System News
back1 2 3 4 5 6 7 next
Articles for the keywords: SPARC T4-4
09 Nov 2012 SPARC T4 Servers Deliver Improved Performance on PeopleSoft Combined Benchmark [28399]
CPU Utilization in Application, Web, and Database Tiers Leaves Significant Headroom for Growth

Oracle's SPARC T4-4 server running Oracle's PeopleSoft HCM 9.1 combined online and batch benchmark achieved a world record 18,000 concurrent users experiencing subsecond response time while executing a PeopleSoft Payroll batch job of 500,000 employees in 32.4 minutes. This result was obtained with a SPARC T4-4 server running Oracle Database 11g Release 2, a SPARC T4-4 server running PeopleSoft HCM 9.1 application server, and a SPARC T4-2 server running Oracle WebLogic Server in the web tier. Average CPU utilization in the web tier T4-2 server was 17%, in the application tier 59%, and in the database tier 47% (online and batch).
(Get More Information . .) open to premium members only

18 Oct 2012 World Record Oracle E-Business Consolidated Workload on SPARC T4-2, T4-4 [28098]
Served 4,100 Users at 2.08 Response Time with Abundant Headroom to Spare

Oracle reported the world record performance of Oracle E-Business Suite Standard Medium multiple-online module benchmark using Oracle's SPARC T4-2 and SPARC T4-4 servers, which ran the application and database. The results demonstrate that a multi-tier configuration of SPARC T4 servers running the Oracle E-Business Suite R12.1.2 application and Oracle Database 11g Release 2 is capable of supporting 4,100 online users with 2.08 second response-times, executing a mix of complex transactions consolidating four Oracle E-Business modules. Oracle reports that the SPARC T4-2 in the application tier utilized about 65% capacity and the SPARC T4-4 in the database tier about 30%, providing significant scalability headroom.
(Get More Information . .) open to premium members only

18 Oct 2012 Combined Oracle Business Intelligence EE 11g, SPARC T4-4 Performance Proves Scalability Potential [28099]
Benchmark Used 25,000 Concurrent Users, Average Response Time of 0.36 Seconds

Oracle reports that a SPARC T4-4 server with internal Solid State Drive (SSD) using the ZFS file system running Oracle Business Intelligence Enterprise Edition 11g achieved 25,000 concurrent users with an average response time of 0.36 seconds with Oracle Business Intelligence Enterprise Edition 11g 11.1.1.6.0 server cache set to ON. This performance clearly shows that the underlying hardware, SPARC T4 server, and the Oracle BI EE 11g (11.1.1.6.0 64-bit) platform deployed in a vertical scale-out fashion scale within a single system while executing 415 transactions/sec. Oracle Internet Directory provided authentication for the 25,000 Oracle BI EE users with sub-second response time.
(Get More Information . .) open to premium members only

05 Oct 2012 SPARC T4-4 Delivers World Record First Result on PeopleSoft Combined Benchmark [27918]
Mark Is First to Involve Concurrent Online and Batch Workloads

Oracle announces that its SPARC T4-4 servers running Oracle's PeopleSoft HCM 9.1 combined online and batch benchmark achieved World Record 18,000 concurrent users while executing a PeopleSoft Payroll batch job of 500,000 employees in 43.32 minutes and maintaining online users response time at < 2 seconds. This benchmark result is the first to involve the concurrent running of online and batch workloads. This record was set with a SPARC T4-4 server running Oracle Database 11g Release 2 and Oracle Solaris Zones, another running PeopleSoft HCM 9.1 application server and a SPARC T4-2 server running Oracle WebLogic Server in the web tier.
(Get More Information . .) open to premium members only

14 Sep 2012 Current SPARC Architectures [27615]
by Darryl Gove

Darryl Gove explains the solution Solaris software engineers have devised to enable all generations of SPARC processor architectures to handle applications that target recent architectures. More recent applications would not work on older processors that lack the instructions provided in the new architecture. The solution? Allow the compiler to assume a "generic" architecture that is the default behavior of the compiler. Then the only flag that doesn't make the assumption is -fast, which tells the compiler to assume the build machine is also the deployment machine - so the compiler can use all the instructions the build machine provides, Gove explains.
(Get More Information . .) open to premium members only

 
back1 2 3 4 5 6 7 next






News and Solutions for Users of Solaris, Java and Oracle's Sun hardware products
30,000+ Members – 30,000+ Articles Published since 1998

!-- end archive_section.tpl -->