By Kevin Kelly on Jun 03, 2010
Using five of Oracle's Sun SPARC Enterprise T5440 systems for application serving along with one of Oracle's Sun SPARC Enterprise M9000 servers for the database server allowed Oracle to deliver a world record result of 28,648.74 SPECjAppServer2004 JOPS@Standard on the SPECjAppServer2004 benchmark.
This result was run using the Oracle WebLogic 10.3.3 Application Server, a component of Oracle Fusion Middleware, and Oracle Database 11g Enterprise Edition with the Oracle Solaris 10 operating system to obtain this world record result.Oracle Performance Advantages
This Oracle result is 26% faster than the IBM result of 22,634.13 SPECjAppServer2004 JOPS@Standard. For the application tier of the benchmark, Oracle used five Sun SPARC Enterprise T5440 servers compared to the sixteen IBM BladeCenter HS blades used by IBM. For the database tier, Oracle used a Sun SPARC Enterprise M9000 server compared to a IBM system p5 595 used by IBM.
The Oracle result is faster than the HP result of 28,463.03 SPECjAppServer2004 JOPS@Standard. For the application tier of the benchmark, Oracle used five Sun SPARC Enterprise T5440 servers compared to the seventeen HP BL870c blade servers used by HP. For the database tier, Oracle used a Sun SPARC Enterprise M9000 server compared to a HP Superdome used by HP.
The five Sun SPARC Enterprise T5440 servers used a total of 20 RU of space to obtain this result which is 26% less than the 27 RU space used by the three blade chassis containing sixteen IBM BladeCenter HS blades.
IBM uses more than 3.4 times the number of application servers than Oracle.
The five Sun SPARC Enterprise T5440 servers occupied 40% of the 50 RU space used by the five blade chassis containing 17 HP BL870c blade servers to obtain this leading result.
HP uses more than 3.2 times the number of application servers than Oracle.
The six Sun Storage F5100 Flash Array storage used in this result occupied 6U of rack space which is 13% of the 44U space used by the database storage in the IBM result.
The database storage in the HP result used 4x EVA81000 Storage arrays consuming112U of space is more than 18 times the 6U space used for database storage in the Oracle result.
The application server storage in the HP result used an EVA6100 storage space which consumed 16U of space for JMS logs. The 5x T5440 each used internal SSDs for the same function - no additional external storage was used.
Six of Oracle's Sun Storage F5100 Flash Array storage were used with Oracle 11g Enterprise Edition on the Sun SPARC Enterprise M9000 server to show outstanding database performance in this benchmark.
These results were obtained using Java Platform, Standard Edition JDK 6 Update 20 on the Sun SPARC Enterprise T5440 servers and running the Oracle Solaris 10 10/09 operating system.
The five Sun SPARC Enterprise T5440 servers used Oracle Solaris Containers to consolidate eight Oracle Weblogic application server instances on each server to achieve this result.
Oracle Fusion Middleware provides a family of complete, integrated, hot pluggable and best-of-breed products known for enabling enterprise customers to create and run agile and intelligent business applications. Oracle WebLogic Servers on-going, record-setting Java application server performance demonstrates why so many customers rely on Oracle Fusion Middleware as their foundation for innovation.
Oracle has other benchmarks that show that Oracle's "Optimized System Performance" is more important than IBM's "Per-core Performance Focus".
SPECjAppServer2004 Performance Chart as of 6/2/2010. Complete benchmark results may be found at the SPEC benchmark website http://www.spec.org. SPECjAppServer2004 JOPS@Standard (bigger is better)
|J2EE Server||DB Server|
|Oracle||28,648.74||5x Sun SPARC Enterprise T5440
1.6 GHz US-T2 Plus
Oracle WebLogic 10.3.3
|1x Sun SPARC Enterprise M9000
2.88 GHz SPARC64-VII
Oracle 11g DB 18.104.22.168
|HP||28,463.03||17x HP BL870c Server Blade
1.6 Ghz Itanium
Oracle WebLogic 10.3
|1x HP Superdome
1.6 GHz Itanium
Oracle 11g DB 22.214.171.124
|IBM||22,634.13||16x IBM BladeCenter HS21
3.32 GHz Intel X5470
WebSphere Application Server V126.96.36.199
|1x IBM System p5 595
2.1 GHz POWER5+
IBM DB2 Universal Database 9.5 FP3
Results and Configuration SummaryApplication Server:
5x Sun SPARC Enterprise T5440
4 x 1.6 GHz UltraSPARC T2 Plus
256 GB memory
2 x 10GbE NIC
2 x 32GB SATA SSD
Oracle Solaris 10 10/09
Oracle Solaris Containers
Oracle WebLogic 10.3.3 Application Server - Standard Edition
Oracle Fusion Middleware
Java Platform, Standard Edition JDK 6 Update 20
Sun SPARC Enterprise M9000
64x 2.88 GHz SPARC64-VII
2048 GB memory
6 x Sun Storage F5100 Flash Array
Oracle Solaris 10 10/09
Oracle Database Enterprise Edition Release 188.8.131.52
Benchmark DescriptionSPECjAppServer2004 (Java Application Server) is a multi-tier benchmark for measuring the performance of Java 2 Enterprise Edition (J2EE) technology-based application servers. SPECjAppServer2004 is an end-to-end application which exercises all major J2EE technologies implemented by compliant application servers as follows:
- The web container, including servlets and JSPs
- The EJB container
- EJB2.0 Container Managed Persistence
- JMS and Message Driven Beans
- Transaction management
- Database connectivity
Key Points and Best Practices
- 8x Oracle WebLogic server instances on each Sun SPARC Enterprise T5440 server were hosted in 4x separate Solaris Containers to demonstrate consolidation of multiple application servers.
- The Oracle WebLogic application servers were executed in the FX scheduling class to improve performance by reducing the frequency of context switches.
- Enhancements in Java to the JVM had a major impact on performance.
- Each Sun SPARC Enterprise T5440 used 2x 10GbE NICs for network traffic from the driver systems.
Disclosure StatementSPECjAppServer2004, 5x Sun SPARC Enterprise T5440 (4 chips, 32 cores) 28648.74 SPECjAppServer2004 JOPS@Standard; 17x HP BL870c (4 chips, 8 cores) 28463.03 SPECjAppServer2004 JOPS@Standard; 16x IBM HS21 (2 chips, 8 cores) 22634.13 SPECjAppServer2004 JOPS@Standard; SPEC, SPECjAppServer reg tm of Standard Performance Evaluation Corporation. Results from www.spec.org as of 6/2/2010.
HP C7000 Blade Chassis (10 RU each). 5x Blade Chassis total 50 RU.
HP EVA8100 2C6D Storage Array(112 disks): 2x HSV210-B controllers (2U each) and 8x M5314C Disk Enclosures (3U each) total 28 RU. 4x EVA8100 2C6D total 112 RU.
HP EVA6100 2C4D Storage Array: 2x HSV200-B controllers (2U each) and 4x M5314C Disk Enclosures (3U each) total 16 RU.
IBM BladeCenter H Chassis (9 RU each). 3x Chassis Total 27 RU.
IBM DS4800 Disk System Model 82 (4U each). 6x IBM DS4000 EXP810 (3U each) total 22 RU. 2x Total STorage DS4800 total 44 RU.