Search NASA⌕ Search

SEARCH · Search NASA

Results for “servers”

Search indexed NASA NTRS and DOE OSTI research on propulsion, heat transfer, battery materials and energy systems. Follow report and document links to the original sources.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 379 records · Page 21
All sourcesNASA NTRSDOE OSTI
NASA NTRS1995

Exploring the use of I/O nodes for computation in a MIMD multiprocessor

As parallel systems move into the production scientific-computing world, the emphasis will be on cost-effective solutions that provide high throughput for a mix of applications. Cost effective solutions demand that a system make effective use of all of its resources. Many MIMD multiprocessors today, however, distinguish between 'compute' and 'I/O' nodes, the latter having attached disks and being dedicated to running the file-system server. This static division of responsibilities simplifies system management but does not necessarily lead to the best performance in workloads that need a different balance of computation and I/O. Of course, computational processes sharing a node with a file-system service may receive less CPU time, network bandwidth, and memory bandwidth than they would on a computation-only node. In this paper we begin to examine this issue experimentally. We found that high performance I/O does not necessarily require substantial CPU time, leaving plenty of time for application computation. There were some complex file-system requests, however, which left little CPU time available to the application. (The impact on network and memory bandwidth still needs to be determined.) For applications (or users) that cannot tolerate an occasional interruption, we recommend that they continue to use only compute nodes. For tolerant applications needing more cycles than those provided by the compute nodes, we recommend that they take full advantage of both compute and I/O nodes for computation, and that operating systems should make this possible.

Kotz, David↗
NASA NTRS1995

Continuation: The EOSDIS testbed data system

The continuation of the EOSDIS testbed ('Testbed') has materialized from a multi-task system to a fully functional stand-alone data archive distribution center that once was only X-Windows driven to a system that is accessible by all types of users and computers via the World Wide Web. Throughout the past months, the Testbed has evolved into a completely new system. The current system is now accessible through Netscape, Mosaic, and all other servers that can contact the World Wide Web. On October 1, 1995 we will open to the public and we expect that the statistics of the type of user, where they are located, and what they are looking for will drastically change. What is the most important change in the Testbed has been the Web interface. This interface will allow more users access to the system and walk them through the data types with more ease than before. All of the callbacks are written in such a way that icons can be used to easily move around in the programs interface. The homepage offers the user the opportunity to go and get more information about each satellite data type and also information on free programs. These programs are grouped into categories for types of computers that the programs are compiled for, along with information on how to FTP the programs back to the end users computer. The heart of the Testbed is still the acquisition of satellite data. From the Testbed homepage, the user selects the 'access to data system' icon, which will take them to the world map and allow them to select an area that they would like coverage on by simply clicking that area of the map. This creates a new map where other similar choices can be made to get the latitude and longitude of the region the satellite data will cover. Once a selection has been made the search parameters page will appear to be filled out. Afterwards, the browse image will be called for once the search is completed and the images for viewing can be selected. There are several other option pages, but once an order has been selected the Testbed will bring up the order list page and the user will then be able to place their order. After the order has been completed, the Testbed will mail the user to notify them of the completed order and how the images can be picked up.

Emery, Bill↗
NASA NTRS1993

A microbased shared virtual world prototype

Virtual reality (VR) allows sensory immersion and interaction with a computer-generated environment. The user adopts a physical interface with the computer, through Input/Output devices such as a head-mounted display, data glove, mouse, keyboard, or monitor, to experience an alternate universe. What this means is that the computer generates an environment which, in its ultimate extension, becomes indistinguishable from the real world. 'Imagine a wraparound television with three-dimensional programs, including three-dimensional sound, and solid objects that you can pick up and manipulate, even feel with your fingers and hands.... 'Imagine that you are the creator as well as the consumer of your artificial experience, with the power to use a gesture or word to remold the world you see and hear and feel. That part is not fiction... three-dimensional computer graphics, input/output devices, computer models that constitute a VR system make it possible, today, to immerse yourself in an artificial world and to reach in and reshape it.' Our research's goal was to propose a feasibility experiment in the construction of a networked virtual reality system, making use of current personal computer (PC) technology. The prototype was built using Borland C compiler, running on an IBM 486 33 MHz and a 386 33 MHz. Each game currently is represented as an IPX client on a non-dedicated Novell server. We initially posed the two questions: (1) Is there a need for networked virtual reality? (2) In what ways can the technology be made available to the most people possible?

Pitts, Gerald↗
NASA NTRS1995

Compression research on the REINAS Project

We present approaches to integrating data compression technology into a database system designed to support research of air, sea, and land phenomena of interest to meteorology, oceanography, and earth science. A key element of the Real-Time Environmental Information Network and Analysis System (REINAS) system is the real-time component: to provide data as soon as acquired. Compression approaches being considered for REINAS include compression of raw data on the way into the database, compression of data produced by scientific visualization on the way out of the database, compression of modeling results, and compression of database query results. These compression needs are being incorporated through client-server, API, utility, and application code development.

Rosen, Eric↗
NASA NTRS1995

Visualization of unsteady computational fluid dynamics

The current computing environment that most researchers are using for the calculation of 3D unsteady Computational Fluid Dynamic (CFD) results is a super-computer class machine. The Massively Parallel Processors (MPP's) such as the 160 node IBM SP2 at NAS and clusters of workstations acting as a single MPP (like NAS's SGI Power-Challenge array) provide the required computation bandwidth for CFD calculations of transient problems. Work is in progress on a set of software tools designed specifically to address visualizing 3D unsteady CFD results in these super-computer-like environments. The visualization is concurrently executed with the CFD solver. The parallel version of Visual3, pV3 required splitting up the unsteady visualization task to allow execution across a network of workstation(s) and compute servers. In this computing model, the network is almost always the bottleneck so much of the effort involved techniques to reduce the size of the data transferred between machines.

Haimes, Robert↗
NASA NTRS1996

Research and Technology 1995

This report selectively summarizes the NASA Lewis Research Center's research and technology accomplishments for fiscal year 1995. It comprises over 150 short articles submitted by the staff members of the technical directorates. The report is organized into six major sections: aeronautics, aerospace technology, space flight systems, engineering support, Lewis Research Academy, and technology transfer. A table of contents, an author index, and a list of NASA Headquarters program offices have been included to assist the reader in finding articles of special interest. This report is not intended to be a comprehensive summary of all research and technology work done over the past fiscal year. Most of the work is reported in Lewis-published technical reports, journal articles, and presentations prepared by Lewis staff members and contractors (for abstracts of these Lewis-authored reports, visit the Lewis Technical Report Server (LETRS) on the World Wide Web-http://letrs.lerc.nasa.gov/LeTRS/). In addition, university grants have enabled faculty members and graduate students to engage in sponsored research that is reported at technical meetings or in journal articles. For each article in this report, a Lewis contact person has been identified, and where possible, reference documents are listed so that additional information can be easily obtained. The diversity of topics attests to the breadth of research and technology being pursued and to the skill mix of the staff that makes it possible. For more information about Lewis' research, visit us on the World Wide web-http://www.lerc.nasa.gov.

Source record↗
NASA NTRS1996

An MPA-IO interface to HPSS

This paper describes an implementation of the proposed MPI-IO (Message Passing Interface - Input/Output) standard for parallel I/O. Our system uses third-party transfer to move data over an external network between the processors where it is used and the I/O devices where it resides. Data travels directly from source to destination, without the need for shuffling it among processors or funneling it through a central node. Our distributed server model lets multiple compute nodes share the burden of coordinating data transfers. The system is built on the High Performance Storage System (HPSS), and a prototype version runs on a Meiko CS-2 parallel computer.

Jones, Terry↗
NASA NTRS1996

Petabyte Class Storage at Jefferson Lab (CEBAF)

By 1997, the Thomas Jefferson National Accelerator Facility will collect over one Terabyte of raw information per day of Accelerator operation from three concurrently operating Experimental Halls. When post-processing is included, roughly 250 TB of raw and formatted experimental data will be generated each year. By the year 2000, a total of one Petabyte will be stored on-line. Critical to the experimental program at Jefferson Lab (JLab) is the networking and computational capability to collect, store, retrieve, and reconstruct data on this scale. The design criteria include support of a raw data stream of 10-12 MB/second from Experimental Hall B, which will operate the CEBAF (Continuous Electron Beam Accelerator Facility) Large Acceptance Spectrometer (CLAS). Keeping up with this data stream implies design strategies that provide storage guarantees during accelerator operation, minimize the number of times data is buffered allow seamless access to specific data sets for the researcher, synchronize data retrievals with the scheduling of postprocessing calculations on the data reconstruction CPU farms, as well as support the site capability to perform data reconstruction and reduction at the same overall rate at which new data is being collected. The current implementation employs state-of-the-art StorageTek Redwood tape drives and robotics library integrated with the Open Storage Manager (OSM) Hierarchical Storage Management software (Computer Associates, International), the use of Fibre Channel RAID disks dual-ported between Sun Microsystems SMP servers, and a network-based interface to a 10,000 SPECint92 data processing CPU farm. Issues of efficiency, scalability, and manageability will become critical to meet the year 2000 requirements for a Petabyte of near-line storage interfaced to over 30,000 SPECint92 of data processing power.

Chambers, Rita↗
NASA NTRS1996

The medium is NOT the message or Indefinitely long-term file storage at Leeds University

Approximately 3 years ago we implemented an archive file storage system which embodies experiences gained over more than 25 years of using and writing file storage systems. It is the third in-house system that we have written, and all three systems have been adopted by other institutions. This paper discusses the requirements for long-term data storage in a university environment, and describes how our present system is designed to meet these requirements indefinitely. Particular emphasis is laid on experiences from past systems, and their influence on current system design. We also look at the influence of the IEEE-MSS standard. We currently have the system operating in five UK universities. The system operates in a multi-server environment, and is currently operational with UNIX (SunOS4, Solaris2, SGI-IRIX, HP-UX), NetWare3 and NetWare4. PCs logged on to NetWare can also archive and recover files that live on their hard disks.

Holdsworth, David↗
NASA NTRS1996

Data Transfer Efficiency Over Satellite Circuits Using a Multi-Socket Extension to the File Transfer Protocol (FTP)

In several experiments using NASA's Advanced Communications Technology Satellite (ACTS), investigators have reported disappointing throughput using the transmission control protocol/Internet protocol (TCP/IP) protocol suite over 1.536Mbit/sec (T1) satellite circuits. A detailed analysis of file transfer protocol (FTP) file transfers reveals that both the TCP window size and the TCP 'slow starter' algorithm contribute to the observed limits in throughput. In this paper we summarize the experimental and and theoretical analysis of the throughput limit imposed by TCP on the satellite circuit. We then discuss in detail the implementation of a multi-socket FTP, XFTP client and server. XFTP has been tested using the ACTS system. Finally, we discuss a preliminary set of tests on a link with non-zero bit error rates. XFTP shows promising performance under these conditions, suggesting the possibility that a multi-socket application may be less effected by bit errors than a single, large-window TCP connection.

Allman, Mark↗
NASA NTRS1996

The Global File System

The global file system (GFS) is a prototype design for a distributed file system in which cluster nodes physically share storage devices connected via a network-like fiber channel. Networks and network-attached storage devices have advanced to a level of performance and extensibility so that the previous disadvantages of shared disk architectures are no longer valid. This shared storage architecture attempts to exploit the sophistication of storage device technologies whereas a server architecture diminishes a device's role to that of a simple component. GFS distributes the file system responsibilities across processing nodes, storage across the devices, and file system resources across the entire storage pool. GFS caches data on the storage devices instead of the main memories of the machines. Consistency is established by using a locking mechanism maintained by the storage devices to facilitate atomic read-modify-write operations. The locking mechanism is being prototyped in the Silicon Graphics IRIX operating system and is accessed using standard Unix commands and modules.

Soltis, Steven R.↗
NASA NTRS1996

DIstributed VIRtual System (DIVIRS) Project

The development of Prospero moved from the University of Washington to ISI and several new versions of the software were released from ISI during the contract period. Changes in the first release from ISI included bug fixes and extensions to support the needs of specific users. Among these changes was a new option to directory queries that allows attributes to be returned for all files in a directory together with the directory listing. This change greatly improves the performance of their server and reduces the number of packets sent across their trans-pacific connection to the rest of the internet. Several new access method were added to the Prospero file method. The Prospero Data Access Protocol was designed, to support secure retrieval of data from systems running Prospero.

Schorr, Herbert↗
NASA NTRS1995

The Schwinger Variational Method

Variational methods have proven invaluable in theoretical physics and chemistry, both for bound state problems and for the study of collision phenomena. The application of the Schwinger variational (SV) method to e-molecule collisions and molecular photoionization has been reviewed previously. The present chapter discusses the implementation of the SV method as applied to e-molecule collisions. Since this is not a review of cross section data, cross sections are presented only to server as illustrative examples. In the SV method, the correct boundary condition is automatically incorporated through the use of Green's function. Thus SV calculations can employ basis functions with arbitrary boundary conditions. The iterative Schwinger method has been used extensively to study molecular photoionization. For e-molecule collisions, it is used at the static exchange level to study elastic scattering and coupled with the distorted wave approximation to study electronically inelastic scattering.

Huo, Winifred M.↗
NASA NTRS1994

Reducing Interprocessor Dependence in Recoverable Distributed Shared Memory

Checkpointing techniques in parallel systems use dependency tracking and/or message logging to ensure that a system rolls back to a consistent state. Traditional dependency tracking in distributed shared memory (DSM) systems is expensive because of high communication frequency. In this paper we show that, if designed correctly, a DSM system only needs to consider dependencies due to the transfer of blocks of data, resulting in reduced dependency tracking overhead and reduced potential for rollback propagation. We develop an ownership timestamp scheme to tolerate the loss of block state information and develop a passive server model of execution where interactions between processors are considered atomic. With our scheme, dependencies are significantly reduced compared to the traditional message-passing model.

Janssens, Bob↗
NASA NTRS1996

A revisit to the requirements methodologies for services provided by the Office of Space Communications

The methodologies of the NASA requirements processing system, originally designed to enhance NASA's customer interface and response time, are reviewed. The response of NASA to the problems associated with the system is presented, and it is shown what was done to facilitate the process and to improve customer relations. The requirements generation system (RGS), a computer-supported client-server system, adopted by NASA is presented. The RGS system is configurable on a per-mission basis and can be structured to allow levels of requirements. The details provided concerning the RGS include the recommended configuration, information on becoming an RGS user and network connectivity worksheets for computer users.

Fishkind, Stanley↗
NASA NTRS1996

An MPI-IO Interface to HPSS

This paper describes an implementation of the proposed MPI-IO standard for parallel I/O. Our system uses third-party transfer to move data over an external network between the processors where it is used and the I/O devices where it resides. Data travels directly from source to destination, without the need for shuffling it among processors or funneling it through a central node. Our distributed server model lets multiple compute nodes share the burden of coordinating data transfers. The system is built on the High Performance Storage System (HPSS), and a prototype version runs on a Meiko CS-2 parallel computer.

Parallel Processing↗
NASA NTRS1997

Opus: A Coordination Language for Multidisciplinary Applications

Data parallel languages, such as High Performance fortran, can be successfully applied to a wide range of numerical applications. However, many advanced scientific and engineering applications are multidisciplinary and heterogeneous in nature, and thus do not fit well into the data parallel paradigm. In this paper we present Opus, a language designed to fill this gap. The central concept of Opus is a mechanism called ShareD Abstractions (SDA). An SDA can be used as a computation server, i.e., a locus of computational activity, or as a data repository for sharing data between asynchronous tasks. SDAs can be internally data parallel, providing support for the integration of data and task parallelism as well as nested task parallelism. They can thus be used to express multidisciplinary applications in a natural and efficient way. In this paper we describe the features of the language through a series of examples and give an overview of the runtime support required to implement these concepts in parallel and distributed environments.

Chapman, Barbara↗
NASA NTRS1997

Buckets, Clusters and Dienst

In this paper we describe NCSTRL+, a unified, canonical digital library for scientific and technical information (STI). NCSTRL+ is based on the Networked Computer Science Technical Report Library (NCSTRL), a World Wide Web (WWW) accessible digital library (DL) that provides access to over 80 university departments and laboratories. NCSTRL+ implements two new technologies: cluster functionality and publishing "buckets." We have extended the Dienst protocol, the protocol underlying NCSTRL, to provide the ability to "cluster" independent collections into a logically centralized digital library based upon subject category classification, type of organization, and genres of material. The concept of "buckets" provides a mechanism for publishing and managing logically linked entities with multiple data formats. The NCSTRL+ prototype DL contains the holdings of NCSTRL and the NASA Technical Report Server (NTRS). The prototype demonstrates the feasibility of publishing into a multi-cluster DL, searching across clusters, and storing and presenting buckets of information. We show that the overhead for these additional capabilities is minimal to both the author and the user when compared to the equivalent process within NCSTRL.

Nelson, Michael L.↗