Central Computer Facility Research Articles

HSM and backup services at INFN-CNAF

IBM Spectrum Protect (ISP) software, one of the leader solutions in data protection, contributes to the data management infrastructure operated at CNAF, the central computing and storage facility of INFN (Istituto Nazionale di Fisica Nucleare – Italian National Institute for Nuclear Physics). It is used to manage about 55 Petabytes of scientific data produced by LHC (Large Hadron Collider at CERN) and other experiments in which INFN is involved, stored on tape resources as the highest latency storage tier within HSM (Hierarchical Space Management) environment. To accomplish this task, ISP works together with IBM Spectrum Scale (formerly GPFS - General Parallel File System) and GEMSS (Grid Enabled Mass Storage System), an in-house developed software layer that manages migration and recall queues. Moreover, we perform backup/archive operation of main IT services running at CNAF, such as mail servers, configurations, repositories, documents, logs, etc. In this paper we present the current configuration of the HSM infrastructure and the backup and recovery service, with particular attention to issues related to the increasing amount of scientific data to manage, expected for the next years.

Dynamic sharing of tape drives accessing scientific data

The data management infrastructure operated at CNAF, the central computing and storage facility of INFN (Italian Institute for Nuclear Physics), is based on both disk and tape storage resources. About 40 Petabytes of scientific data produced by LHC (Large Hadron Collider) at CERN and other experiments in which INFN is involved are stored on tape. This is the highest latency storage tier within HSM (Hierarchical Storage Management) environment. Writing and reading requests on tape media are satisfied through a set of Oracle-StorageTek T10000D tape drives, shared among different scientific communities. In the next years, the usage of tape drives will become more intense not only due to the growing amount of scientific data to manage but also due to general trend to use tapes as “slow disk”, announced by the main user communities. In order to reduce hardware purchases, a key point is to minimize the inactivity periods of tape drives. In this paper we present a software solution designed to optimize the efficiency of the shared usage of tape drives in our environment.

Information security and the Internet

Today, information technology is fundamental to the operation of most businesses, whether they are small companies or multinational corporations. In recent times, the implementation of local and wide area networks and the installation of computing equipment in office areas has brought information technology to nearly every working environment. The result is an increasing dependence on the availability, integrity and confidentiality of information stored and processed by these systems. As the trend shifts from “fortress” style central computer facilities to distributed systems located in generally less secure office environments, the risk of disruption increases, owing to lack of physical security, support services limitations and absence of site monitoring. The net result is higher business impact coupled with greater exposure. Identifies the elements that are at risk, discusses the issues businesses face when seeking to minimize exposures, suggests some practical solutions and describes some selected events that illustrate the hazards associated with having inadequate protection.

Security environment reviews

Today, information technology is fundamental to the operation of most businesses, whether they are small companies or multinational corporations. In recent times, the implementation of local and wide area networks and the installation of computing equipment in office areas has brought information technology to nearly every working environment. The result is an increasing dependence on the availability, integrity and confidentiality of information stored and processed by these systems. As the trend shifts from “fortress” style central computer facilities to distributed systems located in generally less secure office environments, the risk of disruption increases, owing to lack of physical security, support services limitations and absence of site monitoring. The net result is higher business impact coupled with greater exposure. Identifies the elements that are at risk, discusses the issues businesses face when seeking to minimize exposures, suggests some practical solutions and describes some selected eve...

Centers of Supercomputing— Supercomputing At Los Alamos National Laboratory

This paper reports on supercomputing at Los Alamos National Laboratory. Los Alamos has sought to intertwine the fields of computer science and nuclear science, while influencing the design of the computers needed to solve its scientific problems. The complexity and size of the applications prevalent at the Laboratory have dictated a continuing, ever-increasing need for computers one to two orders of magnitude faster than what is currently available. There are currently four CRAY Y-MPs and four X-MPs serving as production computers. The Central Computing Facility (CCF) and the Laboratory Data Communications Center (LDCC), a three-story building completed in 1989, house the supercomputers and associated network servers.

A clinic's perspective on screening, recruitment and data collection

This paper summarizes the approach of one university cardiology section with over a decade of experience in conducting National Institutes of Health and pharmaceutical cardiovascular trials. Many of the organizational and personnel issues discussed can be directly applied to most university cardiovascular clinical research settings. Other aspects reflect a very specialized approach but key features can be modified or adapted to smaller individual research clinics. In terms of organizational features, our multi-hospital recruitment effort is co-ordinated by a weekly clinical research conference which is attended by all nurse coordinators and cardiology fellows. Centralization of all clinic facilities and non-invasive laboratories, the central computer facility, and the availability of clinical research inpatient hospital beds facilitate our clinical research effort. An expanded role of the nurse co-ordinator is considered pivotal to trial performance. Suggestions are made as to the identification and recruitment of ideal nurse co-ordinators, maximizing their productivity, and retaining them. The key feature is the physicians' acceptance of the nurse co-ordinator as a colleague. The roles of the principal investigator and clinical cardiology fellows are delineated, and suggestions made for data entry and computer technical expertise to optimize nurse co-ordinator efficiency, allowing total focus on recruitment and follow-up.

The fermilab central computing facility architectural model

The goal of the current Central Computing Upgrade at Fermilab is to create a computing enviroment that maximizes total productivity, particularly for high energy physics analysis. The Computing Department and the Next Computer Acquisition Committee decided upon a model which includes five components: an interactive front-end, a LargeScale Scientific Computer (LSSC, a mainframe computing engine), a microprocessor farm system, a file server, and workstations. With the exception of the file server, all segments of this model are currently in production: a VAX/VMS cluster interactive front-end, an Amdahl VM computing engine, ACP farms, and (primary) VMS workstations. This paper will discuss the implemetation of the Fermilab Central Computing Facility Architectural Model. Implications for Code Management in such a heterogeneous environment, including issues such as modularity and centrality, will be considered. Special emphasis will be placed on connectivity and communications between the front-end, LSSC, and workstations, as practiced at Fermilab.

Central computer facility software directory

Abstract : This document contains a brief discussion of the function and operating requirements of the software currently supported by the Central Computer Facility. Contents: Editors and Text Processors; Compilers and Interpreters; Data base Management Systems; Engineering Tools; Mathematics and Statistics; and Data Manipulation.

The electronic library manager's guide to using central computer facilities

Many library and information people already use their organisation's mainframe for the provision of library services. More often than not the services will, in fact, be a computerised version of the basic library routines such as circulation, serials control, ordering, cataloguing and so on. The system might be a home‐grown one or it might be one of the many turn‐key integrated library systems available for mainframes. However, with thought, ingenuity and cooperation and some assistance from the Computer Department, the mainframe can be used to provide a whole host of other peripheral library services to staff throughout large organisations. In any such large organisation, especially of a scientific and technical R&D type, there will usually be a significant number of staff who have terminals connected to the main‐frame — for programming, running their own statistical software, CAD/CAE applications, in‐house database access, preparing documents, number‐crunching or whatever — and because they use their terminals daily they become a captive audience which you can reach far more easily, quickly and conveniently than you can with a flier or announcement list that gets distributed in the internal mail and then sits on their desks amidst a pile of other paper for days or longer.

Use of 3-D-computer graphics for imaging of distribution of hepatic metabolites.

In conjunction with the investigation of intercellular compartmentation of liver metabolism and as a logical further step, following the introduction of a new sample isolation procedure for microchemical analysis of functional liver cell heterogeneity, the possible benefit of computer-assisted three-dimensional imaging procedures for the reconstruction of hepatic metabolite distribution was investigated. In this intent, we elected to access a central computer facility by means of a small microcomputer system which, nevertheless, permitted to take full advantage of a large capacity main-frame computer and a high quality graphics plotter, at comparatively low overall costs. Commercially available software (SAS/GRAPH) was tailored to the specific requirements of this application. The three-dimensional imaging process recombines microchemical data (metabolite or enzyme values) with those of the size and location of samples within a particular cross-sectional area of a liver unit and provides an integrated view of metabolite distributions. The three-dimensional images were then used to define general distribution characteristics, as well as, differences in metabolite distribution along sinusoids of portal and septal origin. Glucose increased, whereas glucose-6-P decreased along sinusoids from the beginning to the end and values of both metabolites were found to be higher along 'portal/central' than along 'septal/central' sinusoids. Co-distribution of glucose-6-phosphatase with its substrate (glucose-6-P) was indicated by histochemical and microchemical results and is anticipated to be of considerable regulatory importance, since it further enhances the differences among hepatocytes at different locations along sinusoids with respect to their ability to produce glucose.(ABSTRACT TRUNCATED AT 250 WORDS)

Cost-Effective Data Communications for Personal Computer Applications Using Micro Earth Stations

The reduction in cost of computer processing and storage that led to personal computers has stimulated a need for comparable reduction in telecommunication costs to connect distributed personal computers to central computer facilities. A reexamination of the underlying technical options open to terrestrial and satellite telecommunications alternatives illustrates the advantages of satellite networks for data communication. The principles are illustrated with a description of a particular satellite network technology utilizing user-premises micro Earth stations that are cost-effective for use as accessories to personal computers or equivalent work stations.

Interconnecting computers with the high speed parallel interface

A variety of local computer network architectures have been evaluated for use in the Los Alamos National Laboratory Central Computing Facility in support of scientific research at this laboratory. A store-and-forward switched message system built around hardware products known as high speed parallel interfaces (HSPIs) was determined to be superior in this application to the more conventional contention bus systems. The HSPIs, together with some dedicated computers used as intermediate switching nodes, implement this store-and-forward architecture and form the backbone of the integrated computer network. The HSPI channel standard was developed at Los Alamos for the interconnection of computers of different manufacture. This standard intercomputer interface is used for passing data and messages via the input-output channels of the different computers. Reliable full-duplex point-to-point data transfers at speeds of up to 50 Mbits s −1 are accommodated. Extensive error detection and error correction capabilities are included in the HSPI hardware. HSPIs are currently in around-the-clock use at Los Alamos, interconnecting the computers of one of the world's most powerful computer networks. In this paper the HSPI specifications and use of the HSPIs in the network are discussed. The Los Alamos network architecture and comparisons to a contention bus architecture are also discussed.

A computer graphic study of cardiac truncal septation

AbstractSeptation of the cardiac truncus arteriosus in the normal rat embryo was described and illustrated by three‐dimensional reconstruction from serial sections through the developing outflow tract. Tracings of selected structures were digitized on an Apple II‐plus microcomputer, relayed through a central computer facility, and displayed on a Hewlett‐Packard 9845C graphics computer. Rotation and dissection of the color images allowed a kinetic description of the principal features of truncal septation and comparison with analogous events in the chick.A complex of tissue structures appeared in the downstream, distal truncus at 13 days of gestation and moved toward the ventricle(s) through the following day. As in the chick, the forming semilunar valves remained within 200 μm of the cephalic margin of the myocardial sleeve as they rotated and descended toward their definitive position against the heart. Mesenchymal condensations formed within the intervening aorticopulmonary (AP) septum and remained in close association with the principal bifurcation of the spiralling blood lumens, passing between the valves and descending along the conus septum. As the conus septum fused at 15 days of gestation, three outlets for cardiac outflow were seen: the major left and right streams to the aortic and pulmonary valves, respectively, and an apparently dwindling stream which crossed from the right ventricle behind the conus septum to exit through the aorta. In the chick, but not in the rat, nerve bundles invaded the distal truncus during septation to form the cardiac plexus.

The M7 - A Computer for on-Line Track-Finding

The M7 is a small fast computer with an instruction set designed to match the on-line pattern recognition problems of a high energy physics experiment. It has been used as a trigger processor in a photoproduction experiment at Fermilab. The full off-line track-finding program is being moved to the M7 to allow on-line selection of events based on detailed information and to relieve the burden on the central laboratory computer facility. The hardware, support software, and applications programs are discussed.

Decentralized Fiber Optic Acquisition System

The paper describes a decentralized data acquisition system installed for a long term on-site test at a French power plant. Two local autonomous stations acquire the information from 24 channels ; the data are continuously transmitted to a concentrator through two 600 m long optical cables at a rate of 0.96 Mbits/sec.. An error ratio lower than 10” on transmission, made possible through the use of optical fiber, allows testing to be performed in an industrial environment using only very simple error detection technique. The optical cables which follow interchangeable paths inside and outside the station, and operate in a temperature range of between -20°C and +60°C, are operational transmission media, which, during testing on large sites, eliminate the constraints related to the location of central computer facilities.

Transfer of Reports from an Automated Gas Chromatographic System to a Large Computer for Final Processing

Abstract An automated gas chromatographic system consisting of a Hewlett-Packard 5710 gas chromatograph, a Varian 8000 autosampler, and a Spectra-Physics 4000 laboratory data system has been interfaced to FDA's large, central computer facility by using a Tektronix 4923-01 digital cartridge tape recorder. The autosampler provides single or multiple injections of up to 60 samples. The data system is preprogrammed with appropriate sample and standard information in addition to parameters for proper peak integration. A chromatogram is traced and a report of integration area counts for each peak detected is prepared by the data system after each chromatographic analysis. A duplicate of each report is recorded on the data cartridge. After analysis of all samples, the quality of chromatography is examined for acceptability. The chromatographic reports contained on the data cartridge may then be entered into the computer via a terminal equipped with a similar digital cartridge tape recorder. Translation of the reports, correlation of responses from sample and standard solutions, all calculations, and a complete report of each sample analysis are obtained by using the computer programming language APL. The data system-cartridge tape recorder interface, as well as data reduction using the large computer, is discussed.

Advances in Well Logging

Distinguished Author Series articles are general, descriptiverepresentations that summarize the state of the art in an area of technology bydescribing recent developments for readers who are not specialists in thetopics discussed. Written by individuals recognized as experts in the area, these articles provide key references to more definitive work and presentspecific details only to illustrate the technology. Purpose: to informthe general readership of recent advances in various areas of petroleumengineering. INTRODUCTION Well logging is an integral part of formation evaluation inthat borehole measurements provide the largest source of data. These are usedwith core and fluid data to determine reservoir depth and thickness, porosity, lithology, hydrocarbon saturation, and permeability. This porosity, lithology, hydrocarbon saturation, and permeability. This information also aids indrilling, completion, and operation of wells; geological and geophysicalexploration; and development of reservoir models for efficient production.Borehole measurements of geophysical parameters involve downhole sensors(sondes), means for transmitting data to the surface, and recording andprocessing systems. Physical properties are measured and recorded as functionsof depth to obtain well logs. Then the measured physical parameter logs areinterpreted to obtain logs of derived formation parameter logs are interpretedto obtain logs of derived formation parameters. These include fundamentalproperties such as porosity, parameters. These include fundamental propertiessuch as porosity, permeability, saturation, and any other subsurfaceinformation needed in permeability, saturation, and any other subsurfaceinformation needed in geological, reservoir, and economic analyses. Explorationfor hydrocarbons in high-cost areas and enhanced recovery operations with long, uncertain lead times have increased the demand for more accurate evaluation ofnew formations and re-evaluation of some old ones. This demand for accurateformation evaluation is increasing not only the number of well-logging sensorsneeded but the amount of data required of each. For example, the data rate fora conventional induction/ sonic log is 200 bits per borehole foot, two ordersof magnitude higher for a high-resolution dipmeter, and three times more for anacoustic full waveform log (60 kilobits per foot). Estimated data rates forfuture acoustic and induced gamma ray spectroscopy tools are two orders ofmagnitude higher than these (i.e., on the order of megabits per foot). To putit in a familiar perspective, in an average well the acoustic full waveform logrecords roughly the same amount of data that a conventional seismic surveyrecords over a 1-mile section. Several significant advances have been developedto meet the challenge of data explosion. Logging tools have been equipped withdownhole computers for digital transmission of data to the surface, where othercomputers are used for recording and real-time processing. Combination loggingtools have been developed to reduce rig time during logging; some can recordsix or more petrophysical measurements concurrently. For example, a combinationtool consisting of gamma ray, dual-induction, compensated-neutron, andcompensated-formation-density logs provides, in a single run, a complete suiteof logs for formation provides, in a single run, a complete suite of logs forformation evaluation. Wellsite computers provide quick-look processing of theselog data for immediate completion decisions. They also allow transmission bymeans of satellites or phone lines to central computer facilities. Well loggingmethods usually do not measure directly the primary rock properties needed forreservoir engineering purposes: porosity, properties needed for reservoirengineering purposes: porosity, permeability, fluid saturation, and fluidmobility. These parameters are permeability, fluid saturation, and fluidmobility. These parameters are inferred from borehole measurements ofelectromagnetic, acoustic, and nuclear properties. Nevertheless, these methodsdo provide the best, sometimes the only, opportunity for measuring theseproperties in place in a relatively undisturbed state. Well logging is arapidly developing technology encompassing far too many methods to describe.This article highlights some of the technology in a more general fashion. Ref.1 gives a more detailed overview; references cited therein give furtherdetails. ELECTROMAGNETIC WAVE METHODS(Resistivity Logs). Properties ofelectromagnetic waves are measured in boreholes in a broad frequency rangevarying from DC to gigaHertz, primarily for evaluation of hydrocarbonsaturation. Numerous tools and techniques involving focused resistivity andconductivity and microresistivity have been developed to measure the electricalresistivities of the formation, both within the invaded zone () and beyond(true formation resistivity,). However, none of these alone can measure trueformation resistivity under all borehole and formation conditions. Theselection of a proper combination of deep and shallow investigating tools fordetermining depends on formation conditions such as connate water resistivityand porosity as well as borehole conditions such as mud salinity and holesize. p. 1181

The community file station

AbstractThis paper describes the design and use of the Community File Station, an intelligent terminal system, at a college with a large central computer facility. The Community File Station allows functions such as text preparation, editing, local file management and rapid text display to be performed locally without any interaction with the central computer system. It is hoped that the combination of such a terminal system with a high speed campus network will have a significant impact on the way in which the user community uses the central system. Some examples of the way in which the terminal is used is given, along with the way in which the role of the central system changes for the user of the Community File Station.

Evolution of data communications at the University of Missouri

The University of Missouri system is composed of four campuses, in Columbia, Kansas City, Rolla and St. Louis. The University has been in the data communications business since the fall of 1971, when a remote job entry connection was established between the St. Louis campus and a then large cpu in Columbia. A large central computer facility, consisting of an Amdahl 470 V/7 and an IBM 3031, now serves all four campuses of the University, other Missouri institutions of higher education, and several state and federal government agencies.

Interactive user productivity

The cost of accomplishing work on a central computer facility— providing service to a large number of interactive users—has shifted, with the cost of the aggregate user time being the dominant component. Moreover, user costs are expected to continue to increase and system costs are expected to continue to decrease in the coming decade. This suggests that computer systems should be managed for maximum user effectiveness rather than for maximum machine usage.