Vpm tokens: virtual machine-aware power budgeting in datacenters

Power consumption and cooling overheads are becoming increasingly significant for large scale machines, affecting overall costs and the ability to extend resource capacities and performance capabilities. To help mitigate these issues, active power management technologies are being deployed aggressively, including power budgeting, which enables improved power provisioning and can address critical periods when power delivery or cooling capabilities are temporarily reduced. Given the use of virtualization to encapsulate application components into virtual machines (VMs), however, such power management capabilities must address the interplay between budgeting physical resources and the performance of the virtual machines used to run these applications. This paper proposes a set of cluster- and datacenter-level management components and abstractions for use by power budgeting policies. The key idea is to manage power from a VM-centric point of view, where the goal is to be aware of global utility tradeoffs between different virtual machines (and their applications) when maintaining power constraints for the physical hardware on which they run. Our approach to VM-aware power budgeting uses multiple distributed managers integrated into the VirtualPower Management (VPM) framework whose actions are coordinated via a new abstraction, termed VPM tokens. An implementation with the Xen hypervisor illustrates technical benefits of VPM tokens that include up to 43% improvements in global utility, highlighting the ability to dynamically improve cluster performance while still meeting power budgets.

[1]  Ricardo Bianchini,et al.  Energy conservation in heterogeneous server clusters , 2005, PPoPP.

[2]  Karsten Schwan,et al.  VirtualPower: coordinated power management in virtualized enterprise systems , 2007, SOSP.

[3]  Soraya Ghiasi,et al.  Scheduling for heterogeneous processors in server systems , 2005, CF '05.

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

[5]  Ramakrishna Kotla,et al.  Scheduling processor voltage and frequency in server and cluster systems , 2005, 19th IEEE International Parallel and Distributed Processing Symposium.

[6]  Rong Ge,et al.  CPU MISER: A Performance-Directed, Run-Time System for Power-Aware Clusters , 2007, 2007 International Conference on Parallel Processing (ICPP 2007).

[7]  Ricardo Bianchini,et al.  Mercury and freon: temperature emulation and management for server systems , 2006, ASPLOS XII.

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

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

[10]  Jeffrey S. Chase,et al.  Making Scheduling "Cool": Temperature-Aware Workload Placement in Data Centers , 2005, USENIX Annual Technical Conference, General Track.

[11]  Peter A. Dinda,et al.  PICSEL: measuring user-perceived performance to control dynamic frequency scaling , 2008, ASPLOS.

[12]  Rajarshi Das,et al.  Utility functions in autonomic systems , 2004, International Conference on Autonomic Computing, 2004. Proceedings..

[13]  William E. Weihl,et al.  Lottery scheduling: flexible proportional-share resource management , 1994, OSDI '94.

[14]  D.K. Lowenthal,et al.  Adaptive, Transparent Frequency and Voltage Scaling of Communication Phases in MPI Programs , 2006, ACM/IEEE SC 2006 Conference (SC'06).

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

[16]  Andrew Warfield,et al.  Live migration of virtual machines , 2005, NSDI.

[17]  Norman P. Jouppi,et al.  Single-ISA heterogeneous multi-core architectures for multithreaded workload performance , 2004, Proceedings. 31st Annual International Symposium on Computer Architecture, 2004..

[18]  Vincent W. Freeh,et al.  Boosting Data Center Performance Through Non-Uniform Power Allocation , 2005, Second International Conference on Autonomic Computing (ICAC'05).

[19]  Ripal Nathuji,et al.  Exploiting Platform Heterogeneity for Power Efficient Data Centers , 2007, Fourth International Conference on Autonomic Computing (ICAC'07).

[20]  Martin Schulz,et al.  Bounding energy consumption in large-scale MPI programs , 2007, Proceedings of the 2007 ACM/IEEE Conference on Supercomputing (SC '07).

[21]  Calton Pu,et al.  An Analysis of Performance Interference Effects in Virtual Environments , 2007, 2007 IEEE International Symposium on Performance Analysis of Systems & Software.

[22]  Karthick Rajamani,et al.  On evaluating request-distribution schemes for saving energy in server clusters , 2003, 2003 IEEE International Symposium on Performance Analysis of Systems and Software. ISPASS 2003..

[23]  Gil Neiger,et al.  Intel virtualization technology , 2005, Computer.

[24]  Frank Bellosa,et al.  Energy Management for Hypervisor-Based Virtual Machines , 2007, USENIX Annual Technical Conference.

[25]  Karsten Schwan,et al.  LIVE data workspace: A flexible, dynamic and extensible platform for petascale applications , 2007, 2007 IEEE International Conference on Cluster Computing.

[26]  Frederic P. Miller,et al.  Advanced Configuration and Power Interface: Open standard, Operating system, Power management, Cross- platform, Intel Corporation, Microsoft, Toshiba, ... Sleep mode, Hibernate (OS feature), Synonym , 2009 .

[27]  E. N. Elnozahy,et al.  Energy-Efficient Server Clusters , 2002, PACS.

[28]  Beng-Hong Lim,et al.  Virtualizing I/O Devices on VMware Workstation's Hosted Virtual Machine Monitor , 2001, USENIX Annual Technical Conference, General Track.