Skip navigation

Standard Performance Evaluation Corporation

 
 

SPECvirt_sc2010

SPECvirt_sc2010 is SPEC's first benchmark addressing performance evaluation of datacenter servers used in virtualized server consolidation.  SPECvirt_sc2010 measures the end-to-end performance of all system components including the hardware, virtualization platform, and the virtualized guest operating system and application software.   The benchmark supports hardware virtualization, operating system virtualization, and hardware partitioning schemes.

SPECvirt_sc2010 Retirement

SPECvirt_sc2010 is being retired in favor of its successor, SPECvirt_sc2013. The last date for submitting benchmark results to SPEC for publication on its website is February 26, 2014. On February 26, 2014, the product will no longer be actively supported by SPEC.

Results for SPECvirt_sc2010 are not allowed to be published unless they are reviewed by SPEC. After the February 26, 2014 review cycle, SPEC will no longer be reviewing results; therefore, no publication may be done of alleged rule-compliant results after March 12th (close of final review cycle). See http://www.spec.org/fairuse.html#Retired for more information.

Benchmark Overview

The benchmark utilizes several SPEC workloads representing applications that are common targets of virtualization and server consolidation. We modified each of these standard workloads to match a typical server consolidation scenario of CPU resource requirements, memory, disk I/O, and network utilization for each workload. These workloads are modified versions of SPECweb2005, SPECjAppServer2004, and SPECmail2008. The client-side SPECvirt_sc2010 harness controls the workloads. Scaling is achieved by running additional sets of virtual machines, called "tiles", until overall throughput reaches a peak.   All VMs must continue to meet required quality of service (QoS) criteria.

The benchmark also includes options for measuring power consumption and power/performance relationships. Based on SPECpower methodology, power measurement requires the use one of the accepted power analyzers. The benchmarker has the option of running with power monitoring enabled and can submit results to any of three categories:

  • Performance only (SPECvirt_sc2010)
  • Performance/power for the System Under Test including storage (SPECvirt_sc2010_PPW)
  • Performance/power for the Server-only (SPECvirt_sc2010_ServerPPW)

The benchmark is targeted for use by hardware vendors, virtualization software vendors, application software vendors, datacenter managers, and academic researchers.

For more information please refer to the FAQ, design and user documentation, and Run and Reporting Rules listed below.

The current version of the benchmark is 1.01, released May 17, 2011. Changes in SPECvirt_sc2010 v1.01 are considered performance neutral and the results generated with v1.01 are comparable to results generated with the prior version of the benchmark. Changes consist of minor bug fixes, improvements and clarifications in documentation and run and reporting rules. Starting August 10, 2011, all result submissions must use v1.01. Existing licensees may request a free v1.01 CD by sending a request to info@spec.org.

Results

Submitted Results
Includes all of the results submitted to SPEC from the SPEC member companies and other licensees of the benchmark.

Information

Press Releases
Press release material, documents, and announcements:

SPECvirt_sc2010 Benchmark Documentation