Sun Storage F5100 Flash Array

Sun and Oracle demonstrate the world's fastest database performance. Sun Microsystems using 12 Sun SPARC Enterprise T5440 servers, 60 Sun Storage F5100 Flash arrays and Oracle 11g Enterprise Edition with Real Application Clusters and Partitioning delivered a world-record TPC-C benchmark result. Not only does this result beat the next best result by over 25% in performance with up to 7x better new order transaction times, but it does so by using 1/8 the rack space and with nearly 6x lower power consumption per unit of performance!

Benchmark Description

TPC-C is an OLTP system benchmark. It simulates a complete environment where a population of terminal operators executes transactions against a database. The benchmark is centered around the principal activities (transactions) of an order entry environment. These transactions include entering and delivering orders, recording payments, checking the status of orders, and monitoring the level of stock at the warehouses.

Benchmark Outcome [1]

Sun Microsystems using 12 Sun SPARC Enterprise T5440 servers, 60 Sun Storage F5100 Flash arrays and Oracle 11g Enterprise Edition with Real Application Clusters and Partitioning delivered a world-record TPC-C benchmark result.

• The 12-node Sun SPARC Enterprise T5440 server cluster result delivered a world-record TPC-C benchmark result of 7,646,486.7 tpmC and $2.36 $/tpmC (USD) using Oracle 11g R1 on a configuration available 12/14/09.
• The 12-node Sun SPARC Enterprise T5440 server cluster beats the performance of the IBM Power 595 (5GHz) with IBM DB2 9.5 database by 26% and has 16% better price/performance on the TPC-C benchmark.
• The Oracle/Sun solution utilized Sun FlashFire technology to deliver this result. The Sun Storage F5100 flash array was used for database storage. The Sun Storage F5100 flash array provides sub millisecond I/O response times and much higher I/O rates than traditional disk. Typically 10-50x better I/O performance in much smaller rack space and with lower power consumption.
• The complete Oracle/Sun solution had 10.7x better performance per physical footprint than an IBM configuration resulting in more efficient utilization of datacenter space and power.
• The complete Oracle/Sun solution used 8 times fewer racks than the IBM configuration.
• The complete Oracle/Sun solution delivered over 7 times better new order response times than the IBM configuration.
• The complete Oracle/Sun solution had 5.9x better power/performance than the IBM configuration.
• The 12-node Sun SPARC Enterprise T5440 server cluster beat the performance of the HP Superdome (1.6GHz Itanium2) by 87% and had 19% better price/performance on the TPC-C benchmark.
• With this world record performance result the Oracle 11g Enterprise Edition with Real Application Clusters and Partitioning demonstrated excellent scalability across 12 Sun SPARC Enterprise T5440 servers and extreme data throughput capability with 60 Sun Storage F5100 flash arrays.
• This result showed Sun and Oracle's integrated hardware and software stacks provide industry-leading performance.

• Benchmark Results

• Benchmark Details

• Press Release

In single node runs, the Sun Fire X4270 with 74 GB memory and Sun Storage F5100 Flash Array beat the leading posted results from an HP BL460c G6 with striped SAS drives in an XFS file system on the S4B test (20G).

Benchmark Details

Hardware Performance Sun Fire X4270 and Sun Storage F5100 Flash Array 1970 Seconds HP BL460c G6 2062 Seconds

 

Moreover, the F5100 Flash Array provides nominally up to 15% improvement in performance even when using the maximum possible amount of memory that also contributes to performance improvement by allowing for more I/O to be cached to memory.

The ABAQUS V6.9-1 "Standard" Module Test: "S4B" is nonlinear static model of a cylinder head bolted to an engine block.

Three versions of this benchmark are provided: a version using a smaller model (700,000 DOF) with a low iteration count, a version using a larger model (5,000,000 DOF) model with a low iteration count, and a version using the smaller model but with a higher iteration count. These three models are used to demonstrate that as a general rule parallel scaling in Abaqus/Standard improves as either the model size or the number of iterations increases.

• Press Release

The Sun SPARC Enterprise M4000 server combined with the Sun Storage F5100 Flash Array with Sun FlashFire technology, has produced World Record Performance on PeopleSoft Payroll 9.0 benchmark on large volume model processing 250K Employees Payments in 67.85 minutes. The Sun solution used the Oracle 11g database running on Solaris 10.

Benchmark Details

System Processor OS/Database Time in Minutes: Run 1 Time in Minutes: Run 2 Time in Minutes: Run 3 Version Sun M4000 4x SPARC64 VII Solaris/Oracle 11g 79.35 288.47 527.75 9.0

 

For the benchmark, we collected at least 3 data points with a different number of job streams (parallel jobs). This batch benchmark allows a maximum of eight job streams to be configured to run in parallel.

The PeopleSoft 9.0 Payroll (North America) benchmark is a performance benchmark established by PeopleSoft to demonstrate system performance for a range of processing volumes in a specific configuration. This information may be used to determine the software, hardware, and network configurations necessary to support processing volumes. This workload represents large batch runs typical of OLTP workloads during a mass update.

The five processes used to measure five application business process run times for a database representing large organization are:

• Paysheet Creation: Generates payroll data worksheet for employees, consisting of standard payroll information for each employee for a given pay cycle.
• Payroll Calculation: Looks at pay sheets and calculates checks for those employees.
• Payroll Confirmation: Takes information generated by payroll calculation and updates the employees' balances with the calculated amounts.
• Print Advice Forms: The process takes the information generated by payroll calculations and confirmation and produces an advice form for each employee to report earnings, taxes, deduction, etc.
• Create Direct Deposit File: This process takes the information generated by the above processes and produces an electronic transmittal file which is used to transfer payroll funds directly into an employee bank account.

For the benchmark, we collected at least four data points with a different number of job streams (parallel jobs). This batch benchmark allows a maximum of eight job streams to be configured to run in parallel.

• Press Release

• Sun Performance and Best Practices Blog

For MSC/NASTRAN MDR3 running on a Sun Fire X4270 with 2.93 GHZ Intel X5570 CPU, test case "xxocmd2_8" was run against Internal disk drives and Sun Storage F5100 array.

• With four RAID0 72GB 15K RPM internal drives, the benchmark execution time was 958.81 seconds
• With a 20 Flash Module F5100 Flash array, the time dropped to 462.74 seconds

This is a 2.1x improvement for this benchmark test case.

• Press Release

• Sun Performance and Best Practices Blog