Server-centric Architecture Research Articles

DACON: a reconfigurable application-centric optical network for disaggregated data center infrastructures [Invited

To solve the issues of low resource utilization and performance bottleneck in current server-centric data center networks (DCNs), we propose and experimentally demonstrate a disaggregated application-centric optical network (DACON) for data center infrastructures based on hybrid optical switches. DACON achieves flexible provision and dynamic reconfiguration of hardware nodes exploiting the softwared-define networking (SDN) orchestration plane. A four-node SDN-enabled disaggregated prototype is implemented with a field-programmable-gate-array-based controller of hardware nodes and nanosecond optical switches, performing a minimal node-to-node network latency of 378.6 ns and zero packet loss. Based on the unmodified Linux kernel and two different applications (distributed computing and a Memcached database), the application runtime of the disaggregated prototype is investigated and compared with the server-centric architecture. Experimental results show that the disaggregated prototype performs better with Memcached database applications, achieving a1.46×faster runtime than the server-centric network at a memory node access ratio of 0.9. Based on the customized control plane orchestrator and dynamic resource reallocation, the node-to-node latency is reduced by 21% when CPU nodes access memory nodes. The scalability of DACON is then numerically assessed based on experimentally measured parameters. Results show that the intra-rack node-to-node latency is less than 404.8 ns with a 6144-node network and memory node access ratio of 0.9. Finally, the cost and power consumption are also studied and compared with current DCN architectures. Results indicate DACON saves 13.4% of the cost of an interconnect network compared with current disaggregated architecture and consumes up to 31.1% less power with respect to server-centric DCN architectures.

RDON: a rack-scale disaggregated data center network based on a distributed fast optical switch

Aiming to solve the low utilization and high operational cost in current data centers and the diversified resource requirements for different application types, we propose and investigate what we believe to be a novel rack-scale disaggregated optical data center network (RDON). Different types of hardware resources (i.e., CPU, memory, and storage) are deployed in standalone resource pools of the RDON. The RDON architecture encompasses nanosecond distributed fast optical switches for the low latency and high bandwidth interconnects between the computing and memory nodes, while electrical packet switches are utilized to support the traffic of latency insensitivity and low bandwidth between memory nodes and storage nodes. By replacing the onboard data bus with a network interconnection, RDON architecture can provide a fine granularity hardware resource and relieve the constraints of server-centric architecture. To assess the performance of the RDON under realistic scenarios, statistics of diverse applications are captured from the data center lab. The RDON is modeled based on the OMNeT++ discrete event simulator and compared with the server-centric architecture. Numerical results show that the performance of the RDON is closely coupled with the type of deployed application. Compared to the server-centric architecture, the RDON can achieve up to 2.44 × faster running time when running a single application, whereas at most 2.25 × is the fastest running time under coexisting diverse types of applications. Finally, the analysis of costs and power consumption show that, with respect to server-centric architecture, the RDON requires 21.5% extra capital cost but 46.7% less power consumption.

Energy-Aware Coflow and Antenna Scheduling for Hybrid Server-Centric Data Center Networks

Data center networks (DCNs) continuously evolve to support emerging applications. For instance, server-centric architectures are becoming popular because they improve the modularity and resilience of data centers. In a server-centric DCN, switching functionalities are embedded in each server instead of in dedicated switches. Recently, wireless technologies have been introduced into the design of server-centric DCNs. Wireless interconnects provide great flexibility by creating direct flyways between servers. These wireless links help to reduce the length of paths assigned to flows so that fewer links must be powered-on to transfer data. In this paper, we investigate energy-aware scheduling of coflows and antenna directions in a server-centric DCN. Coflows are groups of parallel and high-volume flows generated by big data applications. We assume that the DCN is hybrid, i.e., that it includes both wired and wireless links. We formulate this scheduling problem as an optimization problem named energy-aware coflow and antenna scheduling (ECAS) and solve it using a mathematical programming solver. We further prove the NP-hardness of the formulated ECAS problem. We also introduce a heuristic algorithm to reduce the computational complexity. Our simulation results show that our optimal solution saves up to 48% of energy compared with representative competitors. Our heuristic algorithm achieves lower energy savings but still generates the shortest paths and lowest transferring time of flows. Further simulations on the network topology with a different size also confirm the efficiency of our proposed model and algorithm.

Towards the Tradeoffs in Designing Data Center Network Architectures

Existing Data Center Network (DCN) architectures are classified into two categories: switch-centric and server-centric architectures. In switch-centric DCNs, routing intelligence is placed on switches; each server usually uses only one port of the Network Interface Card (NIC) to connect to the network. In server-centric DCNs, switches are only used as cross-bars, and routing intelligence is placed on servers, where multiple NIC ports may be used. In this paper, we formally introduce a new category of DCN architectures: the <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">dual-centric</i> DCN architectures, where routing intelligence can be placed on both switches and servers. The dual-centric philosophy can achieve various tradeoffs in designing DCN architectures. We propose three novel dual-centric DCN architectures: FCell, FRectangle, and FSquare, all of which are based on the folded Clos topology. FCell is a power-efficient DCN architecture, with a larger diameter and lower bisection bandwidth than FSquare and FRectangle. FSquare is a high performance DCN architecture, in which the diameter is small and the bisection bandwidth is large; however, the DCN power consumption per server in FSquare is high. FRectangle significantly reduces the DCN power consumption per server, compared to FSquare, at the sacrifice of some networking performances. By investigating FCell, FRectangle and FSquare, and by comparing them with existing architectures, we demonstrate that, the three novel dual-centric architectures enjoy the advantages of both switch-centric designs and server-centric designs, have various nice properties for practical data centers, and provide flexible tradeoff choices in designing DCN architectures.

On the Network Power Effectiveness of Data Center Architectures

Cloud computing not only requires high-capacity data center networks to accelerate bandwidth-hungry computations, but also causes considerable power expenses to cloud providers. In recent years many advanced data center network architectures have been proposed to increase the network throughput, such as Fat-Tree [1] and BCube [2] , but little attention has been paid to the power efficiency of these network architectures. This paper makes the first comprehensive comparison study for typical data center networks with regard to their Network Power Effectiveness (NPE ), which indicates the end-to-end bps per watt in data transmission and reflects the tradeoff between power consumption and network throughput. We take switches, server NICs and server CPU cores into account when evaluating the network power consumption. We measure NPE under both regular routing and power-aware routing, and investigate the impacts of topology size, traffic load, throughput threshold in power-aware routing, network power parameter as well as traffic pattern. The results show that in most cases Flattened Butterfly possesses the highest NPE among the architectures under study, and server-centric architectures usually have higher NPEs than Fat-Tree and VL2 architectures. In addition, the sleep-on-idle technique and power-aware routing can significantly improve the NPEs for all the data center architectures, especially when the traffic load is low. We believe that the results are useful for cloud providers, when they design/upgrade data center networks or employ network power management.

FleCube: A flexibly-connected architecture of data center networks on multi-port servers

Underlying network provides infrastructures for cloud computing in data centers. The server-centric architectures integrate network and compute, which place routing intelligence on servers. However, the existing multi-port server based architectures suffer from determined scale and large path length. In this paper, we propose FleCube, a flexibly-connected architecture on multi-port servers without using any switches. FleCube is recursively constructed on division of multiple ports in a server by means of complete graph. FleCube benefits data center networks by flexible scale and low diameter, as well as large bisection width and small bottleneck degree. Furthermore, we develop multi-path routing (MPR) to take advantage of parallel paths between any two servers. MPR adopts random forwarding to distribute traffic load and relieve network congestion. Analysis and comparisons with existing architectures show the advantages of FleCube. Evaluations under different degrees of network traffic demonstrate the merits of FleCube and the proposed routings.

Designing efficient high performance server-centric data center network architecture

Data center network (DCN) architecture is regarded as one of the most important determinants of network performance. As the most typical representatives of DCN architecture designs, the server-centric scheme stands out due to its good performance in various aspects. In this paper, we firstly present the design, implementation and evaluation of SprintNet, a novel server-centric network architecture for data centers. SprintNet achieves high performance in network capacity, fault tolerance, and network latency. SprintNet is also a scalable, yet low-diameter network architecture where the maximum shortest distance between any pair of servers can be limited by no more than four and is independent of the number of layers. The specially designed routing schemes for SprintNet strengthen its merits. However, all of these kind of server-centric architectures still suffer from some critical shortcomings owing to the server’s responsibility of forwarding packets. With regard to these issues, in this paper, we then propose a hardware based approach, named “Forwarding Unit” to provide an effective solution to these drawbacks and improve the efficiency of server-centric architectures. Both theoretical analysis and simulations are conducted to evaluate the overall performance of SprintNet and the Forwarding Unit approach with respect to cost-effectiveness, fault-tolerance, system latency, packet loss ratio, aggregate bottleneck throughput, and average path length. The evaluation results convince the feasibility and good performance of both SprintNet and Forwarding Unit.

DPillar: Dual-port server interconnection network for large scale data centers

To meet the huge demands of computation power and storage space, a future data center may have to include up to millions of servers. The conventional hierarchical tree-based data center network architecture faces several challenges in scaling a data center to that size. Previous research effort has shown that a server-centric architecture, where servers are not only computation and storage workstations but also intermediate nodes relaying traffic for other servers, performs well in scaling a data center to a huge number of servers. This paper presents a server-centric data center network called DPillar, whose topology is inspired by the classic butterfly network. DPillar provides several nice properties and achieves the balance between topological scalability, network performance, and cost efficiency, which make it suitable for building large scale future data centers. Using only commodity hardware, a DPillar network can easily accommodate millions of servers. The structure of a DPillar network is symmetric so that any network bottleneck is eliminated at the architectural level. With each server having only two ports, DPillar is able to provide the bandwidth to support communication intensive distributed applications. This paper studies the interconnection features of DPillar, how to compute routes in DPillar, and how to forward packets in DPillar. Extensive simulation experiments have been performed to evaluate the performance of DPillar. The results show that DPillar performs well even in the presence of a large number of server and switch failures.

Growing Cloud Computing Efficiency

Cloud computing is basically altering the expectation for how and when computing, storage and networking assets should be allocated, managed and devoted. End-users are progressively more sensitive in response time of services they ingest. Service Developers wish for the Service Providers to make sure or give the ability for dynamically assigning and managing resources in respond to alter the demand patterns in real-time. Ultimately, Service Providers are under anxiety to build their infrastructure to facilitate real-time end-to-end visibility and energetic resource management with well grained control to decrease total cost of tenure for improving quickness. What is required to rethink of the underlying operating system and management infrastructure to put up the on-going renovation of data centre from the traditional server-centric architecture model to a cloud or network centric model? This paper projects and describes a indication model for a network centric data centre infrastructure management heap that make use of it and validates key ideas that have enabled dynamism, the quality of being scalable, reliability and security in the telecommunication industry to the computing engineering. Finally, the paper will explain a proof of concept classification that was implemented to show how dynamic resource management can be enforced to enable real-time service guarantee for network centric data centre architecture.

Towards a Server-Centric Interaction Architecture for Wireless Applications

Traditional web-based services that require users to browse via documents and fill out forms, are difficult to use with mobile devices. Moreover, as the web paradigm assumes active clients, further complications are introduced in cases where the server is the active entity, instead of the client. This paper presents a Server-Centric Interaction Architecture (SCIA) for wireless applications. The architecture enables servers to initiate communication with clients as well as push secure targeted data to them, in a piecemeal fashion. It further enables the development of highly collaborative wireless services with interactive user interfaces.

Microsoft Exchange Implementation on a Distributed Storage Area Network

The ever-increasing demand for fast and reliable data storage has caused dramatic changes in the storage model. Direct attached storage (DAS) architecture, also known as server-centric architecture, is being replaced by the storage area network (SAN), leading to storage-centric architecture. In SAN storage devices exist completely independent of any computer (servers in particular). Multiple servers can access the same storage device without involvement of other servers. Recently, companies have been able to implement storage integration/sharing, remote backup/restoral, near-real-time disk mirroring/replication, and the like, using a new SAN architecture known as distributed storage area network (DSAN). The DSAN is multiple SANs interconnected using existing Internet Protocol (IP) networks to distribute storage over wide geographical areas. Even though DSANs provide additional capabilities to a SAN, the end-to-end latency (ETEL) due to large physical cable lengths (IP networks) imposes limitations on enterprise class application performance. DSANs can also be implemented using IP storage solutions that provide direct links between servers and storages, eliminating translation of fibre channel protocol frames to IP packets. This paper examines the effect of ETEL in DSAN on the performance of an enterprise class application with real-time application replication like Microsoft Exchange Server 2003. This investigation in done in two parts: disk subsystem (DS) characterization using Jetstress benchmarking software and the performance of Microsoft Exchange using LoadSim 2003 benchmarking software. Preliminary results were presented in [1].

Dependability in peer-to-peer systems

Server-centric architectures such as the Web's suffer from well-known problems related to application size and increasing user requests. Peer-to-peer systems can help address some of the key challenges, but this survey of several current P2P systems shows that dependability remains an open issue. To perform in Internet-scale applications, P2P systems must address the four major properties of dependable systems: scalability, fault-tolerance, security, and anonymity. An output of the comparison provided is an attempt to move toward common terms and definitions. Because the models underlying current P2P systems must be understood to support a thorough investigation of dependability properties, we briefly examine the most popular P2P systems and then compare how these systems address dependability.