WebLogic – Java record – SPARC T4-4 Servers Set World Record on SPECjEnterprise2010

SPARC T4-4 Servers Set World Record on SPECjEnterprise2010, Beats IBM POWER7, Cisco x86
Oracle produced a world record SPECjEnterprise2010 benchmark result of 40,104.86 SPECjEnterprise2010 EjOPS using four of Oracle’s SPARC T4-4 servers in the application tier and two more SPARC T4-4 servers for the database server.
  • This result demonstrated a sustained Java EE 5 transaction load generated by approximately 320,000 users.

  • This result using 16 Oracle WebLogic 10.3.5 server instances demonstrated 4.8x better performance per application server instance when compared to the IBM result which used 32 WebSphere instances. 

  • The four SPARC T4-4 servers used for the application tier used Oracle Solaris Containers to consolidate four Oracle WebLogic application server instances on each server to achieve this result.

  • The two SPARC T4-4 servers used for the database tier hosted Oracle Database 11g Release 2 and Oracle RAC cluster software using Oracle Automatic Storage Management (ASM).

  • 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 Server’s on-going, record-setting Java application server performance demonstrates why so many customers rely on Oracle Fusion Middleware as their foundation for innovation.

Performance Landscapeimage

Complete benchmark results are at the SPEC website, SPECjEnterprise2010 Results.

SPECjEnterprise2010 Performance Chart as of 10/11/2011

Submitter EjOPS* Java EE Server DB Server

4 x SPARC T4-4
4 chips, 32 cores, 3.0 GHz SPARC T4
Oracle WebLogic 11g (10.3.5)
2 x SPARC T4-4
4 chips, 32 cores, 3.0 GHz SPARC T4
Oracle 11g DB

Configuration Summary

Application Servers:

4 x SPARC T4-4 servers, each with

4 x 3.0 GHz SPARC T4 processors
512 GB memory
2 x 10GbE NIC
Oracle Solaris 10 8/11
Oracle WebLogic Server 11g Release 1 (10.3.5)
Java HotSpot(TM) 64-Bit Server VM on Solaris, version 1.6.0_26 (Java SE 6 Update 26)

Database Servers:

2 x SPARC T4-4 servers, each with

4 x 3.0 GHz SPARC T4 processors
1024 GB memory
2 x 10GbE NIC
4 x 8Gb FC HBA
Oracle Solaris 10 8/11
Oracle Database 11g Enterprise Edition Release
Oracle Real Application Clusters 11g Release 2

Storage Servers:

8 x Sun Fire X4270 M2 (12-Drive)

1 x 3.0 GHz Intel Xeon
8 GB memory
1 x 8Gb FC HBA
Oracle Solaris 11 Express 2010.11

8 x Sun Storage F5100 Flash Arrays

Switch Hardware:

2 x Sun Network 10GbE 72-port Top of Rack (ToR) Switch
1 x Brocade 5300 80-port Fiber Channel Switch

Benchmark Description

SPECjEnterprise2010 is the third generation of the SPEC organization’s J2EE end-to-end industry standard benchmark application. The new SPECjEnterprise2010 benchmark has been re-designed and developed to cover the Java EE 5 specification’s significantly expanded and simplified programming model, highlighting the major features used by developers in the industry today. This provides a real world workload driving the Application Server’s implementation of the Java EE specification to its maximum potential and allowing maximum stressing of the underlying hardware and software systems,

  • The web container, servlets, and web services
  • The EJB container
  • JPA 1.0 Persistence Model
  • JMS and Message Driven Beans
  • Transaction management
  • Database connectivity
Key Points and Best Practices
  • Four Oracle WebLogic server instances on each SPARC T4-4 server were hosted in 4 separate Oracle Solaris Containers to demonstrate consolidation of multiple application servers.
  • Each Oracle Solaris Container was bound to a separate processor set, each contained 7 cores (total 56 threads). This was done to improve performance by reducing memory access latency by using the physical memory closest to the processors. The default set was used for network and disk interrupt handling.
  • The Oracle WebLogic application servers were executed in the FX scheduling class to improve performance by reducing the frequency of context switches.
  • The Oracle database processes were run in 2 processor sets using psrset(1M) and executed in the FX scheduling class. This improved performance by reducing memory access latency and reducing context switches.
  • The Oracle log writer process was run in a separate processor set containing 2 threads and run in the RT scheduling class. This insured that the log writer had the most efficient use of CPU resources.
See Also

For regular information become a member of the WebLogic Partner Community please register at http://www.oracle.com/partners/goto/wls-emea


Blog Twitter LinkedIn Mix Forum Wiki


Post a Comment:
  • HTML Syntax: NOT allowed

« July 2016