Design and Evaluation of an Energy Agile Computing Cluster

AbstractVariable, intermittent renewable sources of energy arebeing introduced into the national electric grid at scale.However, the current grid paradigm of load-followingsupplies is unable to utilize these sources without im-practical deployments of backup generation and grid-scale energy storage. Thus, it will be crucial to haveenergy agile loads: electric loads that can dynamicallyadapt their energy consumption. Data centers are primecandidates for becoming energy agile because they arelarge energy consumers and often have workloads thatcan be shaped to vary their power consumption. In thispaper we present an energy agile cluster that is powerproportional (uses power proportional to its workload)and exposes slack (the ability to temporarily delay ordegrade service to reduce power consumption). We de-scribe a prototype cluster that consumes 60% less en-ergy on typical workloads by being power proportional.Then, using month-long traces from a 9572 node com-puting cluster and a California wind farm, we show howa grid-aware scheduler can use workload slack to reducesdependence on non-renewable energy sources to 40% ofits original level. Our results show that achieving thesame wind penetration with energy storage alone wouldrequire sufficient battery capacity to run a cluster for fivehours.

[1]  Christopher Stewart,et al.  Some Joules Are More Precious Than Others: Managing Renewable Energy in the Datacenter∗ , 2009 .

[2]  Ricardo Bianchini,et al.  Dynamic cluster reconfiguration for power and performance , 2003 .

[3]  Wensong Zhang.  Linux Virtual Server for Scalable Network Services , 2000 .

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

[5]  Mizanur Rahman.  MediaWiki Administrators' Tutorial Guide , 2007 .

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

[7]  Garrick Staples,et al.  TORQUE resource manager , 2006, SC.

[8]  Eric A. Brewer,et al.  Lessons from Giant-Scale Services , 2001, IEEE Internet Comput..

[9]  KyoungSoo Park,et al.  Wide-area Network Acceleration for the Developing World , 2010, USENIX Annual Technical Conference.

[10]  Andrey Gubarev,et al.  Dremel : Interactive Analysis of Web-Scale Datasets , 2011 .

[11]  Prashant J. Shenoy,et al.  Blink: managing server clusters on intermittent power , 2011, ASPLOS XVI.

[12]  Archana Ganapathi,et al.  Predicting Multiple Metrics for Queries: Better Decisions Enabled by Machine Learning , 2009, 2009 IEEE 25th International Conference on Data Engineering.

[13]  Vincent Salzgeber,et al.  Making cluster applications energy-aware , 2009, ACDC '09.

[14]  Jeffery B. Greenblatt,et al.  California's Energy Future - The View to 2050 - eScholarship , 2011 .

[15]  P. Varaiya,et al.  Bringing Wind Energy to Market , 2012, IEEE Transactions on Power Systems.

[16]  Jerome A. Rolia,et al.  Capacity planning and power management to exploit sustainable energy , 2010, 2010 International Conference on Network and Service Management.

[17]  Amin Vahdat,et al.  Managing energy and server resources in hosting centers , 2001, SOSP.

[18]  Archana Ganapathi,et al.  Statistics-driven workload modeling for the Cloud , 2010, 2010 IEEE 26th International Conference on Data Engineering Workshops (ICDEW 2010).

[19]  Austin Donnelly,et al.  Sierra: practical power-proportionality for data center storage , 2011, EuroSys '11.

[20]  Malgorzata Steinder,et al.  Performance-driven task co-scheduling for MapReduce environments , 2010, 2010 IEEE Network Operations and Management Symposium - NOMS 2010.

[21]  Luiz André Barroso,et al.  The Datacenter as a Computer: An Introduction to the Design of Warehouse-Scale Machines , 2009, The Datacenter as a Computer: An Introduction to the Design of Warehouse-Scale Machines.

[22]  Albert G. Greenberg,et al.  Data center TCP (DCTCP) , 2010, SIGCOMM '10.

[23]  Scott Shenker,et al.  Scheduling for reduced CPU energy , 1994, OSDI '94.

[24]  Martin Greiner,et al.  Reduced storage and balancing needs in a fully renewable European power system with excess wind and solar power generation , 2011 .

[25]  Alan Jay Smith,et al.  Improving dynamic voltage scaling algorithms with PACE , 2001, SIGMETRICS '01.

[26]  Suman Nath,et al.  Energy-Aware Server Provisioning and Load Dispatching for Connection-Intensive Internet Services , 2008, NSDI.

[27]  Michael Stonebraker,et al.  Load Shedding in a Data Stream Manager , 2003, VLDB.

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

[29]  Eric A. Brewer,et al.  Reducing WWW Latency and Bandwidth Requirements by Real-Time Distillation , 1996, Comput. Networks.

[30]  Jordi Torres,et al.  GreenSlot: Scheduling energy consumption in green datacenters , 2011, 2011 International Conference for High Performance Computing, Networking, Storage and Analysis (SC).

[31]  John A. Hules,et al.  National Energy Research Scientific Computing Center 2007 Annual Report , 2008 .

[32]  David E. Culler,et al.  SEDA: an architecture for well-conditioned, scalable internet services , 2001, SOSP.

[33]  Willy Zwaenepoel,et al.  Cluster reserves: a mechanism for resource management in cluster-based network servers , 2000, SIGMETRICS '00.

[34]  Bruce M. Maggs,et al.  Cutting the electric bill for internet-scale systems , 2009, SIGCOMM '09.