ACE: abstracting, characterizing and exploiting peaks and valleys in datacenter power consumption

Peak power management of datacenters has tremendous cost implications. While numerous mechanisms have been proposed to cap power consumption, real datacenter power consumption data is scarce. To address this gap, we collect power demands at multiple spatial and fine-grained temporal resolutions from the load of geo-distributed datacenters of Microsoft over 6 months. We conduct aggregate analysis of this data, to study its statistical properties. With workload characterization a key ingredient for systems design and evaluation, we note the importance of better abstractions for capturing power demands, in the form of peaks and valleys. We identify and characterize attributes for peaks and valleys, and important correlations across these attributes that can influence the choice and effectiveness of different power capping techniques. With the wide scope of exploitability of such characteristics for power provisioning and optimizations, we illustrate its benefits with two specific case studies.

[1]  Feng Zhao,et al.  Virtual machine power metering and provisioning , 2010, SoCC '10.

[2]  Jerome A. Rolia,et al.  Workload Analysis and Demand Prediction of Enterprise Data Center Applications , 2007, 2007 IEEE 10th International Symposium on Workload Characterization.

[3]  Christopher Stewart,et al.  Adaptive green hosting , 2012, ICAC '12.

[4]  Thomas F. Wenisch,et al.  Power routing: dynamic power provisioning in the data center , 2010, ASPLOS XV.

[5]  Lachlan L. H. Andrew,et al.  Greening geographical load balancing , 2011, PERV.

[6]  Wolf-Dietrich Weber,et al.  Power provisioning for a warehouse-sized computer , 2007, ISCA '07.

[7]  Gargi Dasgupta,et al.  BrownMap: Enforcing Power Budget in Shared Data Centers , 2010, Middleware.

[8]  Mark S. Squillante,et al.  Analysis and characterization of large‐scale Web server access patterns and performance , 1999, World Wide Web.

[9]  Thu D. Nguyen,et al.  Cost-and Energy-Aware Load Distribution Across Data Centers , 2009 .

[10]  Bianca Schroeder,et al.  Temperature management in data centers: why some (might) like it hot , 2012, SIGMETRICS '12.

[11]  Frank Bellosa,et al.  Process cruise control: event-driven clock scaling for dynamic power management , 2002, CASES '02.

[12]  John D. Davis,et al.  Including Variability in Large-Scale Cluster Power Models , 2012, IEEE Computer Architecture Letters.

[13]  Margaret Martonosi,et al.  Wattch: a framework for architectural-level power analysis and optimizations , 2000, Proceedings of 27th International Symposium on Computer Architecture (IEEE Cat. No.RS00201).

[14]  David E. Irwin,et al.  Ensemble-level Power Management for Dense Blade Servers , 2006, 33rd International Symposium on Computer Architecture (ISCA'06).

[15]  Walter Willinger,et al.  On the self-similar nature of Ethernet traffic , 1993, SIGCOMM '93.

[16]  Houman Homayoun,et al.  Managing distributed UPS energy for effective power capping in data centers , 2012, 2012 39th Annual International Symposium on Computer Architecture (ISCA).

[17]  Xiaorui Wang,et al.  Server-Level Power Control , 2007, Fourth International Conference on Autonomic Computing (ICAC'07).

[18]  Xifeng Yan,et al.  Workload characterization and prediction in the cloud: A multiple time series approach , 2012, 2012 IEEE Network Operations and Management Symposium.

[19]  Lachlan L. H. Andrew,et al.  Power-aware speed scaling in processor sharing systems: Optimality and robustness , 2012, Perform. Evaluation.

[20]  Martin F. Arlitt,et al.  Web server workload characterization: the search for invariants , 1996, SIGMETRICS '96.

[21]  Thomas F. Wenisch,et al.  Power management of online data-intensive services , 2011, 2011 38th Annual International Symposium on Computer Architecture (ISCA).

[22]  Xiaorui Wang,et al.  How much power oversubscription is safe and allowed in data centers , 2011, ICAC '11.

[23]  Ricardo Bianchini,et al.  Power and energy management for server systems , 2004, Computer.

[24]  Azer Bestavros,et al.  Self-similarity in World Wide Web traffic: evidence and possible causes , 1996, SIGMETRICS '96.

[25]  Lakshmi Ganesh,et al.  Unleash Stranded Power in Data Centers with RackPacker , 2009 .

[26]  Anand Sivasubramaniam,et al.  Statistical profiling-based techniques for effective power provisioning in data centers , 2009, EuroSys '09.

[27]  Xiaorui Wang,et al.  Cluster-level feedback power control for performance optimization , 2008, 2008 IEEE 14th International Symposium on High Performance Computer Architecture.

[28]  Mor Harchol-Balter,et al.  Optimal power allocation in server farms , 2009, SIGMETRICS '09.

[29]  Vanish Talwar,et al.  No "power" struggles: coordinated multi-level power management for the data center , 2008, ASPLOS.

[30]  Ada Gavrilovska,et al.  VM power metering: feasibility and challenges , 2011, PERV.

[31]  Irfan Ahmad,et al.  Modeling workloads and devices for IO load balancing in virtualized environments , 2010, PERV.

[32]  Karthick Rajamani,et al.  A performance-conserving approach for reducing peak power consumption in server systems , 2005, ICS '05.

[33]  Alma Riska,et al.  Disk Drive Level Workload Characterization , 2006, USENIX Annual Technical Conference, General Track.

[34]  Eduardo Pinheiro,et al.  DRAM errors in the wild: a large-scale field study , 2009, SIGMETRICS '09.

[35]  Rajesh Gupta,et al.  Evaluating the effectiveness of model-based power characterization , 2011 .

[36]  Anand Sivasubramaniam,et al.  Worth their watts? - an empirical study of datacenter servers , 2010, HPCA - 16 2010 The Sixteenth International Symposium on High-Performance Computer Architecture.

[37]  Kai Ma,et al.  Scalable power control for many-core architectures running multi-threaded applications , 2011, 2011 38th Annual International Symposium on Computer Architecture (ISCA).

[38]  Christos Kozyrakis,et al.  Full-System Power Analysis and Modeling for Server Environments , 2006 .

[39]  Walter Willinger,et al.  Self-similarity through high-variability: statistical analysis of Ethernet LAN traffic at the source level , 1997, TNET.

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

[41]  Anand Sivasubramaniam,et al.  Leveraging stored energy for handling power emergencies in aggressively provisioned datacenters , 2012, ASPLOS XVII.

[42]  Xiao Zhang,et al.  Power and energy containers for multicore servers , 2012, SIGMETRICS '12.

[43]  Vincent W. Freeh,et al.  Safe Overprovisioning: Using Power Limits to Increase Aggregate Throughput , 2004, PACS.

[44]  James R. Hamilton,et al.  Internet-scale service infrastructure efficiency , 2009, ISCA '09.

[45]  Sriram Sankar,et al.  The need for speed and stability in data center power capping , 2012, 2012 International Green Computing Conference (IGCC).

[46]  Mahadev Satyanarayanan,et al.  A study of file sizes and functional lifetimes , 1981, SOSP.

[47]  Anand Sivasubramaniam,et al.  Benefits and limitations of tapping into stored energy for datacenters , 2011, 2011 38th Annual International Symposium on Computer Architecture (ISCA).

[48]  Mor Harchol-Balter,et al.  The case for sleep states in servers , 2011, HotPower '11.

[49]  Anand Sivasubramaniam,et al.  Energy storage in datacenters: what, where, and how much? , 2012, SIGMETRICS '12.

[50]  Walter Willinger,et al.  Analysis, modeling and generation of self-similar VBR video traffic , 1994, SIGCOMM.

[51]  Gargi Dasgupta,et al.  Server Workload Analysis for Power Minimization using Consolidation , 2009, USENIX Annual Technical Conference.