ACE: Abstracting, characterizing and exploiting datacenter power demands

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. Prior studies have either used a small set of applications and/or servers, or presented data that is at an aggregate scale from which it is difficult to design and evaluate new and existing optimizations. To address this gap, we collect power measurement data at multiple spatial and fine-grained temporal resolutions from several geo-distributed datacenters of Microsoft corporation over 6 months. We conduct aggregate analysis of this data to study its statistical properties. We find evidence of self-similarity in power demands, statistical multiplexing effects, and correlations with the cooling power that caters to the IT equipment. 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 attributes for peaks and valleys, and important correlations across these attributes that can influence the choice and effectiveness of different power capping techniques. We characterize these attributes and their correlations, showing the burstiness of small duration peaks, and the importance of not ignoring the rare but more stringent or long peaks. The correlations between peaks and valleys suggest the need for techniques to aggregate and collectively handle them. With the wide scope of exploitability of such characteristics for power provisioning and optimizations, we illustrate its benefits with two specific case studies. The first shows how peaks can be differentially handled based on our peak and valley characterization using existing approaches, rather than a one-size-fits-all solution. The second illustrates a simple capacity provisioning strategy for energy storage using the peak and valley characteristics.

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

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

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

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

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

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

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

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

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

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

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

[12]  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).

[13]  Carey L. Williamson,et al.  Internet Web servers: workload characterization and performance implications , 1997, TNET.

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

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

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

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

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

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

[21]  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.

[22]  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).

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

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

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

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

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

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

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

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

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

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

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

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