Pub Date : 1994-06-12DOI: 10.1109/MASS.1994.373046
D. Graves
Summary form only given, as follows. Longitudinal magnetic tape recording technology developed by IBM has produced very significant advances that will permit a future generation of products to offer performance well beyond that of the familiar 3480, 3490, and 3490E. Several key technological advances have been integrated to provide significantly higher capacity and data rate, combined with higher reliability. These "jumps" in capacity, data rate, and reliability are far larger than any prior such advances in the history of IBM longitudinal magnetic tape recording. Another benefit of the new technology is that it is affordable: its higher performance and reliability can be offered at prices comparable to those of today's other longitudinal tape devices.<>
{"title":"Major capacity, data rate, and reliability advances in IBM longitudinal magnetic tape recording technology","authors":"D. Graves","doi":"10.1109/MASS.1994.373046","DOIUrl":"https://doi.org/10.1109/MASS.1994.373046","url":null,"abstract":"Summary form only given, as follows. Longitudinal magnetic tape recording technology developed by IBM has produced very significant advances that will permit a future generation of products to offer performance well beyond that of the familiar 3480, 3490, and 3490E. Several key technological advances have been integrated to provide significantly higher capacity and data rate, combined with higher reliability. These \"jumps\" in capacity, data rate, and reliability are far larger than any prior such advances in the history of IBM longitudinal magnetic tape recording. Another benefit of the new technology is that it is affordable: its higher performance and reliability can be offered at prices comparable to those of today's other longitudinal tape devices.<<ETX>>","PeriodicalId":436281,"journal":{"name":"Proceedings Thirteenth IEEE Symposium on Mass Storage Systems. Toward Distributed Storage and Data Management Systems","volume":"4 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":"116954534","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.1994.373026
A. Hoagland
A consortium of American companies and univergoals of these projects include attaining a recordsities called The National Storage Industry Coning density of 10 gigabits per square inch on magnetic sortium (NSIC) has been formed for the purpose of disk and 1 terabyte per cubic inch on magnetic tape; soliciting US Government funding to support “pregoals for optical storage are similar to these. A brief proprietary” technology initiatives focused on accelreview will be given of the NSIC organization, its erating technical advances in data storage technology. technical program structure, and the status of the A set of 5-year projects was funded last year. The ARPA-funded technical activities.
{"title":"Storage Technology Initiatives - NSIC (National Storage Industry Consortium)","authors":"A. Hoagland","doi":"10.1109/MASS.1994.373026","DOIUrl":"https://doi.org/10.1109/MASS.1994.373026","url":null,"abstract":"A consortium of American companies and univergoals of these projects include attaining a recordsities called The National Storage Industry Coning density of 10 gigabits per square inch on magnetic sortium (NSIC) has been formed for the purpose of disk and 1 terabyte per cubic inch on magnetic tape; soliciting US Government funding to support “pregoals for optical storage are similar to these. A brief proprietary” technology initiatives focused on accelreview will be given of the NSIC organization, its erating technical advances in data storage technology. technical program structure, and the status of the A set of 5-year projects was funded last year. The ARPA-funded technical activities.","PeriodicalId":436281,"journal":{"name":"Proceedings Thirteenth IEEE Symposium on Mass Storage Systems. Toward Distributed Storage and Data Management Systems","volume":"28 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":"124912539","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.1994.373014
G. Withee, William T. Turnbull
NOAA's data holdings and user demand for data are both growing rapidly. By the year 2001, we expect to have over I petabyte of environmental data in our archives and to service nearly a million users per year. The archives will be distributed across NOAA, while our users will be both national and international. The modern NOAA data and information management system must serve all users transparently while efficiently handling these tremendous volumes of data.<>
{"title":"NOAA's environmental data system requirements: in search of a distributed data management system","authors":"G. Withee, William T. Turnbull","doi":"10.1109/MASS.1994.373014","DOIUrl":"https://doi.org/10.1109/MASS.1994.373014","url":null,"abstract":"NOAA's data holdings and user demand for data are both growing rapidly. By the year 2001, we expect to have over I petabyte of environmental data in our archives and to service nearly a million users per year. The archives will be distributed across NOAA, while our users will be both national and international. The modern NOAA data and information management system must serve all users transparently while efficiently handling these tremendous volumes of data.<<ETX>>","PeriodicalId":436281,"journal":{"name":"Proceedings Thirteenth IEEE Symposium on Mass Storage Systems. Toward Distributed Storage and Data Management Systems","volume":"54 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":"128047887","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.1994.373056
C. Curran
The European Laboratory for Particle Physics (CERN) is a high-energy particle physics laboratory based at a site shared between France and Switzerland, near Geneva. Altogether, an average of 4,000 staff and visitors are on site, using a lot of data - currently about 80 terabytes (Tbytes) - and a lot of computing power currently about 5,000 workstations of many types. Efforts have been made by CERN’s Computing and Networks Division (CN) to contain the growth in manpower requirements for manipulating data on tapes and cartridges. Initially, this involved making the manual arrangements as efficient as possible, but recent efforts have been directed toward trying to make use of automatic libraries. Beginning with a large protoope Haushahn system, we have now installed two IBM 3495 L50s, an Exabyte 120, an IGM-ATL, and an IBM 3494. Each of these machines has had both excellent and deplorable features, and each has provoked serious problems when exposed to the user community. Not all of these difficulties were expected, and some seem unlikely to be remedied. However, some may be avoidable. Foolish beginnings
{"title":"Robotic experiences or traumatic experiences?","authors":"C. Curran","doi":"10.1109/MASS.1994.373056","DOIUrl":"https://doi.org/10.1109/MASS.1994.373056","url":null,"abstract":"The European Laboratory for Particle Physics (CERN) is a high-energy particle physics laboratory based at a site shared between France and Switzerland, near Geneva. Altogether, an average of 4,000 staff and visitors are on site, using a lot of data - currently about 80 terabytes (Tbytes) - and a lot of computing power currently about 5,000 workstations of many types. Efforts have been made by CERN’s Computing and Networks Division (CN) to contain the growth in manpower requirements for manipulating data on tapes and cartridges. Initially, this involved making the manual arrangements as efficient as possible, but recent efforts have been directed toward trying to make use of automatic libraries. Beginning with a large protoope Haushahn system, we have now installed two IBM 3495 L50s, an Exabyte 120, an IGM-ATL, and an IBM 3494. Each of these machines has had both excellent and deplorable features, and each has provoked serious problems when exposed to the user community. Not all of these difficulties were expected, and some seem unlikely to be remedied. However, some may be avoidable. Foolish beginnings","PeriodicalId":436281,"journal":{"name":"Proceedings Thirteenth IEEE Symposium on Mass Storage Systems. Toward Distributed Storage and Data Management Systems","volume":"31 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":"128290538","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.1994.373040
K. Keeton, A. Drapeau, D. Patterson, R. Katz
In the next decade, video-on-demand (VOD) services will be widely available to customers and potentially highly profitable to service providers. In order to provide access to many movies, video storage servers may contain not only magnetic disks but also high-capacity tertiary storage devices. In this paper, we study two storage device alternatives: an array of magnetic disks and an array of magnetic tapes. Magnetic disk arrays provide high-bandwidth, low-latency retrieval and moderate storage capacity at high cost. Magnetic tape arrays provide low-bandwidth, high-latency retrieval and high storage capacity at low cost. We evaluate these two storage system alternatives to determine the number of users that each can support. Our simulations show that magnetic disk arrays can support considerably more users, at a lower cost per user, than magnetic tape arrays.<>
{"title":"Storage alternatives for video service","authors":"K. Keeton, A. Drapeau, D. Patterson, R. Katz","doi":"10.1109/MASS.1994.373040","DOIUrl":"https://doi.org/10.1109/MASS.1994.373040","url":null,"abstract":"In the next decade, video-on-demand (VOD) services will be widely available to customers and potentially highly profitable to service providers. In order to provide access to many movies, video storage servers may contain not only magnetic disks but also high-capacity tertiary storage devices. In this paper, we study two storage device alternatives: an array of magnetic disks and an array of magnetic tapes. Magnetic disk arrays provide high-bandwidth, low-latency retrieval and moderate storage capacity at high cost. Magnetic tape arrays provide low-bandwidth, high-latency retrieval and high storage capacity at low cost. We evaluate these two storage system alternatives to determine the number of users that each can support. Our simulations show that magnetic disk arrays can support considerably more users, at a lower cost per user, than magnetic tape arrays.<<ETX>>","PeriodicalId":436281,"journal":{"name":"Proceedings Thirteenth IEEE Symposium on Mass Storage Systems. Toward Distributed Storage and Data Management Systems","volume":"79 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":"123273930","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.1994.373029
J. Shiers
The NCAR Mass Storage System, MSS-III, generates I O megabytes a day of transaction log containing information about its workload. Traditional metrics, such as the average amount of data stored and retrieved per hour, are useful but omit information regarding temporality, locality, and burstiness. This infomation is critical to characterizing and understanding the MSS workload. NCAR has begun to use metrics usually applied to virtual memories, hardware caches, and network trafic to analyze the MSS-III transaction logs. Current MSS-III workload characterization falls into three broad categories: parametric statistics (for example, mean and variance for various file and data metrics), trace-driven analysis (for example, working set size), and trace-driven simulation (for example, compulsory and capacity cache miss ratios). Resultsfrom all of these methods are presented. Graphs of MSS-III transactions across a range of time scales show a self-similarity or ‘Ifractal burstiness” typical of network trafic. This suggests that measurements of sevsimilarity (for example, the Hurst parameter) may be useful. Also, the lack of normal distribution suggests that application of nonparametric statistics might be fncitful.
{"title":"Storage System Issues","authors":"J. Shiers","doi":"10.1109/MASS.1994.373029","DOIUrl":"https://doi.org/10.1109/MASS.1994.373029","url":null,"abstract":"The NCAR Mass Storage System, MSS-III, generates I O megabytes a day of transaction log containing information about its workload. Traditional metrics, such as the average amount of data stored and retrieved per hour, are useful but omit information regarding temporality, locality, and burstiness. This infomation is critical to characterizing and understanding the MSS workload. NCAR has begun to use metrics usually applied to virtual memories, hardware caches, and network trafic to analyze the MSS-III transaction logs. Current MSS-III workload characterization falls into three broad categories: parametric statistics (for example, mean and variance for various file and data metrics), trace-driven analysis (for example, working set size), and trace-driven simulation (for example, compulsory and capacity cache miss ratios). Resultsfrom all of these methods are presented. Graphs of MSS-III transactions across a range of time scales show a self-similarity or ‘Ifractal burstiness” typical of network trafic. This suggests that measurements of sevsimilarity (for example, the Hurst parameter) may be useful. Also, the lack of normal distribution suggests that application of nonparametric statistics might be fncitful.","PeriodicalId":436281,"journal":{"name":"Proceedings Thirteenth IEEE Symposium on Mass Storage Systems. Toward Distributed Storage and Data Management Systems","volume":"95 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":"114325991","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.1994.373041
D. Dixon
{"title":"Data Management and Mass Storage Specification","authors":"D. Dixon","doi":"10.1109/MASS.1994.373041","DOIUrl":"https://doi.org/10.1109/MASS.1994.373041","url":null,"abstract":"","PeriodicalId":436281,"journal":{"name":"Proceedings Thirteenth IEEE Symposium on Mass Storage Systems. Toward Distributed Storage and Data Management Systems","volume":"37 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":"134148280","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.1994.373031
D. M. Gaunt
A tape management system was developed in the mainframe era to manage the large number of demountable magnetic volumes. Migration from mainframes to distributed systems and the development of data storage systems necessitated a fresh appraisal of the functionality required from the volume management system. The evolution of the functions provided by the volume management system are described.<>
{"title":"Alternate views on the physical volume library","authors":"D. M. Gaunt","doi":"10.1109/MASS.1994.373031","DOIUrl":"https://doi.org/10.1109/MASS.1994.373031","url":null,"abstract":"A tape management system was developed in the mainframe era to manage the large number of demountable magnetic volumes. Migration from mainframes to distributed systems and the development of data storage systems necessitated a fresh appraisal of the functionality required from the volume management system. The evolution of the functions provided by the volume management system are described.<<ETX>>","PeriodicalId":436281,"journal":{"name":"Proceedings Thirteenth IEEE Symposium on Mass Storage Systems. Toward Distributed Storage and Data Management Systems","volume":"48 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":"114692933","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.1994.373030
J. L. Sloan
The NCAR Mass Storage System, MSS-III, generates 10 megabytes a day of transaction log, containing information about its workload. Traditional metrics, such as the average amount of data stored and retrieved per hour, are useful but omit information regarding temporality, locality, and burstiness. This information is critical to characterizing and understanding the MSS workload. NCAR has begun to use metrics usually applied to virtual memories, hardware caches, and network traffic to analyze the MSS-III transaction logs. Current MSS-III workload characterization falls into three broad categories: parametric statistics (for example, mean and variance for various file and data metrics), trace-driven analysis (for example, working set size), and trace-driven simulation (for example, compulsory and capacity cache miss ratios). Results from all of these methods are presented. Graphs of MSS-III transactions across a range of time scales show a self-similarity or "fractal burstiness", typical of network traffic. This suggests that measurements of self-similarity (for example, the Hurst parameter) may be useful. Also, the lack of normal distribution suggests that application of nonparametric statistics might be fruitful.<>
{"title":"Flying with instruments: characterizing the NCAR MSS-III workload","authors":"J. L. Sloan","doi":"10.1109/MASS.1994.373030","DOIUrl":"https://doi.org/10.1109/MASS.1994.373030","url":null,"abstract":"The NCAR Mass Storage System, MSS-III, generates 10 megabytes a day of transaction log, containing information about its workload. Traditional metrics, such as the average amount of data stored and retrieved per hour, are useful but omit information regarding temporality, locality, and burstiness. This information is critical to characterizing and understanding the MSS workload. NCAR has begun to use metrics usually applied to virtual memories, hardware caches, and network traffic to analyze the MSS-III transaction logs. Current MSS-III workload characterization falls into three broad categories: parametric statistics (for example, mean and variance for various file and data metrics), trace-driven analysis (for example, working set size), and trace-driven simulation (for example, compulsory and capacity cache miss ratios). Results from all of these methods are presented. Graphs of MSS-III transactions across a range of time scales show a self-similarity or \"fractal burstiness\", typical of network traffic. This suggests that measurements of self-similarity (for example, the Hurst parameter) may be useful. Also, the lack of normal distribution suggests that application of nonparametric statistics might be fruitful.<<ETX>>","PeriodicalId":436281,"journal":{"name":"Proceedings Thirteenth IEEE Symposium on Mass Storage Systems. Toward Distributed Storage and Data Management Systems","volume":"79 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":"117233347","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.1994.373034
J. Bernier
Because of the needs and distributed nature of the worldwide high-energy physics (HEP) community, the long-standing involvement of the National Institute of Nuclear Physics and Particle Physics (IN2P3) in networking activities, and the distribution of IN2P3-federated laboratories throughout France, it was natural for IN2P3 to participate in the Broadband Exchange over Trans-European Links (BETEL) project, the first trans-European ATM trial. In addition, participation in the BETEL project provided a unique opportunity to validate-over a real, high-speed, wide area ATM network-some of the distributed concepts recently introduced in the HEP computing centers. We describe the experience gained while running a high-performance distributed computing application over the BETEL platform between the European Laboratory for Particle Physics (CERN), near Geneva, Switzerland, and the IN2P3 Computing Center, in Lyon, France.<>
{"title":"Broadband Exchange over Trans-European Links (BETEL)","authors":"J. Bernier","doi":"10.1109/MASS.1994.373034","DOIUrl":"https://doi.org/10.1109/MASS.1994.373034","url":null,"abstract":"Because of the needs and distributed nature of the worldwide high-energy physics (HEP) community, the long-standing involvement of the National Institute of Nuclear Physics and Particle Physics (IN2P3) in networking activities, and the distribution of IN2P3-federated laboratories throughout France, it was natural for IN2P3 to participate in the Broadband Exchange over Trans-European Links (BETEL) project, the first trans-European ATM trial. In addition, participation in the BETEL project provided a unique opportunity to validate-over a real, high-speed, wide area ATM network-some of the distributed concepts recently introduced in the HEP computing centers. We describe the experience gained while running a high-performance distributed computing application over the BETEL platform between the European Laboratory for Particle Physics (CERN), near Geneva, Switzerland, and the IN2P3 Computing Center, in Lyon, France.<<ETX>>","PeriodicalId":436281,"journal":{"name":"Proceedings Thirteenth IEEE Symposium on Mass Storage Systems. Toward Distributed Storage and Data Management Systems","volume":"129 3 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":"133290283","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：