Multi-layer Prefetching for Hybrid Storage Systems: Algorithms, Models, and Evaluations

Nijim, Mais; Zong, Ziliang; Qin, Xiao; Nijim, Y.W.

doi:10.1109/icppw.2010.18

Cited by 7 publications

(5 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As we go up in the hierarchy, cost in dollars and data retrieval speed increase and size decreases. So, it is better to store the most important data that is most frequently demanded in the top level in order to provide high performance in their retrieval process [1] [12]. When a data block is requested by the application at the client-side node, the system search for it in the top level of the storage-side nodes, if it is not found, the system descends to the lower levels until it is founded and retrieved.…”

Section: Hybrid (Multi-level) Storage Environmentmentioning

confidence: 99%

“…Data Prefetch process in hybrid (multi-levels) storage environment is performed by moving the important data blocks from a bottom level in the hierarchy to the top one. This process is technically challenging as it importantly needs to control both prefetch process aggressiveness and accuracy [7][9][11] [12].…”

Section: Data Prefetchmentioning

confidence: 99%

“…12 show different scenarios of increased SS cache sizes. It is clear that performance trend improves with the increased size SS cache.…”

mentioning

confidence: 99%

See 2 more Smart Citations

Performance Optimization for Distributed Hybrid Storage Systems using a Predictive Approach

Assaf¹

2020

IJATCSE

View full text Add to dashboard Cite

Distributed data centers are considered very important for data storage services in the contemporary computing world especially with the increased amount of data that are needed to be stored and retrieved. Data retrieval speed performance is a sensitive issue when considering the huge amount of data that need to be retrieved from several nodes over the network. Data prefetch has proved to be an important technique for reducing data reading time from the distributed nodes. In such distributed environment, data fetching time from a node to an another consists of the disk reading time and the network transmission time. Multi-layer (hybrid) storage provides high performance solutions for big data centers. We introduce a solution PPDHSS that implements predictive-probability graph to predictively prefetch the data that are expected to be accessed by the application in the near future from the lower level hard disk of the storage-side nodes (slower) to the top level solid state disk (faster) in parallel which the application data reading requests that comes from the client-side node by taking advantage of the storage system's parallelism. Our performance evaluation in which we used real traces shows that our system can reduce the data fetching time from storage side-nodes to the client-side nodes without the need of using caches of large size.

show abstract

Section: Hybrid (Multi-level) Storage Environmentmentioning

confidence: 99%

Section: Data Prefetchmentioning

confidence: 99%

See 1 more Smart Citation

Performance Optimization for Distributed Hybrid Storage Systems using a Predictive Approach

Assaf¹

2020

IJATCSE

View full text Add to dashboard Cite

show abstract

“…Previous studies provided empirical evidences that show how a hybrid storage system can extend the benefits of a single-level cache by augmenting storage systems with multi-level caches [14]- [18]. Nijim proposed a hybrid prefetching algorithm that can speculatively do prefetching in a hybrid storage system from tapes to hard drives and preload data from hard drives to solid state disks [11] [38]. Their study provided experimental results that show how one can leverage prefetching techniques to enhance I/O performance of hybrid storage systems.…”

Section: Prefetching In Hybrid Storage Systemsmentioning

confidence: 99%

Predictive Prefetching for Parallel Hybrid Storage Systems

Assaf¹

2015

IJCNS

View full text Add to dashboard Cite

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.

show abstract

“…For example if a hybrid storage system consists of a HDD at the bottom and SSD at the top, the top level is more energy efficient [40]. Typical storage devices in a modern hybrid storage system include main memory, solid state disks, hard disks, and magnetic tape subsystems (see, for example, [13,14]). …”

Section: Hybrid Storage Systemsmentioning

confidence: 99%

Eco-Storage: A Hybrid Storage System with Energy-Efficient Informed Prefetching

Assaf

Jiang

Abid

et al. 2013

J Sign Process Syst

Self Cite

View full text Add to dashboard Cite

In this paper, we present an energy-aware informed prefetching technique called Eco-Storage that makes use of the application-disclosed access patterns to group the informed prefetching process in a hybrid storage system (e.g., hard disk drive and solid state disks). Since the SSDs are more energy efficient than HDDs, aggressive prefetching for the data in the HDD level enables it to have as much standby time as possible in order to save power. In the Eco-Storage system, the application can still read its on-demand I/O reading requests from the hybrid storage system while the data blocks are prefetched in groups from HDD to SSD. We show that these two steps can be handled in parallel to decreases the system's power consumption. Our Eco-Storage technique differs from existing energy-aware prefetching schemes in two ways. First, EcoStorage is implemented in a hybrid storage system where the SDD level is more energy efficient. Second, it can group the informed prefetching process and quickly prefetch the data from the HDD to the SSD to increase the frequent HDD standby times. This will makes the application finds most of its on-demand I/O reading requests in the SSD level. Finally, we develop a simulator to evaluate our Eco-Storage system performance. Our results show that our Eco-Storage reduces the power consumption by at least 75 % when compared with the worst case of non-Eco-Storage case using a real-world I/O trace.

show abstract

Multi-layer Prefetching for Hybrid Storage Systems: Algorithms, Models, and Evaluations

Cited by 7 publications

References 27 publications

Performance Optimization for Distributed Hybrid Storage Systems using a Predictive Approach

Performance Optimization for Distributed Hybrid Storage Systems using a Predictive Approach

Predictive Prefetching for Parallel Hybrid Storage Systems

Eco-Storage: A Hybrid Storage System with Energy-Efficient Informed Prefetching

Contact Info

Product

Resources

About