Zhang, Ke Xu

Chapter 7. Storage Issues in the Edge

Abstract
Recent years have witnessed a rapid increase of short video traffic in content delivery network (CDN). While the video contributors change from large video studios to distributed ordinary end users, edge computing naturally matches the cache requirements from short video network. But the distributed edge caching exposes some unique characteristics: non-stationary user access pattern and temporal and spatial video popularity pattern, which severely challenge the edge caching performance. While the Quality of Experience (QoE) in traditional CDN has been much improved, prior solutions become invalid in solving the above challenges. In this chapter, we present AutoSight, a distributed edge caching system for short video network, which significantly boosts cache performance. AutoSight consists of two main components, solving the above two challenges, respectively: (i) the CoStore predictor, which solves the non-stationary and unpredictability of local access pattern, by analyzing the complex video correlations, and (ii) a caching engine Viewfinder, which solves the temporal and spatial video popularity problem by automatically adjusting future horizon according to video life span. All these inspirations and experiments are based on the real traces of more than 28 million videos with 100 million accesses from 488 servers located in 33 cities. Experiment results show that AutoSight brings significant boosts on distributed edge caching in short video network.
Yuchao Zhang, Ke Xu

Chapter 8. Computing Issues in the Edge

Abstract
Along with the development of IoT and mobile edge computing in recent years, everything can be connected into the network at anytime, resulting in quite dynamic networks with time-varying connections. Controllability has long been recognized as one of the fundamental properties of such temporal networks, which can provide valuable insights for the construction of new infrastructures, and thus is in urgent need to be explored. In this chapter, we take smart transportation as an example, first disclose the controllability problem in IoV (Internet of Vehicles) and then design a DND (driver node) algorithm based on Kalman’s rank condition to analyze the controllability of dynamic temporal network and also to calculate the minimum number of driver nodes. At last, we conduct a series of experiments to analyze the controllability of IoV network, and the results show the effects from vehicle density, speed, and connection radius on network controllability. These insights are critical for varieties of applications in the future smart connected living.
Yuchao Zhang, Ke Xu
Weitere Informationen

Premium Partner

    Bildnachweise