Lifetime-aware solid-state disk (SSD) cache management for video servers

Solid-state disks (SSDs) are now being used as enterprise storage servers owing to their technical merits such as low power consumption, shock resistance, and excellent random read performance. To handle the large storage requirements for video data, they can be used as a cache for hard disk drives (HDDs) in video servers, but this poses several questions such as (1) which video segments can be cached on SSD, (2) how to guarantee the lifetime of SSD, and (3) how to make combined use of dynamic random-access memory (DRAM) and SSD for caching. We start by introducing the concept of caching gain to express the amount of disk bandwidth saved by caching, and go on to propose three algorithms: (1) a dynamic programming algorithm that allows for segment popularity in determining which videos should have initial segments (prefixes) stored on the SSD; (2) a throttling algorithm, which limits the number of cache replacements to guarantee the specified lifetime while maximizing caching gain using a parametric search technique; (3) an algorithm that determines the intervals between pairs of consecutive requests to be stored on the DRAM. We quantitatively explore the effect of this caching scheme through simulations, which show that: (1) prefix caching is quite effective for disk bandwidth saving, (2) our throttling algorithm guarantees the lifetime of the SSD, and (3) DRAM caching can be effectively combined with SSD caching with the aim of maximizing overall caching gain.

[1]  Mihaela van der Schaar,et al.  Popularity-driven content caching , 2016, IEEE INFOCOM 2016 - The 35th Annual IEEE International Conference on Computer Communications.

[2]  Sungjin Lee,et al.  PCStream: Automatic Stream Allocation Using Program Contexts , 2018, HotStorage.

[3]  Qiang Ling,et al.  A feedback-based adaptive data migration method for hybrid storage VOD caching systems , 2014, Multimedia Tools and Applications.

[4]  Leonard Kleinrock,et al.  Theory, Volume 1, Queueing Systems , 1975 .

[5]  Jing Xu,et al.  CloudCache: On-demand Flash Cache Management for Cloud Computing , 2016, FAST.

[6]  Umakishore Ramachandran,et al.  Impact of flash memory on video-on-demand storage: analysis of tradeoffs , 2011, MMSys.

[7]  Umakishore Ramachandran,et al.  Why are state-of-the-art flash-based multi-tiered storage systems performing poorly for HTTP video streaming? , 2012, NOSSDAV '12.

[8]  Fei Meng,et al.  vCacheShare: Automated Server Flash Cache Space Management in a Virtualization Environment , 2014, USENIX Annual Technical Conference.

[9]  Yonggang Wen,et al.  Resource Provisioning and Profit Maximization for Transcoding in Clouds: A Two-Timescale Approach , 2017, IEEE Transactions on Multimedia.

[10]  Zongpeng Li,et al.  A Geometric Approach to Server Selection for Interactive Video Streaming , 2016, IEEE Transactions on Multimedia.

[11]  Yong-Yeol Ahn,et al.  Analyzing the Video Popularity Characteristics of Large-Scale User Generated Content Systems , 2009, IEEE/ACM Transactions on Networking.

[12]  Riqing Chen,et al.  Efficient Sequential Data Migration Scheme Considering Dying Data for HDD/SSD Hybrid Storage Systems , 2017, IEEE Access.

[13]  Tong Zhang,et al.  Realizing Low-Cost Flash Memory Based Video Caching in Content Delivery Systems , 2018, IEEE Transactions on Circuits and Systems for Video Technology.

[14]  Anand Sivasubramaniam,et al.  HybridStore: A Cost-Efficient, High-Performance Storage System Combining SSDs and HDDs , 2011, 2011 IEEE 19th Annual International Symposium on Modelling, Analysis, and Simulation of Computer and Telecommunication Systems.

[15]  Yang Wang,et al.  Improving Performance of Parallel I/O Systems through Selective and Layout-Aware SSD Cache , 2016, IEEE Transactions on Parallel and Distributed Systems.

[16]  Umakishore Ramachandran,et al.  FlashStream: a multi-tiered storage architecture for adaptive HTTP streaming , 2013, MM '13.

[17]  Tei-Wei Kuo,et al.  Energy-aware data placement strategy for SSD-assisted streaming video servers , 2014, 2014 IEEE Non-Volatile Memory Systems and Applications Symposium (NVMSA).

[18]  Yeonseung Ryu,et al.  A Flash Translation Layer for nand Flash-Based Multimedia Storage Devices , 2011, IEEE Transactions on Multimedia.

[19]  Laurent Lemarchand,et al.  COPS: Cost Based Object Placement Strategies on Hybrid Storage System for DBaaS Cloud , 2017, 2017 17th IEEE/ACM International Symposium on Cluster, Cloud and Grid Computing (CCGRID).

[20]  Minseok Song,et al.  Cache Management for Video Servers by the Combined Use of DRAM and SSD , 2016, 2016 IEEE International Symposium on Multimedia (ISM).

[21]  Baochun Li,et al.  Keep Cache Replacement Simple in Peer-Assisted VoD Systems , 2009, IEEE INFOCOM 2009.

[22]  Myeong-Wuk Jang,et al.  Inter-Chunk Popularity-Based Edge-First Caching in Content-Centric Networking , 2014, IEEE Communications Letters.

[23]  Tao Xie,et al.  An SSD-HDD Integrated Storage Architecture for Write-Once-Read-Once Applications on Clusters , 2015, 2015 IEEE International Conference on Cluster Computing.

[24]  Zvonimir Bandic,et al.  PCAP: Performance-aware Power Capping for the Disk Drive in the Cloud , 2016, FAST.

[25]  Jun Xu,et al.  Hybrid Storage Systems: A Survey of Architectures and Algorithms , 2018, IEEE Access.

[26]  Ben Y. Zhao,et al.  Understanding user behavior in large-scale video-on-demand systems , 2006, EuroSys.

[27]  Minseok Song Minimizing Power Consumption in Video Servers by the Combined Use of Solid-State Disks and Multi-Speed Disks , 2018, IEEE Access.

[28]  Reza Salkhordeh,et al.  ReCA: An Efficient Reconfigurable Cache Architecture for Storage Systems with Online Workload Characterization , 2018, IEEE Transactions on Parallel and Distributed Systems.

[29]  Wenzhi Chen,et al.  A Duplication-Aware SSD-Based Cache Architecture for Primary Storage in Virtualization Environment , 2017, IEEE Systems Journal.

[30]  Kyu Ho Park,et al.  An SSD-Based Storage System for an Interactive Media Server Using Video Frame Grouping , 2013 .

[31]  Asit Dan,et al.  Dynamic batching policies for an on-demand video server , 1996, Multimedia Systems.

[32]  Ge Zhang,et al.  Unreeling Xunlei Kankan: Understanding Hybrid CDN-P2P Video-on-Demand Streaming , 2015, IEEE Transactions on Multimedia.

[33]  Sungjin Lee,et al.  Lifetime management of flash-based SSDs using recovery-aware dynamic throttling , 2012, FAST.

[34]  Sang-Won Lee,et al.  Flash-based Extended Cache for Higher Throughput and Faster Recovery , 2012, Proc. VLDB Endow..

[35]  Steven Swanson,et al.  The bleak future of NAND flash memory , 2012, FAST.

[36]  Yang Guo,et al.  Dynamic Cache Reconfiguration Strategies for a Cluster-Based Streaming Proxy , 2003, WCW.

[37]  Chunfeng Yang,et al.  Video Popularity Dynamics and Its Implication for Replication , 2015, IEEE Transactions on Multimedia.

[38]  Jian Liu,et al.  Endurable SSD-Based Read Cache for Improving the Performance of Selective Restore from Deduplication Systems , 2018, Journal of Computer Science and Technology.

[39]  Jaewon Lee,et al.  DTStorage: Dynamic Tape-Based Storage for Cost-Effective and Highly-Available Streaming Service , 2016, 2016 16th IEEE/ACM International Symposium on Cluster, Cloud and Grid Computing (CCGrid).

[40]  Gaogang Xie,et al.  Video Delivery Performance of a Large-Scale VoD System and the Implications on Content Delivery , 2015, IEEE Transactions on Multimedia.

[41]  Keqin Li,et al.  Accelerating MapReduce on Commodity Clusters: An SSD-Empowered Approach , 2018, IEEE Transactions on Big Data.

[42]  Nimrod Megiddo,et al.  Applying parallel computation algorithms in the design of serial algorithms , 1981, 22nd Annual Symposium on Foundations of Computer Science (sfcs 1981).

[43]  Eui-Jik Kim,et al.  Hybrid storage-based caching strategy for content delivery network services , 2014, Multimedia Tools and Applications.

[44]  Sungjin Lee,et al.  Effective Lifetime-Aware Dynamic Throttling for NAND Flash-Based SSDs , 2016, IEEE Transactions on Computers.

[45]  Tao Xie,et al.  Dynamic data replication on flash SSD assisted Video-on-Demand servers , 2012, 2012 International Conference on Computing, Networking and Communications (ICNC).

[46]  Evangelos Eleftheriou,et al.  Write amplification analysis in flash-based solid state drives , 2009, SYSTOR '09.

[47]  Asit Dan,et al.  Multimedia Caching Strategies for Heterogeneous Application and Server Environments , 2004, Multimedia Tools and Applications.