White Papers of Interest to the Blade Server Community

Blade.org White Papers
	The Many Facets of Virtualization This paper shares many different perspectives from Blade.org vendor and customer members about virtualization, its potential, pitfalls and solutions.
	Blade Server Technology Overview This white paper provides a blade server technology overview using IBM BladeCenter products from Blade.org members as examples of how a blade server is constructed, how it operates and the types of blade servers, I/O and networking expansion cards interoperate.
	Virtualization Technology Overview This white paper provides a brief introduction to virtualization technology and how it applies to blade servers. It introduces the benefits of virtualization, explains how virtualization works, and highlights how virtualization technology affects server processor design.
Blade.org Member Submitted White Papers 2006-08
	Scale-Out Storage and the Dynamic Data Center This paper describes the requirements for scale-out storage in the enterprise in terms of resiliency, scalability, manageability, and other factors. It also discusses the current state of NetApp® scale-out deployments as well as specific operational and business advantages that the NetApp approach delivers to the enterprise data center. The pros and cons of alternative storage approaches are explored and some criteria are offered for evaluating scale-out solutions.
	Best Practices Guide: Emulex Virtual HBA Solutions and VMware ESX Server 3.5 This paper focuses on best practices for configuring and troubleshooting NPIV (N_Port ID Virtualization) using Emulex LightPulse HBAs in VMware ESX Server 3.5 environments. N_Port ID Virtualization is an industry standard Fibre Channel protocol that extends virtualization to the Host Bus Adapter (HBA) by providing a way of assigning multiple Fibre Channel addresses on the same physical link.
	The Green Data Center: Cutting energy costs for a powerful competitive advantage. This white paper discusses the crisis facing IT when capacity growth meets increasing energy costs and strategies for reducing energy costs while gaining competitive advantage.
	Implementing the IBM BladeCenter S Chassis The purpose of this paper is to provide a stand-alone reference compendium, which can be used to quickly and easily set up a BladeCenter S. The paper includes an overview of IBM BladeCenter servers and technology, a technical review of the BladeCenter S and its options, an in-depth explanation of storage zoning and configuration, as well as step-by-step setup guides for both the Advanced Management Module and Storage Configuration Manager. This paper was written for a technical audience with limited or no experience with IBM BladeCenter solutions. After reading it, you should be able to successfully implement the BladeCenter S, customized to your specific needs.
	Edison Group Blade Server Power Study This report presents the results of tests conducted by Edison Group to compare the power consumption of the IBM BladeCenter blade server system with a comparable BladeSystem blade server configuration from HP. It provides background, configuration details, and methodology by which Edison reached its conclusion: that IBM BladeCenter H requires nearly 10 percent less power than the equivalently configured HP BladeSystem c7000.
	Design Considerations for Blade Server Storage Companies are seeing a tremendous growth in the information they handle and are looking for better options to deploy and manage data. Scaling data centers using traditional servers is creating several challenges that stress the capabilities of these data centers.
	10GbE iSCSI Performance With Blade Servers Our test of network throughput capabilities compared performance of 10GbE iSCSI with 4Gb/s Fibre Channel using an actual database workload running on a reference architecture consisting of an IBM BladeCenter H with embedded 10GbE blade switches from Blade Network Technologies (BLADE) and mezzanine network cards for the blade servers and storage controllers from Chelsio Communications (Chelsio), and a NetApp FAS6030C clustered storage system. Results demonstrate that Oracle 10g RAC runs at near wire speeds—8.9 Gb/s using NFS and 7.2 Gb/s using iSCSI—in consolidated blade server architectures using networked storage. When compared with Fibre Channel results of 3.4Gb/s, these results prove that 10GbE environments are viable and can support large-scale business applications.
	IBM BladeCenter Reliability/Availability Evaluation This Research Brief details an in-person evaluation by Clabby Analytics of a suite of tests comparing the IBM BladeCenter H architecture with the Hewlett-Packard BladeSystem c-Class architecture, performed at the IBM BladeCenter benchmarking and testing laboratory in Raleigh, North Carolina. Clabby Analytics discovered the IBM BladeCenter architecture enjoyed a number of reliability and availability advantages in power design, in availability, in disks and in storage integration over the HP BladeSystem c-Class architecture. Essentially, HP blades run hotter than IBM BladeCenter under the same workload. This Research Brief outlines the audit, goes into test results details and examines possible reasons why the results occured. It also goes into detail on a BladeCenter teardown with analysis of the BladeCenter components and architecture.
	Making Large UPS Systems More Efficient There are three subtle but significant factors that can materially affect a company's cost of operating a UPS system and particularly the electrical bill. This paper discusses the common errors and misunderstandings in evaluating UPS efficiency. UPS efficiency curves are explained, compared and their cost implications quantified.
	The Blade-Mainframe Polarization Trend The computing marketplace is becoming polarized. IT buyers are gravitating toward mainframe/scale-up systems at the high end and blade systems as mid-range and low-end server replacements. As evidence, last year IBM reported mainframes grew 8 percent in a market that was supposed to be flat; blades are growing at a 50- to 75-percent compound annual growth rate according to IDC. Sales of mid-range systems in the middle are flattening out.
	Optimized IO Solutions to Maximize IBM BladeCenter ROI The popularity of blade servers, such as the IBM BladeCenter, is growing rapidly due to their advantages over traditional rack servers. This paper explains the design aspects that make blade server IO solutions successful and that enable maximum ROI for IBM BladeCenter customers.
	Virtualization Technologies and Their Impact on Disaster Recovery Planning Virtual server technologies provide companies with the ability to do more with less, enabling the consolidation of data and applications onto a single server. The result is reduced costs, simplified IT management, and minimized space requirements. The need to protect these virtualized systems is paramount and in situations where companies are looking to reduce the costs associated with disaster recovery planning, virtualization can enable easier recovery without a great deal of additional cost.
	ClearSpeed CSX Processor Architecture This paper describes the architecture of the CSX family of processors based on ClearSpeed's multi-threaded array processor; a high performance, power-efficient, scalable, data-parallel processor.
	Blade.org - The Snowball Effect An analysis of the Blade.org ecosystem and how it is delivering more products sooner. This report examines the impact that Blade.org is having on IBM's success in the blade market and concludes taht it is the single, largest contributing factor to IBM's outstanding success in the blade market today.
	Data Protection Strategies Businesses are becoming increasingly dependent on continuous access to stored data and as a result, storage usage is growing at an unprecedented rate. As the number of mission-critical servers and storage resources grow, so does the importance of protecting against service interruptions that can threaten an organization's ability to provide access to key data. There are a number of strategies that can be employed to protect important data, and each has strengths and weaknesses. This paper examines four separate data protection strategies and compares their merits in the most common business continuance scenarios.
	Making the Business Case for Blade Switches Blade servers have been widely adopted in datacenters because they cost less to deploy and less to operate (due to savings in power and cooling) than rack-optimized servers. Embedding switches into blade servers expands and enhances these benefits, providing further infrastructure integration, simplified management, greater scalability, improved power and cooling efficiency, and increased application availability.
	Solutions for the Datacenter's Thermal Challenges This white paper covers the key issues that datacenter managers should consider regarding power and cooling costs associated with hardware in the datacenter. Today's datacenter managers are required to place an increased emphasis on the power and thermal characteristics of their IT systems. The electricity cost of operating the infrastructure can no longer be viewed simply as a cost of doing business, as the expense to power servers is rapidly growing and the thermal capacity of the infrastructure is a limiting factor in the expansion ability of the datacenter. The emerging concern of power and cooling has added to the complexity of the datacenter in terms of both operational and management costs. As such, datacenter managers have a real requirement for energy-efficient systems and power management solutions.
	Electrical Efficiency Modeling of Data Centers Conventional models for estimating electrical efficiency of data centers are grossly inaccurate for real-world installations. Estimates of electrical losses are typically made by summing the inefficiencies of various electrical devices, such as power and cooling equipment. This paper shows that the values commonly used for estimating equipment inefficiency are quite inaccurate. A simple, more accurate efficiency model is described that provides a rational basis to identify and quantify waste in power and cooling equipment.
	Virtual Server-SAN Connectivity Why blade server virtualization and Fibre Channel SAN connectivity are rapidly being adopted.
	QLogic Enables End-to-End Virtualization QLogic's Continous Innovation and Leadership Enables End-to-End Virtualization
	Crystal Cube Consulting - Competitive Analysis of IBM BladeCenter® with Intel Xeon® Processors vs. Sun Bladed Offerings The purpose of this white paper, prepared by Crystal Cube Consulting, is to provide a comprehensive comparison between the IBM BladeCenter™ platform based on Intel® Xeon® Processors and Sun’s various bladed offerings (specifically Netra® CT900 and Sun Fire 8000) with UltraSPARC® IIIi and AMD Opteron® processors.
	Competitive Performance Analysis - BNT vs. Cisco Blade Network Technologies Nortel Layer 2/3 10Gb Uplink Ethernet Switch Module and Nortel Layer 2/3 10Gb Ethernet Switch Module for IBM BladeCenter - Competitive Performance Evaluation versus Cisco Catalyst 6509 Switch
	Storage Area Network - Evolution The introduction of the Internet SCSI (iSCSI) protocol for Storage Area Networking in 2003 has raised interest in whether it can compete against existing SAN technologies such as Fibre Channel and InfiniBand. This paper examines the history of Ethernet against other competing network technologies of the day, and proposes that factors including Ethernet's ease of maintenance, price performance, and speeds of 10Gbps and beyond will drive widespread deployment of iSCSI SANs. This paper includes a feature comparison beween iSCSI and Fibre Channel and a summary of TCO comparisons between the two technologies, and is intended for those who may be considering iSCSI SANs as an initial installation or replacement for their current storage solutions.
	Next-Generation IP Video Surveillance on IBM BladeCenter Providing security for people and property -- whether for businesses, government offices, jails, retail points of sale, banks, casinos, transportation hubs, warehouses -- is more important than ever. You can secure your people and property while maximizing your IBM BladeCenter ROI -- with Blade server switches from Blade Network Technologies and Video Surveillance technology from DataCom.
	Double-Take® Server Recovery Option: Whole Server Protection from a Single Solution The Double-Take® Server Recovery Option is a whole-server data protection solution that, when combined with Double-Take real-time replication, simplifies the restoration process and reduces the time and effort involved with server recovery.
	Reducing the Costs and Risks of Branch Office Data Protection For untrained non-technical staff in branch offices, being responsible for consistent, reliable backup can be tough. Backups may fail without the branch staff even noticing. Improperly labeling, shortcuts, and rotating and removing tapes can result in lost data and slow recovery. Also, if the branch employees have never tested the recovery process, they won't be familiar with how to execute the recovery when a disruption occurs. As a result, in the event of a disaster the branch could be down for a prolonged period of time and often requires the assistance of the central IT staff.
	Zeus Extensible Traffic Manager Performance on Blade Servers ZXTM software was benchmarked on two sets of dual processor IBM blade servers (AMD Opteron based LS20 blades and Intel Xeon based HS20 blades) and compared with performance on the ZXTM 7000 appliance.
	ClearSpeed Accelerator Technology Primer This white paper provides an introduction to ClearSpeed's acceleration technology, first describing the need for acceleration and then providing an overview of the technology ClearSpeed uses to deliver market-leading performance-per-watt.
	Convergence – Driving profound change in the Telecommunications Industry IBM white paper on convergence, driving profound changes in the Telecommunications Industry
	The Storage Area Network Goes Global Combing the reliability of iSCSI with Full Error Recovery and the performance of 10 Gigabit Ethernet.
	IDC White Paper - The Impact of Virtualization Software on Operating Environments, October 2006 This white paper discusses the impact of virtualization on system resources in x86 servers.
	Cost-Effective Data Replication with Double-Take and VMware Double-Take® Software and VMware® provide proven protection for multiple production application servers by leveraging real-time data replication and virtualization technologies to create cost-effective, simplified disaster recovery architectures.
	The Future of Ethernet I/O VIrtualization is Here Today Server virtualization based on virtual machine (VM) software is becoming a popular solution for consolidation of datacenter servers. With VM software, a single physical machine can support a number of guest operating systems, each of which running in its own complete virtual instance of the underlying physical machine. The benefits of software virtualization have led to efforts to further optimized the performance and effectiveness of server virtualization by adding hardware support for virtualization in both the CPU and in the I/O subsystem. This paper discusses techniques and benefits of hardware-based I/O virtualization from NetXen.
	Ten Ways to Protect Your Infrastructure Reduce costs while protecting your critical business systems. This white paper informs you about power, cooling and security issues that put your IT systems at risk. You will find out how to provide clean, conditioned, and continous power for critical systems. It describes how to select the right power protection strategies for your needs.
	Disaster Recovery and High Availability for IBM eServer™ BladeCenter® For enterprises desiring to improve the efficiency and effectiveness of their disaster recovery strategy while reducing overall costs, IBM eServer™ BladeCenter® technology used in combination with Double-Take and virtualization technologies like VMware ESX Server provide a cost-effective, flexible solution for protecting business-critical applications and their data.
	Implementing Energy Efficient Data Centers Electricity usage costs have become an increasing fraction of the total cost of ownership (TCO) for data centers. It is possible to dramatically reduce the electrical consumption of typical data centers through appropriate design of the network-critical physical infrastructure and through the design of the IT architecture. This paper explains how to quantify the electricity savings and provides examples of methods that can greatly reduce electrical power consumption.
	Virtualization's Impact on the Desktop A Hands-on Assessment of Desktop Virtualization using Citrix, IBM, and VMware Technologies
	Multi-Service Switches Using InfiniBand Pave the Way to Grid Computing High-performance, multi-service switching platforms are helping to construct next-generation data centers and form the backbone of compute grids and large computing clusters. Leveraging InfiniBand, they provide high-speed connectivity between servers, and intelligent, multi-layer connectivity to external networks and storage resources.
	Server Consolidation using IBM BladeCenter™ and VMware Infrastructure® This Solution Blueprint addresses the high-level architecture and opportunities created by combining IBM BladeCenter and VMware Infrastructure as complementary technologies to deliver maximum server consolidation.
	Managing Server Energy Consumption Using IBM PowerExecutive IBM PowerExecutive is a standard feature built into selected IBM System x™ and BladeCenter® servers that enables you to measure, track and control server power consumption. It helps you understand how energy is used within the data center and obtain the insight required to optimize your servers and their workloads to obtain optimum performance while adhering to the power supply and cooling constraints of the data center.
	Increasing Data Center Efficiency by Using Improved High Density Power Distribution A new approach to power distribution for high density server installations saves floor space, simplifies power cabling, saves capital cost, reduces weight, and increases electrical efficiency. This paper describes this distribution architecture and quantifies the benefits. Note: The methods in this paper only apply in North America and are for problems that are unique to North America
	A Practical Guide to Disaster Recovery Planning This paper is intended to help simplify the process of starting a disaster recovery plan so as not to be so overwhelming. Through some basic steps, businesses can better protect themselves against data loss while working toward a more complete business continuity plan.