InfiniBand has been recently standardized by the industry to design next generation high-end clusters for both datacenter and high performance computing domains. Though InfiniBand has been able support low latency and high bandwidth, traditional sockets based applications have not been able to take advantage of this; this is mainly attributed to the multiple copies and kernel context switches associated with the traditional TCP/IP protocol stack. The Sockets Direct Protocol (SDP) had been proposed recently in order to enable sockets based applications to take advantage of the enhanced features provided by InfiniBand Architecture. In this

... that in order to provide or design a data-center environment which is efficient and offers high performance, one of the critical issues that needs to be addressed is the effective reuse of cache content stored away from the origin server. In the current web, many cache eviction policies and uncachable resources are driven by two server application goals: Cache Coherence and Cache Consistency. The problem of how to provide consistent caching for dynamic content (Active Caches) has been well studied and researchers have proposed several weak as well as strong consistency algorithms. However, the problem of maintaining cache coherence has not been studied as much. In this paper, we propose an architecture for achieving strong cache coherence for multi-tier data-centers over InfiniBand using the previously proposed client-polling mechanism. The architecture as such could be used with any protocol layer; we have also proposed some optimizations to the algorithm to take advantage of the advanced features provided by InfiniBand. We evaluate this architecture using three protocol platforms: (i) TCP/IP over InfiniBand (IPoIB), (ii) Sockets Direct Protocol over InfiniBand (SDP) and (iii) the native InfiniBand Verbs layer (VAPI) and compare it with the performance of the no-caching based coherence mechanism. Our experimental results show that the InfiniBand-Optimized architecture can achieve an improvement of nearly an order of magnitude compared to the throughput achieved by the TCP/IP based architecture (over IPoIB), the SDP based architecture and the no-cache based coherence scheme.

reconfigurability of the nodes in the data-center environment. This technique enables the nodes in the datacenter environment to efficiently adapt their functionality based on the system load and traffic pattern. While reconfigurability is a widely used technique for clusters, the datacenter environment poses several interesting challenges for the design and implementation of such a scheme. In our approach, we use the advanced features of InfiniBand such as Remote Direct Memory Access (RDMA) operations and network based atomic operations to tackle these challenges in an efficient manner without requiring any modifications to the existing data-center applications. Our experimental results show that the reconfigurability scheme provides a significantly higher performance (up to a factor of 2.5 improvement in the throughput) with the same resources or provides a similar performance while using fewer resources (up to half the nodes) as compared to a rigidly configured data-center. More importantly, our scheme takes advantage of the one-sided communication primitives offered by InfiniBand making it resilient and well-conditioned to the load on the servers as compared to two-sided communication protocols such as TCP/IP (sockets).

It has been well acknowledged in the research community that in order to design a data-center environment which is efficient and offers high performance, one of the critical issues that needs to be addressed is the effective reuse of cache content stored away from the origin server. However, for caching dynamically changing content (e.g., content involved in online banking, Internet auctions, etc.), consistency and coherency issues need to be addressed. In addition, most current real world requests have multiple dynamic dependencies, i.e., these requests might depend on multiple data objects. Further, these requests are not entirely independent; several requests might have common dependencies. While there have been previous research solutions on maintaining coherent caches for dynamic content, these solutions have several shortcommings including inability to adapt to server load or handle multiple dynamic dependencies. In this paper, we propose a load resilient architecture using one sided operations supported by several high performance interconnects such as InfiniBand, while maintaining multiple dynamic dependencies per response. Our experimental results show that our schemes to tackle the multi-dependency issue significantly outperform the existing approaches. Further, our results demonstrate that the proposed load resilient architecture can improve the performance of loaded data-centers by over an order of magnitude in some cases.

Earlier generation protocols such as TCP/IP have traditionally been implemented in the host kernel space and have not been able to scale with the increasing network speeds. Accordingly, they form the primary communication bottleneck in current high-speed networks. In order to allow existing TCP/IP applications that had been written on top of the sockets interface to take advantage of high-speed networks, researchers have come up with a number of solutions including highperformance sockets. The primary idea of high-performance sockets is to build a pseudo sockets-like implementation which utilizes the advanced features of highspeed networks while maintaining the TCP/IP sockets interface; this allows existing TCP/IP sockets based applications to transparently achieve a high performance. The Sockets Direct Protocol (SDP) is an industry standard for such highperformance sockets over the InfiniBand (IB) network and the Internet Wide-Area RDMA Protocol (iWARP) over Ethernet networks. In this thesis, we focus on designing and enhancing SDP over iWARP and IB.

In the past decade several high-speed networks have been introduced, each superseding the others with respect to raw performance, communication features and capabilities. However, such aggressive initiative is accompanied by an increasing divergence in the communication interface or “language” used by each network. Accordingly, portability for applications across these various network languages has recently been a topic of extensive research. Programming models such as the Sockets Interface, Message Passing Interface (MPI), Shared memory models, etc., have been widely accepted as the primary means for achieving such portability. This dissertation investigates the different design choices for implementing one such programming model, i.e., Sockets, in various high-speed network environments (e.g., InfiniBand and 10-Gigabit Ethernet). Specifically, the dissertation targets three important sub-problems: (a) designing efficient sockets implementations to allow existing applications to be directly and transparently deployed on to clusters connected with high-speed networks; (b) analyzing the limitations of the sockets interface in various domains and extending it with features that applications need but are currently