SPECjbb® 2005
SPECjbb® 2005 (Java Server Benchmark) is SPEC's benchmark for evaluating the performance of server side Java. Like its predecessor, SPECjbb 2000, SPECjbb 2005 evaluates the performance of server side Java by emulating a three-tier client/server system (with emphasis on the middle tier). The benchmark exercises the implementations of the JVM (Java Virtual Machine), JIT (Just-In-Time) compiler, garbage collection, threads and some aspects of the operating system. It also measures the performance of CPUs, caches, memory hierarchy and the scalability of shared memory processors (SMPs). SPECjbb 2005 provides a new enhanced workload, implemented in a more object-oriented manner to reflect how real-world applications are designed and introduces new features such as XML processing and BigDecimal computations to make the benchmark a more realistic reflection of today's applications.
Retired
SPECjbb 2005 Retirement
SPECjbb 2005 was retired on October 1, 2013. As of that date, no further submissions are being accepted and technical support is no longer provided. New submissions can be made with its replacement, SPECjbb 2015.
SPECjbb 2005 allows rule-compliant results to be published independently. Although SPEC will not publish new results, it is possible that others might choose to do so. Any such publication must plainly disclose that SPECjbb 2005 has been retired. See http://www.spec.org/fairuse#Retired for more information.
Note: The restriction of compliance in section 4.1 of the SPECjbb 2005 run rules specifically related to setting the input.expected_peak_warehouse property is removed for independent results in retirement.
SPECjbb 2005 Benchmark Highlights

- Emulates a 3-tier system, the most common type of server-side Java application today.
- Business logic and object manipulation, the work of the middle tier, predominate.
- Clients are replaced by driver threads, database storage by binary trees of objects.
- Increasing amounts of workload are applied, providing a graphical view of scalability.
The current version of the benchmark is version 1.07. Updates since the initial release include changing the metric name from "bops" to "SPECjbb2005 bops", changes to correct a dependency on the Sun implementation of HashMap in the benchmark code, and updates to the benchmark tools and documentation. The most recent versions of the benchmark documentation are posted below.
Results
- Submitted Results
- Text and HTML outputs for the SPECjbb 2005 metrics; includes all of the results submitted to SPEC from licensees of the benchmark. Search across all SPECjbb 2005 results.
- Flag Descriptions
- Further documentation about tunings used for a result which are not included in the notes section may be found here.
Information
- SPECjbb 2005 Benchmark Press Release
- Benchmark announcement day press release materials:
- SPECjbb 2005 Benchmark Documentation
SPECjbb 2005 support and technical documents:
- SPECjbb 2005 FAQ (Last updated: March 15, 2006 V1.04)
- SPECjbb 2005 User's Guide (Last updated: April 27, 2006 V1.07)
- SPECjbb 2005 Run and Reporting Rules (Last updated: March 15, 2006 V1.05)
- SPECjbb 2005 Design Document (Last updated: March 15, 2006 V1.05)
- Issues Building/Running SPECjbb 2005
- Installation, build, and runtime issues raised by users of SPECjbb 2005.
Future Benchmark Workload Development, Call For Participation
If you're a developer of an EJB server, this is your opportunity to help shape the standardized testing of your competitors! Contact SPEC at info@spec.org