This paper proposes a novel real-time adaptive admission control (AAC) scheme with a desired quality of service (QoS) guarantee and high network utilization in high speed networks. The QoS is given in terms of service...
详细信息
This paper proposes a novel real-time adaptive admission control (AAC) scheme with a desired quality of service (QoS) guarantee and high network utilization in high speed networks. The QoS is given in terms of service delay, which is defined as the time it takes for a source to get admitted into the network after it initiates its intended request, packet/cell losses, and transmission delay (time taken to complete transmission from its initiation). AAC uses the following information - the available capacity from a novel adaptive bandwidth estimation scheme, a congestion indicator derived from a congestion controller, peak cell rate estimate from new sources, along with the desired QoS metrics, and outputs an 'admit' or 'reject' decision signal to the new sources while guaranteeing QoS and network utilization. Simulation results are presented by streaming ON/OFF and video data into the network. Results show that the proposed AAC admits significantly more traffic compared to other available admission control schemes thereby guaranteeing high network utilization while maintaining the desired QoS.
We present the design, implementation, and evaluation of single assignment data structures and of a software controlled cache in an existing multi-threaded architecture platform – the Efficient Architecture for Runni...
We present the design, implementation, and evaluation of single assignment data structures and of a software controlled cache in an existing multi-threaded architecture platform – the Efficient Architecture for Running Threads (EARTH). The I-Structure Software-Controlled Cache (ISSC) exploits temporal and spatial locality of EARTH split-phased memory transactions for single-assignment memory references. Our experimental evaluation indicates that the caching mechanism for single-assignment storage makes the EARTH memory system more robust to variations in the latency of memory operations. As a consequence the system can be ported to a wider range of machine platforms and deliver speedup for both regular and irregular application.
We develop a new software layer called the Automatic parallel Detection Layer (APDL) for the automatic transformation from sequential to parallel code. The main interest, in this research, is the parallelism at loop l...
详细信息
We develop a new software layer called the Automatic parallel Detection Layer (APDL) for the automatic transformation from sequential to parallel code. The main interest, in this research, is the parallelism at loop level, because significant parallelism in programs almost invariably occurs in loops. The proposed APDL has five processes for code transformation: the sequential source code parser, data dependence analysis of this code, partitioning, scheduling both task and data, and generating parallel source code. Many cases have been studied to evaluate the performance of the developed layer. The performance is evaluated depending on the execution time of: the sequential code, the parallel programmer code, and the code output from APDL for the same case study. Performance results show that APDL greatly improves the execution time with respect to sequential execution time, and saves on the high cost of a parallel programmer.
Large-scale scientific applications present great challenges to computational scientists in terms of obtaining high performance and in managing large datasets. These applications (most of which are simulations) may em...
详细信息
With the increasing number of scientific applications manipulating huge amounts of data, effective high-level data management is an increasingly important problem. Unfortunately, so far the solutions to the high‐leve...
With the increasing number of scientific applications manipulating huge amounts of data, effective high-level data management is an increasingly important problem. Unfortunately, so far the solutions to the high‐level data management problem either require deep understanding of specific storage architectures and file layouts (as in high-performance file storage systems) or produce unsatisfactory I/O performance in exchange for ease-of-use and portability (as in relational DBMSs). In this paper we present a novel application development environment which is built around an active meta-data management system (MDMS) to handle high-level data in an effective manner. The key components of our three-tiered architecture are user application, the MDMS, and a hierarchical storage system (HSS). Our environment overcomes the performance problems of pure database-oriented solutions, while maintaining their advantages in terms of ease-of-use and portability. The high levels of performance are achieved by the MDMS, with the aid of user-specified, performance-oriented directives. Our environment supports a simple, easy-to-use yet powerful user interface, leaving the task of choosing appropriate I/O techniques for the application at hand to the MDMS. We discuss the importance of an active MDMS and show how the three components of our environment, namely the application, the MDMS, and the HSS, fit together. We also report performance numbers from our ongoing implementation and illustrate that significant improvements are made possible without undue programming effort.
Group Communication System (GCS) is an important building block for reliable, fault-tolerant distributed applications. Due to highly variable and unpredictable latency in WANs, GCS needs to cope with frequent membersh...
详细信息
Group Communication System (GCS) is an important building block for reliable, fault-tolerant distributed applications. Due to highly variable and unpredictable latency in WANs, GCS needs to cope with frequent membership changes. It results in diminishing the scalability of GCS. In this paper we propose a new scheme that improves the scalability of group membership service for WANs by exploiting dedicated membership servers configured into multiple layers and reaching global agreement on the view through layered servers. It improves the scalability of a process group of N member processes from O(N/sup 2/) to O(N/sup 3/) with three layers, where N is the number of processes in the group. computer simulation verifies that the proposed scheme requires much smaller number of message exchanges for reaching an agreement on a next view and does that much quicker. In addition, the proposed scheme prevents applications from being blocked until reaching the final view agreement if the applications permit temporary inconsistency.
Our results demonstrate that our novel application development environment provides both ease-of-use and high performance for large-scale, I/O-intensive scientific applications.
ISBN:
(纸本)9781581132700
Our results demonstrate that our novel application development environment provides both ease-of-use and high performance for large-scale, I/O-intensive scientific applications.
Clusters of Symmetrical Multiprocessors (SMPs) have recently become the norm for high-performance economical computing solutions. Multiple nodes in a cluster can be used for parallel programming using a message passin...
Clusters of Symmetrical Multiprocessors (SMPs) have recently become the norm for high-performance economical computing solutions. Multiple nodes in a cluster can be used for parallel programming using a message passing library. An alternate approach is to use a software distributed Shared Memory (DSM) to provide a view of shared memory to the application programmer. This paper describes Strings, a high performance distributed shared memory system designed for such SMP clusters. The distinguishing feature of this system is the use of a fully multi-threaded runtime system, using kernel level threads. Strings allows multiple application threads to be run on each node in a cluster. Since most modern UNIX systems can multiplex these threads on kernel level light weight processes, applications written using Strings can exploit multiple processors on a SMP machine. This paper describes some of the architectural details of the system and illustrates the performance improvements with benchmark programs from the SPLASH-2 suite, some computational kernels as well as a full fledged application. It is found that using multiple processes on SMP nodes provides good speedups only for a few of the programs. Multiple application threads can improve the performance in some cases, but other programs show a slowdown. If kernel threads are used additionally, the overall performance improves significantly in all programs tested. Other design decisions also have a beneficial impact, though to a lesser degree.
We measure the performance of several cooperative caching policies for a database with hot spots. The workload consists of queries and append-only update transactions, and is modeled after a financial database of stoc...
详细信息
We measure the performance of several cooperative caching policies for a database with hot spots. The workload consists of queries and append-only update transactions, and is modeled after a financial database of stock (historical) trading information. We show that cooperative caching is effective for this application. We show that selecting the correct set of peer servers when servicing a cache miss is crucial to achieving high performance, and we demonstrate a greedy algorithm that performs close to optimal for this workload. We also evaluate several cache replacement policies and show that a 2nd-chance algorithm performs best. In a 2nd-chance algorithm, replaced pages are transferred to a peer server rather than being discarded. When a page is selected for replacement a 2nd time, the page is discarded. Our results can be applied in the design of proxy servers for databases or Web servers where a layer of proxy servers are used to scale the system performance.
In computersystems today, speed and responsiveness is often determined by network and storage subsystem performance. Faster, more scalable networking interfaces like Fibre Channel and Gigabit Ethernet provide the sca...
详细信息
In computersystems today, speed and responsiveness is often determined by network and storage subsystem performance. Faster, more scalable networking interfaces like Fibre Channel and Gigabit Ethernet provide the scaffolding from which higher performance implementations may be constructed, but new thinking is required about how machines interact with network-enabled storage devices. We have developed a Linux file system called GFS (the Global File System) that allows multiple Linux machines to access and share disk and tape devices on a Fibre Channel or SCSI storage network. We plan to extend GFS by transporting packetized SCSI commands over IP so that any GFS-enabled Linux machine can access shared network devices. GFS will perform well as a local file system, as a traditional network file system running over LP, and as a high-performance cluster file system running over storage networks like Fibre Channel. GFS device sharing provides a key cluster-enabling technology for Linux, helping to bring the availability, scalability, and load balancing benefits of clustering to Linux. Our goal is to develop a scalable, (in number of clients and devices, capacity, connectivity, and bandwidth) server-less file system that integrates IF-based network attached storage (NAS) and Fibre-Channel-based storage area networks (SAN). We call this new architecture Storage Area InterNetworking (SAINT). It exploits the speed and device scalability of SAN clusters, and provides the client scalability and network interoperability of NAS appliances. Our Linux port shows that the GFS architecture is portable across different platforms, and we are currently working on a port to NetBSD. The GFS code is open source (GPL) software freely available on the Internet at http://***.
暂无评论