Power consumption in enterprise-scale backup storage systems

Power consumption has become an important factor in modern storage system design. Power efficiency is particularly beneficial in disk-based backup systems that store mostly cold data, have significant idle periods, and must compete with the operational costs of tape-based backup. There are no prior published studies on power consumption in these systems, leaving researchers and practitioners to rely on existing assumptions. In this paper we present the first analysis of power consumption in real-world, enterprise, disk-based backup storage systems. We uncovered several important observations, including some that challenge conventional wisdom. We discuss their impact on future power-efficient designs.

[1]  Erez Zadok,et al.  Energy and performance evaluation of lossless file data compression on server systems , 2009, SYSTOR '09.

[2]  Lizy Kurian John,et al.  Complete System Power Estimation: A Trickle-Down Approach Based on Performance Events , 2007, 2007 IEEE International Symposium on Performance Analysis of Systems & Software.

[3]  Akshat Verma,et al.  SRCMap: Energy Proportional Storage Using Dynamic Consolidation , 2010, FAST.

[4]  Karsten Schwan,et al.  Robust and flexible power-proportional storage , 2010, SoCC '10.

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

[6]  Luiz André Barroso,et al.  The Case for Energy-Proportional Computing , 2007, Computer.

[7]  Lizy Kurian John,et al.  Analysis of dynamic power management on multi-core processors , 2008, ICS '08.

[8]  Jacob R. Lorch,et al.  A complete picture of the energy consumption of a portable computer , 1995 .

[9]  Ethan L. Miller,et al.  Pergamum: Replacing Tape with Energy Efficient, Reliable, Disk-Based Archival Storage , 2008, FAST.

[10]  Ragunathan Rajkumar,et al.  Critical power slope: understanding the runtime effects of frequency scaling , 2002, ICS '02.

[11]  Austin Donnelly,et al.  Sierra: a power-proportional, distributed storage system , 2009 .

[12]  Ethan L. Miller,et al.  Semantic data placement for power management in archival storage , 2010, 2010 5th Petascale Data Storage Workshop (PDSW '10).

[13]  Erez Zadok,et al.  Evaluating Performance and Energy in File System Server Workloads , 2010, FAST.

[14]  Amar Phanishayee,et al.  FAWN: a fast array of wimpy nodes , 2009, SOSP '09.

[15]  Gernot Heiser,et al.  An Analysis of Power Consumption in a Smartphone , 2010, USENIX Annual Technical Conference.

[16]  Frank Bellosa,et al.  The benefits of event: driven energy accounting in power-sensitive systems , 2000, ACM SIGOPS European Workshop.

[17]  Karan Gupta,et al.  Energy proportionality for storage: impact and feasibility , 2010, OPSR.

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

[19]  Vibhore Vardhan,et al.  Power Consumption Breakdown on a Modern Laptop , 2004, PACS.

[20]  Fred Douglis,et al.  Characteristics of backup workloads in production systems , 2012, FAST.

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

[22]  Philip Levis,et al.  Policies for dynamic clock scheduling , 2000, OSDI.

[23]  Gernot Heiser,et al.  Slow Down or Sleep, That Is the Question , 2011, USENIX Annual Technical Conference.

[24]  Yuanyuan Zhou,et al.  Hibernator: helping disk arrays sleep through the winter , 2005, SOSP '05.

[25]  J. Koomey Worldwide electricity used in data centers , 2008 .

[26]  Kai Li,et al.  Avoiding the Disk Bottleneck in the Data Domain Deduplication File System , 2008, FAST.

[27]  Assim Sagahyroon Power Consumption in Handheld Computers , 2006, APCCAS 2006 - 2006 IEEE Asia Pacific Conference on Circuits and Systems.