OceanStore is a utility infrastructure designed to span the globe and provide continuous access to persistent information. Since this infrastructure is comprised of untrusted servers, data is protected through redundancy and cryptographic techniques. To improve performance, data is allowed to be cached anywhere, anytime. Additionally, monitoring of usage patterns allows adaptation to regional outages and denial of service attacks; monitoring also enhances performance through pro-active movement of data. A prototype implementation is currently under development.

/pdf/oceanstore-an-architecture-for-global-scale-persistent-4qe9kbb44y.pdf

OceanStore: an architecture for global-scale persistent storage

Computer architecture is about to undergo, if not another revolution, then a vigorous shaking-up. The major chip manufacturers have, for the time being, simply given up trying to make processors run faster. Instead, they have recently started shipping "multicore" architectures, in which multiple processors (cores) communicate directly through shared hardware caches, providing increased concurrency instead of increased clock speed.As a result, system designers and software engineers can no longer rely on increasing clock speed to hide software bloat. Instead, they must somehow learn to make effective use of increasing parallelism. This adaptation will not be easy. Conventional synchronization techniques based on locks and conditions are unlikely to be effective in such a demanding environment. Coarse-grained locks, which protect relatively large amounts of data, do not scale, and fine-grained locks introduce substantial software engineering problem.Transactional memory is a computational model in which threads synchronize by optimistic, lock-free transactions. This synchronization model promises to alleviate many (not all) of the problems associated with locking, and there is a growing community of researchers working on both software and hardware support for this approach. This talk will survey the area, with a focus on open research problems.

The Art of Multiprocessor Programming

The computing world today is in the middle of a revolution: mobile clients and cloud computing have emerged as the dominant paradigms driving programming and hardware innovation today. The Fifth Edition of Computer Architecture focuses on this dramatic shift, exploring the ways in which software and technology in the "cloud" are accessed by cell phones, tablets, laptops, and other mobile computing devices. Each chapter includes two real-world examples, one mobile and one datacenter, to illustrate this revolutionary change. Updated to cover the mobile computing revolutionEmphasizes the two most important topics in architecture today: memory hierarchy and parallelism in all its forms.Develops common themes throughout each chapter: power, performance, cost, dependability, protection, programming models, and emerging trends ("What's Next")Includes three review appendices in the printed text. Additional reference appendices are available online.Includes updated Case Studies and completely new exercises.

Computer Architecture, Fifth Edition: A Quantitative Approach

A management capability is provided for a virtual computing platform. In one example, this platform allows interconnected physical resources such as processors, memory, network interfaces and storage interfaces to be abstracted and mapped to virtual resources (e.g., virtual mainframes, virtual partitions). Virtual resources contained in a virtual partition can be assembled into virtual servers that execute a guest operating system (e.g., Linux). In one example, the abstraction is unique in that any resource is available to any virtual server regardless of the physical boundaries that separate the resources. For example, any number of physical processors or any amount of physical memory can be used by a virtual server even if these resources span different nodes. A virtual computing platform is provided that allows for the creation, deletion, modification, control (e.g., start, stop, suspend, resume) and status (i.e., events) off the virtual servers which execute on the virtual computing platform and the management capability provides controls for these functions. In a particular example, such a platform allows the number and type of virtual resources consumed by a virtual server to be scaled up or down when the virtual server is running. For instance, an administrator may scale a virtual server manually or may define one or more policies that automatically scale a virtual server. Further, using the management API, a virtual server can monitor itself and can scale itself up or down depending on its need for processing, memory and I/O resources. For example, a virtual server may monitor its CPU utilization and invoke controls through the management API to allocate a new processor for itself when its utilization exceeds a specific threshold. Conversely, a virtual server may scale down its processor count when its utilization falls. Policies can be used to execute one or more management controls. More specifically, a management capability is provided that allows policies to be defined using management object's properties, events and/or method results. A management policy may also incorporate external data (e.g., an external event) in its definition. A policy may be triggered, causing the management server or other computing entity to execute an action. An action may utilize one or more management controls. In addition, an action may access external capabilities such as sending notification e-mail or sending a text message to a telephone paging system. Further, management capability controls may be executed using a discrete transaction referred to as a 'job.' A series of management controls may be assembled into a job using one or management interfaces. Errors that occur when a job is executed may cause the job to be rolled back, allowing affected virtual servers to return to their original state.

System and method for managing virtual servers

In this paper, we propose a new paradigm for network file system design, serverless network file systems. While traditional network file systems rely on a central server machine, a serverless system utilizes workstations cooperating as peers to provide all file system services. Any machine in the system can store, cache, or control any block of data. Our approach uses this location independence, in combination with fast local area networks, to provide better performance and scalability than traditional file systems. Further, because any machine in the system can assume the responsibilities of a failed component, our serverless design also provides high availability via redundant data storage. To demonstrate our approach, we have implemented a prototype serverless network file system called xFS. Preliminary performance measurements suggest that our architecture achieves its goal of scalability. For instance, in a 32-node xFS system with 32 active clients, each client receives nearly as much read or write throughput as it would see if it were the only active client.

/pdf/serverless-network-file-systems-3b48sxlzcq.pdf

Serverless Network File Systems

The Data Diffusion Machine (DDM), a cache-only memory architecture (COMA) that relies on a hierarchical network structure, is described. The key ideas behind DDM are introduced by describing a small machine, which could be a COMA on its own or a subsystem of a larger COMA, and its protocol. A large machine with hundreds of processors is also described. The DDM prototype project is discussed, and simulated performance results are presented. >

DDM—a cache-only memory architecture

Large-scale shared-memory multiprocessors typically have long latencies for remote data accesses. A key issue for execution performance of many common applications is the synchronization cost. The communication scalability of synchronization has been improved by the introduction of queue-based spin-locks instead of Test&(Test&Set). For architectures with long access latencies for global data, attention should also be paid to the number of global accesses that are involved in synchronization. We present a method to characterize the performance of proposed queue lock algorithms, and apply it to previously published algorithms. We also present two new queue locks, the LH lock and the M lock. We compare the locks in terms of performance, memory requirements, code size and required hardware support. The LH lock is the simplest of all the locks, yet requires only an atomic swap operation. The M lock is superior in terms of global accesses needed to perform synchronization and still competitive in all other criteria. We conclude that the M lock is the best overall queue lock for the class of architectures studied. >

/pdf/queue-locks-on-cache-coherent-multiprocessors-42l362ranu.pdf

Queue locks on cache coherent multiprocessors

/pdf/ddm-a-cache-only-memory-architecture-ef29bnd9ug.pdf

DDM-a cache-only memory architecture

The widening memory gap reduces performance of applications with poor data locality. Therefore, there is a need for methods to analyze data locality and help application optimization. In this paper we present StatCache, a novel sampling-based method for performing data-locality analysis on realistic workloads. StatCache is based on a probabilistic model of the cache, rather than a functional cache simulator. It uses statistics from a single run to accurately estimate miss ratios of fully-associative caches of arbitrary sizes and generate working-set graphs. We evaluate StatCache using the SPEC CPU2000 benchmarks and show that StatCache gives accurate results with a sampling rate as low as 10/sup -4/. We also provide a proof-of-concept implementation, and discuss potentially very fast implementation alternatives.

/pdf/statcache-a-probabilistic-approach-to-efficient-and-accurate-5gtonpo3si.pdf

StatCache: a probabilistic approach to efficient and accurate data locality analysis

Researchers have searched for scalable alternatives to the symmetric multiprocessor (SMP) architecture since it was first introduced in 1982. The paper introduces an alternative view of the relationship between scalable technologies and SMPs. Instead of replacing large SMPs with scalable technology, we propose new scalable techniques that allow large SMPs to be tied together efficiently, while maintaining the compatibility with, and performance characteristics of, an SMP. The trade-offs of such an architecture differ from those of traditional, scalable, Non-Uniform Memory Architecture (cc-NUMA) approaches. WildFire is a distributed shared memory (DSM) prototype implementation based on large SMPs. It relies on two techniques for creating application-transparent locality: Coherent Memory Replication (CMR), which is a variation of Simple COMA/Reactive NUMA, and Hierarchical Affinity Scheduling (HAS). These two optimizations create extra node locality, which blurs the node boundaries to an application such that SMP-like performance can be achieved with no NUMA-specific optimizations. We present a performance study of a large OLTP benchmark running on DSMs built from various sized nodes and with varying amounts of application-transparent locality. WildFire's measured performance is shown to be more than two times that of an unoptimized NUMA implementation built from small nodes and within 13% of the performance of the ideal implementation: a large SMP with the same access time to its entire shared memory as the local memory access time of WildFire.

/pdf/wildfire-a-scalable-path-for-smps-1ba3lysuqe.pdf

Erik Hagersten

Papers

DDM—a cache-only memory architecture

Queue locks on cache coherent multiprocessors

DDM-a cache-only memory architecture

StatCache: a probabilistic approach to efficient and accurate data locality analysis

WildFire: a scalable path for SMPs