Commercial Data Centers Research Articles

Scalable topological forwarding and routing policies in RINA‐enabled programmable data centers

AbstractGiven the current expansion of cloud computing, the expected advent of the Internet of Things, and the requirements of future fifth‐generation network infrastructures, significantly larger pools of computational and storage resources will soon be required. This emphasizes the need for more scalable data centers that are capable of providing such an amount of resources in a cost‐effective way. A quick look into today's commercial data centers shows that they tend to rely on variations of well‐defined leaf‐spine/Clos data center network (DCN) topologies, offering low latency, ultrahigh bisectional bandwidth, and enhanced reliability against concurrent failures. However, DCNs are typically restricted by the use of the Transmission Control Protocol/Internet Protocol (TCP/IP) suite, thus suffering limited routing scalability. In this work, we study the benefits that replacing TCP/IP with the recursive internetwork architecture (RINA) can bring into commercial DCNs, focusing on forwarding and routing scalability. We quantitatively evaluate the benefits that RINA solutions can yield against those based on TCP/IP and highlight how, by deploying RINA, topological routing solutions can improve even more the efficiency of the network. To this goal, we propose a rule‐and‐exception forwarding policy tailored to the characteristics of several DCN variants, enabling fast forwarding decisions with merely neighbors' information. Upon failures, few exceptions are necessary, whose computation can also profit from the known topology. Extensive numerical results show that the proposed policy requirements depend mainly on the number of neighbors and concurrent failures in the DCN rather than its size, dramatically reducing the amount of forwarding and routing information stored at DCN nodes.

On Fair Attribution of Costs Under Peak-Based Pricing to Cloud Tenants

The costs incurred by cloud providers towards operating their data centers are often determined in large part by their peak demands. The pricing schemes currently used by cloud providers to recoup these costs from their tenants, however, do not distinguish tenants based on their contributions to the cloud’s overall peak demand. Using the concrete example of peak-based pricing as employed by many electric utility companies, we show that this “gap” may lead to unfair attribution of costs to the tenants. Simple enhancements of existing cloud pricing (e.g., analogous to the coincident peak pricing (CPP) used by some electric utilities) do not adequately address these shortcomings and suffer from short-term unfairness and undesirable oscillatory price-vs.-demand relationships offered to tenants. To overcome these shortcomings, we define an alternative pricing scheme to more fairly distribute a cloud’s costs among its tenants. We demonstrate the efficacy of our scheme under price-sensitive tenant demand response using a combination of (i) extensive empirical evaluation with recent workloads from commercial data centers operated by IBM and (ii) analytical [modeling] through non-cooperative game theory for a special case of tenant demand model.

Efficient Multicast Delivery for Data Redundancy Minimization Over Wireless Data Centers

With the explosive growth of cloud-based services, large-scale data centers are widely built for housing critical computing resources to gain significant economic benefits. In data centers, the cloud services are generally accomplished by multicast-based group communications. Recently, many well-known industries, such as Microsoft, Google, and IBM, adopt high-speed wireless technologies to augment network capacity in data centers. However, those well-known multicast delivery schemes for traditional wired data centers do not consider the unique characteristics of wireless communications, which may result in unnecessary data transmissions and network congestions. Under the coexisting scenario of wired and wireless links, this paper studies multicast tree construction and maintenance problems. The objective is to minimize the total multicast traffic. We prove the problems are $\mathcal {NP}$ -hard and propose efficient heuristic algorithms for the two problems. Based on real traces and practical settings obtained from commercial data centers, a series of experiments are conducted, and the experimental results show that our proposed algorithms are effective for reducing multicast data traffic. The results also provide useful insights into the design of multicast tree construction and maintenance for wireless data center networks.

Scalable connectionless RDMA over unreliable datagrams

We demonstrate non-connection-based RDMA methods for iWARP Ethernet networks.RDMA Write-Record is the first RDMA operation for unreliable transports.The new methods show improved performance and scalability.The methods are proven for both commercial and scientific applications.The basic design is applicable to other high speed networks. The overhead imposed by connection-based protocols for high-performance computing (HPC) systems can be detrimental to system resource usage and performance. This paper demonstrates for the first time a unified send/recv and Remote Direct Memory Access (RDMA) Write over datagrams design for RDMA-capable network adapters. We previously designed the first and only unreliable datagram RDMA model, RDMA Write-Record, and demonstrated its superior performance over connection-based RDMA. RDMA Write-Record can be applied to several RDMA capable networks, such as iWARP and InfiniBand (which does not support unreliable RDMA Writes). iWARP is a state-of-the-art, high-speed, connection-based RDMA networking technology for both local and wide-area Ethernet networks. iWARP is used as the platform to demonstrate our unreliable RDMA operation design for both channel and memory semantics. We previously outlined the requirements for extending iWARP to operate over datagrams. Here we extend our work on commercial datacenter applications by providing broadcast support for send/recv. In order to study the scalability of datagram-iWARP, we added Message Passing Interface support for RDMA Write-Record to investigate the scalability of HPC-based scientific applications for both send/recv and RDMA Write-Record. The results show that both models outperform their connection-based alternatives, providing superior performance and scalability in a software prototype.

Cloud-Based Collaborative 3D Mapping in Real-Time With Low-Cost Robots

This paper presents an architecture, protocol, and parallel algorithms for collaborative 3D mapping in the cloud with low-cost robots. The robots run a dense visual odometry algorithm on a smartphone-class processor. Key-frames from the visual odometry are sent to the cloud for parallel optimization and merging with maps produced by other robots. After optimization the cloud pushes the updated poses of the local key-frames back to the robots. All processes are managed by Rapyuta, a cloud robotics framework that runs in a commercial data center. This paper includes qualitative visualization of collaboratively built maps, as well as quantitative evaluation of localization accuracy, bandwidth usage, processing speeds, and map storage.

Rapyuta: A Cloud Robotics Platform

In this paper, we present the design and implementation of Rapyuta, an open-source cloud robotics platform. Rapyuta helps robots to offload heavy computation by providing secured customizable computing environments in the cloud. The computing environments also allow the robots to easily access the RoboEarth knowledge repository. Furthermore, these computing environments are tightly interconnected, paving the way for deployment of robotic teams. We also describe three typical use cases, some benchmarking and performance results, and two proof-of-concept demonstrations. Note to Practitioners - Rapyuta allows to outsource some or all of a robot's onboard computational processes to a commercial data center. Its main difference to other, similar frameworks like the Google App Engine is that it is specifically tailored towards multiprocess high-bandwidth robotics applications/middlewares and provides a well-documented open-source implementation that can be modified to cover a large variety of robotic scenarios. Rapyuta supports the outsourcing of almost all of the current 3000+ ROS packages out of the box and is easily extensible to other robotic middleware. A pre-installed Amazon Machine Image (AMI) is provided that allows to launch Rapyuta in any of Amazon's data center within minutes. Once launched, robots can authenticate themselves to Rapyuta, create one or more secured computational environments in the cloud and launch the desired nodes/processes. The computing environments can also be arbitrarily connected to build parallel computing architectures on the fly. The WebSocket-based communication protocol, which provides synchronous and asynchronous communication mechanisms, allows not only ROS based robots, but also browsers and mobiles phones to connect to the ecosystem. Rapyuta's computing environments are private, secure, and optimized for data throughput. However, its performance is in large part determined by the latency and quality of the network connection and the performance of the data center. Optimizing performance under these constraints is typically highly application-specific. The paper illustrates an example of performance optimization in a collaborative real-time 3-D mapping application. Other target applications include collaborative 3-D mapping, task/grasp planning, object recognition, localization, and teleoperation, among others.

Quo vadis Open-IX?

The recently launched initiative by the Open-IX Association (OIX) to establish the European-style Internet eXchange Point (IXP)model in the US suggests an intriguing strategy to tackle a problem that some Internet stakeholders in the US consider to be detrimental to their business; i.e., a lack of diversity in available peering opportunities. We examine in this paper the cast of Internet stakeholders that are bound to play a critical role in determining the fate of this Open-IX effort. These include the large content and cloud providers, CDNs, Tier-1 ISPs, the well-established and some of the newer commercial datacenter and colocation companies, and the largest IXPs in Europe. In particular, we comment on these different parties' current attitudes with respect to public and private peering and discuss some of the economic arguments that will ultimately determine whether or not the currently pursued strategy by OIX will succeed in achieving the main OIX-articulated goal -- a more level playing field for private and public peering in the US such that the actual demand and supply for the different peering opportunities will be reflected in the cost structure.

Review of underfloor air distribution technology

Underfloor air distribution (UFAD) system, which is a relative new method of providing conditioned air and ventilation to the commercial buildings and data centers, is focused by researchers and designers for its potential advantages of better indoor thermal comfort (ITC) and indoor air quality (IAQ), layout flexibility, reduced life cycle costs, and energy saving. However, the application of UFAD system are still obstructed by the gap in the fundamental understanding of some new elements, such as the cooling load calculation, control of the thermal stratification, and evaluation of energy consumption. This paper reviews the current situation of UFAD technology, and the existing problems in recent researches are summarized. To improve the performance of UFAD system, several possible directions for the further studies are suggested.

Experimental study on the characteristics of supply air for UFAD system with perforated tiles

Abstract Underfloor air distribution (UFAD) system is widely used in commercial buildings and data centers for its potential advantages of superior thermal comfort and indoor air quality, etc. In UFAD system, conditioned air is directly supplied to the occupied zone from a pressurized plenum, which causes temperature stratification from the lower zone to the upper zone. The airflow distribution is determined by the pressure decay and flow pattern in the plenum, which is affected by the size of plenum, the open area of the diffusers, air leakage, and the obstructions under raised floor. This paper summarizes the results of an experimental study of airflows through plenum and perforated tiles in a plenum test facility, and the governing equations and boundary conditions on the distribution of velocity and pressure in the plenum are deduced. The linear models of the lost coefficient of air leakage and the velocity ratio of outlet and inlet of the plenum are proposed to simplify the measurement and calculation of the distribution of velocity and pressure in the plenum. The results show that the calculated results coincide with the experimental results, and the models will help to understand the design and operation for the UFAD system.

The 4 Pillar Framework for energy efficient HPC data centers

Improving energy efficiency has become a major research area not just for commercial data centers but also for high performance computing (HPC) data centers. While many approaches for reducing the energy consumption in data centers and HPC sites have been proposed and implemented, as of today, many research teams focused on improving the energy efficiency of data centers are working independently from others. The main reason being that there is no underlying framework that would allow them to relate their work to achievements made elsewhere. Also, without some frame of correlation, the produced results are either not easily applicable beyond their origin or it is not clear if, when, where, and for whom else they are actually useful. This paper introduces the “4 Pillar Framework for Energy Efficient HPC Data Centers” which can be used by HPC center managers to wholistically evaluate their site, find specific focus areas, classify current research activities, and identify areas for further improvement and research. The 4 pillars are: 1. Building Infrastructure; 2. HPC Hardware; 3. HPC System Software; and 4. HPC Applications. While most HPC centers already implement optimizations within each of the pillars, optimization efforts crossing the pillar boundaries are still rare. The 4 Pillar Framework, however, specifically encourages such cross-pillar optimization efforts. Besides introducing the framework itself, this paper shows its applicability by mapping current research activities in the field of energy efficient HPC conducted at Leibniz Supercomputing Centre of the Bavarian Academy of Sciences and Humanities to the framework as reference.

Cloud libraries

This paper explores information technologies and services that allow organizations to operate more efficiently and at less cost by using commercial data-processing centers and data centers. The services provided by these centers are referred to as cloud computing and/or cloud services, and are increasingly often applied in different fields. It is highly relevant for the library community to pay close attention to and consider the possibility of using these services, which can lead to the emergence of a new area, viz., cloud libraries.

Building a parallel file system simulator

Parallel file systems are gaining in popularity in high-end computing centers as well as commercial data centers. High-end computing systems are expected to scale exponentially and to pose new challenges to their storage scalability in terms of cost and power. To address these challenges scientists and file system designers will need a thorough understanding of the design space of parallel file systems. Yet there exist few systematic studies of parallel file system behavior at petabyte- and exabyte scale. An important reason is the significant cost of getting access to large-scale hardware to test parallel file systems. To contribute to this understanding we are building a parallel file system simulator that can simulate parallel file systems at very large scale. Our goal is to simulate petabyte-scale parallel file systems on a small cluster or even a single machine in reasonable time and fidelity. With this simulator, file system experts will be able to tune existing file systems for specific workloads, scientists and file system deployment engineers will be able to better communicate workload requirements, file system designers and researchers will be able to try out design alternatives and innovations at scale, and instructors will be able to study very large-scale parallel file system behavior in the class room. In this paper we describe our approach and provide preliminary results that are encouraging both in terms of fidelity and simulation scalability.