Addressing the stranded power problem in datacenters using storage workload characterization

Datacenter operators face unique challenges to optimally provision power among deployed servers. Allocated server power is frequently over-provisioned and this results in stranding of available datacenter power capacity. Standardized power efficiency benchmarks like SPECpower_ssj2008 can be used for determining power allocation, in conjunction with methodologies to estimate the contribution from the disk subsystem. In this paper, we explore a trace-driven methodology for determining power contribution of the storage components. We show the benefits of this methodology as opposed to typical power provisioning used in the industry.

[1]  Sriram Sankar,et al.  Storage characterization for unstructured data in online services applications , 2009, 2009 IEEE International Symposium on Workload Characterization (IISWC).

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

[3]  Arvind Krishnamurthy,et al.  Modeling Hard-Disk Power Consumption , 2003, FAST.

[4]  Sriram Sankar,et al.  Intra-disk Parallelism: An Idea Whose Time Has Come , 2008, 2008 International Symposium on Computer Architecture.

[5]  Miriam Allalouf,et al.  Storage modeling for power estimation , 2009, SYSTOR '09.

[6]  吴敌.  面向企业级应用——Seagate Barracuda ES , 2006 .

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

[8]  Brian Jones,et al.  An Analysis of Hard Drive Energy Consumption , 2008, 2008 IEEE International Symposium on Modeling, Analysis and Simulation of Computers and Telecommunication Systems.

[9]  Mahmut T. Kandemir,et al.  Interplay of energy and performance for disk arrays running transaction processing workloads , 2003, 2003 IEEE International Symposium on Performance Analysis of Systems and Software. ISPASS 2003..