期刊文献+
共找到3篇文章
< 1 >
每页显示 20 50 100
TCP/IP协议卸载技术性能与实现的研究 被引量:3
1
作者 朱宏峰 刘天华 +1 位作者 刘杰 常桂然 《小型微型计算机系统》 CSCD 北大核心 2007年第4期609-614,共6页
本文通过分析当前计算机系统主要通信瓶颈,建立模型分析其卸载后的性能,得出协议卸载与节点处理能力、网络带宽、网卡处理能力以及需要处理的应用程序、网络数据包的强度有关的结论,得出了他们之间理想状态下的最优解.建立并初步实现TO... 本文通过分析当前计算机系统主要通信瓶颈,建立模型分析其卸载后的性能,得出协议卸载与节点处理能力、网络带宽、网卡处理能力以及需要处理的应用程序、网络数据包的强度有关的结论,得出了他们之间理想状态下的最优解.建立并初步实现TOE通信平台,实现零拷贝,利用Linux开源特点实现相应的软控制程序并结合ML403开发板实现相应的硬处理功能,实现简单数据包的收发. 展开更多
关键词 TOE zerocopy 吞吐率
下载PDF
NASSN:a NAS-based storage network
2
作者 韩德志 《Journal of Harbin Institute of Technology(New Series)》 EI CAS 2007年第3期334-340,共7页
With the digital information and application requirement on the Internet increasing fleetly nowadays,it is urgent to work out a network storage system with a large capacity,a high availability and scalability.To solve... With the digital information and application requirement on the Internet increasing fleetly nowadays,it is urgent to work out a network storage system with a large capacity,a high availability and scalability.To solve the above-mentioned issues,a NAS-based storage network(for short NASSN)has been designed.Firstly,the NASSN integrates multi-NAS,iNAS(an iSCSI-based NAS)and enterprise SAN with the help of storage virtualization,which can provide a greater capacity and better scalability.Secondly,the NASSN can provide high availability with the help of server and storage subsystem redundancy technologies.Thirdly,the NASSN simultaneously serves for both the file I/O and the block I/O with the help of an iSCSI module,which has the advantages of NAS and SAN.Finally,the NASSN can provide higher I/O speed by a high network-attached channel which implements the direct data transfer between the storage device and client.In the experiments,the NASSN has ultra-high-throughput for both of the file I/O requests and the block I/O requests. 展开更多
关键词 NAS (Network-attached Storage) CLUSTER SAN (Storage Area Network) iSCSI( internet Small Computer System Interface) zero copy
下载PDF
RECONFIGURABLE RDMA COMMUNICATION FRAMEWORK OF MULTI-DSP
3
作者 Wang Qian Lv Dongqiang Zhou Feifei 《Journal of Electronics(China)》 2009年第3期380-386,共7页
The processing speed of the communication between nodes in a parallel processor has become the major bottleneck of the processor's performance.RDMA(Remote Direct Memory Access) technology has drawn more attention ... The processing speed of the communication between nodes in a parallel processor has become the major bottleneck of the processor's performance.RDMA(Remote Direct Memory Access) technology has drawn more attention recently due to its capability of transferring a larger amount of data, higher speed and reliability.4DSP(4 Digital Signal Processing) module comprised of Tiger-SHARC201 chip is connected by LVDS(Low Voltage Differential Signal) circuits.This paper proposes a general and reconfigurable RDMA platform and its corresponding communication protocol with all the routes linked based on the zero copy.The protocol transfers message of DSP by interrupting of DMA and is applied on massive remote image impression, which reduces memory needs and working burden of CPU.The experiment results show this platform is efficient, flexible, and expandable of being integrated to a larger scale in the next development stages. 展开更多
关键词 DSP (Digital Signal Processing) DMA (Direct Memory Access) LVDS (Low VoltageDifferential Signal) Parallel processing zero copy
下载PDF
上一页 1 下一页 到第
使用帮助 返回顶部