Pub Date : 1993-10-14DOI: 10.1109/WWOS.1993.348177
C. Pu, Robert M. Fuhrer
Fine-grain scheduling based on software feedback was introduced in the Synthesis operating system to solve two problems: the dependency between jobs in a pipeline and the low-latency requirements of multimedia type applications. The performance level achieved and the adaptiveness of applications running on Synthesis demonstrated the success of fine-grain scheduling based on software feedback. However, the Synthesis implementation of software feedback is specialized for that particular architecture and a particular application (pipelined process scheduling). Consequently, despite the proven success of fine-grain scheduling, it is not easy to port it to another operating system or to apply its lessons elsewhere, even within Synthesis. To address the problems of portability and extensibility of software feedback scheduling mechanisms, we have taken a toolbox approach in our current research. Instead of creating a specialized solution for each particular scheduling problem, we are developing a toolbox of standard, relatively simple components with well-defined performance and functionality characteristics. The goal is the ability to quickly implement sophisticated software feedback mechanisms by composing these basic toolbox components. The intended applications are primarily in the adaptive scheduling needed in multimedia and real-time domains, especially when input/output operations introduce a large variance in job completion time,.<>
{"title":"Feedback-based scheduling: a toolbox approach","authors":"C. Pu, Robert M. Fuhrer","doi":"10.1109/WWOS.1993.348177","DOIUrl":"https://doi.org/10.1109/WWOS.1993.348177","url":null,"abstract":"Fine-grain scheduling based on software feedback was introduced in the Synthesis operating system to solve two problems: the dependency between jobs in a pipeline and the low-latency requirements of multimedia type applications. The performance level achieved and the adaptiveness of applications running on Synthesis demonstrated the success of fine-grain scheduling based on software feedback. However, the Synthesis implementation of software feedback is specialized for that particular architecture and a particular application (pipelined process scheduling). Consequently, despite the proven success of fine-grain scheduling, it is not easy to port it to another operating system or to apply its lessons elsewhere, even within Synthesis. To address the problems of portability and extensibility of software feedback scheduling mechanisms, we have taken a toolbox approach in our current research. Instead of creating a specialized solution for each particular scheduling problem, we are developing a toolbox of standard, relatively simple components with well-defined performance and functionality characteristics. The goal is the ability to quickly implement sophisticated software feedback mechanisms by composing these basic toolbox components. The intended applications are primarily in the adaptive scheduling needed in multimedia and real-time domains, especially when input/output operations introduce a large variance in job completion time,.<<ETX>>","PeriodicalId":345070,"journal":{"name":"Proceedings of IEEE 4th Workshop on Workstation Operating Systems. WWOS-III","volume":"37 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1993-10-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126576651","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 : 1993-10-14DOI: 10.1109/WWOS.1993.348178
R. Cáceres, F. Douglis, Kai Li, B. Marsh
Trends in storage technology indicate that future notebook, palmtop, and smaller mobile computers will contain battery-backed DRAM as primary storage and direct-mapped hash memory as secondary storage, but no disk. All storage will offer uniform, random access read times through a single-level 64-bit address space. The paper explores the operating system implications of this storage organization. The system should exploit the benefits of having all data reside in fast memory. It can do away with much of the data duplication and related data movement that take place in conventional organizations. The system also needs to hide the limitations of flash memory: write access times higher than read access times, the need to erase memory before rewriting it, and a limited number of write cycles in the lifetime of the device. It needs to limit write traffic to flash memory and avoid writing repeatedly to the same area of flash memory. These steps will increase performance, improve space utilization, and prolong the life of flash memory.<>
{"title":"Operating system implications of solid-state mobile computers","authors":"R. Cáceres, F. Douglis, Kai Li, B. Marsh","doi":"10.1109/WWOS.1993.348178","DOIUrl":"https://doi.org/10.1109/WWOS.1993.348178","url":null,"abstract":"Trends in storage technology indicate that future notebook, palmtop, and smaller mobile computers will contain battery-backed DRAM as primary storage and direct-mapped hash memory as secondary storage, but no disk. All storage will offer uniform, random access read times through a single-level 64-bit address space. The paper explores the operating system implications of this storage organization. The system should exploit the benefits of having all data reside in fast memory. It can do away with much of the data duplication and related data movement that take place in conventional organizations. The system also needs to hide the limitations of flash memory: write access times higher than read access times, the need to erase memory before rewriting it, and a limited number of write cycles in the lifetime of the device. It needs to limit write traffic to flash memory and avoid writing repeatedly to the same area of flash memory. These steps will increase performance, improve space utilization, and prolong the life of flash memory.<<ETX>>","PeriodicalId":345070,"journal":{"name":"Proceedings of IEEE 4th Workshop on Workstation Operating Systems. WWOS-III","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1993-10-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125259140","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 : 1993-10-14DOI: 10.1109/WWOS.1993.348157
J. Chase, M. Feeley, H. Levy
We previously described Opal, an OS environment that has a single virtual address space common to all protection domains, rather than the usual private virtual address space per protection domain (e.g., a Unix process). All threads on an Opal node see the same mapping of virtual to physical addresses; any thread can reference any virtual address, but access to the data is determined by the thread's protection domain. The single address space approach is made feasible by the large virtual address spaces of the newest RISC processors. It allows protection domains to pass and share memory segments by mutual consent, while preserving the meaning of pointers. At the time Opal was a paper design, with only a few pieces of implementation. Since that time the key features of Opal have been prototyped. While the current prototype runs on 32-bit MIPS systems, it demonstrates that the model is both workable and useful. Yet the single address space idea remains a difficult adjustment, both conceptually and practically, for those of us long accustomed to per-process address spaces. Having spent much of the past year arguing the benefits of the model, our purpose now is to outline some of its limitations and complications. The goal is to separate the real problems from the false ones, and to focus the debate on the areas that we think are most important, based on our experience.<>
{"title":"Some issues for single address space systems","authors":"J. Chase, M. Feeley, H. Levy","doi":"10.1109/WWOS.1993.348157","DOIUrl":"https://doi.org/10.1109/WWOS.1993.348157","url":null,"abstract":"We previously described Opal, an OS environment that has a single virtual address space common to all protection domains, rather than the usual private virtual address space per protection domain (e.g., a Unix process). All threads on an Opal node see the same mapping of virtual to physical addresses; any thread can reference any virtual address, but access to the data is determined by the thread's protection domain. The single address space approach is made feasible by the large virtual address spaces of the newest RISC processors. It allows protection domains to pass and share memory segments by mutual consent, while preserving the meaning of pointers. At the time Opal was a paper design, with only a few pieces of implementation. Since that time the key features of Opal have been prototyped. While the current prototype runs on 32-bit MIPS systems, it demonstrates that the model is both workable and useful. Yet the single address space idea remains a difficult adjustment, both conceptually and practically, for those of us long accustomed to per-process address spaces. Having spent much of the past year arguing the benefits of the model, our purpose now is to outline some of its limitations and complications. The goal is to separate the real problems from the false ones, and to focus the debate on the areas that we think are most important, based on our experience.<<ETX>>","PeriodicalId":345070,"journal":{"name":"Proceedings of IEEE 4th Workshop on Workstation Operating Systems. WWOS-III","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1993-10-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134199290","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 : 1993-10-14DOI: 10.1109/WWOS.1993.348173
B. Mah, S. Seshan, K. Keeton, R. Katz, D. Ferrari
Mobile computing and multimedia are two emerging trends in computer systems. One foreseeable application suggested by these two trends is the playback of stored video on both mobile devices and conventional workstations. A system supporting such an application must provide performance-guaranteed delivery of video data to different types of clients, some of which may be mobile. In this paper, we address some of the issues involved in supporting such an application, namely the efficient layout of multiple representations of video data on a file server and network support for host mobility.<>
{"title":"Providing network video service to mobile clients","authors":"B. Mah, S. Seshan, K. Keeton, R. Katz, D. Ferrari","doi":"10.1109/WWOS.1993.348173","DOIUrl":"https://doi.org/10.1109/WWOS.1993.348173","url":null,"abstract":"Mobile computing and multimedia are two emerging trends in computer systems. One foreseeable application suggested by these two trends is the playback of stored video on both mobile devices and conventional workstations. A system supporting such an application must provide performance-guaranteed delivery of video data to different types of clients, some of which may be mobile. In this paper, we address some of the issues involved in supporting such an application, namely the efficient layout of multiple representations of video data on a file server and network support for host mobility.<<ETX>>","PeriodicalId":345070,"journal":{"name":"Proceedings of IEEE 4th Workshop on Workstation Operating Systems. WWOS-III","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1993-10-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124559131","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 : 1993-10-14DOI: 10.1109/WWOS.1993.348158
P. Guedes, M. Castro
This paper describes the goals, programming model and design of DiSOM, a software based distributed shared memory system for a multicomputer composed of heterogeneous nodes connected by a high-speed network. A typical configuration is a cluster of tens of high-performance workstations and shared-memory multiprocessors of two or three different architectures, each with a processing power of a few hundred MIPS and several hundred kilobytes of memory, and connected by a high-speed interconnect such as ATM. Programs in DiSOM are written using a shared-memory multiprocessor model where synchronization objects are associated with data items. Programs use a threads library to start new threads, possibly at a specified node, and to synchronize between concurrent threads. Programs must call the synchronization primitives explicitly, as they would in a shared-memory multiprocessor. The system traps these calls and uses the information to drive both distributed synchronization and the memory coherence protocol. DiSOM uses the entry consistency memory model to ensure coherence. This model guarantees memory consistency, as long as an access to a data item is enclosed between an acquire and a release on the synchronization object associated with the data item. Stronger consistency models, such as release consistency and processor consistency, may also be supported.<>
{"title":"Distributed shared object memory","authors":"P. Guedes, M. Castro","doi":"10.1109/WWOS.1993.348158","DOIUrl":"https://doi.org/10.1109/WWOS.1993.348158","url":null,"abstract":"This paper describes the goals, programming model and design of DiSOM, a software based distributed shared memory system for a multicomputer composed of heterogeneous nodes connected by a high-speed network. A typical configuration is a cluster of tens of high-performance workstations and shared-memory multiprocessors of two or three different architectures, each with a processing power of a few hundred MIPS and several hundred kilobytes of memory, and connected by a high-speed interconnect such as ATM. Programs in DiSOM are written using a shared-memory multiprocessor model where synchronization objects are associated with data items. Programs use a threads library to start new threads, possibly at a specified node, and to synchronize between concurrent threads. Programs must call the synchronization primitives explicitly, as they would in a shared-memory multiprocessor. The system traps these calls and uses the information to drive both distributed synchronization and the memory coherence protocol. DiSOM uses the entry consistency memory model to ensure coherence. This model guarantees memory consistency, as long as an access to a data item is enclosed between an acquire and a release on the synchronization object associated with the data item. Stronger consistency models, such as release consistency and processor consistency, may also be supported.<<ETX>>","PeriodicalId":345070,"journal":{"name":"Proceedings of IEEE 4th Workshop on Workstation Operating Systems. WWOS-III","volume":"59 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1993-10-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116531115","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 : 1993-10-14DOI: 10.1109/WWOS.1993.348167
David B. Johnson
Argues that being a mobile host (or a mobile capable host) should be a standard property of all hosts in the Internet, and summarizes the design of a new protocol for transparently allowing these mobile hosts to interoperate in the Internet using IP. A mobile host may move from one network to another at any time, while always using only its "home" IP address. Any host may be configured to be a "mobile host" simply by running the appropriate software on it, and there is no penalty for this configuration, since the protocol automatically uses only the standard IP routing mechanisms, adding no overhead to IP, when a mobile host is currently connected to its home network. The protocol scales well to very large numbers of mobile hosts and adds little overhead for packets sent to a mobile host currently connected to a foreign network. The protocol is currently being implemented within the Berkeley networking code and is expected to be available shortly to interested groups outside Carnegie Mellon.<>
{"title":"Ubiquitous mobile host internetworking","authors":"David B. Johnson","doi":"10.1109/WWOS.1993.348167","DOIUrl":"https://doi.org/10.1109/WWOS.1993.348167","url":null,"abstract":"Argues that being a mobile host (or a mobile capable host) should be a standard property of all hosts in the Internet, and summarizes the design of a new protocol for transparently allowing these mobile hosts to interoperate in the Internet using IP. A mobile host may move from one network to another at any time, while always using only its \"home\" IP address. Any host may be configured to be a \"mobile host\" simply by running the appropriate software on it, and there is no penalty for this configuration, since the protocol automatically uses only the standard IP routing mechanisms, adding no overhead to IP, when a mobile host is currently connected to its home network. The protocol scales well to very large numbers of mobile hosts and adds little overhead for packets sent to a mobile host currently connected to a foreign network. The protocol is currently being implemented within the Berkeley networking code and is expected to be available shortly to interested groups outside Carnegie Mellon.<<ETX>>","PeriodicalId":345070,"journal":{"name":"Proceedings of IEEE 4th Workshop on Workstation Operating Systems. WWOS-III","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1993-10-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132941813","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 : 1993-10-14DOI: 10.1109/WWOS.1993.348176
David Goldberg, M. M. Tso
What is the correct programming model for networked portable computers? Such computers come in many shapes and sizes, so it is unreasonable to expect that there is one programming model appropriate for every single variety. However, it is likely that there is some model that will work well for a wide range of cases. We propose the intelligently autonomous model for this role. Our goal for a widely applicable model is that it should allow applications to operate during disconnections, and that during disconnections the user shouldn't be surprised, that is, applications should behave predictably. The intelligently autonomous model fulfills these goals by having a remote file system with caching, and allowing user control over the cache. In more detail, we are interested in portable networked computers that: frequently access external data, have a reasonably powerful CPU, have a wireless network that suffers from intermittent, unpredictable disruptions. We survey existing models, and then explain why we think they fall short of user requirements. In particular, we feel that existing models have wrongly assumed that it is not necessary to customize applications for an intermittently connected environment. Then we present our intelligently autonomous model, and give a very brief report of our experiences with a prototype of it.<>
{"title":"How to program networked portable computers","authors":"David Goldberg, M. M. Tso","doi":"10.1109/WWOS.1993.348176","DOIUrl":"https://doi.org/10.1109/WWOS.1993.348176","url":null,"abstract":"What is the correct programming model for networked portable computers? Such computers come in many shapes and sizes, so it is unreasonable to expect that there is one programming model appropriate for every single variety. However, it is likely that there is some model that will work well for a wide range of cases. We propose the intelligently autonomous model for this role. Our goal for a widely applicable model is that it should allow applications to operate during disconnections, and that during disconnections the user shouldn't be surprised, that is, applications should behave predictably. The intelligently autonomous model fulfills these goals by having a remote file system with caching, and allowing user control over the cache. In more detail, we are interested in portable networked computers that: frequently access external data, have a reasonably powerful CPU, have a wireless network that suffers from intermittent, unpredictable disruptions. We survey existing models, and then explain why we think they fall short of user requirements. In particular, we feel that existing models have wrongly assumed that it is not necessary to customize applications for an intermittently connected environment. Then we present our intelligently autonomous model, and give a very brief report of our experiences with a prototype of it.<<ETX>>","PeriodicalId":345070,"journal":{"name":"Proceedings of IEEE 4th Workshop on Workstation Operating Systems. WWOS-III","volume":"43 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1993-10-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124466069","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 : 1993-10-14DOI: 10.1109/WWOS.1993.348170
Puneet Kumar, M. Satyanarayanan
We describe an interface to incorporate application-specific knowledge for conflict resolution in an optimistically replicated file system. Conflicts arise in such systems because replicas of an object can be modified simultaneously in different network partitions. Application-specific knowledge is made available by the application writer in specialized tools called Application-Specific Resolvers (or ASRS). The interface we describe here is used to bind ASRs to objects and to specify the conditions under which a specific ASR is invoked. This allows the system to make conflict resolution transparent to the user, thus improving the usability of optimistic replication.<>
{"title":"Supporting application-specific resolution in an optimistically replicated file system","authors":"Puneet Kumar, M. Satyanarayanan","doi":"10.1109/WWOS.1993.348170","DOIUrl":"https://doi.org/10.1109/WWOS.1993.348170","url":null,"abstract":"We describe an interface to incorporate application-specific knowledge for conflict resolution in an optimistically replicated file system. Conflicts arise in such systems because replicas of an object can be modified simultaneously in different network partitions. Application-specific knowledge is made available by the application writer in specialized tools called Application-Specific Resolvers (or ASRS). The interface we describe here is used to bind ASRs to objects and to specify the conditions under which a specific ASR is invoked. This allows the system to make conflict resolution transparent to the user, thus improving the usability of optimistic replication.<<ETX>>","PeriodicalId":345070,"journal":{"name":"Proceedings of IEEE 4th Workshop on Workstation Operating Systems. WWOS-III","volume":"114 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1993-10-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126130713","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 : 1993-10-14DOI: 10.1109/WWOS.1993.348165
M. Blaze
This position paper advocates the development of new mechanisms to support cooperative computing requiring less than complete trust. Traditional OS security mechanisms have assumed a monolithic or hierarchical model for controlling and arbitrating access to local resources. Operating systems authenticate users as they log in and enforce controlled access to files, devices and memory. Distributed systems change the picture somewhat, with less-trusted clients obtaining some resources from centralized servers, but typically retain some notion of central authority within a framework of global trust and control. Boundaries of trust are going to become increasingly important to future workstation operating systems. Cryptographic algorithms and protocols can protect these boundaries, but the interfaces to them need some attention first. Our experiences, which are admittedly within the research environment, lead us to believe that cryptographic protection can be quite practical across a variety of layers of the system; importantly, no one layer emerges as a decisive winner as to where this protection best belongs. (The application layer, however, does appear to be the clear loser.).<>
{"title":"Transparent mistrust: OS support for cryptography-in-the-large","authors":"M. Blaze","doi":"10.1109/WWOS.1993.348165","DOIUrl":"https://doi.org/10.1109/WWOS.1993.348165","url":null,"abstract":"This position paper advocates the development of new mechanisms to support cooperative computing requiring less than complete trust. Traditional OS security mechanisms have assumed a monolithic or hierarchical model for controlling and arbitrating access to local resources. Operating systems authenticate users as they log in and enforce controlled access to files, devices and memory. Distributed systems change the picture somewhat, with less-trusted clients obtaining some resources from centralized servers, but typically retain some notion of central authority within a framework of global trust and control. Boundaries of trust are going to become increasingly important to future workstation operating systems. Cryptographic algorithms and protocols can protect these boundaries, but the interfaces to them need some attention first. Our experiences, which are admittedly within the research environment, lead us to believe that cryptographic protection can be quite practical across a variety of layers of the system; importantly, no one layer emerges as a decisive winner as to where this protection best belongs. (The application layer, however, does appear to be the clear loser.).<<ETX>>","PeriodicalId":345070,"journal":{"name":"Proceedings of IEEE 4th Workshop on Workstation Operating Systems. WWOS-III","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1993-10-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126162720","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 : 1993-10-14DOI: 10.1109/WWOS.1993.348164
Y. Khalidi, Madhusudhan Talluri, M. Nelson, Dock Williams
The advent of computers with 64-bit virtual address spaces and giga-bytes of physical memory will provide applications with many more orders of magnitude of memory than is possible today. However, to tap the potential of this new hardware, we need to re-examine how virtual memory is traditionally managed. We concentrate in this note on two aspects of virtual memory: software support for multiple page sizes, and memory management policies tuned to large amounts of physical memory. We argue for the need to examine these areas, and we identify several questions that need to be answered. In particular, we show that providing support for multiple page sizes is not as straightforward as may initially appear.<>
{"title":"Virtual memory support for multiple page sizes","authors":"Y. Khalidi, Madhusudhan Talluri, M. Nelson, Dock Williams","doi":"10.1109/WWOS.1993.348164","DOIUrl":"https://doi.org/10.1109/WWOS.1993.348164","url":null,"abstract":"The advent of computers with 64-bit virtual address spaces and giga-bytes of physical memory will provide applications with many more orders of magnitude of memory than is possible today. However, to tap the potential of this new hardware, we need to re-examine how virtual memory is traditionally managed. We concentrate in this note on two aspects of virtual memory: software support for multiple page sizes, and memory management policies tuned to large amounts of physical memory. We argue for the need to examine these areas, and we identify several questions that need to be answered. In particular, we show that providing support for multiple page sizes is not as straightforward as may initially appear.<<ETX>>","PeriodicalId":345070,"journal":{"name":"Proceedings of IEEE 4th Workshop on Workstation Operating Systems. WWOS-III","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1993-10-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125800174","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：