Metadata prefetching and data placement play a critical role in enhancing access performance for file systems operating over wide-area networks.However,developing effective strategies for metadata prefetching in envir...Metadata prefetching and data placement play a critical role in enhancing access performance for file systems operating over wide-area networks.However,developing effective strategies for metadata prefetching in environments with concurrent workloads and for data placement across distributed networks remains a significant challenge.This study introduces novel and efficient methodologies for metadata prefetching and data placement,leveraging fine-grained control of prefetching strategies and variable-sized data fragment writing to optimize the I/O bandwidth of distributed file systems.The proposed metadata prefetching technique employs dynamic workload analysis to identify dominant workload patterns and adaptively refines prefetching policies,thereby boosting metadata access efficiency under concurrent scenarios.Meanwhile,the data placement strategy improves write performance by storing data fragments locally within the nearest data center and transmitting only the fragment location metadata to the remote data center hosting the original file.Experimental evaluations using real-world system traces demonstrate that the proposed approaches reduce metadata access times by up to 33.5%and application data access times by 17.19%compared to state-of-the-art techniques.展开更多
In distributed storage systems,file access efficiency has an important impact on the real-time nature of information forensics.As a popular approach to improve file accessing efficiency,prefetching model can fetches d...In distributed storage systems,file access efficiency has an important impact on the real-time nature of information forensics.As a popular approach to improve file accessing efficiency,prefetching model can fetches data before it is needed according to the file access pattern,which can reduce the I/O waiting time and increase the system concurrency.However,prefetching model needs to mine the degree of association between files to ensure the accuracy of prefetching.In the massive small file situation,the sheer volume of files poses a challenge to the efficiency and accuracy of relevance mining.In this paper,we propose a massive files prefetching model based on LSTM neural network with cache transaction strategy to improve file access efficiency.Firstly,we propose a file clustering algorithm based on temporal locality and spatial locality to reduce the computational complexity.Secondly,we propose a definition of cache transaction according to files occurrence in cache instead of time-offset distance based methods to extract file block feature accurately.Lastly,we innovatively propose a file access prediction algorithm based on LSTM neural network which predict the file that have high possibility to be accessed.Experiments show that compared with the traditional LRU and the plain grouping methods,the proposed model notably increase the cache hit rate and effectively reduces the I/O wait time.展开更多
In this paper, we present a comparative study between informed and predictive prefetching mechanisms that were presented to leverage the performance gap between I/O storage systems and CPU. In particular, we will focu...In this paper, we present a comparative study between informed and predictive prefetching mechanisms that were presented to leverage the performance gap between I/O storage systems and CPU. In particular, we will focus on transparent informed prefetching (TIP) and predictive prefetching using probability graph approach (PG). Our main objective is to show the main features, motivations, and implementation overview of each mechanism. We also conducted a performance evaluation discussion that shows a comparison between both mechanisms performance when using different cache size values.展开更多
A novel approach that integrates occlusion culling within the view-dependent rendering framework is proposed. The algorithm uses the prioritized-layered projection（PLP） algorithm to occlude those obscured objects, a...A novel approach that integrates occlusion culling within the view-dependent rendering framework is proposed. The algorithm uses the prioritized-layered projection（PLP） algorithm to occlude those obscured objects, and uses an approximate visibility technique to accurately and efficiently determine which objects will be visible in the coming future and prefetch those objects from disk before they are rendered, view-dependent rendering technique provides the ability to change level of detail over the surface seamlessly and smoothly in real-time according to cell solidity value.展开更多
With the number of connected devices increasing rapidly,the access latency issue increases drastically in the edge cloud environment.Massive low time-constrained and data-intensive mobile applications require efficien...With the number of connected devices increasing rapidly,the access latency issue increases drastically in the edge cloud environment.Massive low time-constrained and data-intensive mobile applications require efficient replication strategies to decrease retrieval time.However,the determination of replicas is not reasonable in many previous works,which incurs high response delay.To this end,a correlation-aware replica prefetching(CRP)strategy based on the file correlation principle is proposed,which can prefetch the files with high access probability.The key is to determine and obtain the implicit high-value files effectively,which has a significant impact on the performance of CRP.To achieve the goal of accelerating the acquisition of implicit highvalue files,an access rule management method based on consistent hashing is proposed,and then the storage and query mechanisms for access rules based on adjacency list storage structure are further presented.The theoretical analysis and simulation results corroborate that CRP shortens average response time over 4.8%,improves average hit ratio over 4.2%,reduces transmitting data amount over 8.3%,and maintains replication frequency at a reasonable level when compared to other schemes.展开更多
In this paper, we present a predictive prefetching mechanism that is based on probability graph approach to perform prefetching between different levels in a parallel hybrid storage system. The fundamental concept of ...In this paper, we present a predictive prefetching mechanism that is based on probability graph approach to perform prefetching between different levels in a parallel hybrid storage system. The fundamental concept of our approach is to invoke parallel hybrid storage system’s parallelism and prefetch data among multiple storage levels (e.g. solid state disks, and hard disk drives) in parallel with the application’s on-demand I/O reading requests. In this study, we show that a predictive prefetching across multiple storage levels is an efficient technique for placing near future needed data blocks in the uppermost levels near the application. Our PPHSS approach extends previous ideas of predictive prefetching in two ways: (1) our approach reduces applications’ execution elapsed time by keeping data blocks that are predicted to be accessed in the near future cached in the uppermost level;(2) we propose a parallel data fetching scheme in which multiple fetching mechanisms (i.e. predictive prefetching and application’s on-demand data requests) can work in parallel;where the first one fetches data blocks among the different levels of the hybrid storage systems (i.e. low-level (slow) to high-level (fast) storage devices) and the other one fetches the data from the storage system to the application. Our PPHSS strategy integrated with the predictive prefetching mechanism significantly reduces overall I/O access time in a hybrid storage system. Finally, we developed a simulator to evaluate the performance of the proposed predictive prefetching scheme in the context of hybrid storage systems. Our results show that our PPHSS can improve system performance by 4% across real-world I/O traces without the need of using large size caches.展开更多
In this paper, a prefetching technique is proposed to solve the performance problem caused by remote data access delay. In the technique, the map tasks which will cause the delay are predicted first and then the input...In this paper, a prefetching technique is proposed to solve the performance problem caused by remote data access delay. In the technique, the map tasks which will cause the delay are predicted first and then the input data of these tasks will be preloaded before the tasks are scheduled. During the execution, the input data can be read from local nodes. Therefore, the delay can be hidden. The technique has been implemented in Hadoop-0. 20.1. The experiment results have shown that the technique reduces map tasks causing delay, and improves the performance of Hadoop MapRe- duce by 20%.展开更多
A scheme for high-speed data transfer via the Internet for Web service in an extremely large delay environment is proposed. With the wide-spread use of Internet services in recent years, WLAN Internet service in high-...A scheme for high-speed data transfer via the Internet for Web service in an extremely large delay environment is proposed. With the wide-spread use of Internet services in recent years, WLAN Internet service in high-speed trains has commenced. The system for this is composed of a satellite communication system between the train and the ground station, which is characterized by extremely large latency of several hundred milliseconds due to long propagation latency. High-speed web access is not available to users in a train in such an extremely large latency network system. Thus, a prefetch scheme for performance acceleration of Web services in this environment is proposed. A test-bed system that implements the proposed scheme is implemented and is its performance in this test-bed is evaluated. The proposed scheme is verified to enable high-speed Web access in the extremely large delay environment compared to conventional schemes.展开更多
With the speed gap between storage system access and processor computing, end-to-end data processing has become a bottleneck to improve the total performance of computer systems over the Internet. Based on the analysi...With the speed gap between storage system access and processor computing, end-to-end data processing has become a bottleneck to improve the total performance of computer systems over the Internet. Based on the analysis of data processing behavior, an adaptive cache organization scheme is proposed with fast address calculation. This scheme can make full use of the characteristics of stack space data access, adopt fast address calculation strategy, and reduce the hit time of stack access. Adaptively, the stack cache can be turned off from beginning to end, when a stack overflow occurs to avoid the effect of stack switching on processor performance. Also, through the instruction cache and the failure behavior for the data cache, a prefetching policy is developed, which is combined with the data capture of the failover queue state. Finally, the proposed method can maintain the order of instruction and data access, which facilitates the extraction of prefetching in the end-to-end data processing.展开更多
Data prefetching is an effective data access latency hiding technique to mask the CPU stall caused by cache misses and to bridge the performance gap between processor and memory. With hardware and/or software support,...Data prefetching is an effective data access latency hiding technique to mask the CPU stall caused by cache misses and to bridge the performance gap between processor and memory. With hardware and/or software support, data prefetching brings data closer to a processor before it is actually needed. Many prefetching techniques have been developed for single-core processors. Recent developments in processor technology have brought multicore processors into mainstream. While some of the single-core prefetching techniques are directly applicable to multicore processors, numerous novel strategies have been proposed in the past few years to take advantage of multiple cores. This paper aims to provide a comprehensive review of the state-of-the-art prefetching techniques, and proposes a taxonomy that classifies various design concerns in developing a prefetching strategy, especially for multicore processors. We compare various existing methods through analysis as well.展开更多
Hardware prefetching and replacement policies are two techniques to improve the performance of the memory subsystem.While prefetching hides memory latency and improves performance,interactions take place with the cach...Hardware prefetching and replacement policies are two techniques to improve the performance of the memory subsystem.While prefetching hides memory latency and improves performance,interactions take place with the cache replacement policies,thereby introducing performance variability in the application.To improve the accuracy of reuse of cache blocks in the presence of hardware prefetching,we propose Prefetch-Adaptive Intelligent Cache Replacement Policy(PAIC).PAIC is designed with separate predictors for prefetch and demand requests,and uses machine learning to optimize reuse prediction in the presence of prefetching.By distinguishing reuse predictions for prefetch and demand requests,PAIC can better combine the performance benefits from prefetching and replacement policies.We evaluate PAIC on a set of 27 memory-intensive programs from the SPEC 2006 and SPEC 2017.Under single-core configuration,PAIC improves performance over Least Recently Used(LRU)replacement policy by 37.22%,compared with improvements of 32.93%for Signature-based Hit Predictor(SHiP),34.56%for Hawkeye,and 34.43%for Glider.Under the four-core configuration,PAIC improves performance over LRU by 20.99%,versus 13.23%for SHiP,17.89%for Hawkeye and 15.50%for Glider.展开更多
The World Wide Web has become the primary means for information dissemination. Due to the limited resources of the network bandwidth, users always suffer from long time waiting. Web prefetching and web caching are the...The World Wide Web has become the primary means for information dissemination. Due to the limited resources of the network bandwidth, users always suffer from long time waiting. Web prefetching and web caching are the primary approaches to reducing the user perceived access latency and improving the quality of services. In this paper, a Stochastic Petri Nets （SPN） based integrated web prefetching and caching model （IWPCM） is presented and the performance evaluation of IWPCM is made. The performance metrics, access latency, throughput, HR （hit ratio） and BHR （byte hit ratio） are analyzed and discussed. Simulations show that compared with caching only model （CM）, IWPCM can further improve the throughput, HR and BHR efficiently and reduce the access latency. The performance evaluation based on the SPN model can provide a basis for implementation of web prefetching and caching and the combination of web prefetching and caching holds the promise of improving the QoS of web systems.展开更多
As the speed gap between main memory and modern processors continues to widen, the cache behavior becomes more important for main memory database systems （MMDBs）. Indexing technique is a key component of MMDBs. Unfo...As the speed gap between main memory and modern processors continues to widen, the cache behavior becomes more important for main memory database systems （MMDBs）. Indexing technique is a key component of MMDBs. Unfortunately, the predominant indexes -B^＋-trees and T-trees -- have been shown to utilize cache poorly, which triggers the development of many cache-conscious indexes, such as CSB^＋-trees and pB^＋-trees. Most of these cache-conscious indexes are variants of conventional B^＋-trees, and have better cache performance than B^＋-trees. In this paper, we develop a novel J^＋-tree index, inspired by the Judy structure which is an associative array data structure, and propose a more cacheoptimized index -- Prefetching J^＋-tree （pJ^＋-tree）, which applies prefetching to J^＋-tree to accelerate range scan operations. The J^＋-tree stores all the keys in its leaf nodes and keeps the reference values of leaf nodes in a Judy structure, which makes J^＋-tree not only hold the advantages of Judy （such as fast single value search） but also outperform it in other aspects. For example, J^＋-trees can achieve better performance on range queries than Judy. The pJ^＋-tree index exploits prefetching techniques to further improve the cache behavior of J^＋-trees and yields a speedup of 2.0 on range scans. Compared with B^＋-trees, CSB^＋-trees, pB^＋-trees and T-trees, our extensive experimental Study shows that pJ^＋-trees can provide better performance on both time （search, scan, update） and space aspects.展开更多
Docker,as a mainstream container solution,adopts the Copy-on-Write(CoW)mechanism in its storage drivers.This mechanism satisfies the need of different containers to share the same image.However,when a single container...Docker,as a mainstream container solution,adopts the Copy-on-Write(CoW)mechanism in its storage drivers.This mechanism satisfies the need of different containers to share the same image.However,when a single container performs operations such as modification of an image file,a duplicate is created in the upper readwrite layer,which contributes to the runtime overhead.When the accessed image file is fairly large,this additional overhead becomes non-negligible.Here we present the concept of Dynamic Prefetching Strategy Optimization(DPSO),which optimizes the Co W mechanism for a Docker container on the basis of the dynamic prefetching strategy.At the beginning of the container life cycle,DPSO pre-copies up the image files that are most likely to be copied up later to eliminate the overhead caused by performing this operation during application runtime.The experimental results show that DPSO has an average prefetch accuracy of greater than 78%in complex scenarios and could effectively eliminate the overhead caused by the CoW mechanism.展开更多
Modern High-Performance Computing(HPC)systems are adding extra layers to the memory and storage hierarchy,named deep memory and storage hierarchy(DMSH),to increase I/O performance.New hardware technologies,such as NVM...Modern High-Performance Computing(HPC)systems are adding extra layers to the memory and storage hierarchy,named deep memory and storage hierarchy(DMSH),to increase I/O performance.New hardware technologies,such as NVMe and SSD,have been introduced in burst buffer installations to reduce the pressure for external storage and boost the burstiness of modern I/O systems.The DMSH has demonstrated its strength and potential in practice.However,each layer of DMSH is an independent heterogeneous system and data movement among more layers is significantly more complex even without considering heterogeneity.How to efficiently utilize the DMSH is a subject of research facing the HPC community.Further,accessing data with a high-throughput and low-latency is more imperative than ever.Data prefetching is a well-known technique for hiding read latency by requesting data before it is needed to move it from a high-latency medium(e.g.,disk)to a low-latency one(e.g.,main memory).However,existing solutions do not consider the new deep memory and storage hierarchy and also suffer from under-utilization of prefetching resources and unnecessary evictions.Additionally,existing approaches implement a client-pull model where understanding the application's I/O behavior drives prefetching decisions.Moving towards exascale,where machines run multiple applications concurrently by accessing files in a workflow,a more data-centric approach resolves challenges such as cache pollution and redundancy.In this paper,we present the design and implementation of Hermes:a new,heterogeneous-aware,multi-tiered,dynamic,and distributed I/O buffering system.Hermes enables,manages,supervises,and,in some sense,extends I/O buffering to fully integrate into the DMSH.We introduce three novel data placement policies to efficiently utilize all layers and we present three novel techniques to perform memory,metadata,and communication management in hierarchical buffering systems.Additionally,we demonstrate the benefits of a truly hierarchical data prefetcher that adopts a server-push approach to data prefetching.Our evaluation shows that,in addition to automatic data movement through the hierarchy,Hermes can significantly accelerate I/O and outperforms by more than 2x state-of-the-art buffering platforms.Lastly,results show 10%-35%performance gains over existing prefetchers and over 50%when compared to systems with no prefetching.展开更多
基金funded by the National Natural Science Foundation of China under Grant No.62362019the Hainan Provincial Natural Science Foundation of China under Grant No.624RC482.
文摘Metadata prefetching and data placement play a critical role in enhancing access performance for file systems operating over wide-area networks.However,developing effective strategies for metadata prefetching in environments with concurrent workloads and for data placement across distributed networks remains a significant challenge.This study introduces novel and efficient methodologies for metadata prefetching and data placement,leveraging fine-grained control of prefetching strategies and variable-sized data fragment writing to optimize the I/O bandwidth of distributed file systems.The proposed metadata prefetching technique employs dynamic workload analysis to identify dominant workload patterns and adaptively refines prefetching policies,thereby boosting metadata access efficiency under concurrent scenarios.Meanwhile,the data placement strategy improves write performance by storing data fragments locally within the nearest data center and transmitting only the fragment location metadata to the remote data center hosting the original file.Experimental evaluations using real-world system traces demonstrate that the proposed approaches reduce metadata access times by up to 33.5%and application data access times by 17.19%compared to state-of-the-art techniques.
基金This work is supported by‘The Fundamental Research Funds for the Central Universities(Grant No.HIT.NSRIF.201714)’‘Weihai Science and Technology Development Program(2016DXGJMS15)’‘Key Research and Development Program in Shandong Provincial(2017GGX90103)’.
文摘In distributed storage systems,file access efficiency has an important impact on the real-time nature of information forensics.As a popular approach to improve file accessing efficiency,prefetching model can fetches data before it is needed according to the file access pattern,which can reduce the I/O waiting time and increase the system concurrency.However,prefetching model needs to mine the degree of association between files to ensure the accuracy of prefetching.In the massive small file situation,the sheer volume of files poses a challenge to the efficiency and accuracy of relevance mining.In this paper,we propose a massive files prefetching model based on LSTM neural network with cache transaction strategy to improve file access efficiency.Firstly,we propose a file clustering algorithm based on temporal locality and spatial locality to reduce the computational complexity.Secondly,we propose a definition of cache transaction according to files occurrence in cache instead of time-offset distance based methods to extract file block feature accurately.Lastly,we innovatively propose a file access prediction algorithm based on LSTM neural network which predict the file that have high possibility to be accessed.Experiments show that compared with the traditional LRU and the plain grouping methods,the proposed model notably increase the cache hit rate and effectively reduces the I/O wait time.
文摘In this paper, we present a comparative study between informed and predictive prefetching mechanisms that were presented to leverage the performance gap between I/O storage systems and CPU. In particular, we will focus on transparent informed prefetching (TIP) and predictive prefetching using probability graph approach (PG). Our main objective is to show the main features, motivations, and implementation overview of each mechanism. We also conducted a performance evaluation discussion that shows a comparison between both mechanisms performance when using different cache size values.
文摘A novel approach that integrates occlusion culling within the view-dependent rendering framework is proposed. The algorithm uses the prioritized-layered projection（PLP） algorithm to occlude those obscured objects, and uses an approximate visibility technique to accurately and efficiently determine which objects will be visible in the coming future and prefetch those objects from disk before they are rendered, view-dependent rendering technique provides the ability to change level of detail over the surface seamlessly and smoothly in real-time according to cell solidity value.
基金the National Natural Science Foundation of China(No.61602525,No.61572525)the Research Foundation of Education Bureau of Hunan Province of China(No.19C1391)the Natural Science Foundation of Hunan Province of China(No.2020JJ5775)。
文摘With the number of connected devices increasing rapidly,the access latency issue increases drastically in the edge cloud environment.Massive low time-constrained and data-intensive mobile applications require efficient replication strategies to decrease retrieval time.However,the determination of replicas is not reasonable in many previous works,which incurs high response delay.To this end,a correlation-aware replica prefetching(CRP)strategy based on the file correlation principle is proposed,which can prefetch the files with high access probability.The key is to determine and obtain the implicit high-value files effectively,which has a significant impact on the performance of CRP.To achieve the goal of accelerating the acquisition of implicit highvalue files,an access rule management method based on consistent hashing is proposed,and then the storage and query mechanisms for access rules based on adjacency list storage structure are further presented.The theoretical analysis and simulation results corroborate that CRP shortens average response time over 4.8%,improves average hit ratio over 4.2%,reduces transmitting data amount over 8.3%,and maintains replication frequency at a reasonable level when compared to other schemes.
文摘In this paper, we present a predictive prefetching mechanism that is based on probability graph approach to perform prefetching between different levels in a parallel hybrid storage system. The fundamental concept of our approach is to invoke parallel hybrid storage system’s parallelism and prefetch data among multiple storage levels (e.g. solid state disks, and hard disk drives) in parallel with the application’s on-demand I/O reading requests. In this study, we show that a predictive prefetching across multiple storage levels is an efficient technique for placing near future needed data blocks in the uppermost levels near the application. Our PPHSS approach extends previous ideas of predictive prefetching in two ways: (1) our approach reduces applications’ execution elapsed time by keeping data blocks that are predicted to be accessed in the near future cached in the uppermost level;(2) we propose a parallel data fetching scheme in which multiple fetching mechanisms (i.e. predictive prefetching and application’s on-demand data requests) can work in parallel;where the first one fetches data blocks among the different levels of the hybrid storage systems (i.e. low-level (slow) to high-level (fast) storage devices) and the other one fetches the data from the storage system to the application. Our PPHSS strategy integrated with the predictive prefetching mechanism significantly reduces overall I/O access time in a hybrid storage system. Finally, we developed a simulator to evaluate the performance of the proposed predictive prefetching scheme in the context of hybrid storage systems. Our results show that our PPHSS can improve system performance by 4% across real-world I/O traces without the need of using large size caches.
文摘In this paper, a prefetching technique is proposed to solve the performance problem caused by remote data access delay. In the technique, the map tasks which will cause the delay are predicted first and then the input data of these tasks will be preloaded before the tasks are scheduled. During the execution, the input data can be read from local nodes. Therefore, the delay can be hidden. The technique has been implemented in Hadoop-0. 20.1. The experiment results have shown that the technique reduces map tasks causing delay, and improves the performance of Hadoop MapRe- duce by 20%.
文摘A scheme for high-speed data transfer via the Internet for Web service in an extremely large delay environment is proposed. With the wide-spread use of Internet services in recent years, WLAN Internet service in high-speed trains has commenced. The system for this is composed of a satellite communication system between the train and the ground station, which is characterized by extremely large latency of several hundred milliseconds due to long propagation latency. High-speed web access is not available to users in a train in such an extremely large latency network system. Thus, a prefetch scheme for performance acceleration of Web services in this environment is proposed. A test-bed system that implements the proposed scheme is implemented and is its performance in this test-bed is evaluated. The proposed scheme is verified to enable high-speed Web access in the extremely large delay environment compared to conventional schemes.
文摘With the speed gap between storage system access and processor computing, end-to-end data processing has become a bottleneck to improve the total performance of computer systems over the Internet. Based on the analysis of data processing behavior, an adaptive cache organization scheme is proposed with fast address calculation. This scheme can make full use of the characteristics of stack space data access, adopt fast address calculation strategy, and reduce the hit time of stack access. Adaptively, the stack cache can be turned off from beginning to end, when a stack overflow occurs to avoid the effect of stack switching on processor performance. Also, through the instruction cache and the failure behavior for the data cache, a prefetching policy is developed, which is combined with the data capture of the failover queue state. Finally, the proposed method can maintain the order of instruction and data access, which facilitates the extraction of prefetching in the end-to-end data processing.
基金supported in part by the National Science Foundation of USA under Grant Nos.EIA-0224377,CNS-0406328,CNS-0509118,and CCF-0621435.
文摘Data prefetching is an effective data access latency hiding technique to mask the CPU stall caused by cache misses and to bridge the performance gap between processor and memory. With hardware and/or software support, data prefetching brings data closer to a processor before it is actually needed. Many prefetching techniques have been developed for single-core processors. Recent developments in processor technology have brought multicore processors into mainstream. While some of the single-core prefetching techniques are directly applicable to multicore processors, numerous novel strategies have been proposed in the past few years to take advantage of multiple cores. This paper aims to provide a comprehensive review of the state-of-the-art prefetching techniques, and proposes a taxonomy that classifies various design concerns in developing a prefetching strategy, especially for multicore processors. We compare various existing methods through analysis as well.
基金supported by the Natural Science Foundation of Beijing under Grant No.4192007the National Natural Science Foundation of China under Grant No.61202076.
文摘Hardware prefetching and replacement policies are two techniques to improve the performance of the memory subsystem.While prefetching hides memory latency and improves performance,interactions take place with the cache replacement policies,thereby introducing performance variability in the application.To improve the accuracy of reuse of cache blocks in the presence of hardware prefetching,we propose Prefetch-Adaptive Intelligent Cache Replacement Policy(PAIC).PAIC is designed with separate predictors for prefetch and demand requests,and uses machine learning to optimize reuse prediction in the presence of prefetching.By distinguishing reuse predictions for prefetch and demand requests,PAIC can better combine the performance benefits from prefetching and replacement policies.We evaluate PAIC on a set of 27 memory-intensive programs from the SPEC 2006 and SPEC 2017.Under single-core configuration,PAIC improves performance over Least Recently Used(LRU)replacement policy by 37.22%,compared with improvements of 32.93%for Signature-based Hit Predictor(SHiP),34.56%for Hawkeye,and 34.43%for Glider.Under the four-core configuration,PAIC improves performance over LRU by 20.99%,versus 13.23%for SHiP,17.89%for Hawkeye and 15.50%for Glider.
基金Supported by the National Natural Science Foundation of China under Grant No. 60472044. The authors would like to thank research fellow Dr. Yun Shi of China State Post Bureau and Professor Dr. Jun Zou of Tsinghua University for their helpful and constructive comments.
文摘The World Wide Web has become the primary means for information dissemination. Due to the limited resources of the network bandwidth, users always suffer from long time waiting. Web prefetching and web caching are the primary approaches to reducing the user perceived access latency and improving the quality of services. In this paper, a Stochastic Petri Nets （SPN） based integrated web prefetching and caching model （IWPCM） is presented and the performance evaluation of IWPCM is made. The performance metrics, access latency, throughput, HR （hit ratio） and BHR （byte hit ratio） are analyzed and discussed. Simulations show that compared with caching only model （CM）, IWPCM can further improve the throughput, HR and BHR efficiently and reduce the access latency. The performance evaluation based on the SPN model can provide a basis for implementation of web prefetching and caching and the combination of web prefetching and caching holds the promise of improving the QoS of web systems.
基金supported by a grant from HP Lab China,and the National Natural Science Foundation of China under Grant Nos.60496325 and 60573092
文摘As the speed gap between main memory and modern processors continues to widen, the cache behavior becomes more important for main memory database systems （MMDBs）. Indexing technique is a key component of MMDBs. Unfortunately, the predominant indexes -B^＋-trees and T-trees -- have been shown to utilize cache poorly, which triggers the development of many cache-conscious indexes, such as CSB^＋-trees and pB^＋-trees. Most of these cache-conscious indexes are variants of conventional B^＋-trees, and have better cache performance than B^＋-trees. In this paper, we develop a novel J^＋-tree index, inspired by the Judy structure which is an associative array data structure, and propose a more cacheoptimized index -- Prefetching J^＋-tree （pJ^＋-tree）, which applies prefetching to J^＋-tree to accelerate range scan operations. The J^＋-tree stores all the keys in its leaf nodes and keeps the reference values of leaf nodes in a Judy structure, which makes J^＋-tree not only hold the advantages of Judy （such as fast single value search） but also outperform it in other aspects. For example, J^＋-trees can achieve better performance on range queries than Judy. The pJ^＋-tree index exploits prefetching techniques to further improve the cache behavior of J^＋-trees and yields a speedup of 2.0 on range scans. Compared with B^＋-trees, CSB^＋-trees, pB^＋-trees and T-trees, our extensive experimental Study shows that pJ^＋-trees can provide better performance on both time （search, scan, update） and space aspects.
基金supported by the National Key Research and Development Program of China(No.2018YFB1003203)the National Natural Science Foundation of China(Nos.61772218 and 61433019)+1 种基金the Outstanding Youth Foundation of Hubei Province(No.2016CFA032)the Chinese Universities Scientific Fund(No.2019kfyRCPY030)。
文摘Docker,as a mainstream container solution,adopts the Copy-on-Write(CoW)mechanism in its storage drivers.This mechanism satisfies the need of different containers to share the same image.However,when a single container performs operations such as modification of an image file,a duplicate is created in the upper readwrite layer,which contributes to the runtime overhead.When the accessed image file is fairly large,this additional overhead becomes non-negligible.Here we present the concept of Dynamic Prefetching Strategy Optimization(DPSO),which optimizes the Co W mechanism for a Docker container on the basis of the dynamic prefetching strategy.At the beginning of the container life cycle,DPSO pre-copies up the image files that are most likely to be copied up later to eliminate the overhead caused by performing this operation during application runtime.The experimental results show that DPSO has an average prefetch accuracy of greater than 78%in complex scenarios and could effectively eliminate the overhead caused by the CoW mechanism.
基金This work is funded by the National Science Foundation of USA under Grants Nos.OCI-1835764 and CSR-1814872。
文摘Modern High-Performance Computing(HPC)systems are adding extra layers to the memory and storage hierarchy,named deep memory and storage hierarchy(DMSH),to increase I/O performance.New hardware technologies,such as NVMe and SSD,have been introduced in burst buffer installations to reduce the pressure for external storage and boost the burstiness of modern I/O systems.The DMSH has demonstrated its strength and potential in practice.However,each layer of DMSH is an independent heterogeneous system and data movement among more layers is significantly more complex even without considering heterogeneity.How to efficiently utilize the DMSH is a subject of research facing the HPC community.Further,accessing data with a high-throughput and low-latency is more imperative than ever.Data prefetching is a well-known technique for hiding read latency by requesting data before it is needed to move it from a high-latency medium(e.g.,disk)to a low-latency one(e.g.,main memory).However,existing solutions do not consider the new deep memory and storage hierarchy and also suffer from under-utilization of prefetching resources and unnecessary evictions.Additionally,existing approaches implement a client-pull model where understanding the application's I/O behavior drives prefetching decisions.Moving towards exascale,where machines run multiple applications concurrently by accessing files in a workflow,a more data-centric approach resolves challenges such as cache pollution and redundancy.In this paper,we present the design and implementation of Hermes:a new,heterogeneous-aware,multi-tiered,dynamic,and distributed I/O buffering system.Hermes enables,manages,supervises,and,in some sense,extends I/O buffering to fully integrate into the DMSH.We introduce three novel data placement policies to efficiently utilize all layers and we present three novel techniques to perform memory,metadata,and communication management in hierarchical buffering systems.Additionally,we demonstrate the benefits of a truly hierarchical data prefetcher that adopts a server-push approach to data prefetching.Our evaluation shows that,in addition to automatic data movement through the hierarchy,Hermes can significantly accelerate I/O and outperforms by more than 2x state-of-the-art buffering platforms.Lastly,results show 10%-35%performance gains over existing prefetchers and over 50%when compared to systems with no prefetching.
