In this paper, we propose a new user-level file system to support block relocation by modifying the without actual data copying. The key idea of the proposed system is to provide the block insertion and deletion function for file manipulation. This approach can be used very effectively for block-aligned file modification applications such as a compress utility and a TAR archival system. To show the usefulness of the proposed file system, we adapted the new functionality to TAR application by modifying TAR file to support an efficient sub-file management scheme. Experiment results show that the proposed system can significantly reduce the file I/O overhead and improve the I/O performance of a file system.

抄録全体を表示

Due to the detachability of Flash storage, which is a dominant portable storage, data integrity stored in Flash storages becomes an important issue. This study considers the performance of Flash Translation Layer (FTL) schemes embedded in Flash storages in conjunction with file system behavior that pursue high data integrity. To assure extreme data integrity, file systems synchronously write all file data to storage accompanying hot write references. In this study, we concentrate on the effect of hot write references on Flash storage, and we consider the effect of absorbing the hot write references via nonvolatile write cache on the performance of the FTL schemes in Flash storage. In so doing, we quantify the performance of typical FTL schemes for a realistic digital camera workload that contains hot write references through experiments on a real system environment. Results show that for the workload with hot write references FTL performance does not conform with previously reported studies. We also conclude that the impact of the underlying FTL schemes on the performance of Flash storage is dramatically reduced by absorbing the hot write references via nonvolatile write cache.

抄録全体を表示

The hardware chosen for fMRI data analysis may depend on the platform already present in the laboratory or the supporting software. In this study, we ran SPM99 software on multiple platforms to examine whether we could analyze fMRI data by SPM99, and to compare their differences and limitations in processing fMRI data, which can be attributed to hardware capabilities. Six normal right-handed volunteers participated in a study of hand-grasping to obtain fMRI data. Each subject performed a run that consisted of 98 images. The run was measured using a gradient echo-type echo planar imaging sequence on a 1.5T apparatus with a head coil. We used several personal computer (PC), Unix and Linux machines to analyze the fMRI data. There were no differences in the results obtained on several PC, Unix and Linux machines. The only limitations in processing large amounts of the fMRI data were found using PC machines. This suggests that the results obtained with different machines were not affected by differences in hardware components, such as the CPU, memory and hard drive. Rather, it is likely that the limitations in analyzing a huge amount of the fMRI data were due to differences in the operating system (OS).

抄録全体を表示

A project to observe lightning and sprites from the International Space Station (ISS), with altitude of 407 km and inclination of 51.6°, is planned for 2012. GLIMS (global lightning and sprite measurements) is an instrument designed for this project, and it includes a CMOS camera, photomultipliers, a VLF receiver, and a VHF interferometer. This is the first project for simultaneous measurements of lightning, sprites, and radiowaves from lightning simultaneously. The sensors used for GLIMS were developed based on previous satellite projects. However, for this project, the sensors used needed to be synchronized, and controlled through the Japanese experiment module (JEM) interface. A science data-handling unit (SHU) was newly developed for this purpose; it included a function for suppressing data traffic using a high-speed lossless compression code (HIREW).

抄録全体を表示

File systems make use of the buffer cache to enhance their performance. Traditionally, part of DRAM, which is volatile memory, is used as the buffer cache. In this paper, we consider the use of of Non-Volatile RAM (NVRAM) as a write cache for metadata of the file system in embedded systems. NVRAM is a state-of-the-art memory that provides characteristics of both non-volatility and random byte addressability. By employing NVRAM as a write cache for dirty metadata, we retain the same integrity of a file system that always synchronously writes its metadata to storage, while at the same time improving file system performance to the level of a file system that always writes asynchronously. To show quantitative results, we developed an embedded board with NVRAM and modify the VFAT file system provided in Linux 2.6.11 to accommodate the NVRAM write cache. We performed a wide range of experiments on this platform for various synthetic and realistic workloads. The results show that substantial reductions in execution time are possible from an application viewpoint. Another consequence of the write cache is its benefits at the FTL layer, leading to improved wear leveling of Flash memory and increased energy savings, which are important measures in embedded systems. From the real numbers obtained through our experiments, we show that wear leveling is improved considerably and also quantify the improvements in terms of energy.

抄録全体を表示

The airborne sensors with high data rate demand the onboard high-speed storage system due to the limited bandwidth of the downlinks. The NAND Flash and its products are the most common storage medium, and the conventional FAT file system is widely used in the storage systems. However, there has been a problem in recording the live high-speed data stably with this file system. The management time of the FAT file system is relatively long due to the internal overhead which includes the retrieving and updating of the FAT and FDT. The aim of this study is to investigate the technology for the real-time file system. A technology called FPFPA (FAT post- and FDT post- allocation) method is presented to solve this problem. To evaluate the performance of the proposed method, the management time of the file system using our proposed method is tested on the high-speed storage system of an airborne radar. The result indicates that the proposed method achieves our goal successfully in that the management time of the file system is significantly reduced and sufficiently small.

抄録全体を表示

MPEG映像ファイル、データベースファイルなどの大容量ファイルをシーケンシャルに高速読み出し可能な経済的なファイルシステム装置の実現が強く望まれている。そこで我々は、広く普及している安価なDOS/Vパソコン(PC)上に高速MS-DOSファイルシステムを構築することを提案し、高速化のためにシーケンシャル読み出しについて最適に動作する新しい技術を開発した。具体的には「階層ストライピング」と「連続DMA」という2つの技術を提案する。試作システムを実験的に評価した結果、9台のハードディスク構成の場合で80Mbyte/sを超えるシーケンシャル読み出し速度を達成できることを確認した。

抄録全体を表示

プログラム理解はソフトウェアの保守にとって重要である. 識別子はプログラム理解にとって重要な働きをする. 我々はこの識別子に注目し, プログラム理解ツールの提案を目的とした, 識別子を調査する基盤となる識別子断片コーパスを提案する. 識別子断片とは識別子を構成する1 つの単語であり, その中で人がプログラム理解に有用であると判断できるものをキーワードという. 教育用OS(udos) を事例とし識別子断片コーパスの有用性について調べる. 事例から読み手が出現頻度などの機械処理を適用することである程度キーワード候補しぼりこむことができた. この結果はコーパスをプログラム理解ツールに応用できることを示唆している.

抄録全体を表示

パーソナルコンピューターと組込み制御システムを応用対象とし, マイクロコンピューター用ソフトウェアの動向を開発, 流通の両側面から解説する.
また, トピックスとしてシリコンソフトウェアについても言及する.

抄録全体を表示

We developed a new digital ocean bottom seismometer with a hydrophone using a magneto optical storage device, called MOOBS/H (Magneto-Optical Ocean Bottom Seismometer with Hydrophone) -1. This unit is designed to intend equipping a large-amount data storage, higher accuracy for the data and the random access capability, and improving the reliability of data storage; those features were not realized by the first generation. By the use of the power on-off control of the slave CPU, the SCSI interface, and the MO unit, the total power is reduced to 1/100 compared to the full use. By the MOOBS/H-1, 2000-3000 earthquakes can be stored in an MO disk.
The MOOBS/H-1 is composed of seismic sensors, amplifiers, a multiplexer, a 16-bit A/D, a watch-dog processor, a time-keeper, a data-transfer processor and a five inch MO storage. Two 8 bit CPUs are used : one for a watch-dog and the other for data I/O between the main memory and the MO unit. One 16-bit A/D device is used. Recording channels can be selected among 8 channels. Six channels out of 8 channels have amplifiers. The sampling rate of A/D can be selected among various frequencies from 1 to 800Hz. The recording mode is chosen among several modes such as continuous, time window, logical trigger, and amplitude trigger modes. The necessary parameters for each observation are set using external key-pad unit through a bus-connector. The key-pad unit can be removed after setting parameters.
The maximum amount of the data storage is 320Mb. The maximum number of earthquake events are c.a. 2, 200 if 100Hz sampling, 4 channels and 3 minutes record length are used. In this case, the maximum record length for each event can be extendible up to more than 42 minutes. When lithium batteries are used, the recording life is roughly 2 months.
The data in the MO disk are directly readable by an NEC-PC and can be transferred from the PC to a workstation for analysis. Software to use the MOOBS/H data was also developed.
The usefulness of MOOBS/H was confirmed by a number of deep-sea observations in such as the Japan Trench, the Okinawa Trough, off Japan, the Mariana Trough and the TAG area of the Mid-Atlantic Ridge. Using frequency characteristics of hydrophone, amplifier and recording unit, the very low frequency behavior of hydrothermal vent was firstly observed.

抄録全体を表示