Ever alert to the benchmarking results achieved by Sun solutions, BM Seer has posted links in his blog to the Sun SPARC Enterprise T5440 world record Siebel performance. He notes that Oracle typically didn't allow vendors to do public comparisons; then points out that anyone can do the math with the data from Oracle's website and draw the appropriate conclusions.

Seer provides a link to the Oracle white paper "Performance and Scalability Benchmark: Siebel CRM Release 8.0 Industry Applications and Oracle 10g R2 DB on Sun SPARC Enterprise T5440 Server Running the Solaris 10 OS."

The benchmark comprised 14,000 concurrent users running Siebel CRM Release 8.0 industry applications and Oracle 10g R2 DB on a single Sun SPARC Enterprise T5440 Server running free and OpenSolaris 10 OS using Solaris Containers to improve server utilization while greatly reducing energy, space and cooling requirements.

The white paper notes that Oracle’s Siebel Platform Sizing and Performance Program is a test suite certified by Siebel and executed independently by Sun Microsystems. Sun completed the benchmark on September 07, 2008; Oracle certified it on October 08, 2008.

Oracle's white paper concludes that the test system demonstrated the efficacy of the powerful combination of Oracle's Siebel CRM Release 8.0 architecture with Oracle 10g R2 database running entire solution on a single Sun SPARC Enterprise T5440 server based on UltraSPARC T2 Plus processor, Sun Java System Web Server, and OpenSolaris 10 OS, providing the highest performing and the most cost-effective available business solution.

Findings include:

• Siebel on UltraSPARC T2 Plus platform: All tiers of the Siebel CRM Release 8.0 architecture ran on a single quad socket Sun SPARC Enterprise T5440 server based on UltraSPARC T2 plus processor running Solaris 10 5/08. Multithreading capability of the US T2 Plus processor allowed each of the active Object Manager (OM) processes to run hundreds of Light Weight Processes (LWP), thus utilizing the available resources very effectively. A total number of 48 object managers serviced the work load of 14,000 concurrent users.

• Scalability: The Sun SPARC Enterprise T5440 server and Solaris 10 proves once again to be the best combination for scalability and resource utilization using Solaris Containers in the datacenter, giving users a consistent response time and future growth on critical applications as 14,000 users benchmark on Siebel CRM Release 8.0 application shows.

• Low network utilization: The Siebel CRM Release 8.0 Smart Web Architecture and Smart Network Architecture efficiently managed the network, consuming only 6.48 kilobits per second per user.

• Efficient use of the database server: Siebel CRM Release 8.0 Smart Database Connection Pooling and Multiplexing allowed the database to service 14,000 concurrent users and the supporting Siebel CRM Release 8.0 server application services with only 957 database connections using Siebel database pooling ratio 15:1.

• Energy efficiency: While supporting 14,000 concurrent Siebel users, the entire Sun Solution based on a single Sun SPARC Enterprise T5440 server running Siebel CRM Release 8.0 and Oracle 10g R2 on top of Solaris 10 consumed 1276 watts in a 4U rack space. As a result the T5440 supports 10.97 users per watt of energy consumed and supports 3500 users per rack unit.

Seer also provides a link to the Oracle white paper that reports on a similar test of the IBM System p570 Servers running AIX 5.3.

He also does some of the math for readers, pointing out that Sun Microsystems' 14,000 user benchmark on a single T5440 outperformed both IBM's 7,000 user benchmark result by 1.9x (IBM published the 7,000 user result with 3 x p570 systems running AIX), and HP's 5,200 user benchmark result by 2.5x (HP published the 5,200 user result with a combination of 2 x BL460c running Windows Server 2003 and 1 x rx6600 HP system running HP-UX.) He adds that Sun's own 10,000 user benchmark result on a combination of 2 x T5120 and 2 x T5220s by was beaten by a factor of 1.4x.

Finally, it is important to keep in mind the statement that Oracle appends to all of its benchmarking reports: "This benchmark data is intended for general information purposes and not as a substitute for implementation-specific sizing or benchmarks." [...read more...]

From the latest issue:

Recent Blog Entries as of March 19, 2010, 1:48 am
Oracle Enterprise Manager Ops Center Released Suits and Their Countersuits A More Direct Channel Model Planned for Oracle-Sun Oracle, OpenSolaris, and Solaris Flash Storage in Exadata V2 Cuts Query Processing Time Significantly	Sun Storage 7000 2010.Q1 Quality and Features PSA Deploys GlassFish in the Manufacture of Peugeot, Citroën Vehicles Running VirtualBox VMs as Services in Windows 'Solaris 10 ZFS Essentials' Mobile Desktop Grid
Blog RSS Feed