In this paper, we present a distributed multi-level cache system based on cloud storage, which is aimed at the low access efficiency of small spatio-temporal data files in information service system of Smart City. Tak...In this paper, we present a distributed multi-level cache system based on cloud storage, which is aimed at the low access efficiency of small spatio-temporal data files in information service system of Smart City. Taking classification attribute of small spatio-temporal data files in Smart City as the basis of cache content selection, the cache system adopts different cache pool management strategies in different levels of cache. The results of experiment in prototype system indicate that multi-level cache in this paper effectively increases the access bandwidth of small spatio-temporal files in Smart City and greatly improves service quality of multiple concurrent access in system.展开更多
为了在数据密集型工作流下有效降低缓存碎片整理开销并提高缓存命中率,提出一种持久性分布式文件系统客户端缓存DFS-Cache(Distributed File System Cache)。DFS-Cache基于非易失性内存(NVM)设计实现,能够保证数据的持久性和崩溃一致性...为了在数据密集型工作流下有效降低缓存碎片整理开销并提高缓存命中率,提出一种持久性分布式文件系统客户端缓存DFS-Cache(Distributed File System Cache)。DFS-Cache基于非易失性内存(NVM)设计实现,能够保证数据的持久性和崩溃一致性,并大幅减少冷启动时间。DFS-Cache包括基于虚拟内存重映射的缓存碎片整理机制和基于生存时间(TTL)的缓存空间管理策略。前者基于NVM可被内存控制器直接寻址的特性,动态修改虚拟地址和物理地址之间的映射关系,实现零拷贝的内存碎片整理;后者是一种冷热分离的分组管理策略,借助重映射的缓存碎片整理机制,提升缓存空间的管理效率。实验采用真实的Intel傲腾持久性内存设备,对比商用的分布式文件系统MooseFS和GlusterFS,采用Fio和Filebench等标准测试程序,DFS-Cache最高能提升5.73倍和1.89倍的系统吞吐量。展开更多
针对多核处理器性能优化问题,文中深入研究多核处理器上共享Cache的管理策略,提出了基于缓存时间公平性与吞吐率的共享Cache划分算法MT-FTP(Memory Time based Fair and Throughput Partitioning)。以公平性和吞吐率两个评价性指标建立...针对多核处理器性能优化问题,文中深入研究多核处理器上共享Cache的管理策略,提出了基于缓存时间公平性与吞吐率的共享Cache划分算法MT-FTP(Memory Time based Fair and Throughput Partitioning)。以公平性和吞吐率两个评价性指标建立数学模型,并分析了算法的划分流程。仿真实验结果表明,MT-FTP算法在系统吞吐率方面表现较好,其平均IPC(Instructions Per Cycles)值比UCP(Use Case Point)算法高1.3%,比LRU(Least Recently Used)算法高11.6%。MT-FTP算法对应的系统平均公平性比LRU算法的系统平均公平性高17%,比UCP算法的平均公平性高16.5%。该算法实现了共享Cache划分公平性并兼顾了系统的吞吐率。展开更多
The cache-based covert channel is one of the common vulnerabilities exploited in the Spectre attacks.Current mitigation strategies focus on blocking the eviction-based channel by using a random/encrypted mapping funct...The cache-based covert channel is one of the common vulnerabilities exploited in the Spectre attacks.Current mitigation strategies focus on blocking the eviction-based channel by using a random/encrypted mapping function to translate memory address to the cache address,while the updated-based channel is still vulnerable.In addition,some mitigation strategies are also costly as it needs software and hardware modifications.In this paper,our objective is to devise low-cost,comprehensive-protection techniques for mitigating the Spectre attacks.We proposed a novel cache structure,named EBCache,which focuses on the RISC-V processor and applies the address encryption and blacklist to resist the Spectre attacks.The addresses encryption mechanism increases the difficulty of pruning a minimal eviction set.The blacklist mechanism makes the updated cache lines loaded by the malicious updates invisible.Our experiments demonstrated that the EBCache can prevent malicious modifications.The EBCache,however,reduces the processor’s performance by about 23%but involves only a low-cost modification in the hardware.展开更多
A notable portion of cachelines in real-world workloads exhibits inner non-uniform access behaviors.However,modern cache management rarely considers this fine-grained feature,which impacts the effective cache capacity...A notable portion of cachelines in real-world workloads exhibits inner non-uniform access behaviors.However,modern cache management rarely considers this fine-grained feature,which impacts the effective cache capacity of contemporary high-performance spacecraft processors.To harness these non-uniform access behaviors,an efficient cache replacement framework featuring an auxiliary cache specifically designed to retain evicted hot data was proposed.This framework reconstructs the cache replacement policy,facilitating data migration between the main cache and the auxiliary cache.Unlike traditional cacheline-granularity policies,the approach excels at identifying and evicting infrequently used data,thereby optimizing cache utilization.The evaluation shows impressive performance improvement,especially on workloads with irregular access patterns.Benefiting from fine granularity,the proposal achieves superior storage efficiency compared with commonly used cache management schemes,providing a potential optimization opportunity for modern resource-constrained processors,such as spacecraft processors.Furthermore,the framework complements existing modern cache replacement policies and can be seamlessly integrated with minimal modifications,enhancing their overall efficacy.展开更多
The dual frequency Heterogeneous Network(HetNet),including sub-6 GHz networks together with Millimeter Wave(mmWave),achieves the high data rates of user in the networks with hotspots.The cache-enabled HetNets with hot...The dual frequency Heterogeneous Network(HetNet),including sub-6 GHz networks together with Millimeter Wave(mmWave),achieves the high data rates of user in the networks with hotspots.The cache-enabled HetNets with hotspots are investigated using an analytical framework in which Macro Base Stations(MBSs)and hotspot centers are treated as two independent homogeneous Poisson Point Processes(PPPs),and locations of Small Base Stations(SBSs)and users are modeled as two Poisson Cluster Processes(PCPs).Under the PCP-based modeling method and the Most Popular Caching(MPC)scheme,we propose a cache-enabled association strategy for HetNets with limited storage capacity.The performance of association probability and coverage probability is explicitly derived,and Monte Carlo simulation is utilized to verify that the results are correct.The outcomes of the simulation present the influence of antenna configuration and cache capacities of MBSs and SBSs on network performance.Numerical optimization of the standard deviation ratio of SBSs and users of association probability is enabled by our analysis.展开更多
Virtual Reality(VR)is a key industry for the development of the digital economy in the future.Mobile VR has advantages in terms of mobility,lightweight and cost-effectiveness,which has gradually become the mainstream ...Virtual Reality(VR)is a key industry for the development of the digital economy in the future.Mobile VR has advantages in terms of mobility,lightweight and cost-effectiveness,which has gradually become the mainstream implementation of VR.In this paper,a mobile VR video adaptive transmission mechanism based on intelligent caching and hierarchical buffering strategy in Mobile Edge Computing(MEC)-equipped 5G networks is proposed,aiming at the low latency requirements of mobile VR services and flexible buffer management for VR video adaptive transmission.To support VR content proactive caching and intelligent buffer management,users’behavioral similarity and head movement trajectory are jointly used for viewpoint prediction.The tile-based content is proactively cached in the MEC nodes based on the popularity of the VR content.Second,a hierarchical buffer-based adaptive update algorithm is presented,which jointly considers bandwidth,buffer,and predicted viewpoint status to update the tile chunk in client buffer.Then,according to the decomposition of the problem,the buffer update problem is modeled as an optimization problem,and the corresponding solution algorithms are presented.Finally,the simulation results show that the adaptive caching algorithm based on 5G intelligent edge and hierarchical buffer strategy can improve the user experience in the case of bandwidth fluctuations,and the proposed viewpoint prediction method can significantly improve the accuracy of viewpoint prediction by 15%.展开更多
This paper proposed a novel multilevel data cache model by Web cache （MDWC） based on network cost in data grid. By constructing a communicating tree of grid sites based on network cost and using a single leader for ...This paper proposed a novel multilevel data cache model by Web cache （MDWC） based on network cost in data grid. By constructing a communicating tree of grid sites based on network cost and using a single leader for each data segment within each region, the MDWC makes the most use of the Web cache of other sites whose bandwidth is as broad as covering the job executing site. The experiment result indicates that the MDWC reduces data response time and data update cost by avoiding network congestions while designing on the parameters concluded by the environment of application.展开更多
基金Supported by the Natural Science Foundation of Hubei Province(2012FFC034,2014CFC1100)
文摘In this paper, we present a distributed multi-level cache system based on cloud storage, which is aimed at the low access efficiency of small spatio-temporal data files in information service system of Smart City. Taking classification attribute of small spatio-temporal data files in Smart City as the basis of cache content selection, the cache system adopts different cache pool management strategies in different levels of cache. The results of experiment in prototype system indicate that multi-level cache in this paper effectively increases the access bandwidth of small spatio-temporal files in Smart City and greatly improves service quality of multiple concurrent access in system.
文摘为了在数据密集型工作流下有效降低缓存碎片整理开销并提高缓存命中率,提出一种持久性分布式文件系统客户端缓存DFS-Cache(Distributed File System Cache)。DFS-Cache基于非易失性内存(NVM)设计实现,能够保证数据的持久性和崩溃一致性,并大幅减少冷启动时间。DFS-Cache包括基于虚拟内存重映射的缓存碎片整理机制和基于生存时间(TTL)的缓存空间管理策略。前者基于NVM可被内存控制器直接寻址的特性,动态修改虚拟地址和物理地址之间的映射关系,实现零拷贝的内存碎片整理;后者是一种冷热分离的分组管理策略,借助重映射的缓存碎片整理机制,提升缓存空间的管理效率。实验采用真实的Intel傲腾持久性内存设备,对比商用的分布式文件系统MooseFS和GlusterFS,采用Fio和Filebench等标准测试程序,DFS-Cache最高能提升5.73倍和1.89倍的系统吞吐量。
文摘针对多核处理器性能优化问题,文中深入研究多核处理器上共享Cache的管理策略,提出了基于缓存时间公平性与吞吐率的共享Cache划分算法MT-FTP(Memory Time based Fair and Throughput Partitioning)。以公平性和吞吐率两个评价性指标建立数学模型,并分析了算法的划分流程。仿真实验结果表明,MT-FTP算法在系统吞吐率方面表现较好,其平均IPC(Instructions Per Cycles)值比UCP(Use Case Point)算法高1.3%,比LRU(Least Recently Used)算法高11.6%。MT-FTP算法对应的系统平均公平性比LRU算法的系统平均公平性高17%,比UCP算法的平均公平性高16.5%。该算法实现了共享Cache划分公平性并兼顾了系统的吞吐率。
基金This work was supported in part by the China Ministry of Science and Technology under Grant 2015GA600002。
文摘The cache-based covert channel is one of the common vulnerabilities exploited in the Spectre attacks.Current mitigation strategies focus on blocking the eviction-based channel by using a random/encrypted mapping function to translate memory address to the cache address,while the updated-based channel is still vulnerable.In addition,some mitigation strategies are also costly as it needs software and hardware modifications.In this paper,our objective is to devise low-cost,comprehensive-protection techniques for mitigating the Spectre attacks.We proposed a novel cache structure,named EBCache,which focuses on the RISC-V processor and applies the address encryption and blacklist to resist the Spectre attacks.The addresses encryption mechanism increases the difficulty of pruning a minimal eviction set.The blacklist mechanism makes the updated cache lines loaded by the malicious updates invisible.Our experiments demonstrated that the EBCache can prevent malicious modifications.The EBCache,however,reduces the processor’s performance by about 23%but involves only a low-cost modification in the hardware.
文摘A notable portion of cachelines in real-world workloads exhibits inner non-uniform access behaviors.However,modern cache management rarely considers this fine-grained feature,which impacts the effective cache capacity of contemporary high-performance spacecraft processors.To harness these non-uniform access behaviors,an efficient cache replacement framework featuring an auxiliary cache specifically designed to retain evicted hot data was proposed.This framework reconstructs the cache replacement policy,facilitating data migration between the main cache and the auxiliary cache.Unlike traditional cacheline-granularity policies,the approach excels at identifying and evicting infrequently used data,thereby optimizing cache utilization.The evaluation shows impressive performance improvement,especially on workloads with irregular access patterns.Benefiting from fine granularity,the proposal achieves superior storage efficiency compared with commonly used cache management schemes,providing a potential optimization opportunity for modern resource-constrained processors,such as spacecraft processors.Furthermore,the framework complements existing modern cache replacement policies and can be seamlessly integrated with minimal modifications,enhancing their overall efficacy.
基金supported in part by National Key Research and Development Project under Grant 2020YFB1807204in part by the National Natural Science Foundation of China under Grant U2001213 and 61971191+2 种基金in part by the Beijing Natural Science Foundation under Grant L201011in part by the Key project of Natural Science Foundation of Jiangxi Province under Grant 20202ACBL202006in part by the Science and Technology Foundation of Jiangxi Province(20202BCD42010)。
文摘The dual frequency Heterogeneous Network(HetNet),including sub-6 GHz networks together with Millimeter Wave(mmWave),achieves the high data rates of user in the networks with hotspots.The cache-enabled HetNets with hotspots are investigated using an analytical framework in which Macro Base Stations(MBSs)and hotspot centers are treated as two independent homogeneous Poisson Point Processes(PPPs),and locations of Small Base Stations(SBSs)and users are modeled as two Poisson Cluster Processes(PCPs).Under the PCP-based modeling method and the Most Popular Caching(MPC)scheme,we propose a cache-enabled association strategy for HetNets with limited storage capacity.The performance of association probability and coverage probability is explicitly derived,and Monte Carlo simulation is utilized to verify that the results are correct.The outcomes of the simulation present the influence of antenna configuration and cache capacities of MBSs and SBSs on network performance.Numerical optimization of the standard deviation ratio of SBSs and users of association probability is enabled by our analysis.
基金supported in part by the Chongqing Municipal Education Commission projects under Grant No.KJCX2020035,KJQN202200829Chongqing Science and Technology Commission projects under grant No.CSTB2022BSXM-JCX0117 and cstc2020jcyjmsxmX0339+1 种基金supported in part by National Natural Science Foundation of China under Grant No.(62171072,62172064,62003067,61901067)supported in part by Chongqing Technology and Business University projects under Grant no.(2156004,212017).
文摘Virtual Reality(VR)is a key industry for the development of the digital economy in the future.Mobile VR has advantages in terms of mobility,lightweight and cost-effectiveness,which has gradually become the mainstream implementation of VR.In this paper,a mobile VR video adaptive transmission mechanism based on intelligent caching and hierarchical buffering strategy in Mobile Edge Computing(MEC)-equipped 5G networks is proposed,aiming at the low latency requirements of mobile VR services and flexible buffer management for VR video adaptive transmission.To support VR content proactive caching and intelligent buffer management,users’behavioral similarity and head movement trajectory are jointly used for viewpoint prediction.The tile-based content is proactively cached in the MEC nodes based on the popularity of the VR content.Second,a hierarchical buffer-based adaptive update algorithm is presented,which jointly considers bandwidth,buffer,and predicted viewpoint status to update the tile chunk in client buffer.Then,according to the decomposition of the problem,the buffer update problem is modeled as an optimization problem,and the corresponding solution algorithms are presented.Finally,the simulation results show that the adaptive caching algorithm based on 5G intelligent edge and hierarchical buffer strategy can improve the user experience in the case of bandwidth fluctuations,and the proposed viewpoint prediction method can significantly improve the accuracy of viewpoint prediction by 15%.
基金Supported by SEC E-Institute :Shanghai HighIn-stitutions Grid Project
文摘This paper proposed a novel multilevel data cache model by Web cache （MDWC） based on network cost in data grid. By constructing a communicating tree of grid sites based on network cost and using a single leader for each data segment within each region, the MDWC makes the most use of the Web cache of other sites whose bandwidth is as broad as covering the job executing site. The experiment result indicates that the MDWC reduces data response time and data update cost by avoiding network congestions while designing on the parameters concluded by the environment of application.
