Benchmark LINUX

For some, tweaking computers is like fine-tuning a car. Changing a configuration option here or a piece of hardware there can dramatically improve performance. In a car, you can measure performance by gauging a car's acceleration and top speed. Computer tweakers use benchmarks to measure the performance of their systems.

The open-source nature of Linux definitely appeals to computer tweakers. Even if you don't know how to hack source code, there are a variety of tweaks (such as installing a new kernel) that can boost efficiency. Unfortunately, there aren't many widely known Linux benchmarks. This month, we'll take a look at lmbench, a collection of benchmark tools for Linux. We'll show you how to install lmbench and how to use it to measure your Linux system's performance.

Prerequisites

Your Linux system may not come with lmbench, but it's relatively easy to install. Simply download the file from ftp://ftp.bitmover.com/lmbench. We downloaded the latest stable version as of press time (2.0.4) and saved the tarball to a directory on our system.

For best results, you should run lmbench from the command line and completely shut down any graphical environment you might be running. In most cases, you can simply log out and then select the command line from the login manager. If you can't exit to a command line, try switching run levels. In Mandrake 10.0, for instance, open a terminal and use the su command to become root (enter the root password when prompted). Type init 3 to change to run level 3. This will shutdown XFree86 and le....

PC Operating Instructions
October 2004 • Vol.15 Issue 10


http://www.smartcomputing.com/

Technical benchmarking or Product Benchmarking

The technique initially used to compare existing corporate strategies with a view to achieving the best possible performance in new situations (see above), has recently been extended to the comparison of technical products. This process is usually referred to as "Technical Benchmarking" or "Product Benchmarking'. Its use is particularly well developed within the automotive industry ("Automotive Benchmarking"), where it is vital to design products that match precise user expectations, at minimum possible cost, by applying the best technologies available worldwide. Many data are obtained by fully disassembling existing cars and their systems. Such analyses were initially carried out in-house by car makers and their suppliers. However, as they are expensive, they are increasingly outsourced to companies specialized in this area. Indeed, outsourcing has enabled a drastic decrease in costs for each company (by cost sharing) and the development of very efficient tools (standards, software).

http://en.wikipedia.org

Benchmarking XML Parsers

by Clark Cooper
May 05, 1999

A performance comparison of six stream-oriented XML parsers

This article compares the performance of six implementations of a single program that processes XML. Each implementation uses a different XML parser and four different languages are used: C, Java, Perl, and Python. Only a single parser is tested for Perl and Python, but two parsers each are tested for C and Java.
All of these parsers run under Linux, and all are stream-oriented. An application must provide callbacks (or their equivalent) in order to receive information back from the parser. While some of them have a validating mode, all the parsers were run as non-validating parsers. When I say that a single program was implemented six times, I mean that each implementation produces (or should produce) exactly the same output for a given input document. But as long as that constraint was met, I attempted to write each in the most efficient manner for the given language and parser.
http://www.xml.com/pub/a/Benchmark/article.html

Benchmark Your Distribution Center or Warehouse Online

Every warehouse and distribution center is different but, for all, the key to success is effectively using resources to deliver required services. Benchmark your facility's performance with a new online self-assessment tool developed at Georgia Tech with the cooperation of MHIA's Logistics Execution Systems Association (LESA) and Order Fulfillment Council
(OFC).

What Is It?
This is a system based assessment tool. System based assessment goes beyond conventional single-factor productivity metrics (picks/hr, cube/line) to provide a "system view" of warehouse performance. It computes a single "efficiency score" based on a set of resources used, and a set of operational results achieved. In addition, the self-assessment tool indicates where you may have an opportunity to reduce resource usage or increase operational results.

More...

Benchmark Linux

For some, tweaking computers is like fine-tuning a car. Changing a configuration option here or a piece of hardware there can dramatically improve performance. In a car, you can measure performance by gauging a car's acceleration and top speed. Computer tweakers use benchmarks to measure the performance of their systems.
The open-source nature of Linux definitely appeals to computer tweakers. Even if you don't know how to hack source code, there are a variety of tweaks (such as installing a new kernel) that can boost efficiency. Unfortunately, there aren't many widely known Linux benchmarks. This month, we'll take a look at lmbench, a collection of benchmark tools for Linux. We'll show you how to install lmbench and how to use it to measure your Linux system's performance.

Prerequisites

Your Linux system may not come with lmbench, but it's relatively easy to install. Simply download the file from ftp://ftp.bitmover.com/lmbench. We downloaded the latest stable version as of press time (2.0.4) and saved the tarball to a directory on our system.

For best results, you should run lmbench from the command line and completely shut down any graphical environment you might be running. In most cases, you can simply log out and then select the command line from the login manager. If you can't exit to a command line, try switching run levels. In Mandrake 10.0, for instance, open a terminal and use the su command to become root (enter the root password when prompted). Type init 3 to change to run level 3. This will shutdown XFree86 and le....

PC Operating Instructions
October 2004 • Vol.15 Issue 10

Benchmark UK Search Engine Marketing survey released

A survey has been released this week for the 'UK Search Engine Marketing Report' by E-Consultancy - the UK's leading Internet marketing and ecommerce specialists. The survey has experienced a phenomenal response rate with over 400 people taking it the first few hours and looks to be the most successful UK Search Engine Marketing report this year. Sponsoring the survey are leading UK Search Engine Marketing agency Neutralize (**); "This survey is designed to answer common questions about the current state of the UK Search Marketing industry. We worked hard with E-Consultancy to ensure that the report is as comprehensive as possible and is specifically dedicated to the UK marketplace" comments Janine Laity, General Manager at Neutralize (**). "By working hand-in-hand with E-Consultancy we hope to achieve a broader, in-depth understanding of our industry as well as unearth some ideas on its future direction". The finished report will highlight key information such as UK spend on SEO and PPC advertising, the effectiveness of these campaigns, attitudes toward search engines, ROI from search as well as specific information regarding vertical sectors. The survey is critical for anyone who is currently running, is interested in or has outsourced a search marketing campaign. Participants will be given access to the latest figures and trends helping to inform their own marketing decisions as well as provided a unique forecast into the future of the UK industry. To take part in the survey and receive a complimentary copy (normally worth £149) prior to its release on the E-Consultancy website in April, follow this link to the E-Consultancy Neutralize (**) UK Search Engine Marketing Report. http://www.neutralize.com/search-engine-marketing-report/ About E-Consultancy http://www.e-consultancy.com E-Consultancy were awarded AOP Publisher of the Year 2006 for their best practice internet marketing reports, research and how-to guides. They help businesses to gain a practical understanding of e-commerce and Internet marketing. About Neutralize PR Contact: Tom Bennison http://www.neutralize.com Tel: 0870 0630707 Neutralize (**) is one of the UK's leading full service search engine marketing agencies, specialising in enterprise Search Engine Optimisation and advanced Pay Per Click Management. Neutralize (**) have unrivalled experience in driving business success - in 2005 they were Finalists for "Marketing Firm of the Year" in the UK Innovation and Growth Awards and placed 6th in the Deloitte Fast 50 business growth awards. Neutralize (**) are dedicated members of the Nominet Steering Committee and Committee Members of the Search Marketing Association (UK).

Your Name Tom Bennison Public Relations Agency Neutralize Telephone 0870 063 0707

Benchmarking

From F. John Reh

Who's best? How good are they? How do we get that good?

What is Benchmarking

Benchmarking is the process of determining who is the very best, who sets the standard, and what that standard is. In baseball, you could argue that seven consecutive World Series Championships made the New York Yankees the benchmark.

If we were to benchmark "world conquest", what objective measure would we use to compare Julius Caesar to Adolph Hitler; Gengis Khan to Napoleon? Which of them was the epitome, and why?

We do the same thing in business. Who is the best sales organization? The most responsive customer service department? The leanest manufacturing operation? And how do we quantify that standard?

Related Issues

Once we decide what to benchmark, and how to measure it, the object is to figure out how the winner got to be the best and determine what we have to do to get there.

Benchmarking is usually part of a larger effort, usually a Process Re-engineering or Quality Improvement initiative. The US Department of Energy's Quality Management Implementation Guidelines shows one way of fitting it all together.

Why Should I Benchmark

If you don't know what the standard is you cannot compare yourself against it. If a customer asks "What is the MTBF on your widget?" it is not enough to know that your Mean Time Between Failures is 120 hours on your standard widget and 150 for your deluxe widget.

You also have to know where your competitors stand. If the company against whom you are competing for this order has a MTBF of 100 hours you are probably okay. However, if their MTBF is 10,000 hours who do you think will get the order?

What can I Benchmark

Most of the early work in the area of benchmarking was done in manufacturing, like the example above. Now benchmarking is a management tool that is being applied almost anywhere. The Fortune Magazine article "Beat the Budget and Astound your CFO" outlines how Rank Xerox even applied benchmarking to their sales effort. (Note: This article is now in their archives and there is a small fee if you are not a subscriber.)

Where can I learn more

The Benchmarking in Australia site includes the feature "Ten Benchmarking Mistakes to Avoid" which is a good place to start.

The Defense Technical Information Center maintains an Business Process Improvement site site. Their Business Transformation Toolkit explains how to implement many of the steps.

The VA Office of Acquisition and Materiél Management's Guide to Logistics Best Practices has extensive citations in both categories.

And the American Productivity & Quality Center has a page of benchmarking terms.

Final Thoughts

You know you need to benchmark, but you are just too busy. Well if you don't benchmark, and then implement improvements based on it, you will find yourself out of business. Then you'll have plenty of time to benchmark, but it won't matter.