TPC takes the measure of big data systems

The fresh TPCx-HS benchmark could provide an apples-to-apples comparison of commercial Hadoop systems

Comparing commercial Hadoop big data-styled analysis systems might get a little easier, thanks to a new benchmark from the Transaction Processing Performance Council (TPC).

The TPCx-HS benchmark, posted Monday, offers a performance assessment of Hadoop-based systems.

"There has been a lot of push from our customers for a standard to objectively measure performance and price performance of big data systems," said Raghunath Nambiar, who is the chairman of the TPCx-HS committee, as well as a distinguished engineer at Cisco.

The worldwide IT market for big data-styled analysis should swell to over US$240 billion by 2016, according to IDC, and companies such as IBM and Hewlett-Packard are offering prepackaged systems running Hadoop, currently the most popular of the big data systems now being tested and used within the enterprise.

Today vendors may offer performance metrics of their Hadoop systems, though each company uses its own benchmark, making it difficult for customers to compare systems.

TPC hopes that Hadoop system vendors will run its benchmark against their own systems, allowing potential customers to directly compare the price performance across different offerings.

TPCx-HS "defines a level playing field. The number you get from vendor X can be fairly compared to the number from vendor Y," Nambiar said.

A benchmark kit, which can be downloaded from the TPC site, tests overall performance of a Hadoop system. It includes the specification and user documentation, as well as scripts to run the benchmark code and a Java program to execute the benchmark load.

The benchmark itself measures how quickly an Apache Hadoop system organizes data using the widely used terasort sorting algorithm. Vendors can tune their systems either by optimizing the software through various means, or by running the fastest hardware available.

Using the benchmark, a tester can choose one of a number of different-sized machine-generated data sets, ranging now from a single terabyte to 10,000 terabytes.

The benchmark provides a score for overall performance, as well as a price-performance score to specify how much performance the system offers per the cost of the system. A third optional test measures the energy efficiency of the system.

The test must be conducted twice, according to the TPC rules, and the slowest run of the two is the official benchmark speed. Published TPC results can be challenged by other parties within 60 days.

Like with all of its benchmarks, TPC requires that all the official testing be done by a third party. With the big data benchmark, this can be done through an independent auditor or, more informally, a peer audit, which probably would not be as costly.

Founded in 1988, the TPC is a nonprofit corporation that provides vendor-neutral benchmarks for testing the performance of transaction processing and database systems.

Although the organization started with the intent of producing benchmarks for transactional database systems, it has, in recent years, been expanding out to covering other computational systems as well. In 2012, it published a benchmark for virtualization software.

Companies such as Dell, Cisco, IBM, Hewlett-Packard, Oracle, Unisys, Intel and Microsoft are members of the TPC, as well as Hadoop software vendors Cloudera, Pivotal and Red Hat.

Joab Jackson covers enterprise software and general technology breaking news for The IDG News Service. Follow Joab on Twitter at @Joab_Jackson. Joab's e-mail address is Joab_Jackson@idg.com

Join the newsletter!

Error: Please check your email address.
Rocket to Success - Your 10 Tips for Smarter ERP System Selection

Tags applicationsdata miningsoftwareTransaction Performance Councildata warehousing

Keep up with the latest tech news, reviews and previews by subscribing to the Good Gear Guide newsletter.

Joab Jackson

IDG News Service
Show Comments

Cool Tech

Breitling Superocean Heritage Chronographe 44

Learn more >

SanDisk MicroSDXC™ for Nintendo® Switch™

Learn more >

Toys for Boys

Family Friendly

Panasonic 4K UHD Blu-Ray Player and Full HD Recorder with Netflix - UBT1GL-K

Learn more >

Stocking Stuffer

Razer DeathAdder Expert Ergonomic Gaming Mouse

Learn more >

Christmas Gift Guide

Click for more ›

Most Popular Reviews

Latest Articles

Resources

PCW Evaluation Team

Walid Mikhael

Brother QL-820NWB Professional Label Printer

It’s easy to set up, it’s compact and quiet when printing and to top if off, the print quality is excellent. This is hands down the best printer I’ve used for printing labels.

Ben Ramsden

Sharp PN-40TC1 Huddle Board

Brainstorming, innovation, problem solving, and negotiation have all become much more productive and valuable if people can easily collaborate in real time with minimal friction.

Sarah Ieroianni

Brother QL-820NWB Professional Label Printer

The print quality also does not disappoint, it’s clear, bold, doesn’t smudge and the text is perfectly sized.

Ratchada Dunn

Sharp PN-40TC1 Huddle Board

The Huddle Board’s built in program; Sharp Touch Viewing software allows us to easily manipulate and edit our documents (jpegs and PDFs) all at the same time on the dashboard.

George Khoury

Sharp PN-40TC1 Huddle Board

The biggest perks for me would be that it comes with easy to use and comprehensive programs that make the collaboration process a whole lot more intuitive and organic

David Coyle

Brother PocketJet PJ-773 A4 Portable Thermal Printer

I rate the printer as a 5 out of 5 stars as it has been able to fit seamlessly into my busy and mobile lifestyle.

Featured Content

Latest Jobs

Don’t have an account? Sign up here

Don't have an account? Sign up now

Forgot password?