BM Seer Unofficial thoughts from an anonymous Sun employee

World Record ERP SAP-SD 2-Tier ECC 6.0 Sun SPARC Enterprise T5120

Tuesday Oct 09, 2007

Best 1 processor, two SAP SD Standard Application Benchmark. This benchmark shows that the UltraSPARC T2 is well-suited as an Oracle 10G OLTP database server. The Sun SPARC Enterprise T5120 server with a single 1.4 GHz UltraSPARC T2 processor set a new World Record for single processor systems achieving 2175 SD benchmark users on the two-tier SAP Sales and Distribution (SD) standard SAP ERP 2005 application benchmark.

The Sun SPARC Enterprise T5120 server (1.4GHz UltraSPARC T2) outperformed the 4-core IBM System p570 (4.7 GHz POWER6) by 7%. The 4RU IBM p570 POWER6 is 4 times larger than the 1RU Sun SPARC Enterprise T5120 system.

The Sun SPARC Enterprise T5120 server (1.4GHz UltraSPARC T2) is the first single processor to exceed 10,000 SAPS.

The Sun SPARC Enterprise T5120 server (1.4GHz UltraSPARC T2) outperformed the HP BL460C with two 3 GHz Xeon quad-core processors by 5%.

The Sun SPARC Enterprise T5120 server (1.4GHz UltraSPARC T2) outperformed the HP DL380 G5 with two 3.0 GHz Xeon quad-core processors by 5%.

The Sun SPARC Enterprise T5120 server (1.4GHz UltraSPARC T2) outperformed the HP rx6600 with four 1.6 GHz Itanium dual-core processors.

The Sun SPARC Enterprise T5120 server (1.4GHz UltraSPARC T2) outperformed all 1-chip and 2-chip systems.

SAP wants customers to comput their own perf/watt or SWaP. The SWaP metric is a measure of server efficiency ratio that includes system performance, power and space consumption on a specific benchmark. (SWaP = Perf /[ Space (RU) x Watts ] )

The Sun SPARC Enterprise T5120 server (1.4GHz UltraSPARC T2) showed a 2x improvement compared to Sun SPARC Enterprise T2000 (1.4 GHz UltraSPARC T1). The UltraSPARC T2 has twice the thread count of the UltraSPARC T1.

SAP-SD 2-Tier Performance Table (bigger is better, sorted by perf)

System Users # Type GHz GB OS DB LI/Hr SAPS BM rev. Date
Sun T5120 2175 1 US T2 1.4GHz 64 GB Solaris 10 Oracle 10g 219,000 10,950 6.0 09-Oct-07
HP Integrity rx6600 2150 4 Itan2 1.6GHz 48 GB HP-UX 11iV3 Oracle 10g 215,670 10,780 6.0 27-Nov-06
HP ProLiant BL685c 2100 4 Opt 3GHz 32 GB Windows 2003 EE SQL 2005 210,670 10,530 6.0 03-Sep-07
HP ProLiant DL460c 2080 2 Xeon 3GHz 32 GB Windows 2003 EE SQL 2005 208,000 10,400 6.0 03-Sep-07
HP ProLiant DL380 G5 2080 2 Xeon 3GHz 32 GB Windows 2003 EE SQL 2005 208,670 10,430 6.0 03-Sep-07
IBM p 570 2035 4-core POWER6 4.7GHz 32 GB AIX 5L 5.3 Oracle 10g 203,670 10,180 6.0 21-May-07
Fujitsu BX620 S4 1940 2 Xeon 3GHz 32 GB Windows 2003 EE SQL 2005 194,000 9,700 6.0 13-Aug-07
Sun Fire T2000 1100 1 US T1 1.4GHz 64 GB Solaris 10 Oracle 10g 110,670 5,530 6.0 22-Aug-07
HP Integrity rx2660 1090 2 Itan2 1.6GHz 32 GB HP-UX 11iV3 DB2 9 109,670 5,480 6.0 20-Mar-07
HP ProLiant DL365 1083 2 Opt 2.8GHz 32 GB Windows 2003 EE SQL 2005 108,670 5,430 6.0 09-Feb-07
Fujitsu BFi20 S2 1020 2 Xeon 3GHz 16 GB Solaris 10 Oracle 10g 102,330 5,120 6.0
Uni
code		 04-May-07
IBM x3250 850 1 Xeon 2.13GHz 8 GB Windows 2003 EE DB2 9 88,000 4,400 6.0 11-May-07

Complete benchmark results may be found at the SAP benchmark website http://www.sap.com/solutions/benchmark.

Benchmark Description

The SAP Standard Application SD (Sales and Distribution) Benchmark is a two-tier ERP business test that is indicative of full business workloads of complete order processing and invoice processing, and demonstrates the ability to run both the application and database software on a single system. The SAP Standard Application SD Benchmark represents the critical tasks performed in real-world ERP business environments.

SAP is one of the premier world-wide ERP application providers, and maintains a suite of benchmark tests to demonstrate the performance of competetive systems on the various SAP products.

Disclosure Statement:

Two-tier SAP Standard Sales and Distribution (SD) standard SAP ERP 2005 application benchmark: SPARC Enterprise Model T5120 (1-way, 1 proc, 8 cores, 64 threads) 1 x 1.4 GHz UltraSPARC T2, 64GB memory, 2175 SD Benchmark users, 1.91 sec avg response time, Cert#2007059, Oracle 10g, Solaris 10; SPARC Enterprise Model T2000 | Sun Fire T2000 (1-way, 1 proc, 8 cores, 32 threads) 1 x 1.4 GHz UltraSPARC T1, 64GB memory, 1100 SD Benchmark users, 1.91 sec avg response time, Cert#2007051, Oracle 10g, Solaris 10; HP ProLiant BL460c (2-way, 2 processors, 8 cores, 8 threads) 2 x 3.0 GHz Quad-Core Intel Xeon, 32GB memory, 2080 SAP SD Benchmark users, 1.99 sec avg response time, Cert#2007054, SQL Server 2005, Windows Server 2003 Enterprise Edition; HP ProLiant DL380 G5 (2-way, 2 processors, 4 cores, 4 threads) 2 x 3.0 GHz Quad-Core Intel Xeon, 32GB memory, 2080 SAP SD Benchmark users, 1.95 sec avg response time, Cert#2007057, SQL Server 2005, Windows Server 2003 Enterprise Edition; HP Integrity rx6600 (4-way, 4 processors, 8 cores, 16 threads) 4 x 1.6 GHz Dual-Core Intel Itanium, 48GB memory, 2150 SAP SD Benchmark users, 1.97 sec avg response time, Cert#2006083, Oracle 10g, HP-UX 11iV3; IBM System p 570 (2-way, 2 processors, 4 cores, 8 threads) 2 x 4.7 GHz POWER6+, 32GB memory, 2035 SD Benchmark users, 1.99s avg resp time, Cert#2007037, Oracle 10g, AIX 5L Version 5.3; SAP, R/3, mySAP reg TM of SAP AG in Germany and other countries. More info www.sap.com/solutions/benchmark.

Submitted results for the SAP-SD 2-Tier benchmark
Certified Results
Performance: 2175 benchmark users
Server: Sun SPARC Enterprise
Processors: 1 x 1.4 GHz UltraSPARC T2
Memory: 64 GB
Operating system: Solaris 10
Database S/W: Oracle 10g
SAP S/W: SAP ECC 6.0
SAP Certification: 2007059
Storage: 2 x Sun StorEdge(tm) 3510 FC Array Rack Mounted

[5] Comments
Like this post? del.icio.us | furl | slashdot | technorati | digg
Posted at 01:11PM Oct 09, 2007 in Benchmarks
Tags:
Comments:

[Trackback] SUN выпустил сервера t5220 и t5120 с процессором Niagara II на борту, которые снова не впечатляют. Вместе

Posted by Yo! RDBMS blog on October 09, 2007 at 03:19 PM PDT #

>The Sun SPARC Enterprise T5120 server (1.4GHz UltraSPARC T2) outperformed the HP BL460C with two 3 GHz Xeon quad-core processors by 5%.

But Xeon was on mssql2k5. Microsoft in SAP-SD is 25-40% slower than oracle10g, based on last 3 results on equal hardware:

http://www.sap.com/solutions/benchmark/pdf/cert7006.pdf
http://www.sap.com/solutions/benchmark/pdf/cert8306.pdf
oracle10g 30% faster

http://www.sap.com/solutions/benchmark/pdf/cert6806.pdf
http://www.sap.com/solutions/benchmark/pdf/cert7106.pdf
oracle10g 41% faster

http://www.sap.com/solutions/benchmark/pdf/cert2306.pdf
http://www.sap.com/solutions/benchmark/pdf/cert1506.pdf
oracle9i 25% faster

So really Xeon already faster and Opteron Barselona can be 70% faster than this T2 result. I think we will see Barselona on oracle10g very soon.

P.S. Why SUN use 64Gb RAM ? All competitors use only 32Gb to get the same result ...
Will SUN publish TPC-E on T2 ?

Posted by Triffids on October 11, 2007 at 01:58 AM PDT #

YOU CAN NOT ESTIMATE RESULTS ON SAP-SD, SAP does not allow your sort of playing estimation of benchmark results.

These are easy to run benchmarks, why haven't there been certified results on 2-processor Xeon that are faster than the 1-processor UltraSPARC T2?

The memory attack is not a valid attack, I've already blogged about memory configurations. I thought you understood SAP applications?

When will IBM Power6 publish on TPC-E?

When will Xeon quad-core publish on TPC-E?

When will Opteron quad-core publish on TPC-E?

When will anything more than dual-core publish on TPC-E?

When will Itanium2 publish on TPC-E?

When will Oracle publish on TPC-E?

When will DB-2 publish on TPC-E?

When will HP publish on TPC-E?

When will Fujitsu publish on TPC-E?

Posted by BM Seer on October 11, 2007 at 09:04 AM PDT #

When will SuSE Linux publish on TPC-E?

When will Redhat Linux publish on TPC-E?

Posted by BM Seer on October 11, 2007 at 09:06 AM PDT #

>YOU CAN NOT ESTIMATE RESULTS ON SAP-SD
We can check this then Barselona result will be published ... :)

Posted by Triffids on October 12, 2007 at 04:43 AM PDT #

Post a Comment:
Comments are closed for this entry.