Oracle’s SPARC T8-1 servers have set a world record for the SPECjEnterprise2010 benchmark for solutions using a single application server with one to four chips. The result of 34,259.69 SPECjEnterprise2010 EjOPS used two SPARC T8-1 servers, one server for the application tier and the other server for the database tier.
-
The SPARC T8-1 servers obtained a result of 32,622.97 SPECjEnterprise2010 EjOPS using encrypted data. This secured result used Oracle Advanced Security Transparent Data Encryption (TDE) for the application database tablespaces with the AES-256-CFB cipher. The network connection between the application server and the database server was also encrypted using the secure JDBC.
-
The SPARC T8-1 server solution delivered 77% more performance compared to the two-chip IBM x3650 M5 server result of 19,282.14 SPECjEnterprise2010 EjOPS.
-
The SPARC T8-1 server solution delivered 51% more performance compared to the four-chip IBM Power System S824 server result of 22,543.34 SPECjEnterprise2010 EjOPS.
-
The SPARC T8-1 server based results demonstrated 23% more performance compared to the Oracle Server X6-2 system result of 27,803.39 SPECjEnterprise2010 EjOPS. Oracle holds the top x86 two-chip application server SPECjEnterprise2010 result.
-
The application server used Oracle Fusion Middleware components including the Oracle WebLogic 12.1 application server and Java HotSpot(TM) 64-Bit Server VM on Solaris, version 1.8.0_144. The database server was configured with Oracle Database 12c Release 2.
-
For the secure result, the application data was encrypted in the Oracle database using the Oracle Advanced Security Transparent Data Encryption (TDE) feature. Hardware accelerated cryptography support in the SPARC M8 processor for the AES-256-CFB cipher was used to provide data security.
-
The benchmark performance using the secure SPARC T8-1 server configuration with encryption was only 5% less when compared to the peak result.
-
This result demonstrated less than 1 second average response times for all SPECjEnterprise2010 transactions and represents Java EE 5.0 transactions generated by over 279,500 users.
Performance Landscape
Select single application server results. Complete benchmark results are at the SPEC website, SPECjEnterprise2010 Results.
| SPECjEnterprise2010 Performance Chart 12/18/2017 | ||||
|---|---|---|---|---|
| Owner | EjOPS* | Java EE Server | DB Server | Notes |
| Oracle | 34,259.69 | 1 x SPARC T8-1 1 x 5.0 GHz SPARC M8 Oracle WebLogic 12c (12.2.1) |
1 x SPARC T8-1 1 x 5.0 GHz SPARC M8 Oracle Database 12c (12.2.0.1) |
– |
| Oracle | 32,622.97 | 1 x SPARC T8-1 1 x 5.0 GHz SPARC M8 Oracle WebLogic 12c (12.2.1.2) Network Data Encryption for JDBC |
1 x SPARC T8-1 1 x 5.0 GHz SPARC M8 Oracle Database 12c (12.2.0.1) Transparent Data Encryption |
Secure |
| Oracle | 27,803.39 | 1 x Oracle Server X6-2 2 x 2.2 GHz Intel Xeon E5-2699 v4 Oracle WebLogic 12c (12.2.1.2) |
1 x Oracle Server X6-2 2 x 2.2 GHz Intel Xeon E5-2699 v4 Oracle Database 12c (12.1.0.2) |
– |
| Oracle | 25,818.85 | 1 x SPARC T7-1 1 x 4.13 GHz SPARC M7 Oracle WebLogic 12c (12.1.3) |
1 x SPARC T7-1 1 x 4.13 GHz SPARC M7 Oracle Database 12c (12.1.0.2) |
– |
| Oracle | 25,093.06 | 1 x SPARC T7-1 1 x 4.13 GHz SPARC M7 Oracle WebLogic 12c (12.1.3) Network Data Encryption for JDBC |
1 x SPARC T7-1 1 x 4.13 GHz SPARC M7 Oracle Database 12c (12.1.0.2) Transparent Data Encryption |
Secure |
| IBM | 22,543.34 | 1 x IBM Power S824 4 x 3.5 GHz POWER 8 WebSphere Application Server V8.5 |
1 x IBM Power S824 4 x 3.5 GHz POWER 8 IBM DB2 10.5 FP3 |
– |
| IBM | 19,282.14 | 1 x System x3650 M5 2 x 2.6 GHz Intel Xeon E5-2697 v3 WebSphere Application Server V8.5 |
1 x System x3850 X6 4 x 2.8 GHz Intel Xeon E7-4890 v2 IBM DB2 10.5 FP5 |
– |
* SPECjEnterprise2010 EjOPS (bigger is better)
The Cluster on Die (COD) mode is a BIOS setting that effectively splits the chip in half, making the operating system think it has twice as many chips as it does (in this case, four, 11 core chips). Intel has stated that COD is appropriate only for highly NUMA optimized workloads. Dell has shown that there is a 3.7x slower bandwidth to the other half of the chip split by COD.
–>Configuration Summary
Application Server:
1024 GB memory (16 x 64 GB)
2 x 600 GB SAS HDD
2 x 800 GB SAS SSD
4 x Sun Dual Port 10 GbE PCIe 2.0 Networking card with Intel 82599 10 GbE Controller
Oracle WebLogic Server 12c (12.2.1.2)
Java HotSpot(TM) 64-Bit Server VM on Solaris, version 1.8.0_144
Database Server:
512 GB memory (16 x 32 GB)
2 x 600 GB SAS HDD
1 x Sun Dual Port 10 GbE PCIe 2.0 Networking card with Intel 82599 10 GbE Controller
4 x 3.2TB Flash Accelerator F320 PCIe Card
2 x 3.2TB Flash Accelerator F320 SFF SSD
Oracle Database 12c (12.2.0.1)
Benchmark Description
SPECjEnterprise2010 is the third generation of the SPEC organization’s J2EE end-to-end industry standard benchmark application. The SPECjEnterprise2010 benchmark has been 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 zone, servlets, and web services
- The EJB zone
- JPA 1.0 Persistence Model
- JMS and Message Driven Beans
- Transaction management
- Database connectivity
The primary metric of the SPECjEnterprise2010 benchmark is jEnterprise Operations Per Second (SPECjEnterprise2010 EjOPS). The primary metric for the SPECjEnterprise2010 benchmark is calculated by adding the metrics of the Dealership Management Application in the Dealer Domain and the Manufacturing Application in the Manufacturing Domain. There is NO price/performance metric in this benchmark.
Key Points and Best Practices
- Four Oracle WebLogic server instances on the SPARC T8-1 server were hosted in 4 separate processor sets.
- The Oracle WebLogic application servers were executed in the FX scheduling class to improve performance by reducing the frequency of context switches.
- The JVM was run using libumem.so.
- The Oracle log writer process was run in a separate processor set containing one whole core on the database system.
- All database foreground processes were run in the FX scheduling class.
See Also
- SPECjEnterprise2010 Results Page
- SPARC T8-1 Result Page at SPEC
- Encrypted SPARC T8-1 Result Page at SPEC
Disclosure Statement
SPEC and the benchmark name SPECjEnterprise are registered trademarks of the Standard Performance Evaluation Corporation. Results from www.spec.org as of 9/30/2017. SPARC T8-1, 34,259.69 SPECjEnterprise2010 EjOPS (unsecure); SPARC T8-1, 32,622.97 SPECjEnterprise2010 EjOPS (secure); SPARC T7-1, 25,818.84 SPECjEnterprise2010 EjOPS (unsecure); SPARC T7-1, 25,093.06 SPECjEnterprise2010 EjOPS (secure); Oracle Server X6-2, 27,803.39 SPECjEnterprise2010 EjOPS (unsecure); IBM Power S824, 22,543.34 SPECjEnterprise2010 EjOPS (unsecure); IBM x3650 M5, 19,282.14 SPECjEnterprise2010 EjOPS (unsecure);