Pub Date : 1994-06-12DOI: 10.1109/MASS.1994.373015
Kazuo Yoshida
On February 4, 1994 the National Space Development Agency (NASDA) of Japan successfully launched H-II, a new Japanese rocket vehicle. In February 1996, the H-II rocket vehicle will launch the Advanced Earth-Observing Satellite (ADEOS) from the Tanegashima Space Center. ADEOS, which will conduct international missions, will contribute to the global observation of environmental changes for the international community. In addition to ADEOS, a variety of other Earth-observing satellites will provide a large volume of data from space. In order to monitor, understand and predict global change, space agencies consider it imperative to make maximum use of data from space. NASDA considers it essential to build up closer cooperation among world Earth science experts. NASDA has begun developing the Earth-Observing Data and Information System (EOIS). Using such things as the data mass storage system (DMSS) and networks, EOIS will provide highly processed, scientifically verified Earth observation data from space to Earth science experts around the world.<>
{"title":"Data management for the National Space Development Agency's (NASDA's) Earth-Observing Data and Information System (EOIS)","authors":"Kazuo Yoshida","doi":"10.1109/MASS.1994.373015","DOIUrl":"https://doi.org/10.1109/MASS.1994.373015","url":null,"abstract":"On February 4, 1994 the National Space Development Agency (NASDA) of Japan successfully launched H-II, a new Japanese rocket vehicle. In February 1996, the H-II rocket vehicle will launch the Advanced Earth-Observing Satellite (ADEOS) from the Tanegashima Space Center. ADEOS, which will conduct international missions, will contribute to the global observation of environmental changes for the international community. In addition to ADEOS, a variety of other Earth-observing satellites will provide a large volume of data from space. In order to monitor, understand and predict global change, space agencies consider it imperative to make maximum use of data from space. NASDA considers it essential to build up closer cooperation among world Earth science experts. NASDA has begun developing the Earth-Observing Data and Information System (EOIS). Using such things as the data mass storage system (DMSS) and networks, EOIS will provide highly processed, scientifically verified Earth observation data from space to Earth science experts around the world.<<ETX>>","PeriodicalId":436281,"journal":{"name":"Proceedings Thirteenth IEEE Symposium on Mass Storage Systems. Toward Distributed Storage and Data Management Systems","volume":"350 3","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1994-06-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133940263","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 1994-06-12DOI: 10.1109/MASS.1994.373012
A. Kerr
{"title":"Towards Distributed Storage and Data Management Systems","authors":"A. Kerr","doi":"10.1109/MASS.1994.373012","DOIUrl":"https://doi.org/10.1109/MASS.1994.373012","url":null,"abstract":"","PeriodicalId":436281,"journal":{"name":"Proceedings Thirteenth IEEE Symposium on Mass Storage Systems. Toward Distributed Storage and Data Management Systems","volume":"45 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1994-06-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125012917","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 1994-06-12DOI: 10.1109/MASS.1994.373021
Rainer Töebbicke
Currently, there is a move away from huge, monolithic mainframe computers to smaller, individual workstations. This move requires that data and programs be shared between individual users on the same computer as well as across machines on a local area network (LAN) or even on a wide area network (WAN). A popular distributed file system is Transarc's Andrew File System (AFS), the precursor of the Open Software Foundation's (OSF) Distributed File Service (DFS), part of OSF's Distributed Computing Environment. This paper compares AFS and DFS with other successful distributed file systems, discussing clients and file servers, data cache (cache consistency and authentication), file system topology, access rights, privileged programs, critical data, and authentication in long-running batch jobs.<>
{"title":"Distributed file systems: focus on Andrew File System/Distributed File Service (AFS/DFS)","authors":"Rainer Töebbicke","doi":"10.1109/MASS.1994.373021","DOIUrl":"https://doi.org/10.1109/MASS.1994.373021","url":null,"abstract":"Currently, there is a move away from huge, monolithic mainframe computers to smaller, individual workstations. This move requires that data and programs be shared between individual users on the same computer as well as across machines on a local area network (LAN) or even on a wide area network (WAN). A popular distributed file system is Transarc's Andrew File System (AFS), the precursor of the Open Software Foundation's (OSF) Distributed File Service (DFS), part of OSF's Distributed Computing Environment. This paper compares AFS and DFS with other successful distributed file systems, discussing clients and file servers, data cache (cache consistency and authentication), file system topology, access rights, privileged programs, critical data, and authentication in long-running batch jobs.<<ETX>>","PeriodicalId":436281,"journal":{"name":"Proceedings Thirteenth IEEE Symposium on Mass Storage Systems. Toward Distributed Storage and Data Management Systems","volume":"10 2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1994-06-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134544182","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 1994-06-12DOI: 10.1109/MASS.1994.373024
B. Olear
The National Storage Laboratory (NSL) was organized to investigate, demonstrate, and commercialize high-performance hardware and sofnyare storage technologies that promise to remove network computing bottlenecks and to provide critically needed new storage system functionality. This paper briefly outlines the NSL ’s goals, the NSL collaboration, the NSL’s current status and organization, and the applications drive for the NSL. The NSL‘s goals and the NSL collaboration The goals of organizing the National Storage Laboratory (NSL) were to investigate, demonstrate, and commercialize high-performance hardware and software storage technologies that promise to remove network computing bottlenecks and to provide critically needed new storage system functionality [ 1],[2],[3]. This new functionality will help meet the storage requirements of crucial scientific, engineering, industrial, and commercial applications; provide new methods of storage system resource utilization to commercial vendors; provide capabilities needed in the planned United States national information infrastructure; and help guide the efforts of storage system standards groups. 0
{"title":"Reference Model and Storage Consortia","authors":"B. Olear","doi":"10.1109/MASS.1994.373024","DOIUrl":"https://doi.org/10.1109/MASS.1994.373024","url":null,"abstract":"The National Storage Laboratory (NSL) was organized to investigate, demonstrate, and commercialize high-performance hardware and sofnyare storage technologies that promise to remove network computing bottlenecks and to provide critically needed new storage system functionality. This paper briefly outlines the NSL ’s goals, the NSL collaboration, the NSL’s current status and organization, and the applications drive for the NSL. The NSL‘s goals and the NSL collaboration The goals of organizing the National Storage Laboratory (NSL) were to investigate, demonstrate, and commercialize high-performance hardware and software storage technologies that promise to remove network computing bottlenecks and to provide critically needed new storage system functionality [ 1],[2],[3]. This new functionality will help meet the storage requirements of crucial scientific, engineering, industrial, and commercial applications; provide new methods of storage system resource utilization to commercial vendors; provide capabilities needed in the planned United States national information infrastructure; and help guide the efforts of storage system standards groups. 0","PeriodicalId":436281,"journal":{"name":"Proceedings Thirteenth IEEE Symposium on Mass Storage Systems. Toward Distributed Storage and Data Management Systems","volume":"264 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1994-06-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132498053","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 1994-06-12DOI: 10.1109/MASS.1994.373022
Christopher Maher, Jonathan S. Goldick, C. Kirby, Bill Zumach
The benefits of integrating distributed file systems with mass storage systems are presented. Key integration issues are discussed. Examples of efforts to integrate the Network File System (NFS) and the Andrew File System (AFS) with a number of mass storage systems are presented. Future research and development issues are discussed.<>
{"title":"The integration of distributed file systems and mass storage systems","authors":"Christopher Maher, Jonathan S. Goldick, C. Kirby, Bill Zumach","doi":"10.1109/MASS.1994.373022","DOIUrl":"https://doi.org/10.1109/MASS.1994.373022","url":null,"abstract":"The benefits of integrating distributed file systems with mass storage systems are presented. Key integration issues are discussed. Examples of efforts to integrate the Network File System (NFS) and the Andrew File System (AFS) with a number of mass storage systems are presented. Future research and development issues are discussed.<<ETX>>","PeriodicalId":436281,"journal":{"name":"Proceedings Thirteenth IEEE Symposium on Mass Storage Systems. Toward Distributed Storage and Data Management Systems","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1994-06-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128623067","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 1994-06-12DOI: 10.1109/MASS.1994.373039
G. Weikum
Summary form only given, as follows. Parallel storage systems such as disk arrays or disk farms provide opportunities for exploiting I/O parallelism in two possible ways: via interrequest parallelism and via intrarequest parallelism. We argue for software-controlled storage systems in which each disk can be accessed individually and data partitioning, as well as data allocation, is completely under the control of the file system. We discuss the main issues in performance tuning of such systems-striping and load balancing-and show their relationship to response time and throughput. We outline the main components of an intelligent file system that performs striping on a file-specific basis by taking into account the requirements of the applications and performs load balancing by judicious file allocation and dynamic redistributions of the data when access patterns change. Our system uses simple but effective heuristics that incur only little overhead. We report on experiments based on real-life traces. >
{"title":"Data partitioning and load balancing in parallel storage systems","authors":"G. Weikum","doi":"10.1109/MASS.1994.373039","DOIUrl":"https://doi.org/10.1109/MASS.1994.373039","url":null,"abstract":"Summary form only given, as follows. Parallel storage systems such as disk arrays or disk farms provide opportunities for exploiting I/O parallelism in two possible ways: via interrequest parallelism and via intrarequest parallelism. We argue for software-controlled storage systems in which each disk can be accessed individually and data partitioning, as well as data allocation, is completely under the control of the file system. We discuss the main issues in performance tuning of such systems-striping and load balancing-and show their relationship to response time and throughput. We outline the main components of an intelligent file system that performs striping on a file-specific basis by taking into account the requirements of the applications and performs load balancing by judicious file allocation and dynamic redistributions of the data when access patterns change. Our system uses simple but effective heuristics that incur only little overhead. We report on experiments based on real-life traces. >","PeriodicalId":436281,"journal":{"name":"Proceedings Thirteenth IEEE Symposium on Mass Storage Systems. Toward Distributed Storage and Data Management Systems","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1994-06-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131427806","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 1994-06-12DOI: 10.1109/MASS.1994.373032
R. Gurin, A. Maslennikov
A compact, interactive tape management system is described. It is fast, requires no commercial software, and includes a user-friendly human interface. The CASPUR tape management system (TMS) was designed for relatively small (up to several tens of thousands tapes) tape pools. The main design principle was simplicity: no sophisticated database tools or systems are used; instead, the TMS server keeps all the information in plain text file. This design decision could have led to difficulties, such as those that could be encountered if one needs to change/introduce some fields in the database. However, this difficulty does not occur with the CASPUR TMS because all the data fields are well defined from the very beginning.<>
{"title":"Simple tape management system","authors":"R. Gurin, A. Maslennikov","doi":"10.1109/MASS.1994.373032","DOIUrl":"https://doi.org/10.1109/MASS.1994.373032","url":null,"abstract":"A compact, interactive tape management system is described. It is fast, requires no commercial software, and includes a user-friendly human interface. The CASPUR tape management system (TMS) was designed for relatively small (up to several tens of thousands tapes) tape pools. The main design principle was simplicity: no sophisticated database tools or systems are used; instead, the TMS server keeps all the information in plain text file. This design decision could have led to difficulties, such as those that could be encountered if one needs to change/introduce some fields in the database. However, this difficulty does not occur with the CASPUR TMS because all the data fields are well defined from the very beginning.<<ETX>>","PeriodicalId":436281,"journal":{"name":"Proceedings Thirteenth IEEE Symposium on Mass Storage Systems. Toward Distributed Storage and Data Management Systems","volume":"56 10","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1994-06-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"113956546","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 1994-06-12DOI: 10.1109/MASS.1994.373043
D. Dixon
In September 1993, a workshop on mass storage requirements was held at the European Centre for Medium-Range Weather Forecasts (ECMWF) with the objective of discussing, and hopefully finding a common approach to, the problems facing large-scale scientific data processing sites in Europe and elsewhere. The outcome of the workshop was a cooperative venture to develop a specification for a mass storage system that could meet, or come close to meeting, the needs of most of the sites represented in the working group. The hope was to demonstrate a common direction and a common set of interests in the group, thus influencing developers and suppliers of large mass storage systems to align their offerings more closely with the group's needs. By allowing free access to the specification itself, we hope to provide a valuable resource for those who write requests for proposals (RFPs) in the area of mass storage systems. This effort is still in its early stages. The eventual results are intended to be of use to both installations and suppliers, resulting in a better outcome for all those working in large mass storage systems in scientific environments.<>
{"title":"A joint European mass storage specification effort","authors":"D. Dixon","doi":"10.1109/MASS.1994.373043","DOIUrl":"https://doi.org/10.1109/MASS.1994.373043","url":null,"abstract":"In September 1993, a workshop on mass storage requirements was held at the European Centre for Medium-Range Weather Forecasts (ECMWF) with the objective of discussing, and hopefully finding a common approach to, the problems facing large-scale scientific data processing sites in Europe and elsewhere. The outcome of the workshop was a cooperative venture to develop a specification for a mass storage system that could meet, or come close to meeting, the needs of most of the sites represented in the working group. The hope was to demonstrate a common direction and a common set of interests in the group, thus influencing developers and suppliers of large mass storage systems to align their offerings more closely with the group's needs. By allowing free access to the specification itself, we hope to provide a valuable resource for those who write requests for proposals (RFPs) in the area of mass storage systems. This effort is still in its early stages. The eventual results are intended to be of use to both installations and suppliers, resulting in a better outcome for all those working in large mass storage systems in scientific environments.<<ETX>>","PeriodicalId":436281,"journal":{"name":"Proceedings Thirteenth IEEE Symposium on Mass Storage Systems. Toward Distributed Storage and Data Management Systems","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1994-06-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122270056","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 1994-06-12DOI: 10.1109/MASS.1994.373050
R. Abraham, R. C. Freeman
The market for removable-media mass storage devices is driven by mushrooming memory requirements for imaging, CAD/CAM, and archiving applications. The diverse products serving these needs will slash as users and integrators weigh performance requirements, functionality, and costs, according to Mass Storage Outlook, a market analysis published by Freeman Associates, Inc., (1993). The authors analyzed seven categories of tape libraries and six categories of optical-disk libraries to determine the key trends and issues in this dynamic market.<>
{"title":"Overview of the removable-media mass storage market","authors":"R. Abraham, R. C. Freeman","doi":"10.1109/MASS.1994.373050","DOIUrl":"https://doi.org/10.1109/MASS.1994.373050","url":null,"abstract":"The market for removable-media mass storage devices is driven by mushrooming memory requirements for imaging, CAD/CAM, and archiving applications. The diverse products serving these needs will slash as users and integrators weigh performance requirements, functionality, and costs, according to Mass Storage Outlook, a market analysis published by Freeman Associates, Inc., (1993). The authors analyzed seven categories of tape libraries and six categories of optical-disk libraries to determine the key trends and issues in this dynamic market.<<ETX>>","PeriodicalId":436281,"journal":{"name":"Proceedings Thirteenth IEEE Symposium on Mass Storage Systems. Toward Distributed Storage and Data Management Systems","volume":"196 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1994-06-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133880421","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 1994-06-12DOI: 10.1109/MASS.1994.373049
B. Bidwell, Ma Chi, Roberto Colao, Brian D. Herr, Joe Kavaky, Charles Richards
Summary form only given, as follows. We present capabilities considered necessary for an IBM-9076-based parallel file system and discuss ways that these capabilities can be delivered in an IBM 9076 environment. Expected input/output performance of both existing serial and specially coded kernels of code are discussed.<>
{"title":"Parallel file system experience on the IBM 9076","authors":"B. Bidwell, Ma Chi, Roberto Colao, Brian D. Herr, Joe Kavaky, Charles Richards","doi":"10.1109/MASS.1994.373049","DOIUrl":"https://doi.org/10.1109/MASS.1994.373049","url":null,"abstract":"Summary form only given, as follows. We present capabilities considered necessary for an IBM-9076-based parallel file system and discuss ways that these capabilities can be delivered in an IBM 9076 environment. Expected input/output performance of both existing serial and specially coded kernels of code are discussed.<<ETX>>","PeriodicalId":436281,"journal":{"name":"Proceedings Thirteenth IEEE Symposium on Mass Storage Systems. Toward Distributed Storage and Data Management Systems","volume":"41 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1994-06-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131130756","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：