The search functionality is under construction.

Author Search Result

[Author] Tetsuya ONODA(6hit)

1-6hit
  • Synchronous CDMA for Optical Subscriber Systems Using Block-Interleave and Redundancy Code Sequences

    Tetsuya ONODA  Noriki MIKI  

     
    PAPER

      Vol:
    E76-B No:8
      Page(s):
    969-983

    A new type of synchronous code division multiple access (S/CDMA) scheme for optical subscriber systems is reported. Passive channel multiplexing is promising for optical subscriber systems because it realizes high system performance at low cost. Unfortunately, passive channel multiplexing suffers from phase differences among the upstream channels, and these differences prevent the usage of traditional synchronous CDMA techniques that reduce cross channel interference. This paper proposes the new technique of block-interleaving & redundancy code sequences to overcome this problem. This combination realizes S/CDMA even in the presence of phase differences and eliminates cross channel interference completely. Therefore, in an optical subscriber system using the new type S/CDMA, the bit error rate performance is independent of phase difference levels and the number of multiplexed channels.

  • Design and Implementation of a High-Speed File Server Based on PC-UNIX

    Tetsuo TSUJIOKA  Kazuaki OBANA  Tetsuya ONODA  

     
    PAPER

      Vol:
    E82-C No:12
      Page(s):
    2191-2200

    Recent attractive high-speed networks require network file servers with high-speed read performance to deliver huge multimedia files, like voice or movie files. This paper proposes new design and implementation techniques that yield high-speed file servers based on UNIX. The techniques are request reduction, in which contiguous blocks on UNIX file system (UFS) are gathered for reducing the number of command requests from the file system to the device driver, and a direct access method for cutting through the buffer cache mechanism. A file server prototype based on a general-purpose personal computer (PC) is constructed and its performance is evaluated. The preliminary results show that the prototype achieves high-speed file read performance in excess of 100 Mbytes/s even on an OpenBSD PC-UNIX system with 3 RAID controllers and 9 hard drives in RAID level 0 configuration.

  • Throughput Characteristic of TCP with Window Size Expansion and Network Direct Memory Access over a Large Delay-Bandwidth Link

    Satoshi KOTABE  Tetsuo TSUJIOKA  Tetsuya ONODA  

     
    PAPER-QoS Control and Traffic Control

      Vol:
    E81-B No:12
      Page(s):
    2357-2363

    This paper experimentally confirms the throughput characteristics of TCP and Network Direct Memory Access (Network DMA), our proposed data transfer protocol, over a large delay-band-width link. The experiments clarify that the various problems of TCP over large delay-bandwidth links include limited window size, data retransmission mechanism, and protocol processing overhead. The test results suggest that we must improve not only protocol itself but also the protocol processing architecture to realize Gbit/s class throughput over such links. To avoid these problems, Network DMA realizes high speed memory copy across a network by labeling each packet with its memory address without host CPU intervention; protocol processing is done by firmware on the network interface card. Moreover, it realizes selective retransmission by using the memory addresses. Test results show that Network DMA achieves the sustained throughput of 535Mbit/s over a 10,000km 622Mbit/s ATM link and over 400Mbit/s effective throughput even when the cell loss ratio is 10-4.

  • Jam-Packing: An Efficient QoS Service for Transferring Huge Files

    Tetsuya ONODA  Hui ZHANG  

     
    PAPER-Flow and Congestion Control

      Vol:
    E84-B No:8
      Page(s):
    2095-2104

    This paper proposes a novel file transfer scheme named "Jam-packing file transfer" that consists of a call admission control and a packet scheduling mechanism. This combination can efficiently multiplex the traffic of file transfer and provides a guaranteed delivery time. Simulation results show the highness of extreme the multiplexing efficiency as the improvement in call blocking probabilities compared with the conventional rate-based reservation schemes. Furthermore, simulations of the packet scheduling indicate that file deliveries are done at the predicted delivery time.

  • "Service-uniform" ONU Based on Low Cost Audio AD/DA Converters and CDM with Novel Code Word Sets

    Tetsuya ONODA  Tetsuo TSUJIOKA  Ryuma KAKINUMA  Seiichi YAMANO  

     
    PAPER-Optical Communication

      Vol:
    E82-B No:9
      Page(s):
    1446-1458

    This paper proposes a novel universal line termination scheme for the ONUs (optical network units) of fiber-optic local access systems. Its main feature is that only low cost AD/DA converters for Hi-Fi audio are needed. Because audio AD/DA converters are insufficient for ISDN basic rate access (● 320kbaud) and cause waveform distortion, we develop a simple detection algorithm that does not use any equalizing filter. The algorithm can handle plural channels with one general purpose MPU (micro-processing unit). Based on this, a novel architecture for a fiber-optic local access system is presented that removes the MPUs from each optical network unit (ONU) and places them in the central office (CO). The proposed system yields a small, service-uniform ONU that supports a wide range of narrow-band services (POTS & ISDN) with no distinction. To realize this system at the lowest possible cost, a high-speed code division multiplexing (CDM) scheme with novel code word sets is developed.

  • An Ultra High-Speed File Server with 105 Mbytes/s Read Performance Based on a Personal Computer

    Tetsuo TSUJIOKA  Tetsuya ONODA  

     
    PAPER-Network Design, Operation, and Management

      Vol:
    E81-B No:12
      Page(s):
    2503-2508

    This paper proposes a novel ultra high-speed file server based on a personal computer (PC) to provide the instantaneous delivery of huge files, like movie files, graphic images and computer programs, over high-speed networks. In order to improve the sustained sequential read speed from arrays of hard drives to host memory in the server, two key techniques are proposed: "multi-stage striping (MSS)" and the "sequential file system (SFS)." An experimental file server based on a general-purpose PC is constructed and its performance is measured. The results show that the server offers ultra high read speeds, up to 105Mbytes/s, with just 8 hard drives.