IBM eServer X3 Architecture: Application Server Performance Gains

IBM eServer X3 Architecture: Application Server Performance Gains

The ability of application servers to deliver high performance varies greatly, depending on the specifics of any given customer’s workload. IBM raises the bar for scalable, high-performance application servers with the introduction of IBM eServer X3 Architecturethe ground-breaking third-generation of the IBM Enterprise X-Architecture XA-64e™ chipset. Incorporating this new chipset, the IBM eServer xSeries 366 and 460 have demonstrated unprecedented levels of performance and availability. X3 Architecture’s performance advantage over the competition, given various typical application server functions, has been demonstrated by recently published record-setting benchmark results (http://www-03.ibm.com/servers/eserver/xseries/benchmarks).

Given a variety of typical application server functions, IBM eServer X3 Architecture offers great improvements, in every instance, in overall system performance through the use of features not available on any competitor’s system. This paper will illustrate the benefits of IBM eServer X3 Architecture for typical application server functions, such as SSL encryption, messaging, Web service interactions (e.g., SOAP/XML serialization), HTTP services, and ODBC database interactions under various types of application server workloads. The paper presents the results of various test scenarios used to highlight the performance improvements that the reader can expect from systems based on X3 Architecture.

The term “application server” is applied broadly in the server world, but it typically pertains to a “middle-tier” server that receives requests from client systems, retrieves data from a separate database, and performs some data processing before returning a response. In this paper, the term “application server” refers to the commonly deployed, managed application server environments, such as Java™ application servers (e.g., IBM WebSphere®) and Microsoft® .NET application servers. The performance characteristics described in this paper were obtained from statistics collected from a selection of Microsoft .NET 1.1 applications running on an IBM eServer xSeries 366.

Get pdf IBM eServer X3 Architecture: Application Server Performance Gains

Hardware Vendor CDM Requirements

Hardware Vendor CDM Requirements

The Common Diagnostic Model (CDM) is an architecture and methodology for exposing system diagnostic instrumentation through the Common Information Model (CIM) standard interfaces. CIM is an extensible object oriented schema for system management being developed by the Distributed Management Task Force (DMTF), and is evolving, industry-wide, as the basis for system management architectures. IBM, Intel and PC-Doctor, Inc., introduced the CDM at the DMTF annual conference in June of 1999. Since then, the proposed extensions required to support diagnostics have been accepted by the DMTF and included in Version 2.3 of the CIM schema (see the White paper at http://www.dmtf.org/educ/whit.html).

The ability to transparently run diagnostic tests and exercisers while the user operating system is functional (no reboot) can significantly contribute to the reduction of Total Cost of Ownership (TCO) and will also lower warranty costs by reducing the incidence of defect-free parts being returned for service. This functionality is referred to as OS-Present Diagnostics (a.k.a. On-line Diagnostics and Concurrent Diagnostics).

A primary objective of the CDM is to standardize the way Independent Hardware Vendors (IHVs) interface their OS-Present Diagnostics to the operating environment, making them accessible to all diagnostic applications that query CIM for diagnostic data and/or register with CIM to execute diagnostic methods and receive events.

Get pdf Hardware Vendor CDM Requirements

IBM POWER6 Processor-based Systems: Designed for Reliability

IBM POWER6 Processor-based Systems: Designed for Reliability

The base reliability of a computing system is, at its most fundamental level, dependent upon the intrinsic failure rates of the components that comprise it. Very simply, highly reliable servers are built with highly reliable components. On POWER6™ processor-based systems, this basic premise is augmented with a clear “design for reliability” architecture and methodology. The POWER6 Reliability strategy evolves from, and improves upon, the Reliability design points developed throughout the IBM POWER™ program.

At IBM, trained RAS engineers use a concentrated, systematic, architecture-based approach with the objective to improve overall server reliability with each successive generation of system offerings. At the core of this effort is an intensive focus on sensible, well-managed server design strategies that both stress high system instruction execution performance and require logic circuit implementations that operate consistently and reliably despite potentially wide disparities in manufacturing process variances and operating environments. Intensive critical circuit path modeling and simulation procedures are used to identify critical system timing dependencies, so that time-dependent system operations complete successfully under a wide variety of process tolerances.

This white paper provides an overview of the design points that contribute to a reliable POWER6 processor-based system.

Get pdf IBM POWER6 Processor-based Systems: Designed for Reliability

Managing your HP Virtual Server Environment for HP Integrity servers and HP 9000 servers

Managing your HP Virtual Server Environment for HP Integrity servers and HP 9000 servers

Your business needs to grow, increase profitability, and gain competitive advantage. To achieve this, you need an IT infrastructure that helps you reduce operational costs, accelerate the speed of IT change, and deliver higher quality of service to increase business efficiency. And that’s where the HP Adaptive Infrastructure comes into play. Through the use of technology, you can achieve better business outcomes.

Virtualization is a catalyst in the transformation to an Adaptive Infrastructure. Virtualization is an approach to pooling and sharing IT resources so that supply always meets demand. With virtualization solutions from HP, you can reduce costs, increase agility, and improve the quality of your IT service delivery.

The HP Virtual Server Environment (VSE) for HP Integrity and HP 9000 servers allows you to optimize server utilization in real time. The VSE delivers additional resources to critical applications during peak times by creating virtual servers that automatically grow and shrink based on business priorities. Through tight integration of intelligent control with partitioning, high availability, and utility pricing, the HP VSE allows you to maintain service levels and pay for spare capacity on an as-needed basis. The heart of the HP Virtual Server Environment is a fully integrated software family for planning, management, and automation that includes:
•HP Capacity Advisor
•HP Virtualization Manager
•HP Global Workload Manager

Get pdf Managing your HP Virtual Server Environment for HP Integrity servers and HP 9000 servers