This dissertation demonstrates new methods for increasing the performance and scalability of high performance networking technologies for use in clustered computing systems, concentrating on Ethernet/High-Speed networking convergence. The motivation behind the improvement of high performance networking technologies and their importance to the viability of modern data centers is discussed first. It then introduces the concepts of high performance networking in a commercial data center context as well as high performance computing (HPC) and describes some of the most important challenges facing such networks in the future. It reviews current relevant literature and discusses problems that are not yet solved. Through a study of existing high performance networks, the most promising features for future networks are identified. Sockets Direct Protocol (SDP) is shown to have unexpected performance issues for commercial applications, due to inefficiencies in handling large numbers of simultaneous connections. The first SDP over eXtended Reliable Connections implementation is developed to reduce connection management overhead, demonstrating that performance issues are related to protocol overhead at the SDP level. Datagram offloading for IP over InfiniBand (IPoIB) is found to work well. In the first work of its kind, hybrid high-speed/Ethernet networks are shown to resolve the issues of SDP underperformance and demonstrate the potential for hybrid high-speed networking local area Remote Direct Memory Access (RDMA) technologies and Ethernet wide area networking for data centers. Given the promising results from these studies, a set of solutions to enhance performance at the local and wide area network level for Ethernet is introduced, providing a scalable, connectionless, socket-compatible, fully RDMA-capable networking technology, datagram-iWARP. A novel method of performing RDMA Write operations (called RDMA Write-Record) and RDMA Read over unreliable datagrams over Ethernet is designed, implemented and tested. It shows its applicability in scientific and commercial application spaces and is applicable to other verbs-based networking interfaces such as InfiniBand. The newly proposed RDMA methods, both for send/recv and RDMA Write-Record, are supplemented with interfaces for both socket-based applications and Message Passing Interface (MPI) applications. An MPI implementation is adapted to support datagram-iWARP. Both scalability and performance improvements are demonstrated for HPC and commercial applications. / Thesis (Ph.D, Electrical & Computer Engineering) -- Queen's University, 2012-09-25 09:43:55.262

Many next-generation e-science applications require fast and reliable transfer of large volumes of data, now frequently termed as ``big data", with guaranteed performance, which is typically enabled by the bandwidth reservation service in high-performance networks (HPNs). Users normally specify the properties and requirements of their data transfers in the bandwidth reservation requests (BRRs), and want to make bandwidth reservations on the HPNs to satisfy the requirements of their data transfers. The challenges of the bandwidth reservation arise from the requirements desired by both the users and the bandwidth reservation service providers of the HPNs. We focus on two important bandwidth reservation problems formulated from the combinations of the requirements from both users and the bandwidth reservation service providers of the HPNs: (i) Problem of scheduling all BRRs in one batch while achieving their best average data transfer earliest completion time and shortest duration, and (ii) Problem of scheduling two generic types of BRRs concerning data transfer reliability with different objectives and constraints in unreliable HPNs that are subject to node and link failures. We prove the two subproblems of the first problem are NP-complete problems, and fast and efficient heuristic algorithms are proposed. While the two subproblems of the second problem can be optimally solved in polynomial time. The corresponding optimal algorithms and proofs are given. We conduct extensive simulations to compare the performance of the proposed heuristic and optimal algorithms with naive scheduling algorithms and the algorithms currently used in production network in various performance metrics. The performance superiority of the proposed heuristic and optimal algorithms is verified.

No description available.

High-performance networking (HPN) is of significance today in order to enable next-generation applications using wired and wireless networks. Some of the examples of HPN include low-latency industrial sensing, monitoring and automation using Wireless Sensor Networks (WSNs). HPN however requires protocol optimization at many layers of the open system interface (OSI) network model in order to meet the stringent performance constraints of the given applications. Furthermore, these protocols need to be impervious to denial of service (DoS) and distributed DoS (DDoS) attacks. Some of the key performance aspects of HPN are low point-to-point and end-to-end latency, high reliability of transmitted frames and performance predictability under various network load situations. This work focuses on two discrete issues in designing protocols for HPN applications. The first research issue looks at the Medium Access Control (MAC) layer of the OSI network model for designing of MAC protocols that provide low-latency and high reliability for point-to-point communication under a WSN. Existing standards in this area are governed by IEEE 802.15.4 specification which defines protocols for MAC and PHY layers for short-range, low bit-rate, and low-cost wireless networks. However, the IEEE 802.15.4 specification is inefficient in terms of latency and reliability performance and, as a result, is unable to meet the stringent operational requirements as defined by counterpart wired sensor networks. Work presented under current research issue describes new MAC protocols that are able to show low-latency transmission performance under strict timing constants for power limited WSNs. This enhancement of the MAC protocols is named extended GTS (XGTS) contained under extended CFP (ECFP) and is published under the IEEE's 802.15.4e standard. The second research issue focuses on the application layer of the OSI network model to design protocols that enhance the robustness of the text based protocols to various traffic inputs. The purpose of this is to increase the reliability of the given text based application layer protocol under a varied load. Session Initiation Protocol (SIP) is used as a case study and the work aims to build algorithms that ensure that SIP can continue to function under specific traffic conditions, which would otherwise deem the protocol useless due to DoS and DDoS attacks. Proposed algorithms investigate techniques that enhance the robustness of the SIP against parsing attacks without performing a deep parse of the protocol data unit (PDU). The desired effect of this is to reduce the time spent in parsing the SIP messages at a SIP router and as a result increase the number of SIP messages processed per unit time at a SIP router.