Speaker Notes: Goals of the presentation: Communicate Oracle’s commitment to creating best in class storage solutions Illustrate Oracle’s strategy for integrated hardware and software solutions These notes assume the speaker is familiar with Oracle’s storage portfolio but may be new to ECM.
This is the current SPARC Enterprise family including the M-Series and the T-series. The products shown here range from T-Series blades, 1 processor, 1RU, T5120, the 1cpu, 2RU M3000 all the way up to the 64 processor M9000 with up to 4TB of RAM and up to 288 I/O slots. They are designed to meet the requirements of just about any mission-critical workload from the web tier up to the back end database tier. They have mainframe-class RAS, virtualization technology (dynamic domains, Containers and Oracle VM SPARC—LDOMS) and are highly scalable. A key point is that all of the SPARC servers run the same OS (Solaris), have the same architecture (SMP) and are completely binary compatible with each other. The customer can standardize on one OS/Processor family yet meet all of the requirements of a multi-tier deployment in an economical fashion. This complete server family is an ideal platform for consolidation. The new SPARC T3 processor has 16 cores, 8 threads per core, 16 crypto units and 10GbE built in. These servers support PCIe Gen2. There are four servers containig T3….SPARC T3-1 is a single processor server, SPARC T3-2 is a dual-processor server and SPARC T3-4 is a four processor server. The T3-4 uses a “glueless” interconnect to connect all for processors so no switch is needed providing a more scalable interconnect than on the T5440. There is a single processor blade server called the SPARC T3-1B and it goes into the existing Blade chassis 6000.
These are just a few of Solaris’ unique values. Predictive Self Healing makes both hardware *and* software more resilient. DTrace, unlike other technologies, allows you to safely analyze production environments We’ll talk about Solaris Cluster in a moment. ZFS and other Solaris data management services are not only leading-edge – since they’re built in, you don’t have to buy extra file management software (avoid the “Veritas tax”) Solaris has the highest levels of independent security certification, covering a larger “Target of Evaluation” (what parts of the OS are actually certified) than other OSes Solaris has two decades of optimization work under its belt, and the world records to prove it, on systems ranging from low-cost intel rack mount servers, to the incredibly powerful Sun Enterprise systems During this time, we have put many unique features in especially for Oracle DB optimization, such as: Intimate shared memory Scheduler optimizations 64-bit support since 1998, and the first commercial OS to support 64-bit x86 Event polling optimizations Support for hardware dynamic reconfiguration Many other performance and resiliency optimizations
Old way of judging performance by CPU was 100% right in old datacenters... but computing has evolved. Does better &quot;per-core performance&quot; predict better system performance or $/perf? No. Modern server & CPU designers can make various trade-offs on complexity, performance and number of threads & cores. The best way to address these trade-offs is to look at the integrated system design. Below are two examples where better &quot;system design&quot; is far more important than a focus on &quot;per-core&quot; performance: * Oracle's 12-node Sun SPARC T5440 server TPC-C world record. o beats IBM's Power 595 (5GHz) with IBM DB2 9.5 perf by 26% o beats IBM's Power 595 $/perf (3 yr TCO: HW, SW, maint,) by 16% o Oracle solution also has better response time, Oracle's New Order response time was 7.3x faster than IBM!
Oracle demonstrated the world's fastest database performance using Oracle's SPARC Supercluster with T30-4 (27 SPARC T3-4 servers), 138 Sun Storage F5100 Flash Array storage systems and Oracle Database 11g Release 2 Enterprise Edition with Real Application Clusters (RAC) & Partitioning set a world-record TPC-C result. The SPARC T3-4 server cluster delivered a world record TPC-C benchmark result of 30,249,688 tpmC and $1.01 $/tpmC (USD) using Oracle Database 11g Release 2 on a configuration available 6/1/2011. The SPARC T3-4 server cluster is 2.9x faster than the performance of the IBM Power 780 (POWER7 3.86 GHz) cluster with IBM DB2 9.7 database and has 27% better price/performance on the TPC-C benchmark. Almost identical price discount levels were applied by Oracle and IBM. The Oracle solution has three times better performance than the IBM configuration and only used twice the power during the run of the TPC-C benchmark. The Oracle solution delivered 2x the performance in the same amount of space compared to IBM on the TPC-C benchmark. The SPARC T3-4 server with Sun Storage F5100 Flash Array storage solution demonstrates 3.2x faster response time than IBM Power 780 (POWER7 3.86 GHz) result on the TPC-C benchmark. Oracle used a single-image database, whereas IBM used 96 separate database partitions on their 3-node cluster. It is interesting to note that IBM used 32 database images instead of running each server as a simple SMP. IBM did not use DB2 Enterprise Database, but instead IBM used &quot;DB2 InfoSphere Warehouse 9.7&quot; which is a data warehouse and data management product and not their flagship OLTP product. The multi-node SPARC T3-4 server cluster is 7.4x faster than the HP Superdome (1.6 GHz Itanium2) solution and has 66% better price/perf on the TPC-C benchmark. The Oracle solution utilized Oracle's Sun FlashFire technology to deliver this result. The Sun Storage F5100 Flash Array storage system was used for database storage. Oracle Database 11g Enterprise Edition Release 2 with Real Application Clusters and Partitioning scales and effectively uses all of the nodes in this configuration to produce the world record TPC-C benchmark performance. This result showed Oracle's integrated hardware and software stacks provide industry leading performance .
Any consolidation platform must be able to partition its resource so that many applications can run appropriately. All applications need IO, cpu, RAM resources but in a consolidated environment all applications much share server resources. To prevent applications from “hogging” resources or to prevent an error in one application affecting the other applications or to prevent a user on one application gaining unauthorized access to a different application in the same server it is necessary to have virtualization technology that provides the necessary separation. Not all workloads are the same so Sun offers three primary types of virtualization technologies. A very important “feature” of Sun’s SPARC virtualization technologies is that they are no charge to the customer. No per core licenses are required as is the case with HP and IBM and their virtualization technologies. IBM and HP charge in the 10’s of thousands of $$ for virtualization for their Itanium and Power servers. Sun customers do need to pay for support if they want patches or upgrades to the SPARC virtualization technologies but no license fees. This means that customers can deploy the appropriate virtualization technology when they need to without having to worry about license fees. These notes will not go into detail on each virtualization solution. There are other sources of much more detailed information. Some things to note: Solaris containers is available on all systems that run Solaris…even on non-SPARC systems. Oracle VM SPARC (Ldoms) is only available on T-Series and Dynamic Domains (formerly known as Dynamic System Domains on Sun Fire systems) is only on Mseries systems. LDOMs cannot be implemented on Mseries because hypervisor support is not available on Mseries. Dynamic domains is a hardware partitioning scheme and Tseries does not have the hardware functionality for domains. Solaris containers has more than just zones. Solaris resource manager with fair-share scheduler, resource pools and processor sets are some key virtualization technologies besides zones.
Dynamic domains are dynamic meaning that they can be resized while the domain is running and applications are running. Shown is typical example of how the dynamic nature of domains can be help to improve system utilization and datacenter efficiency. We start with an M9000 with 20 processors configuration with two dynamic domains. The daytime configuration has a large 15 processor domain running some type of OLTP business application. DomainB has 5 processors running a batch application. During the day the OLTP application has heavier compute requirements and has more processors. However, in the evening the workload on the OLTP domain declines (e.g. an app that is supporting a retail store) but the batch requirements increase (setting retail accounts, or analyzing the day’s sales patterns or calculating new stocking, etc). Using Dynamic reconfiguration 8 processors can be moved from the OLTP domain to the batch domain to meet the increased batch workload. With DR neither domain or application is shut down…the movement of resources happens will each domain and application are running. Thus the two domains are sharing 8 processors that are moved around to meet changes in workloads. This is a much more efficient use of resources. Without dynamic reconfiguration the server would have 28 processors (vs 20 processors) to make sure that the compute requirements for both the batch and OLTP environments were met.
Enterprise Mission Critical: Reliability, availability, serviceability, and security Highly scalable (Vertical, Horizontal) Flash optimized for business critical database performance acceleratio COMPLETE. Solutions Infrastructure is the pathway to achieving next generation performance by taking a “holistic view” of IT environment From App to Disk, Systems w/Software, Enterprise Services and Support DBMS Application & Platform Performance from optimization at the “best” place For ease of deployment and management For best price/performance and flexibility for changing business needs Remove customer pain with coordinated patching & upgrades Provide integrated offerings Database + Applications + Servers + Flash + Disk + OS + Software Infrastructure + services + and more…. Proven performance and reliability of SPARC systems relies on hardware features and the strong integration of the operating system. The Solaris operating system is a 20 year evolution with Oracle. There are a broad range of features of unique features designed to lower costs in the datacenter by preventing unplanned downtime, optimizing performance, and preventing security breaches. For example, Unplanned downtime costs and average of $42K per hour or about 3.6% of revenue (16% for financial services). The average security breach cost an average of $6.6M in 2008.
Solution - complete, large scale systems for mission critical database needs of Database environments with: Business Critical requirements, SMP centric workloads, low latency workloads, large memory needs and vertical scale minded customers For Oracle Database, RAC & Applications – we offer: Oracle EM Ops Center Oracle Solaris Cluster Oracle Solaris operating system Oracle Sun SPARC Enterprise Servers Oracle FlashFire Oracle Sun Storage 6000 & 7000
We talked about the value of the Oracle + Sun stack in the keynote presentation. Only Oracle is positioned to offer the complete stack from Application to Disk. With the acquisition of Sun, we are extending the capabilities and benefits of the integrated stack down through the Operating System, the VM, the Servers and Storage. We are focused on engineering best of breed components, based on open Standards that will be integrated and engineered to work together so you don’t have to. This will result in Lower Cost of Ownership, considerably less Risk and One-Stop Support from a single vendor standing behind you.
SPARC Server strategy continues to focus on building the best Open Servers for Oracle Applications, and other applications from SAP and others. Trajectory of systems: 2 Families of SPARC servers, conceptually named T and M-series. M-series are intended for higher scale, mission critical RAS business applications T-series built for energy efficient, security integrated volume systems. Expect continued performance improvements across both families of servers, along with investment protection Up to 40X improvements in transaction processing performance Massive increases in cores, threads and memory Will lead to very high performance systems with data in memory Not just limited to Oracle applications, other applications will benefit as well. May 18, 2010 Copyright Oracle Corporation
Oracle believes in showing benchmark leadership as well as the best practices learned in these benchmarks in public. This information can be found at http://blogs.sun.com/BestPerf
This Oracle presentation “Tuning Oracle Database on SPARC Servers” can be presented to customers at events or workshops . Before use, partners must format the presentation using partners standard template, removing the Oracle template.
The following is intended to outline our general product direction. It is intended for information purposes only, and may not be incorporated into any contract. It is not a commitment to deliver any material, code, or functionality, and should not be relied upon in making purchasing decisions. The development, release, and timing of any features or functionality described for Oracle ’s products remains at the sole discretion of Oracle.
Oracle Flash Storage World’s Fastest and Most Efficient Flash Storage Accelerate Your Application Reduce Operating Costs Flash Modules Embedded in Servers and Flash Array Flash Drives (2.5” & 3.5” SSDs) Optional with Servers and Storage Flash Controllers Flash/HBA PCIe cards for Servers Flash Array Compact Storage Device Sun FlashFire Technology - delivering the highest level of performance, durability and reliability
Oracle Solaris Unmatched Reliability, Security and Scalability Trusted Extensions, Secure Certificates Least Privilege, Role Based Access Control DTrace ZFS Data Management Predictive Self Healing Crypto Infrastructure Optimized for Databases Tuned for SPARC and x86 Scale Up, Scale Out Solaris Cluster Scalability Security Reliability
Oracle's Integrated System Design You Can Compute Only As Fast As You Can Move Data
Sun SPARC Solaris: New World Record 30,249,699 tpmC Source: Transaction Processing Performance Council, www.tpc.org as of 12/2/10. Oracle Sun SPARC T3-4 server cluster, 30,249,688 tpmC, $1.01/tpmC, available 6/1/11. IBM Power 780 Server, 10,366,254 tpmC, $1.38/tpmC, available 10/13/10. HP Integrity Superdome-Itanium2, 4,092,799 tpmC, $2.93/tpmC, available 8/6/07.
World Record Datawarehouse Results 3TB TPC-H on M9000 with 64 processors
64 processors 1.94x faster than 32 processors (1)(2)
2.4x faster than best IBM 3TB result (3)
M9000 with 64 SPARC64 VII+ quad-core processors
Oracle 11gR2 database
Sun Storage 6180 arrays
As of March 22, 2011: (1) SPARC Enterprise M9000 server (64 CPUs): 386,478 QphH@3000GB, $19.25/QphH@3000GB, available March 22. Oracle used Storage Redundancy Level 3 (highest) as defined by the TPC-H 2.14.0 specification. Database Load Time - 10,741 sec. (2) Sun SPARC Enterprise M9000 server (32 CPUs): 198,907.5Q phH@3000GB, $16.58/QphH@3000GB, available 04/05/2011. 32 vs 64 CPUs results show 1.94x scalabilty. (3) IBM POWER 595 Model 9119-FHA, 156,537.3 QphH@3000GB, $20.60/QphH@3000GB, available 11/24/2009. (Best IBM TPC-H 3000GB performance (QphH) and price/performance ($/QphH) result). Database Load Time – 36,145 sec. 36,145/10,741 = 3.365
Configuring Oracle DB for M-series Memory considerations
Large memory densities possible with a single system image
“ In-Memory” parallel query with 11gR2 becomes interesting
15x average speedup System Memory M9000-64 4TB M9000-32 2TB M8000 1TB M5000 512GB
Configuring Oracle DB for SPARC Sockets / Cores / Threads
SPARC64 VII+ processor (4 cores/8 threads per processor)
SPARC T3 processor (16 cores/128 threads per processor)
Hard Partitions SPARC Hypervisors Solaris Containers SPARC Virtualization Enabling Consolidation Single OS Multiple OSes All Sun Systems Solaris Containers (Zones + SRM) Solaris Trusted Extensions Solaris 8 and 9 Containers T-Series Oracle VM SPARC (Logical Domains) Granular Dynamic Low-overhead M-Series Dynamic Domains Complete Isolation: Resources Security Faults Service Included at No Cost! Included at No Cost! Included at No Cost!
Required Benchmark Disclosure Statement 1 Must be in T-Series Presentations with Benchmarks
TPC Benchmark C, tpmC, and TPC-C are trademarks of the Transaction Performance Processing Council (TPC). 12-node Sun SPARC Enterprise T5440 Cluster (1.6GHz UltraSPARC T2 Plus, 4 processor) with Oracle 11g Enterprise Edition with Real Application Clusters and Partitioning, 7,646,486.7 tpmC, $2.36/tpmC. Available 3/19/10. IBM Power 595 (5GHz Power6, 32 chips, 64 cores, 128 threads) with IBM DB2 9.5, 6,085,166 tpmC, $2.81/tpmC, available 12/10/08. HP Integrity Superdome(1.6GHz Itanium2, 64 processors, 128 cores, 256 threads) with Oracle 10g Enterprise Edition, 4,092,799 tpmC, $2.93/tpmC. Available 8/06/07. Source: http://www.tpc.org, results as of 10/11/09.
SPECjAppServer2004, 5x Sun SPARC Enterprise T5440 (4 chips, 32 cores) 28,648.74 SPECjAppServer2004 JOPS@Standard; 17x HP BL870c (4 chips, 8 cores) 28,463.03 SPECjAppServer2004 JOPS@Standard; 16x IBM HS21 (2 chips, 8 cores) 22,634.13 SPECjAppServer2004 JOPS@Standard; SPEC, SPECjAppServer reg tm of Standard Performance Evaluation Corporation. Results from www.spec.org as of 6/2/2010. HP C7000 Blade Chassis (10 RU each). 5x Blade Chassis total 50 RU. HP EVA8100 2C6D Storage Array(112 disks): 2x HSV210-B controllers (2U each) and 8x M5314C Disk Enclosures (3U each) total 28 RU. 4x EVA8100 2C6D total 112 RU. HP EVA6100 2C4D Storage Array: 2x HSV200-B controllers (2U each) and 4x M5314C Disk Enclosures (3U each) total 16 RU. http://h20000.www2.hp.com/bc/docs/support/SupportManual/c00816246/c00816246.pdf http://h18004.www1.hp.com/products/quickspecs/12745_div/12745_div.pdf IBM BladeCenter H Chassis (9 RU each). 3x Chassis Total 27 RU. IBM DS4800 Disk System Model 82 (4U each). 6x IBM DS4000 EXP810 (3U each) total 22 RU. 2x Total Storage DS4800 total 44 RU. http://www-03.ibm.com/systems/xbc/cog/bc_h_8852/bc_h_8852aag.html ftp://ftp.software.ibm.com/systems/support/system_x_pdf/59y7294.pdf ftp://ftp.software.ibm.com/systems/support/bladecenter/gc26779809.pdf
SPECjAppServer2004, Sun SPARC Enterprise T5440 (4 chips, 32 cores) 7661.16 SPECjAppServer2004 JOPS@Standard; HP DL580 G5 (4 chips, 24 cores) 4410.07 SPECjAppServer2004 JOPS@Standard; HP DL580 G5 (4 chips, 16 cores) 3339.94 SPECjAppServer2004 JOPS@Standard; Two Dell PowerEdge 2950 (4 chips, 16 cores) 4794.33 SPECjAppServer2004 JOPS@Standard; Dell PowerEdge R610 (2 chips, 8 cores) 3975.13 SPECjAppServer2004 JOPS@Standard; Two Dell PowerEdge R610 (4 chips, 16 cores) 7311.50 SPECjAppServer2004 JOPS@Standard; IBM p570 (2 chips, 4 cores) 1197.51 SPECjAppServer2004 JOPS@Standard; SPEC, SPECjAppServer reg tm of Standard Performance Evaluation Corporation. Results from www.spec.org as of 7/20/09
Siebel CRM 8.0 Platform Sizing and Performance Program (PSPP) benchmark as of 10/01/08. Sun Microsystems:14,000 users, 1 x Sun SPARC Enterprise T5440 ( 4 x 1.4 GHz, 32 cores, 128GB RAM) Siebel CRM 8.0 SIA  ENU, Sun Java System Web Server 6.1 SP8, Oracle 10g R2 V 10.2.0.3.0,Solaris 10 5/08; Sun Microsystems: 10,000 users, 1 x Sun SPARC Enterprise T5120 web server (4 cores, 1 chip @1.2 GHz US-T2, 8 GB RAM), Siebel CRM 8.0 SIA  ENU, Sun Java System Web Server 6.1 SP8, Solaris 10 8/07, 1 x Sun SPARC Enterprise T5220 application server (8 cores, 1 chip @1.4 GHz US-T2, 32 GB RAM), 1 x Sun SPARC Enterprise T5220 application server (8 cores, 1 chip @1.2 GHz US-T2, 32 GB RAM) Siebel CRM 8.0 SIA  ENU, Solaris 10 8/07, 1 x Sun SPARC Enterprise T5120 database server (8 cores, 1 chip @1.2 GHz US-T2, 32 GB RAM), Oracle 10gR2 Database Server v10.2.0.1.0, Solaris 10 8/07; IBM: 7,000 users, 1 x IBM p570 web server (2 cores, 1 chip @1.9 GHz POWER5+ 8 GB RAM),Siebel CRM 8.0 SIA  ENU, IBM HTTP Server v18.104.22.168 PQ94086, AIX 5.3, SMT Enabled, 1 x IBM p570 application server (8 cores, 4 chips @4.7 GHz POWER6 64 GB RAM), Siebel CRM 8.0 SIA  ENU, Oracle 10gR2 Database Client v10.2.0.2.0, AIX 5.3, SMT Enabled, 1 x IBM p570 database server (4 cores, 2 chip @4.7 GHz POWER6 32 GB RAM), Oracle 10gR2 Database Server v10.2.0.2.0, AIX 5.3 SMT Enabled; IBM: 3,900 users, 1 x IBM x3850 web server (2 cores, 1 chip @3.0 GHz Xeon, 16 GB RAM), Siebel CRM 8.0 SIA  ENU, Microsoft IIS 6.0.3790.3959, Microsoft Windows 2003 Server EE, Hyperthreading Enabled, 1 x IBM x3850 application server (8 cores, 4 chips @3.0 GHz Xeon, 32 GB RAM), Siebel CRM 8.0 SIA  ENU, Oracle 10gR2 Database Client v10.2.0.1.0, Microsoft Windows 2003 Server EE, Hyperthreading Enabled, 1 x IBM x3850 database server (4 cores, 2 chip @3.0 GHz Xeon, 32 GB RAM) Oracle 10gR2 Database Server v10.2.0.2.0, RHEL4 AS U4, Hyperthreading Enabled; IBM 3,500 users, 1 x IBM x3850 web server (2 cores, 1 chip @3.0 GHz Xeon, 16 GB RAM), Siebel CRM 8.0 SIA  ENU, IBM HTTP Server v22.214.171.124 PQ04086, RHEL4 AS U4, Hyperthreading Enabled, 1 x IBM x3850 application server (8 cores, 4 chips @3.0 GHz Xeon, 32 GB RAM), Siebel CRM 8.0 SIA  ENU, Oracle 10gR2 Database Client v10.2.0.2.0, RHEL4 AS U4, Hyperthreading Enabled, 1 x IBM x3850 database server (4 cores, 2 chip @3.0 GHz Xeon, 16 GB RAM), Oracle 10gR2 Database Server v10.2.0.2.0, RHEL4 AS U4, Hyperthreading Enabled.
Oracle BI EE benchmark results 10/13/2009, see www.oracle.com/solutions/business_intelligence/resource-library-whitepapers.html
SPEC, SPECweb reg tm of Standard Performance Evaluation Corporation. Results from www.spec.org as of Oct 8, 2009 and this report. Sun SPARC Enterprise T5440, 100,209 SPECweb2005. HP ProLiant DL370 G6, 83,073 SPECweb2005. HP ProLiant DL585 G5, 71,629 SPECweb2005. HP ProLiant DL580 G5, 50,013 SPECweb2005.
SPEC, SPECmail reg tm of Standard Performance Evaluation Corporation. Results as of 08/07/2009 on www.spec.org. SPECmail2009: Sun SPARC Enterprise T5240 (16 cores, 2 chips) SPECmail_Ent2009 12,000 users at 57,758 SPECmail2009 Sessions/hour. Apple Xserv3,1 (8 cores, 2 chips) SPECmail_Ent2009 6,000 users at 28,887 SPECmail2009 Sessions/hour.
Two-tier SAP Sales and Distribution (SD) standard SAP ERP 6.0 2005/EP4 (Unicode) application benchmarks as of 07/21/09: Sun SPARC Enterprise T5440 Server (4 proc, 32 cores, 256 threads) 4,720 SAP SD Users, 4x 1.6 GHz UltraSPARC T2 Plus, 256 GB, Oracle10g, Solaris10, Cert# 2009026. HP ProLiant DL585 G6 (4 proc, 24 cores, 24 threads) 4,665 SAP SD Users, 4x 2.8 GHz AMD Opteron 8439 SE, 64 GB, SQL Server 2008, Windows Server 2008 Enterprise Ed, Cert# 2009025. HP ProLiant BL685c G6 (4 proc, 24 cores, 24 threads) 4,422 SAP SD Users, 4x 2.6 GHz AMD Opteron 8435, 64 GB memory, SQL Server 2008, Windows Server 2008 Enterprise Ed, Cert# 2009021. IBM System 550 (4 processors, 8 cores, 16 threads) 3,752 SAP SD Users, 4x 5 GHz Power6, 64 GB memory, DB2 9.5, AIX 6.1, Cert# 2009023. HP ProLiant DL585 G5 (4 proc, 16 cores, 16 threads) 3,430 SAP SD Users, 4x 3.1 GHz AMD Opteron 8393 SE, 64 GB , SQL Server 2008, Windows Server 2008 Enterprise Ed, Cert# 2009008. HP ProLiant BL685 G6 (4 proc, 16 cores, 16 threads) 3,118 SAP SD Users, 4x 2.9 GHz AMD Opteron 8389, 64 GB , SQL Server 2008, Windows Server 2008 Enterprise Ed, Cert# 2009007. NEC Express5800 (4 proc, 24 cores, 24 threads) 2,957 SAP SD Users, 4x 2.66 GHz Intel Xeon X7460, 64 GB , SQL Server 2008, Windows Server 2008 Enterprise Ed, Cert# 2009018. Dell PowerEdge M905 (4 proc, 16 cores, 16 threads) 2,129 SAP SD Users, 4x 2.7 GHz AMD Opteron 8384, 96 GB, SQL Server 2005, Windows Server 2003 Enterprise Ed, Cert# 2009017. Sun Fire X4600M2 (8 proc, 32 cores, 32 threads) 7,825 SAP SD Users, 8x 2.7 GHz AMD Opteron 8384, 128 GB memory, MaxDB 7.6, Solaris 10, Cert# 2008070. IBM System x3650 M2 (2 proc, 8 Cores, 16 Threads) 5,100 SAP SD users,2x 2.93 Ghz Intel Xeon X5570, DB2 9.5, Windows Server 2003 Enterprise Ed, Cert# 2008079. HP ProLiant DL380 G6 (2 proc, 8 cores, 16 threads) 4,995 SAP SD Users, 2x 2.93 GHz Intel Xeon x5570, 48 GB , SQL Server 2005, Windows Server 2003 Enterprise Ed, Cert# 2008071.
Zeus ZXTM Traffic Manager HTTPThroughput, results as of 7/20/2009, also see http://www.zeus.com/news/press_articles/zeus-price-performance-press-release.html
RSA/DSA Cryptography Benchmark Performance as of 08/07/07 as measured by Sun on the following platforms: Sun SPARC Enterprise T5220 37K RSA1024 signs/s, 38.9 AES128 Gb/s; Sun SCA6000 (actual) 13K RSA1024 signs/s, 1 AES128 Gb/s; Cavium Nitrox PX (datasheet) 12K RSA1024 signs/s, 2.5 AES128 Gb/s; 2-chip quad-core Xeon 3GHz 9K RSA1024 signs/s, 8.4 AES128 Gb/s; 2-chip dual-core Opteron 2.6GHz 4K RSA1024 signs/s, 3.9 AES128 Gb/s; Sun Fire T2000 1.2 GHz (8 cores, 1 chip) Solaris 10, 12,850 RSA1024 signs/s; Sun Fire T1000 1GHz (8 cores, 1 chip) Solaris 10, 10,764 RSA1024 signs/s; IBM p690 1.3 GHz (32 cores, 16 chips) AIX 5.1, 6,131 RSA1024 signs/s; Fujitsu PRIMEPOWER850 1.9 GHz (16 cores, 16 chips) Solaris 10, 6,038 RSA1024 signs/s; Dell PowerEdge 1850 3.6 GHz (2 cores, 2 chips) RHEL4 U1, 1,926 RSA1024 signs/s; Dell PowerEdge 2850 3.6 GHz (2 cores, 2 chips) SLES 9, 1,900 RSA1024 signs/s; IBM p5 510 1.5 GHz (2 cores, 1 chip, SMT) AIX 5.3, 1,200 RSA1024 signs/s.
Required Benchmark Disclosure Statement Must be in M-Series Presentations with Benchmarks
Two-tier SAP Sales and Distribution (SD) standard SAP ERP 6.0 2005/EP4 (Unicode) application benchmarks as of 11/18/09: Sun SPARC Enterprise M9000 (64 processors, 256 cores, 512 threads) 32,000 SAP SD Users, 64 x 2.88 GHz SPARC VII, 1152 GB memory, Oracle10g, Solaris10, Cert# 2009046. Sun SPARC Enterprise M9000 (32 processors, 128 cores, 256 threads) 17,430 SAP SD Users, 32 x 2.88 GHz SPARC VII, 1024 GB memory, Oracle10g, Solaris10, Cert# 2009038. IBM System 550 (4 processors, 8 cores, 16 threads) 3,752 SAP SD Users, 4x 5 GHz Power6, 64 GB memory, DB2 9.5, AIX 6.1, Cert# 2009023. Sun SPARC Enterprise M9000 (64 processors, 256 cores, 512 threads) 64 x 2.52 GHz SPARC64 VII, 1024GB memory, 39,100 SD benchmark users, 1.93 sec. avg. response time, Cert#2008042, Oracle 10g, Solaris 10, SAP ECC Release 6.0. SAP, R/3, reg TM of SAP AG in Germany and other countries. More info www.sap.com/benchmark
Linpack HPC, results from http://www.netlib.org/benchmark/index.html as of 07/14/08. Sun SPARC Enterprise M8000 (SPARC64 VII @2.52GHz, 16 chips), 548.2 GFLOPS. Sun SPARC Enterprise M8000 (SPARC64 VI @2.4GHz, 16 chips, 32 cores), 268.6 GFLOPS. IBM Power 570 (POWER6 4.7GHz, 8 chips, 16 cores) 239.4 GFLOPS.
SPEC, SPECfp, SPECint reg tm of Standard Performance Evaluation Corporation. Results from www.spec.org as of 7/9/08. Sun SPARC Enterprise M9000 SPARC64 VII 2.52GHz, 2290 SPECint_rate2006, 2010 SPECfp_rate2006. Sun SPARC Enterprise M9000 SPARC64 VII 2.52GHz, 1240 SPECint_rate2006, 1110 SPECfp_rate2006. Sun SPARC Enterprise M8000 SPARC64 VII 2.52GHz, 637 SPECint_rate2006, 582 SPECfp_rate2006. Sun SPARC Enterprise M5000 SPARC64 VII 2.4GHz, 264 SPECint_rate2006, 213 SPECfp_rate2006. Sun SPARC Enterprise M4000 SPARC64 VII 2.4GHz, 135 SPECint_rate2006, 112 SPECfp_rate2006. IBM Power 595 POWER6 5.0GHz, 2080 SPECint_rate2006, 2110 SPECfp_rate2006.
SPEC, SPECint, SPECfp reg tm of Standard Performance Evaluation Corporation. Competitive results from www.spec.org as of 10 October 2009. Sun SPARC Enterprise M9000 2400 SPECint_rate_base2006, 2590 SPECint_rate2006, 1930 SPECfp_rate_base2006, 2100 SPECfp_rate2006; Sun SPARC Enterprise M9000 (32 chips) 1370 SPECint_rate_base2006, 1450 SPECint_rate2006, 1190 SPECfp_rate_base2006, 1250 SPECfp_rate2006; Sun SPARC Enterprise M8000 706 SPECint_rate_base2006, 753 SPECint_rate2006, 616 SPECfp_rate_base2006, 666 SPECfp_rate2006; Sun SPARC Enterprise M5000 267 SPECint_rate_base2006, 296 SPECint_rate2006, 218 SPECfp_rate_base2006, 234 SPECfp_rate2006; Sun SPARC Enterprise M4000 136 SPECint_rate_base2006, 152 SPECint_rate2006, 111 SPECfp_rate_base2006, 116 SPECfp_rate2006; Sun SPARC Enterprise M9000 (2.52GHz) 2088 SPECint_rate_base2006, 2288 SPECint_rate2006, 1860 SPECfp_rate_base2006, 2010 SPECfp_rate2006; IBM Power 595 1866 SPECint_rate_base2006, 2155 SPECint_rate2006.
SPEC, SPECfp reg tm of Standard Performance Evaluation Corporation. Results from www.spec.org as of 7/1/08 and this announcment. Sun SPARC Enterprise M8000 SPARC64 VII @2.52GHz, 28.8 SPECfp2006. IBM Power 595 POWER6 @5.0GHz, 24.9 SPECfp2006. SPEC, SPECfp reg tm of Standard Performance Evaluation Corporation. Results from www.spec.org as of 7/1/08 and this announcment. Sun SPARC Enterprise M8000 SPARC64 VII @2.52GHz, 25.0 SPECfp_base2006. IBM Power 595 POWER6 @5.0GHz, 20.1 SPECfp_base2006.
Oracle Peoplesoft Payroll 9.0 benchmark, Sun M4000 (4 2.53GHz SPARC64) 79.35 min, IBM Z990 (6 gen1) 107.34 min, HP rx6600 (4 1.6GHz Itanium2) 105.70 min, www.oracle.com/apps_benchmark/html/white-papers-peoplesoft.html Results 10/13/2009.
Required Benchmark Disclosure Statement Must be in Storage Presentations with Benchmarks
SPC-1C, SPC-1C IOPS, SPC-1C LRT are trademarks of Storage Performance Council (SPC), see www.storageperformance.org for more information. Sun Storage F5100 flash array SPC-1C submission identifier C00010 results of 300,873.47 SPC-1C IOPS over a total ASU capacity of 1374.390 GB using unprotected data protection, a SPC-1C LRT of 0.33 milliseconds, a 100% load over all ASU response time of 2.63 milliseconds and a total TSC price (including three-year maintenance) of $151,381. This compares with IBM System Storage EXP12S SPC-1C/E Submission identifier E00001 results of 45,000.20 SPC-1C IOPS over a total ASU capacity of 547.61 GB using unprotected data protection level, a SPC-1C LRT of 0.46 milliseconds, a 100% load over all ASU response time of 6.95 milliseconds and a total TSC price (including three-year maintenance) of $87,468. The Sun Storage F5100 flash array is a 1RU (1.75") array. The IBM System Storage EXP12S is a 2RU (3.5") array.