The poor performance of random writes has been a cause of major concern which needs to be addressed to better utilize the potential of flash in enterprise-scale environments. We examine one of the important causes of ...The poor performance of random writes has been a cause of major concern which needs to be addressed to better utilize the potential of flash in enterprise-scale environments. We examine one of the important causes of this poor performance： the design of the flash translation layer （FTL） which performs the virtual-to-physical address translations and hides the erase-before-write characteristics of flash. We propose a complete paradigm shift in the design of the core FTL engine from the existing techniques with our Demand-Based Flash Translation Layer （DFTL） which selectively caches page- level address mappings. Our experimental evaluation using FlashSim with realistic enterprise-scale workloads endorses the utility of DFTL in enterprise-scale storage systems by demonstrating： 1） improved performance, 2） reduced garbage collection overhead and 3） better overload behavior compared with hybrid FTL schemes which are the most popular implementation methods. For example, a predominantly random-write dominant I/O trace from an OLTP application running at a large financial institution shows a 78% improvement in average response time （due to a 3-fold reduction in operations of the garbage collector）, compared with the hybrid FTL scheme. Even for the well-known read-dominant TPC-H benchmark, for which DFTL introduces additional overheads, we improve system response time by 56%. Moreover, interestingly, when write-back cache on DFTL-based SSD is enabled, DFTL even outperforms the page-based FTL scheme, improving their response time by 72% in Financial trace.展开更多
Flash solid-state drives （SSDs） provide much faster access to data compared with traditional hard disk drives （HDDs）. The current price and performance of SSD suggest it can be adopted as a data buffer between mai...Flash solid-state drives （SSDs） provide much faster access to data compared with traditional hard disk drives （HDDs）. The current price and performance of SSD suggest it can be adopted as a data buffer between main memory and HDD, and buffer management policy in such hybrid systems has attracted more and more interest from research community recently. In this paper, we propose a novel approach to manage the buffer in flash-based hybrid storage systems, named hotness aware hit （HAT）. HAT exploits a page reference queue to record the access history as well as the status of accessed pages, i.e., hot, warm, and cold. Additionally, the page reference queue is further split into hot and warm regions which correspond to the memory and flash in general. The HAT approach updates the page status and deals with the page migration in the memory hierarchy according to the current page status and hit position in the page reference queue. Compared with the existing hybrid storage approaches, the proposed HAT can manage the memory and flash cache layers more effectively. Our empirical evaluation on benchmark traces demonstrates the superiority of the proposed strategy against the state-of-the-art competitors.展开更多
Purpose-The purpose of this paper is to make an overview of 474 publications and 512 patents of FTL from 1987 to 2020 in order to provide a conclusive and comprehensive analysis for researchers in this field,as well a...Purpose-The purpose of this paper is to make an overview of 474 publications and 512 patents of FTL from 1987 to 2020 in order to provide a conclusive and comprehensive analysis for researchers in this field,as well as a preliminary knowledge of FTL for interested researchers.Design/methodology/approach-Firstly,the FTL algorithms are classified and its functions are introduced in detail.Secondly,the structures of the publications are analyzed in terms of the fundamental information and the publication of the most productive countries/regions,institutions and authors.After that,co-citation networks of institutions,authors and papers illustrated by VOS Viewer are given to show the relationship among those and the most influential of them is further analyzed.Then,the characteristics of the patent are analyzed based on the basic information and classification of the patent and the most productive inventors.In order to obtain research hotspots and trends in this field,the time-line review and citation burst detection of keywords carried out by Cite Space are made to be visual.Finally,based on the above analysis,it draws some other important conclusions and the development trend of this field.Findings-The research on FTL algorithm is still the top priority in the future,and how to improve the performance of SSD in the era of big data is one of the research hotspots.Research limitations/implications-This paper makes a comprehensive analysis of FTL with the method of bibliometrics,and it is valuable for researchers can quickly grasp the hotspots in this area.Originality/value-This article draws the structural characteristics of the publications in this field and summarizes the research hotspots and trends in this field in recent years,aiming to inspire new ideas for researchers.展开更多
基金funded in part by the Natural Science Foundation of U.S.under Grant Nos.CCF-0811670,CNS-0720456a gift from Cisco System,Inc.and partially through the Ofce of Science of the U.S.Department of Energy under Contract No.DE-AC05-00OR22725
文摘The poor performance of random writes has been a cause of major concern which needs to be addressed to better utilize the potential of flash in enterprise-scale environments. We examine one of the important causes of this poor performance： the design of the flash translation layer （FTL） which performs the virtual-to-physical address translations and hides the erase-before-write characteristics of flash. We propose a complete paradigm shift in the design of the core FTL engine from the existing techniques with our Demand-Based Flash Translation Layer （DFTL） which selectively caches page- level address mappings. Our experimental evaluation using FlashSim with realistic enterprise-scale workloads endorses the utility of DFTL in enterprise-scale storage systems by demonstrating： 1） improved performance, 2） reduced garbage collection overhead and 3） better overload behavior compared with hybrid FTL schemes which are the most popular implementation methods. For example, a predominantly random-write dominant I/O trace from an OLTP application running at a large financial institution shows a 78% improvement in average response time （due to a 3-fold reduction in operations of the garbage collector）, compared with the hybrid FTL scheme. Even for the well-known read-dominant TPC-H benchmark, for which DFTL introduces additional overheads, we improve system response time by 56%. Moreover, interestingly, when write-back cache on DFTL-based SSD is enabled, DFTL even outperforms the page-based FTL scheme, improving their response time by 72% in Financial trace.
基金Acknowledgements This research was supported by the Nalional Natural Science Foundation of China （Grant No. 61272155） and Ministry of Industry and Information Technology （2010ZX01042-001-001-04）.
文摘Flash solid-state drives （SSDs） provide much faster access to data compared with traditional hard disk drives （HDDs）. The current price and performance of SSD suggest it can be adopted as a data buffer between main memory and HDD, and buffer management policy in such hybrid systems has attracted more and more interest from research community recently. In this paper, we propose a novel approach to manage the buffer in flash-based hybrid storage systems, named hotness aware hit （HAT）. HAT exploits a page reference queue to record the access history as well as the status of accessed pages, i.e., hot, warm, and cold. Additionally, the page reference queue is further split into hot and warm regions which correspond to the memory and flash in general. The HAT approach updates the page status and deals with the page migration in the memory hierarchy according to the current page status and hit position in the page reference queue. Compared with the existing hybrid storage approaches, the proposed HAT can manage the memory and flash cache layers more effectively. Our empirical evaluation on benchmark traces demonstrates the superiority of the proposed strategy against the state-of-the-art competitors.
文摘Purpose-The purpose of this paper is to make an overview of 474 publications and 512 patents of FTL from 1987 to 2020 in order to provide a conclusive and comprehensive analysis for researchers in this field,as well as a preliminary knowledge of FTL for interested researchers.Design/methodology/approach-Firstly,the FTL algorithms are classified and its functions are introduced in detail.Secondly,the structures of the publications are analyzed in terms of the fundamental information and the publication of the most productive countries/regions,institutions and authors.After that,co-citation networks of institutions,authors and papers illustrated by VOS Viewer are given to show the relationship among those and the most influential of them is further analyzed.Then,the characteristics of the patent are analyzed based on the basic information and classification of the patent and the most productive inventors.In order to obtain research hotspots and trends in this field,the time-line review and citation burst detection of keywords carried out by Cite Space are made to be visual.Finally,based on the above analysis,it draws some other important conclusions and the development trend of this field.Findings-The research on FTL algorithm is still the top priority in the future,and how to improve the performance of SSD in the era of big data is one of the research hotspots.Research limitations/implications-This paper makes a comprehensive analysis of FTL with the method of bibliometrics,and it is valuable for researchers can quickly grasp the hotspots in this area.Originality/value-This article draws the structural characteristics of the publications in this field and summarizes the research hotspots and trends in this field in recent years,aiming to inspire new ideas for researchers.
