Kevin Lim
Parthasarathy Ranganathan
Jichuan Chang
Trevor Mudge
ABSTRACT
This paper seeks to understand and design next-generation servers for emerging "warehouse-computing" environments. We make two key contributions. First, we put together a detailed evaluation infrastructure including a new benchmark suite for warehouse-computing workloads, and detailed performance, cost, and power models, to quantitatively characterize bottlenecks. Second, we study a new solution that incorporates volume non-server-class components in novel packaging solutions, with memory sharing and flash-based disk caching. Our results show that this approach has promise, with a 2X improvement on average in performance-per-dollar for our benchmark suite.
- AMD. AMD Geode LX¿ Processor Family. http://www.amd.com/geodelx900.Google Scholar
- APC. InfraStruXure® Express On-demand Mobile Data Center. http://www.apc.com.Google Scholar
- L. Barroso. Warehouse-scale Computers. Invited talk at the USENIX Annual Technical Conference, Santa Clara, CA, June 2007.Google Scholar
- L. Barroso, J. Dean, and U. Holzle. Web Search for a Planet: The Google Cluster Architecture. IEEE Micro, 23(2), March/April 2003. Google ScholarDigital Library
- R. Bedichek. SimNow¿: Fast Platform Simulation Purely in Software. In HotChips 16, 2004.Google Scholar
- R. Bryant. Data Intensive Super Computing. In FCRC, 2007. Keynote.Google Scholar
- J. Dean and S. Ghemawat. MapReduce: Simplified Data Processing on Large Clusters. In OSDI-6, 2004. Google ScholarDigital Library
- DRAMeXchange. DRAM Price Quotes. http://www.dramexchange.com.Google Scholar
- M. Ekman and P. Stenstrom. A Cost-Effective Main Memory Organization for Future Servers. In PDPS, 2005. Google ScholarDigital Library
- A. Falcon, P. Faraboschi, and D. Ortega. Combining Simulation and Virtualization through Dynamic Sampling. In ISPASS, 2007.Google ScholarCross Ref
- X. Fan, W. Weber, and L. Barroso. Power Provisioning for a Warehouse-sized Computer. In ISCA-34, 2007. Google ScholarDigital Library
- W. Felter, T. Keller, M. Kistler, C. Lefurgy, K. Rajamani, R. Rajamony, F. Rawson, B. Smith, and E. Van Hensbergen. On the Performance and Use of Dense Servers. IBM Journal of Rearch and Development, 47(5/6), 2003. Google ScholarDigital Library
- Apache Software Foundation. Hadoop. http://lucene.apache.org/hadoop/index.html.Google Scholar
- P. Gill, M. Arlitt, Z. Li, and A. Mahanti. YouTube Traffic Characterization: A View From the Edge. In Internet Measurement Conference, 2007. Google ScholarDigital Library
- B. Holden. Latency Comparison Between HyperTransport and PCI-Express in Communication Systems. Technical report, HyperTransport Consortium White Paper, November 2006.Google Scholar
- Silicon Mechanics Inc. Xeon 3000 1U Server. http://www.siliconmechanics.com/i7573/xeon-3000-server.php.Google Scholar
- Intel. Intel Microprocessor Family Quick Reference Guide. http://www.intel.com/pressroom/kits/quickreffam.htm.Google Scholar
- Intel. Intel Server/Workstation Chipsets Comparison Chart. http://developer.intel.com/products/chipsets/index.htm.Google Scholar
- R. Katz. Research Directions in Internet-Scale Computing. Keynote presentation, 3rd International Week on Management of Networks and Services, 2007.Google Scholar
- T. Kgil and T. Mudge. FlashCache: a NAND Flash Memory File Cache for Low Power Web Servers. In CASES'06, 2006. Google ScholarDigital Library
- R. Khare, D. Cutting, K. Sitaker, and A. Rifkin. Nutch: A Flexible and Scalable Open-Source Web Search Engine. Technical Report CN-TR-04-04, CommerceNet Labs, November 2004.Google Scholar
- A.R. Lebeck, X. Fan, H. Zeng, and C. Ellis. Power Aware Page Allocation. In ASPLOX-IX, 2000. Google ScholarDigital Library
- K. Leigh, P. Ranganathan, and J. Subhlok. Fabric Convergence Implications on Systems Architecture. In HPCA 14, 2008.Google ScholarCross Ref
- Micron. DDR2 Memory Power Calculator. http://download.micron.com/downloads/misc/ddr2_power_calc_web .xls.Google Scholar
- C. Moore. A Framework for Innovation. Keynote, FCRC, 2007.Google Scholar
- G. Papadopoulos. Redshift: The Explosion of Massive Scale Systems. Analyst Summit, 2007.Google Scholar
- C. Patel and P. Ranganathan. Enterprise Power and Cooling: A Chip-to-DataCenter Perspective. In HotChips 19, August 2007. Tutorial.Google Scholar
- C. Patel and A. Shah. Cost Model for Planning, Development and Operation of a Data Center. Technical Report HPL-2005- 107R1, Hewlett Packard Technical Report, 2005.Google Scholar
- PCIMG. Advanced TCA Specification. http://www.picmg.org/pdf/PICMG_3_0_Shortform.pdf.Google Scholar
- PLX. PLX PCIe Switch Power Consumption. http:// www.plxtech.com/pdf/technical/expresslane/Power_Consumption_E xplained.pdf.Google Scholar
- P. Ranganathan, P. Leech, D. Irwin, and J. Chase. Ensemble-level Power Management for Dense Blade Servers. In ISCA-33, 2006. Google ScholarDigital Library
- Seagate. Barracuda 7200.10 Data Sheet. http://www.seagate.com/docs/pdf/datasheet/disc/ds_barracuda_7200 _10.pdf.Google Scholar
- H. Simon. Energy Efficiency and Computing. In Lawrence Berkeley National Laboratory, 2007. Keynote.Google Scholar
- A. Sucharitakul. Benchmarking in the Web 2.0 Era. In IISWC 2007, 2007. Panel Session.Google Scholar
- Microsoft Technet. Tools for Performance Stressing Exchange 2003 Servers. 2003, http://technet.microsoft.com/enus/library/aa996207.aspx.Google Scholar
- C. Thacker. Rethinking Data Centers. Invited talk at Stanford University Networking Seminar, October 2007.Google Scholar
- R. Tremaine, P. Franaszek, J. Robinson, C. Schulz, T, Smith, M. Wazlowski, and P. Bland. IBM Memory Expansion Technology (MXT). IBM Journal of Rearch and Development, 45(2), 2001. Google ScholarDigital Library
- C.A. Waldspurger. Memory Resource Management in VMware ESX Server. In OSDI-4, 2002. Google ScholarDigital Library
- M. Wu and W. Zwaenepoel. eNVy: A Non-Volatile, Main Memory Storage System. In ASPLOS, 1994. Google ScholarDigital Library
- Y. Xie and D. O'Hallaron. Locality in Search Engine Queries and Its Implications for Caching. In Infocomm, 2002.Google Scholar
Index Terms
- Understanding and Designing New Server Architectures for Emerging Warehouse-Computing Environments
Recommendations
Understanding and Designing New Server Architectures for Emerging Warehouse-Computing Environments
This paper seeks to understand and design next-generation servers for emerging "warehouse-computing" environments. We make two key contributions. First, we put together a detailed evaluation infrastructure including a new benchmark suite for warehouse-...
Server Designs for Warehouse-Computing Environments
The enormous scale of warehouse-computing environments leads to unique requirements in which cost and power figure prominently. Models and metrics quantifying these requirements, along with a benchmark suite to capture workload behavior, help identify ...
Cloud Server Benchmark Suite for Evaluating New Hardware Architectures
Adding new hardware features to a cloud computing server requires testing both the functionality and the performance of the new hardware mechanisms. However, commonly used cloud computing server workloads are not well-represented by the SPEC integer and ...
Comments