Don’t make the mistake of dismissing benchmarks because they don’t reflect real-world applications. Benchmarks are critical measurement tools.
Benchmarks are a serious business in the database industry. When server vendors release new server hardware or database providers like Microsoft and Oracle release new versions of database servers, they often will embark on a new set of benchmarks to provide evidence that the new hardware and/or software outperforms the older versions. The new release is expected to outperform the old release and if all goes well it will also outperform the benchmark numbers set by the competition as well.
Some people believe that benchmarks are not valid performance measurements because they don’t necessarily reflect real-world applications or they don’t necessarily show what the hardware and software combination would do in their own specific environment. However, I think that official standardized benchmarks like the TPC (Transaction Processing Council) tests do successfully demonstrate the high-end scalability of a database system. The TPC benchmarks provide information about both the performance of a system and the price/performance, giving you a good idea of the value proposition for a system.
These official benchmark tests are conducted by the companies themselves, ensuring that each company applies the full measure of its technical expertise into the tests. This eliminates any doubts about the system installation as well as questions about whether the application or database was properly tuned. This levels the playing field and enables the tests to fairly compare database and platform performance and value.
Designed to support extreme scalability, the HPE Integrity Superdome X Server holds several number one spots in various system benchmarks. Some of the HPE Superdome X top benchmark scores include:
- Two world records on TPC-H benchmark @ 10000 scale factor
- #1 overall performance @ 10000 GB scale factor on non-clustered TPC-H benchmark
- #1 overall 8-socket price/performance @ 10000 GB scale factor on non-clustered TPC-H benchmark
- #1 x86 and #1 16P max-jOPS results on the SPECjbb2015-MultiJVM benchmark
Showing its enterprise application scalability, the HPE Superdome X has the lead in 16-processor results on the two-tier SAP Sales and Distribution (SD) standard application benchmark with a score of 100,000 SAP benchmark users and 545,780 SAPS. To achieve this result, the HPE Superdome X used 16 Intel Xeon Processors E7-8890 v3- at 2.5 GHz and 4 TB of memory running Microsoft Windows Server 2012 R2 Datacenter Edition, Microsoft SQL Server 2014 Enterprise Edition, and SAP enhancement package 5 for the SAP ERP application 6.0.
Underwritten by HPE and Microsoft