DiscPOP: Power-aware buffer management for disk accesses

Abstract Much research has been conducted on energy efficient cache buffer management for disk based storage systems. Some of them use greedy prefetching technique to artificially increase disk idle intervals if there is a large number of known future requests. However, this might result in sub-optimal solution by not exploiting the relationship between I/O access pattern (sequential/random) and application pattern (cpu time required for computing). In a cpu-bound application, by explicitly taking into account the required CPU time it may reduce energy conservation by up to 50% and increase power cycle number by 100% compared to an existing efficient prefetching scheme without this consideration. In this paper, we consider the tradeoff between disk power consumption, performance guarantee and disk reliability all together by proposing a Dis k c haracteristic based P ower- O ptimal P refetching (DiscPOP) scheme. Specifically, we make three contributions: (i) A theoretical model is proposed to analyze energy-efficient cache buffer management in disk I/O system and it was formulated as an optimization problem. We have shown it can be solved via an Integer Linear Programming (ILP) technique, we further conduct the following research. (ii) For offline cases, we proposed a Greedy Partition algorithm (GP) to divide the problem into several small ones and solve them separately via the proposed ILP algorithm. (iii) For online cases, we proposed two heuristic algorithms based on Lazy Start Power-Optimal Prefetching (LSPOP) technique. Both of them use simple threshold controlled algorithms to select a prefetching start judiciously and cautiously. We use a trace-driven simulation to evaluate our proposed schemes. The results show GP outperforms the traditional aggressive prefetching by up to 26.9% more disk energy conservation and 17.8% power cycle reduction. The online heuristic algorithms can also improve disk energy saving by up to 20.5% and reduce power cycle by 14.3%.

[1]  David Hung-Chang Du.  Recent Advancements and Future Challenges of Storage Systems , 2008, Proceedings of the IEEE.

[2]  Yuhui Deng,et al.  Conserving disk energy in virtual machine based environments by amplifying bursts , 2010, Computing.

[3]  Mahmut T. Kandemir,et al.  Energy-aware data prefetching for multi-speed disks , 2006, CF '06.

[4]  Wei Luo,et al.  Energy-Aware Prefetching for Parallel Disk Systems: Algorithms, Models, and Evaluation , 2009, 2009 Eighth IEEE International Symposium on Network Computing and Applications.

[5]  Dirk Grunwald,et al.  Massive Arrays of Idle Disks For Storage Archives , 2002, ACM/IEEE SC 2002 Conference (SC'02).

[6]  David J. Lilja,et al.  Data prefetch mechanisms , 2000, CSUR.

[7]  Dong Li,et al.  eRAID: A Queueing Model Based Energy Saving Policy , 2006, 14th IEEE International Symposium on Modeling, Analysis, and Simulation.

[8]  Luis Angel D. Bathen,et al.  AMP: Adaptive Multi-stream Prefetching in a Shared Cache , 2007, FAST.

[9]  Xiaodong Zhang,et al.  PS-BC: Power-saving considerations in design of buffer caches serving heterogeneous storage devices , 2010, 2010 ACM/IEEE International Symposium on Low-Power Electronics and Design (ISLPED).

[10]  Anna R. Karlin,et al.  A study of integrated prefetching and caching strategies , 1995, SIGMETRICS '95/PERFORMANCE '95.

[11]  Steve Vandebogart,et al.  Reducing Seek Overhead with Application-Directed Prefetching , 2009, USENIX Annual Technical Conference.

[12]  Laszlo A. Belady,et al.  A Study of Replacement Algorithms for Virtual-Storage Computer , 1966, IBM Syst. J..

[13]  Xiaodong Li,et al.  Performance directed energy management for main memory and disks , 2004, ASPLOS XI.

[14]  Chris Gniady,et al.  Context-Aware Mechanisms for Reducing Interactive Delays of Energy Management in Disks , 2008, USENIX Annual Technical Conference.

[15]  Giovanni De Micheli,et al.  Comparing System-Level Power Management Policies , 2001, IEEE Des. Test Comput..

[16]  Jin Qian,et al.  PARAID: A gear-shifting power-aware RAID , 2007, TOS.

[17]  John B. Carter,et al.  Reliability-aware energy management for hybrid storage systems , 2011, 2011 IEEE 27th Symposium on Mass Storage Systems and Technologies (MSST).

[18]  Xiaodong Zhang,et al.  Caching for bursts (C-Burst): let hard disks sleep well and work energetically , 2008, Proceeding of the 13th international symposium on Low power electronics and design (ISLPED '08).

[19]  Antony I. T. Rowstron,et al.  Write off-loading: Practical power management for enterprise storage , 2008, TOS.

[20]  Ricardo Bianchini,et al.  Exploiting redundancy to conserve energy in storage systems , 2006, SIGMETRICS '06/Performance '06.

[21]  Jinoh Kim,et al.  Energy-Aware Scheduling in Disk Storage Systems , 2011, 2011 31st International Conference on Distributed Computing Systems.

[22]  Jim Zelenka,et al.  Informed prefetching and caching , 1995, SOSP.

[23]  David Hung-Chang Du,et al.  GreenStor: Application-Aided Energy-Efficient Storage , 2007, 24th IEEE Conference on Mass Storage Systems and Technologies (MSST 2007).

[24]  Zhe Zhang,et al.  Memory resource allocation for file system prefetching: from a supply chain management perspective , 2009, EuroSys '09.

[25]  Xiao Qin,et al.  Conserving energy in real-time storage systems with I/O burstiness , 2010, TECS.

[26]  Eduardo Pinheiro,et al.  Failure Trends in a Large Disk Drive Population , 2007, FAST.

[27]  Michael L. Scott,et al.  Energy efficient prefetching and caching , 2004 .

[28]  Yuanyuan Zhou,et al.  Reducing Energy Consumption of Disk Storage Using Power-Aware Cache Management , 2004, 10th International Symposium on High Performance Computer Architecture (HPCA'04).

[29]  Scott A. Brandt,et al.  A Hybrid Disk-Aware Spin-Down Algorithm with I/O Subsystem Support , 2007, 2007 IEEE International Performance, Computing, and Communications Conference.

[30]  Arvind Krishnamurthy,et al.  Modeling Hard-Disk Power Consumption , 2003, FAST.

[31]  Yung-Hsiang Lu,et al.  Joint power management of memory and disk , 2005, Design, Automation and Test in Europe.

[32]  Geoffrey H. Kuenning,et al.  Automated hoarding for mobile computers , 1997, SOSP.

[33]  Paul Horton,et al.  A Quantitative Analysis of Disk Drive Power Management in Portable Computers , 1994, USENIX Winter.

[34]  Giovanni De Micheli,et al.  Adaptive hard disk power management on personal computers , 1999, Proceedings Ninth Great Lakes Symposium on VLSI.

[35]  Matthew Garrett,et al.  Powering Down , 2007, ACM Queue.

[36]  Xiaoning Ding,et al.  DULO: an effective buffer cache management scheme to exploit both temporal and spatial locality , 2005, FAST'05.

[37]  Darrell D. E. Long,et al.  A dynamic disk spin-down technique for mobile computing , 1996, MobiCom '96.

[38]  Nimrod Megiddo,et al.  ARC: A Self-Tuning, Low Overhead Replacement Cache , 2003, FAST.

[39]  Mahmut T. Kandemir,et al.  DRPM: dynamic speed control for power management in server class disks , 2003, 30th Annual International Symposium on Computer Architecture, 2003. Proceedings..