Fujitsu PRIMERGY TX150 Torre manual

Version 5.1 November 2008 Pages 33 Performance Report PRIMERGY TX150 S6 Abstract This document contains a su mmary of the benchmarks executed for the PRIMERGY TX150 S6. The PRIMERGY TX150 S6 performance d ata are compared with the data of other PRIMERGY models and discussed. In addition to the benchmark re sults, an explanation h as been included f[...]

White Paper ⏐ Performance Report PRIMERGY TX150 S6 Version: 5.1, November 2008 Technical Data The PRIMERGY TX150 S6 is a mono -sock et tower server. It includes the Intel 3210 chipset, one Celer on, Pentium Dual-Core, Core 2 Duo, Dual- Core Xeon or Quad-C ore Xeon processor, up to 8 GB PC2-6400 DDR2-SDRAM, dep end- ing on the processor us ed a 80[...]

White Paper ⏐ Performance Report PRIMERGY TX150 S6 Version: 5.1, November 2008 SPECcpu2006 ∗ Benchmark description SPECcpu2006 is a benchmark to measure s ystem efficiency duri ng integer and floating p oint operations. It consists of an integer test suite containing 12 app lications and a floating poi nt test suite containing 17 app lications [...]

White Paper ⏐ Performance Report PRIMERGY TX150 S6 Version: 5.1, November 2008 • Xeon E3110 a nd E3120 (Wolfdale, 2 cores per chip, 6 MB L2 cache per chip) • Xeon X3210 and X3220 (Kentsfield, 4 cores per chip, 4 MB L2 cache per 2 cores) • Xeon X3350, X336 0 and X3370 (Yorkfield, 4 cores per chip, 6 MB L2 cache per 2 cores) The following two[...]

White Paper ⏐ Performance Report PRIMERGY TX150 S6 Version: 5.1, November 2008 The measured SPECint_rate_ 2006 results are 12-17 % a bove the SPECint_rate_bas e2006 results. Processor cores/ chip GHz L2 cache FSB TDP SPECfp_rate_base2006 SPECfp_rate2006 Celeron 440 1 2 ½ MB per chip 800 MHz 35 watt 12.3 13.1 Pentium Dual-Core E2140 2 1.60 1 MB p[...]

White Paper ⏐ Performance Report PRIMERGY TX150 S6 Version: 5.1, November 2008 The measured SPECfp_rate_ 2006 results ar e 4-9% above the SPECfp_rat e_base 2006 results. The following four tables show results, in which all benchmark progr ams were compiled with the Intel C++ /Fortran com- piler 10.1 and run u nder SUSE Linux Enter prise Server 10[...]

White Paper ⏐ Performance Report PRIMERGY TX150 S6 Version: 5.1, November 2008 Benchmark environment All SPECcpu2006 measurem ents were performed on a PRIMERGY T X150 S6 with the following har dware and software configuration: Hardware Model PRIMERGY TX150 S6 CPU Celeron 440 Pentium Dual-Core E2140, E216 0 and E2200 Core 2 Duo E4500, E4600 and E7[...]

White Paper ⏐ Performance Report PRIMERGY TX150 S6 Version: 5.1, November 2008 SPECjbb2005 ∗ Benchmark description SPECjbb2005 is a Java busin ess benchmark that focuses on the per formance of Java server pl atforms. It is essential ly a modernized version of SPECjbb2 000 with the main differences being: • The transactions have become more co[...]

White Paper ⏐ Performance Report PRIMERGY TX150 S6 Version: 5.1, November 2008 Benchmark results In November 2007 the PRIMERGY TX150 S6 was measured with the Xeon X321 0 processor and a memory of 8 GB PC2-6400 DDR2-SDRAM. The me asurement was taken under W indo ws Server 2003 R 2 Enterprise x64 Edition SP 1. As JVM, two instances of JRockit(R) 6.[...]

White Paper ⏐ Performance Report PRIMERGY TX150 S6 Version: 5.1, November 2008 In August 2008 the PRIMERGY TX150 S6 was measure d with the Xeon X3 370 processor an d a memory of 8 GB PC2- 6400 DDR2-SDRAM. T he measurement was taken under Windows Server 2003 R 2 Enterprise x64 E dition. As JVM, two instances of JRockit(R) 6.0 P27.5.0 (build P27. 5[...]

White Paper ⏐ Performance Report PRIMERGY TX150 S6 Version: 5.1, November 2008 Benchmark environment The SPECjbb2005 measurem ents were performed on a PRIMERGY TX150 S6 with the follo wing hardware and software configuration: Hardware Model PRIMERGY TX150 S6 CPU Xeon X3210, X336 0 and X3370 Number of chips 1 chip, 4 cores, 4 cores per chip Primar[...]

White Paper ⏐ Performance Report PRIMERGY TX150 S6 Version: 5.1, November 2008 SPECpower_ssj2008 * Benchmark description SPECpower_ssj2008 is the first industr y-standard SPEC benc hmark that evaluates the po wer and performance charac- teristics of server class computers. With SPECpower_ssj2008, SPEC has defin ed server po wer measurement standa[...]

White Paper ⏐ Performance Report PRIMERGY TX150 S6 Version: 5.1, November 2008 Benchmark results In June 2008 the PRIMERGY T X150 S6 was measured with an Intel Xeon X3360 processor and 4 GB of PC2-6400E DDR2-SDRAM memory. T he measurement was taken u nder Windows Server 2003 R2 Enterpr ise x64 Edition and a JRockit(R) 6.0 P27.5.0 JVM by Oracle wa[...]

White Paper ⏐ Performance Report PRIMERGY TX150 S6 Version: 5.1, November 2008 The Xeon pro cessor comparison dia gram shows measurement s with four different Xeon CPUs measured with the PRIMERGY TX150 S6. All other configuration deta ils rem ained unchanged dur ing the measurements. Obviously the throughp ut changes when using d ifferent CPUs wi[...]

White Paper ⏐ Performance Report PRIMERGY TX150 S6 Version: 5.1, November 2008 As you can see in the diagram above not only the right choice of pr ocessors has a s ignificant influence on p ower con- sumption but other configuration d etails as well. Doublin g the memory for example from 2 x 2 GB to 4 x 2 GB increases the power consumption at all[...]

White Paper ⏐ Performance Report PRIMERGY TX150 S6 Version: 5.1, November 2008 As you can see the most energy efficient configur ation does not c onsume the lo west power. It is still about 108% m ore efficient compared to the leas t energy efficient configuratio n. The configuration with the Xeon E3120 processor has the lowest power consumption.[...]

White Paper ⏐ Performance Report PRIMERGY TX150 S6 Version: 5.1, November 2008 SPECweb2005 ∗ Benchmark description SPECweb2005 is the next g eneration web server be nchmar k developed by the Open S ystems Group (OSG) of the Standard Performance Evalua tion Corporation (SPEC). It is the successor of SPECweb99 and SPEC web99_SSL and it measures t[...]

White Paper ⏐ Performance Report PRIMERGY TX150 S6 Version: 5.1, November 2008 Benchmark results In April 2008 the PRIMERGY T X150 S6 was measured with o ne Xeon X322 0 processor and 8 GB PC2-6400 DDR2- SDRAM. Two quad-port Intel PRO/1000GT and one Broa dcom NetXtreme II BCM57 08 (onboard) were used for the network. A FibreCAT CX500 with 45 h ard[...]

White Paper ⏐ Performance Report PRIMERGY TX150 S6 Version: 5.1, November 2008 Benchmark environment TX150 S6 with Xeon X3220: 60 × PRIMERGY BX300 2 x Pentium III 933 MHz 1 GB RAM 2 x Broadcom NetXtreme (on board) Windows XP Professional SP 1 PRIMERGY TX150 S6 1 × Xeon 3220 8 GB PC2-6400 DDR2-SDRAM 1 × Emulex LP10000D C fibre channel controlle[...]

White Paper ⏐ Performance Report PRIMERGY TX150 S6 Version: 5.1, November 2008 TX150 S6 with Xeon X3360: 80 × PRIMERGY BX300 2 x Pentium III 933 MHz 1 GB RAM 2 x Broadcom NetXtreme (on board) Windows XP Professional SP 1 PRIMERGY TX150 S6 1 × Xeon 3360 8 GB PC2-6400 DDR2-SDRAM 1 × Emulex LPe11002 fibre c hannel controll er 2 × dual-channel In[...]

White Paper ⏐ Performance Report PRIMERGY TX150 S6 Version: 5.1, November 2008 StorageBench Benchmark description To estimate the capability of disk subsystems Fujitsu Te chnolog y Solutions defined a benchmark cal led StorageBench to compare the different storage systems con nected to a s ystem. T o do this StorageBench makes use of the Iometer [...]

White Paper ⏐ Performance Report PRIMERGY TX150 S6 Version: 5.1, November 2008 Measurement scenario In order to obtain compar able measurement results it is im portant to perform all th e m easurements in identica l, repro- ducible environ ments. This is why Stor ageBench is base d, in addition to the l oad profile descri bed above, on t he follo[...]

White Paper ⏐ Performance Report PRIMERGY TX150 S6 Version: 5.1, November 2008 Benchmark results The PRIMERGY TX150 S6 is equipped with controllers from the “Modular RAID” family. The variet y of the RAID solu- tions enables the user to choose the ri ght controller for his appl ication scenario. The PRIMERGY TX150 S6 has the follo wing RAID s[...]

White Paper ⏐ Performance Report PRIMERGY TX150 S6 Version: 5.1, November 2008 the shorter latency times. H ere again the RAID 0 array ac hiev es alm ost twice the write throughp ut through parallel ac - cesses, as compared with the other two configurations. Enabling the disk cache lea ds to an increase in throughput during ran dom access. Howeve[...]

White Paper ⏐ Performance Report PRIMERGY TX150 S6 Version: 5.1, November 2008 LSI MegaRAID SAS 1068 Below is a comparison of the performa nce of various hard disk t ypes with the LSI MegaRAID SAS 1068 controller. The controller does not have a c ontroller cache. Therefore, measurements were only perf ormed with and without a disk cache. In the t[...]

White Paper ⏐ Performance Report PRIMERGY TX150 S6 Version: 5.1, November 2008 The following diagram shows that for rando m access with 67% reads the disk cache also plays an important role in im- proving throughput. An increase in throughput of up to 30% was achieved for the SAT A hard disk with 8 KB blocks. For the 3½" 15 krpm SAS hard di[...]

White Paper ⏐ Performance Report PRIMERGY TX150 S6 Version: 5.1, November 2008 The following graphic s hows that during random acc ess in RA ID 1 the combination of the “W rite-back” and “Disk cach e enabled” options has a dec isive influence on throughput. T he improvement in throughput is 48% or 56%, depen ding on whether access is with[...]

White Paper ⏐ Performance Report PRIMERGY TX150 S6 Version: 5.1, November 2008 When the onboard SATA ICH9R controller is compared with the LSI MegaRAID SAS 1068 contro ller, it is evident that both controllers offer roughl y the same performance when measurements are carried out with the same SAT A hard disks and optimum cache settings. The varia[...]

White Paper ⏐ Performance Report PRIMERGY TX150 S6 Version: 5.1, November 2008 Benchmark environment All the measurements presen ted here were performed with the hardware and software components listed be low. Component Details Server PRIMERGY TX150 S6 Operating system Windows Server 2003, Enterprise Ed ition Version: 5.2.3790 Service Pack 1 Buil[...]

White Paper ⏐ Performance Report PRIMERGY TX150 S6 Version: 5.1, November 2008 OLTP-2 Benchmark description OLTP stands for Online Tr ansaction Processing. T he OLTP-2 benchmark is bas ed on the typical a pplication scen ario of a database sol ution. In OLTP-2 databas e access is simulated a nd the number of tra nsactions achieved per second (tps[...]

White Paper ⏐ Performance Report PRIMERGY TX150 S6 Version: 5.1, November 2008 O L T P-2: P R IM E R G Y TX150 S6 75.05 64.54 62.38 50.32 20.07 43.06 46.50 0 25 50 75 10 0 12 5 15 0 17 5 Ce le ro n 440 1 c o r e 2 G H z 800 M H z F S B ½ M B L2 - c ac he 35 Wa tt Pent i um D C E2 1 4 0 2 c or e s 1. 6 0 G H z 800 M H z FS B 1 M B L2 - c ac he 65[...]

White Paper ⏐ Performance Report PRIMERGY TX150 S6 Version: 5.1, November 2008 Benchmark environment Microsoft Windows Server 2008 Enterprise x64 Edition and database SQL Server 2008 Enterprise x64 Editio n. LAN Switch Storage: 2 x FibreCAT CX500 180 data disks FC RAID 0 (36 GB, 15 krpm) Clients: 2 x PRIMERGY Econel 200 with 2 x Xeon 3.40 GHz, 2 [...]

White Paper ⏐ Performance Report PRIMERGY TX150 S6 Version: 5.1, November 2008 Literature PRIMERGY Systems http://ts.fujitsu.com/primergy PRIMERGY TX150 S6 http://docs.ts.fujitsu.com/dl.aspx?id= af1d8493-dfbb-478e-89c9-9 2e917929234 PRIMERGY Performance http://ts.fujitsu.com/products/st andard_servers/primergy_bov.html OLTP-2 Benchmark Overview O[...]