Using an online component of "Day in the Life" test that represents the most popular of Oracle's JD Edwards EnterpriseOne applications, Oracle's SPARC T3-1 server running Oracle Application Server 10g Release 3 and JD Edwards EnterpriseOne 9.0.1 in Oracle Solaris Containers, in tandem with Oracle's Sun SPARC Enterprise M3000 server running Oracle Database 11g, delivered a record result of 4200 users.
A SPARC T3-1 server paired with a Sun SPARC Enterprise M3000 server beat the IBM POWER7 result by 5% on the JD Edwards EnterpriseOne 9.0.1 Day in the Life test.
The JD Edwards EnterpriseOne 9.0.1 application takes advantage of the large number of threads in SPARC T3-1 server on the application tier achieving 4200 users with < 2 sec response time.
This benchmark uses Oracle Solaris Containers for Web and Application tier consolidation. Containers provide flexibility, easier maintenance and better CPU utilization of the server leaving processing capacity for additional growth.
The Sun SPARC Enterprise M3000 server provides enterprise class RAS features for customers deploying DB. Customers can take advantage of the SmartFlash feature in Oracle Database 11g Release 1 on Oracle Solaris.
To obtain this leading result, a number of Oracle technologies were used: Oracle Solaris 10, Oracle Solaris Containers, Oracle Java Hotspot Server VM, Oracle OC4J Application Server, Oracle Database 11g Release 1, SPARC T3-1 server, and Sun SPARC Enterprise M3000 server.
JDE EnterpriseOne DIL Kit Performance Chart
|SPARC T3-1, 1x1.65 GHz SPARC T3||128||Solaris 10||4200||9.0.1||2U|
|IBM Power 750, 1x3.55 GHz POWER7||120||IBM i7.1||4000||9.0||4U|
|IBM Power 570, 4x4.2 GHz POWER6||128||IBM i6.1||2400||8.12||4U|
|IBM x3650M2, 2x2.93 GHz X5570||64||OVM||1000||9.0||2U|
Results as of 9/17/2010.
Oracle's JD Edwards EnterpriseOne is an integrated applications suite of Enterprise Resource Planning software.
The workload consists of online transactions. It does not include the batch processing job components.
LoadRunner is used to run the workload and collect the users transactions response times against increasing numbers of users. Key metric used to evaluate performance is the transaction response time which is reported by LoadRunner.
Two JD Edwards EnterpriseOne and two Oracle Application server instances on the SPARC T3-1 server were hosted in four separate Oracle Solaris Containers to demonstrate consolidation of multiple application and web servers.
Each Oracle Solaris container was bound to a separate processor set, each containing 3 cores (with 4 cores left for the default processor set). This was done to improve performance by using the physical memory closest to the processors, thereby, reducing memory access latency and reduce processors cross calls. The default processor set was used for network and disk interrupt handling.
The applications were executed in the FX scheduling class to improve performance by reducing the frequency of context switches.
The database server was run in an Oracle Solaris Container hosted on the Sun SPARC Enterprise M3000 server.
Copyright 2010, Oracle and/or its affiliates. All rights reserved. Oracle and Java are registered trademarks of Oracle and/or its affiliates. Other names may be trademarks of their respective owners. Results as of 9/20/2010.