IBM e Server p Series IBM p Series

IBM e. Server p. Series Notes to Presenter REQUIRED CHARTS The presenter must display the Special Notices chart, the Notes on Benchmarks and Values charts (if the referenced values are given), and the Notes on Performance Estimates chart (if the referenced performance estimates are given) during the course of the presentation. Any printed copies of this presentation that are distributed must include legible copies of these charts. If printed copies are not distributed, the I to receive legible printed copies of attendees must be offered the option these charts. TRADEMARKS Please review the Special Notices page prior to updating this presentation to ensure all trademarks used are given proper attribution. SPEAKER NOTES This presentation may contain speaker notes available imbedded or as a separate file. Please ensure these are utilized if available. Revised January 9, 2003 2 © 2004 IBM Corporation

IBM e. Server p. Series Notes to Presenter (Cont. ) To properly view this presentation, you will need to install the IBM ~ True Type Font - IBMeserver. If it is not properly installed, you will see IBM ^ or ~ instead of IBM ~. The font can be downloaded by IBMers from: I http: //w 3. ibm. com/sales/systems/portal/_s. 155/254? nav. ID=f 220 s 220 t 260&geo. ID = All&prod. ID=p. Series&doc. ID=eserverfont or by IBM Business Partners from: http: //www. ibm. com/partnerworld/sales/systems; document: eserverfontbp Revised May 6, 2004 3 © 2004 IBM Corporation

IBM e. Server p. Series Special Notices This document was developed for IBM offerings in the United States as of the date of publication. IBM may not make these offerings available in other countries, and the information is subject to change without notice. Consult your local IBM business contact for information on the IBM offerings available in your area. Information in this document concerning non-IBM products was obtained from the suppliers of these products or other public sources. Questions on the capabilities of non-IBM products should be addressed to the suppliers of those products. IBM may have patents or pending patent applications covering subject matter in this document. The furnishing of this document does not give you any license to these patents. Send license inquires, in writing, to IBM Director of Licensing, IBM Corporation, New Castle Drive, Armonk, NY 10504 -1785 USA. All statements regarding IBM future direction and intent are subject to change or withdrawal without notice, and represent goals and objectives only. The information contained in this document has not been submitted to any formal IBM test and is provided "AS IS" with no warranties or guarantees either expressed or implied. All examples cited or described in this document are presented as illustrations of the manner in which some IBM products can be used and the results that may be achieved. Actual environmental costs and performance characteristics will vary depending on individual client configurations and conditions. IBM Global Financing offerings are provided through IBM Credit Corporation in the United States and other IBM subsidiaries and divisions worldwide to qualified commercial and government clients. Rates are based on a client's credit rating, financing terms, offering type, equipment type and options, and may vary by country. Other restrictions may apply. Rates and offerings are subject to change, extension or withdrawal without notice. IBM is not responsible for printing errors in this document that result in pricing or information inaccuracies. All prices shown are IBM's United States suggested list prices and are subject to change without notice; reseller prices may vary. IBM hardware products are manufactured from new parts, or new and serviceable used parts. Regardless, our warranty terms apply. Many of the p. Series features described in this document are operating system dependent and may not be available on Linux. For more information, please check: http: //www. ibm. com/servers/eserver/pseries/linux/whitepapers/linux_pseries. html. Any performance data contained in this document was determined in a controlled environment. Actual results may vary significantly and are dependent on many factors including system hardware configuration and software design and configuration. Some measurements quoted in this document may have been made on development-level systems. There is no guarantee these measurements will be the same on generally-available systems. Some measurements quoted in this document may have been estimated through extrapolation. Users of this document should verify the applicable data for their specific environment. I Revised February 6, 2004 4 © 2004 IBM Corporation

IBM e. Server p. Series Special Notices (Cont. ) The following terms are registered trademarks of International Business Machines Corporation in the United States and/or other countries: AIX, AIX/L(logo), alpha. Works, AS/400, Blue Gene, Blue Lightning, C Set++, CICS/6000, CT/2, Data. Hub, Data. Joiner, DB 2, DEEP BLUE, developer. Works, DFDSM, Direct. Talk, DYNIX/ptx, e business(logo), e(logo)business, e(logo)server, Enterprise Storage Server, ESCON, Flash. Copy, GDDM, IBM(logo), ibm. com, IBM Total. Storage Proven, Intelli. Station, IQ-Link, LANStreamer, Load. Leveler, Lotus Notes, Lotusphere, Magstar, Media. Streamer, Micro Channel, MQSeries, Net. Data, Netfinity, Net. View, Network Station, Notes, NUMA-Q, Operating System/2, Operating System/400, OS/2, OS/390, OS/400, Parallel Sysplex, Partner. Link, Partner. World, POWERparallel, Power. PC(logo), Predictive Failure Analysis, p. Series, PTX, ptx/ADMIN, RISC System/6000, RS/6000, S/390, Scalable POWERparallel Systems, Secure. Way, Sequent, Server. Proven, SP 1, SP 2, Space. Ball, System/390, The Engines of e-business, THINK, Think. Pad, Tivoli(logo), Tivoli Management Environment, Tivoli Ready(logo), TME, Total. Storage, TURBOWAYS, Visual. Age, Web. Sphere, x. Series, z/OS, z. Series. The following terms are trademarks of International Business Machines Corporation in the United States and/or other countries: AIX/L(logo), AIX 5 L, AIX PVMe, AS/400 e, Blade. Center, Chipkill, Cloudscape, DB 2 OLAP Server, DB 2 Universal Database, DFDSM, DFSORT, Domino, e-business(logo), e-business on demand, e. Server, Giga. Processor, HACMP/6000, i 5/OS, IBMLink, IBM Virtualization Engine, IMS, Intelligent Micro-Partitioning, Miner, i. Series, NUMACenter, POWER Hypervisor, Power Architecture, Power Everywhere, POWER Hypervisor, Power. PC Architecture, Power. PC 603 e, Power. PC 604, Power. PC 750, POWER 2 Architecture, POWER 3, POWER 4+, POWER 5+, POWER 6, Redbooks, Sequent (logo), Sequent. LINK, Server Advantage, Serve. RAID, Service Director, Smooth. Start, SP, S/390 Parallel Enterprise Server, Think. Vision, Tivoli Enterprise, TME 10, Total. Storage Proven, Ultramedia, Video. Charger, Visualization Data Explorer, X-Architecture, z/Architecture. I A full list of U. S. trademarks owned by IBM may be found at: http: //www. ibm. com/legal/copytrade. shtml. UNIX is a registered trademark in the United States and other countries licensed exclusively through The Open Group. Linux is a registered trademark of Linus Torvalds in the United States, other countries or both. Microsoft, Windows NT and the Windows logo are registered trademarks of Microsoft Corporation in the United States and/or other countries. Intel, Itanium and Pentium are registered trademarks and Intel Xeon and MMX are trademarks of Intel Corporation in the United States and/or other countries AMD Opteron ia a trademark of Advanced Micro Devices, Inc. Java and all Java-based trademarks and logos are trademarks of Sun Microsystems, Inc. in the United States and/or other countries. Other company, product and service names may be trademarks or service marks of others. Revised July 1, 2004 5 © 2004 IBM Corporation

IBM e. Server p. Series Notes on Benchmarks and Values The benchmarks and values shown herein were derived using particular, well configured, development-level computer systems. Unless otherwise indicated for a system, the values were derived using external cache, if external cache is supported on the system. Buyers should consult other sources of information to evaluate the performance of systems they are considering buying and should consider conducting application oriented testing. For additional information about the benchmarks, values and systems tested, contact your local IBM office or IBM authorized reseller or access the following on the Web: TPC http: //www. tpc. org Linpack http: //www. netlib. no/netlib/benchmark/performance. ps Pro/E http: //www. proe. com SPEC http: //www. spec. org GPC http: //www. spec. org/gpc Notes. Bench Mail http: //www. notesbench. org Volano. Mark http: //www. volano. com STREAM http: //www. cs. virginia. edu/stream/ Unless otherwise indicated for a system, the performance benchmarks were conducted using AIX V 4. 3 or AIX 5 L. IBM C Set++ for AIX and IBM XL FORTRAN for AIX with optimization were the compilers used in the benchmark tests. The preprocessors used in some benchmark tests include KAP 3. 2 for FORTRAN and KAP/C 1. 4. 2 from Kuck & Associates and VAST-2 v 4. 01 X 8 from Pacific-Sierra Research. The preprocessors were purchased separately from these vendors. Other software packages like IBM ESSL for AIX and MASS for AIX were also used in some benchmarks. The following SPEC and Linpack benchmarks reflect microprocessor, memory architecture, and compiler performance of the tested system (XX is either 95 or 2000): –SPECint. XX - SPEC component-level benchmark that measures integer performance. Result is the geometric mean of eight tests comprising the CINTXX benchmark suite. All of these are written in the C language. SPECint_base. XX is the result of the same tests as CINTXX with a maximum of four compiler flags that must be used in all eight tests. –SPECint_rate. XX - Geometric average of the eight SPEC rates from the SPEC integer tests (CINTXX). SPECint_base_rate. XX is the result of the same tests as CINTXX with a maximum of four compiler flags that must be used in all eight tests. –SPECfp. XX - SPEC component-level benchmark that measures floating-point performance. Result is the geometric mean of ten tests, all written in FORTRAN, included in the CFPXX benchmark suite. SPECfp_base. XX is the result of the same tests as CFPXX with a maximum of four compiler flags that must be used in all ten tests. –SPECfp_rate. XX - Geometric average of the ten SPEC rates from SPEC floating-point tests (CFPXX). SPECfp_base_rate. XX is the result of the same tests as CFPXX with a maximum of four compiler flags that must be used in all ten tests. –SPECweb 96 - Maximum number of Hypertext Transfer Protocol (HTTP) operations per second achieved on the SPECweb 96 benchmark without significant degradation of response time. The Web server software is ZEUS v. 1. 1 from Zeus Technology Ltd. –SPECweb 99 - Number of conforming, simultaneous connections the Web server can support using a predefined workload. The SPECweb 99 test harness emulates clients sending the HTTP requests in the workload over slow Internet connections to the Web server. The Web server software is Zeus from Zeus Technology Ltd. –SPECweb 99_SSL - Number of conforming, simultaneous SSL encryption/decryption connections the Web server can support using a predefined workload. The Web server software is Zeus from Zeus Technology Ltd. –SPEC OMP 2001 - Measures performance based on Open. MP applications. –SPECsfs 97_R 1 - Measures speed and request-handling capabilities of NFS (network file server) computers. I Revised May 28, 2003 6 © 2004 IBM Corporation

IBM e. Server p. Series Notes on Benchmarks and Values (Cont. ) –SPECj. App. Server 200 X (where X is 1 or 2) - Measures the performance of Java Enterprise Application Servers using a subset of J 2 EE APIs in a complete endto-end Web application. The Linpack benchmark measures floating-point performance of a system. –Linpack DP (Double Precision) - n=100 is the array size. The results are measured in megaflops (MFLOPS). –Linpack SP (Single Precision) - n=100 is the array size. The results are measured in MFLOPS. –Linpack TPP (Toward Peak Performance) - n=1, 000 is the array size. The results are measured in MFLOPS. –Linpack HPC (Highly Parallel Computing) - solves the largest system of linear equations possible. The results are measured in GFLOPS. STREAM is a simple synthetic benchmark program that measures sustainable memory bandwidth (in MB/s) and the corresponding computation rate for simple vector kernels. Both standard and tuned results may be reported. http: //www. cc. virginia. edu/stream/ Volano. Mark is a 100% pure Java server benchmark that creates long-lasting network client connections in groups of 20 and measures how long it takes for the clients to take turns broadcasting their messages to the group. The benchmark reports a score as the average number of messages transferred by the server per second. –The I following Transaction Processing Performance Council (TPC) benchmarks reflect the performance of the microprocessor, memory subsystem, disk subsystem, and some portions of the network: –tpm. C - TPC Benchmark C throughput measured as the average number of transactions processed per minute during a valid TPC-C configuration run of at least twenty minutes. –$/tpm. C - TPC Benchmark C price/performance ratio reflects the estimated five year total cost of ownership for system hardware, software, and maintenance and is determined by dividing such estimated total cost by the tpm. C for the system. –Qpp. H is the power metric of TPC-H and is based on a geometric mean of the 17 TPC-H queries, the insert test, and the delete test. It measures the ability of the system to give a single user the best possible response time by harnessing all available resources. Qpp. H is scaled based on database size from 30 GB to 10 TB. –Qth. H is the throughput metric of TPC-H and is a classical throughput measurement characterizing the ability of the system to support a multiuser workload in a balanced way. A number of query users is chosen, each of which must execute the full set of 17 queries in a different order. In the background, there is an update stream running a series of insert/delete operations. Qth. H is scaled based on the database size from 30 GB to 10 TB. –$/Qph. H is the price/performance metric for the TPC-H benchmark where Qph. H is the geometric mean of Qpp. H and Qth. H. The price is the five-year cost of ownership for the tested configuration and includes maintenance and software support. Revised February 6, 2004 7 © 2004 IBM Corporation

IBM e. Server p. Series Notes on Benchmarks and Values (Cont. ) The following graphics benchmarks reflect the performance of the microprocessor, memory subsystem, and graphics adapter: –SPECxpc results - Xmark 93 is the weighted geometric mean of 447 tests executed in the x 11 perf suite and is an indicator of 2 D graphics performance in an X environment. Larger values indicate better performance. –SPECplb results (gra. PHIGS) - PLBwire 93 and PLBsurf 93 are geometric means of literal and optimized Picture Level Benchmark (PLB) tests for 3 D wireframe and 3 D surface tests, respectively. Larger values indicate better performance. –SPECopc results - Viewperf 7 (3 dsmax-01, DRV-08, DX-07, Light-05, Pro. E-01, UGS-01) and Viewperf 6. 1. 2 (AWadvs-04, DRV-07, DX-06, Light-04, med. MCAD-01, Pro. CDRS-03) are weighted geometric means of individual viewset metrics. Larger values indicate better performance. The following graphics benchmarks reflect the performance of the microprocessor, memory subsystem, graphics adapter and disk subsystem. –SPECapc Pro/Engineer 2000 i 2 results - PROE 2000 I 2_2000370 was developed by the SPECapc committee to measure UNIX and Windows workstations in a comparable real-world environment. Larger numbers indicate better performance. The Notes. Bench Mail workload simulates users reading and sending mail. A simulated user will execute a prescribed set of functions 4 times per hour and will generate mail traffic about every 90 minutes. Performance metrics are: –Notes. Mark - transactions/minute (TPM). –Notes. Bench users - number of client (user) sessions being simulated by the Notes. Bench workload. –$/Notes. Mark - ratio of total system cost divided by the Notes. Mark (TPM) achieved on the Mail workload. –$/User - ratio of total system cost divided by the number of client sessions successfully simulated for the Notes. Bench Mail workload measured. Total system cost is the price of the server under test to the client, including hardware, operating system, and Domino Server licenses. I Application Benchmarks –SAP - Benchmark overview information: http: // www. sap-ag. de/solutions/technology/bench. htm; Benchmark White Paper September, 2000; http: //www. sap-ag. de/solutions/technology/pdf/50020428. pdf. –People. Soft - To get information on People. Soft benchmarks, contact People. Soft directly or the People. Soft/IBM International Competency Center in San Mateo, CA. –Oracle Applications - Benchmark overview information: http: //www. oracle. com/apps_benchmark/ –Baan - The Baan benchmark demonstrates the scalability of Baan ERP solutions. The test results provide the number of Baan Reference Users (BRUs) that can be supported on a specific system. BRU is a single on-line user or a batch unit workload. These metrics are consistent with those used internally by both IBM and Baan to size systems. To get more information on Baan benchmarks, go to http: //www. ssaglobal. com. –J. D. Edwards Applications - Product overview information at http: //www. jdedwards. com. Revised December 9, 2003 8 © 2004 IBM Corporation

IBM e. Server p. Series Notes on Performance Estimates r. Perf –r. Perf (Relative Performance) is an estimate of commercial processing performance relative to other p. Series systems. It is derived from an IBM analytical model which uses characteristics from IBM internal workloads, TPC and SPEC benchmarks. The r. Perf model is not intended to represent any specific public benchmark results and should not be reasonably used in that way. The model simulates some of the system operations such as CPU, cache and memory. However, the model does not simulate disk or network I/O operations. –r. Perf estimates are calculated based on systems with the latest levels of AIX 5 L and other pertinent software at the time of system announcement. Actual performance will vary based on application and configuration specifics. The IBM ~ p. Series 640 is the baseline reference system and has a value of 1. 0. Although r. Perf may be used to approximate relative IBM UNIX commercial processing performance, actual system performance may vary and is dependent upon many factors including system hardware configuration and software design and configuration. –All performance estimates are provided "AS IS" and no warranties or guarantees are expressed or implied by IBM. Buyers should consult other sources of information, including system benchmarks, and application sizing guides to evaluate the performance of a system they are considering buying. For additional information about r. Perf, contact your local IBM office or IBM authorized reseller. I Revised June 28, 2004 9 © 2004 IBM Corporation

IBM e. Server p. Series IBM ~® p 5 550 Where does. I p

IBM e. Server p. Series IBM ~ p 5 and p. Series® Product Lines POWER 4+™ and POWER 5™ Servers IBM High-end IBM p. Series Mid-range server IBM p. Series 690 Entry deskside IBM p. Series 655 high-density cluster p. Series IBM p. Series server p 5 -570 I p 5 -550 server H C R U 6 IBM p 5 -520 p. Series 615 Model 6 E 3 p 5 -550 Cluster 1600 IBM server IBM H C R U 6 server p. Series IBM p 5 -520 server IBM IBM H C R U 6 server p. Series IBM p. Series 615 Model 6 C 3 11 Entry rack I B M © 2004 IBM Corporation IBM

IBM e. Server p. Series Incredible Values at the Low-end of IBM ~ POWER 5 Product Line … the IBM ~ p 5 550 ● Great choice for small and medium businesses IBM p. Series server IBM H C R U 6 server p. Series IBM ● Departmental or regional server for distributed enterprise applications ● Flexibility of dynamic LPAR, virtualization, on demand processing I ● Retains mainframe-inspired reliability, availability and serviceability (RAS) capabilities from the POWER 4+ product line ● Contains new POWER 5 RAS enhancements ● Outstanding value for the money for a UNIX® class server and runs both Linux® and UNIX ● Simple for the client to set up ● Easy to order and enhance through Value Pak Configurations 12 © 2004 IBM Corporation

IBM e. Server p. Series IBM ~ p 5 Leading-edge Entry Servers 2 -way p 5 -520 delivers 1. 9 x the performance of HP rx 2600 on SPEC OMPM 2001 4 -way p 5 -550 delivers 2. 8 x the performance of HP rx 5670 on SPECsfs 97 Jaw-dropping Performance IBM HP p 5 -550 I p 5 -520 rx 5670 rx 2600 HP IBM SPEComp SPECsfs **note: see www. spec. org as of 7/13/04 13 © 2004 IBM Corporation

IBM e. Server p. Series Incredible Value at the Low-end of POWER 5 Product Line…the p 5 -550 IBM p. Series server ● Continuing to refresh and replace IBM H C R U 6 server p. Series IBM with new technology I Added value Processor speed Memory Micro-Partitioning™* I/O drawers Internal disk Internal RAID Processor Cu. OD* p 5 -550 POWER 5 p 630 POWER 4+ 1. 65 GHz 64 GB up to 40 8 8 in split backplane optional yes 1. 2 or 1. 45 GHz 32 GB 4 LPARs 2 4 no no * Note: optional feature 14 © 2004 IBM Corporation

IBM e. Server p. Series p 5 -550 Target Opportunities Great as a standalone server for small / medium businesses, and as an extremely reliable member of a tiered e-infrastructure in large enterprises IBM server H C R U 6 server p. Series IBM I IBM p. Series server 15 © 2004 IBM Corporation

IBM e. Server p. Series Some of Many Applications Well Suited for the p 5 -550 IBM server IBM H C R U 6 server p. Series IBM server ● Departmental and regional servers I ● Starting point for server consolidation ● Scalable database servers ● Robust e-commerce applications ● ERP, CRM, SCM, BI ● Billing and operational systems 16 © 2004 IBM Corporation

IBM e. Server p. Series Financing Advantages* Continuing in the footsteps of the powerful, reliable line of IBM UNIX servers – the IBM ~ p 5 570 will provide a comprehensive mid-range position into the POWER 5 product line. Complementing this exciting value, IBM Global Financing can help make the difference. IBM Global Financing’s portfolio of offerings and services designed specifically I for small and medium businesses, feature streamlined applications, simplified contracts and fast approvals. LINK TO: http: //www-1. ibm. com/financing/it_products/hardware/servers/ p. Series. html Financing from IBM Global Financing can make acquiring complete multivendor IT solutions less expensive through competitive rates, fair market value leases, innovative offerings, and special financing promotions. Please visit our Web site for the latest on Special Promotions: LINK TO: http: //www-1. ibm. com/financing/promotions/index. html For AP and EMEA go to ibm. com/financing and “select a country” from the right navigation drop down list. 17 © 2004 IBM Corporation *Note: this is for North American clients only. Similar promotions may be available in other geographies

IBM e. Server p. Series IBM ~ p 5 550 Product. I Line Capabilities

IBM e. Server p. Series Product Transition Path to IBM ~ p 5 Servers 2 Q 2004 3 Q 2004 POWER 4+ POWER 5 TBD p 690 p 5 -570 16 -way p 670 I p 655 p 5 -570 12 -way p 5 -570 8 -way 19 p 650 p 5 -570 2 - or 4 -way p 630 p 5 -550 2 - or 4 -way p 615 p 5 -520 2 -way © 2004 IBM Corporation TBD

IBM e. Server p. Series Homogeneous Environment Across the Infrastructure to Help Lower TCO and Simplify Management High-end p. Series 690 IBM Operational consistency across all levels for the system administrator Mid-range Large database server IBM IBM p. Series 670 p. Series 650 p 5 -570 s Application servers, Web hosting Entry H C R U 6 IBM p 5 -550 s IBM server p 5 -520 IBM server H C R U 6 server p. Series IBM p 5 -520 Department servers, end-user applications © 2004 IBM Corporation

IBM e. Server p. Series POWER 4+ Technology Product Line IBM IBM p. Series server Binary compatibility from over $6 M … to under $6 K! Footprint, packaging 1, 2 24 -inch frames No. of SMPs GHz clock GB memory Int. storage PCI-X slots I/O drawers LPARs Max. r. Perf Cluster 1600 HACMP™ 8, 16, 24, 32 1. 5, 1. 7, 1. 9 8 to 1024 18. 7 TB 10 to 160 8 32 104. 17 Yes 21 1 24 -inch frame 4, 8, 16 1. 5 4 to 256 7. 0 TB 10 to 60 3 16 46. 79 Yes IBM p S e 19 -inch rack, r deskside i 1, 2, 4 e 1. 2, 1. 45 s 1 to 32 H C R U 6 server I 1, 2 24 -inch frames 4, 8 1. 7 4 to 64 2. 6 TB 3 to 23 1 4 21. 87 Yes 19 -inch rack 2, 4, 6, 8 1. 2, 1. 45 2 to 64 14. 5 TB 7 to 63 8 8 18. 67 Yes © 2004 IBM Corporation IBM 4. 1 TB 6 to 20 (6 C 4) 2 (6 C 4) 4 (6 C 4) 8. 69 Yes (6 C 4) Yes p S 19 -inch rack, e deskside r i 1, 2 1. 2, 1. 45 (2 -w) e 1 to 16 s 1. 1 TB IBM server H C R U 6 server p. Series IBM 6 N/A 4. 41 Yes (6 C 3) Yes

IBM e. Server p. Series POWER 5 Technology Product Evolution IBM p S e 19 -inch rack, r deskside i 2, 4 e 1. 65 s 1 to 64 H C R U 6 server Footprint, packaging 1, 2 24 -inch frames No. of SMPs GHz clock GB memory Int. storage* PCI-X slots* I/O Drawers LPARs Max. r. Perf Cluster 1600 HACMP 22 * Note: includes I/O drawer capacity; ** 2 -, 4 -, 8 -way only I 19 -inch rack 2, 4, 8, 12, 16 1. 5**, 1. 65, 1. 9 2 to 512 38. 7 TB 6 to 163 20 160 77. 45 Yes © 2004 IBM Corporation IBM 15. 2 TB 5 to 60 8 40 19. 66 Yes p S e rack, 19 -inch deskside r i 2 e 1 1. 65 to 32 s 8. 2 TB IBM server H C R U 6 server p. Series IBM 6 to 34 4 20 9. 86 Yes

IBM e. Server p. Series POWER 5 Reliability Across the Product Line IBM Mainframe-inspired RAS* Reliability, Availability and I Serviceability Functions IBM p p S S Online firmware updates** e e First Failure Data Capture r DDR ECC Chipkill memory r i Bit-steering/redundant memory i e Memory soft scrubbing e Redundant power, s fans s Dynamic Processor Deallocation H C R U 6 server IBM server H C R U 6 server p. Series *Note: Some RAS functions **Note: Planned for 4 Q 04 may not be available at the same time on SLES 9 and RHEL AS 3 Deallocate PCI-X bus, L 2/L 3 cache Persistent memory deallocation Hot-plug PCI-X slots, fans, power Internal LED diagnostics Hot-swappable disk drives 23 © 2004 IBM Corporation IBM

IBM e. Server p. Series IBM ~ Cluster 1600 Building Blocks* IBM High-end IBM Mid-range IBM p. Series server IBM p. Series 670 p. Series 690 t n e m e g a. 3 I p 5 -570 n a V 5 M s L 5 m te AIX s y or S r f e ) t 4 s. 1 u Cl M v S C ( p. Series 655 p. Series 650 IBM server H C R U 6 server p. Series IBM H C R U 6 IBM p 5 -550 p. Series 630 IBM server H C R U 6 server p. Series IBM p. Series 615 Entry 24 p 5 -520 Manages POWER™ servers and x. Series® servers from a single-point-ofcontrol. © 2004 IBM Corporation

IBM e. Server p. Series IBM ~ p 5 550 POWER 5 and I

IBM e. Server p. Series What’s New with the p 5 -550 Shared L 2 Distributed switch 27 Mem Ctl ● 1. 65 GHz 2 -way POWER 5 advanced technology processors 276 million transistors Small, dense chips (0. 13 microns) I 389 sq/mm die size 1. 65 GHz clock speed On-chip memory controller L 3 cache no longer in path to memory © 2004 IBM Corporation

IBM e. Server p. Series Model 550 Server Peak Bandwidth per 1. 65 GHz 2 -way Chip 26. 4 GB/sec x 2 = 52. 8 GB/sec for 4 -way For 2 -way chip 4 -way 12. 8 GB/sec x 2 = 25. 5 GB/sec for 4 -way M E M O R Y L 3 Shared L 2 Distributed switch Ctl I GX Bus on second processor card 4. 4 GB/sec (4 -way only) GX Bus 4. 4 GB/sec Four I/O Drawers 28 Five PCI-X slots I/O Hub 4 GB/sec 1 to 64 GB DDR 1 266 MHz 4 GB/sec 5 2 nd I/O Hub adapter 4 I/O Drawers 4 GB/sec I/O Hub adapter uses slot 5 real estate © 2004 IBM Corporation

IBM e. Server p. Series Standard Virtualization Capabilities 1 CPU 2 CPUs 4 CPUs Linux AIX 5 L V 5. 2 AIX 5 L V 5. 3 AIX 5 L V 5. 2 . . . I POWER Hypervisor ● Includes: - LPAR - Dynamic LPAR (AIX 5 L and SLES 9) - Virtual LAN 29 © 2004 IBM Corporation

IBM e. Server p. Series Advanced POWER Virtualization Option Partition Load Manager AIX 5 L v 5. 3 Virtual IP Virtual Disks AIX 5 L V 5. 3 AIX 5 L V 5. 2 Routing Disks Linux AIX 5 L V 5. 2 Hosting Partition pool of 20 Linux 4 CPUs AIX 5 L V 5. 3 2 CPUs I Virtual I/O Paths POWER Hypervisor I/O Storage Network LAN, WAN, . . . ● This feature includes: Feature no. - Micro-Partitioning - Shared processor pool - Hosting LPAR for Virtual I/O (disk and LAN) - Partition Load Manager for AIX 5 L LPARs 30 © 2004 IBM Corporation 7940 7941 7942 Server p 5 -520 p 5 -550 p 5 -570

IBM e. Server p. Series IBM POWER 5 – Designed for Productivity Efficient Utilization Helps to LOWER COST of COMPUTING POWER Hypervisor Dynamic Micro-Partitions* Shared Processor Pools* Virtual I/O Virtual LAN* Dynamic LPAR Capacity Upgrade on Demand* (select models) Simultaneous Multithreading I ●Allows the server to have more partitions than processors, in which processing resources can be finetuned with allocations as small as 1/10 th of a processor and increments of 1/100 th of a processor. *Note: optional feature 31 © 2004 IBM Corporation

IBM e. Server p. Series IBM POWER 5 – Designed for Productivity Efficient Utilization Helps to LOWER COST of COMPUTING POWER Hypervisor Dynamic Micro-Partitions* Shared Processor Pools* Virtual I/O Virtual LAN* Dynamic LPAR Capacity Upgrade on Demand* (select models) Simultaneous Multithreading) I ●Provides a pool of processing power that is shared between partitions helping to improve utilization and throughput. Also can be changed dynamically to suit ever-changing environments *Note: optional feature 32 © 2004 IBM Corporation

IBM e. Server p. Series IBM POWER 5 – Designed for Productivity Efficient Utilization Helps to LOWER COST of COMPUTING POWER Hypervisor Dynamic Micro-Partitions* Shared Processor Pools* Virtual I/O Virtual LAN* Dynamic LPAR** Capacity Upgrade on Demand* (select models) Simultaneous Multithreading I ●Helps administrators reallocate system resources between partitions and across operating systems, including processors, memory, and I/O without rebooting the partition or system for faster response to changing workload requirements *Note: optional feature 33 **Note: Not available on Linux RHEL AS 3 © 2004 IBM Corporation

IBM e. Server p. Series IBM POWER 5 – Designed for Productivity Efficient Utilization Helps to LOWER COST of COMPUTING POWER Hypervisor Dynamic Micro-Partitions* Shared Processor Pools* Virtual I/O Virtual LAN* Dynamic LPAR Capacity Upgrade on Demand* (select models) Simultaneous Multithreading I ●Supports physical sharing of disk drives, communications adapters, helping to reduce the number of expensive devices and improve system utilization and administration. ●Allows high-speed, secure partition-to-partition communications to help improve performance *Note: optional feature 34 © 2004 IBM Corporation

IBM e. Server p. Series IBM POWER 5 – Designed for Productivity Efficient Utilization Helps to LOWER COST of COMPUTING POWER Hypervisor Dynamic Micro-Partitions* Shared Processor Pools* Virtual I/O Virtual LAN* Dynamic LPAR Capacity Upgrade on Demand* (select models) Simultaneous Multithreading I ●Servers with these features may be reconfigured dynamically with additional processors or memory to respond quickly to changing application workloads. Helps clients pay for what they use when they use it. With Reserve Co. D the system can automatically adjust processing power for LPARs assigned to the shared processor pool. *Note: optional feature 35 © 2004 IBM Corporation

IBM e. Server p. Series IBM POWER 5 – Designed for Productivity Efficient Utilization Helps to LOWER COST of COMPUTING POWER Hypervisor Dynamic Micro-Partitions* Shared Processor Pools* Virtual I/O Virtual LAN* Dynamic LPAR Capacity Upgrade on Demand* (select models) Simultaneous Multithreading I ●Simultaneous multi-threading technology allows latency times of one thread of instructions to be utilized by another totally independent thread of instructions, resulting in improved system throughput. Each processor looks like two to the system. Performance can be up to 30%** faster than same speed systems without simultaneous multithreading. *Note: optional feature; ** Based on IBM relative performance (r. Perf) projections 36 © 2004 IBM Corporation

IBM e. Server p. Series POWER 5 Micro-Partitioning for p 5 -550 Increases System Productivity POWER 4+ POWER 5 SMP virtualization with Micro-Partitioning: SMP partitioning: One partition per CPU Multiple partitions activated in each CPU I CPU 0 CPU 2 Dedicated, Under-utilized Resources 37 CPU 1 CPU 3 Up to 40 Micro-Partitions in a 4 -way SMP 1 to 4 partitions in a 4 -way SMP © 2004 IBM Corporation

IBM e. Server p. Series POWER 5 Virtualization POWER 4+ AIX 5 L V 5. 3 and Linux Simplification through virtualization ● Micro-Partitioning* ● Shared processor pools* AIX 5 L V 5. 2 Flexibility Dynamic LPAR § Move resources between partitions Capacity on Demand ● Dynamic LPAR ● Virtual I/O*, LAN ● Partition Load Manager* Reduced resources ● Fewer processors and I/O adapters Helps to increase overall server throughput I AIX 5 L V 5. 2 2 CPUs 4 CPUs Linux 4 CPUs AIX 5 L V 5. 2 V 5. 1 Disks 2 CPUs 4 CPUs AIX 5 L V 5. 2 V 5. 3 Routing Virtual I/O Paths Hypervisor POWER Hypervisor Storage I/O Network * Note: optional feature 38 AIX 5 L V 5. 2 pool of 20 AIX 5 L V 5. 3 Linux AIX 5 L V 5. 3 8 CPUs 2 CPUs Hosting Partition AIX 5 L v 5. 3 Virtual IP Virtual Disks © 2004 IBM Corporation LAN, WAN, . . .

IBM e. Server p. Series Partition Load Manager* ● Policy-based, automatic partition resource tuning ● Can dynamically adjust CPU and memory allocations ● Supports AIX 5 L V 5. 3/V 5. 2 partitions ● p 5 -520, p 5 -550, and p 5 -570 systems Before resource tuning CPU Unbalanced resource allocation CPU Adjust resource allocation based on business priorities CPU After tuning CPU I Test LPAR CRM LPAR Finance LPAR Test LPAR Finance LPAR 3 CPU 5 CPU 6 CPU 1 CPU 3 CPU 10 CPU Agent Agent * Note: optional feature 39 CRM LPAR © 2004 IBM Corporation

IBM e. Server p. Series POWER 5 Simultaneous Multi-threading POWER 5 (Simultaneous Multi-threaded) Execution units utilization POWER 4+ (Single Threaded) ● Utilizes unused execution System throughput FX 0 FX 1 LS 0 LS 1 FP 0 FP 1 BRX CRL I SMT ST unit cycles ● Presents SMP programming model to software ● Natural fit with superscalar out-of-order execution core ● Higher performance Net result: Higher system throughput FX 0 FX 1 LS 0 LS 1 FP 0 FP 1 BRX CRL Legend Thread 0 active No Thread active Thread 1 active Execution units utilization 40 © 2004 IBM Corporation

IBM e. Server p. Series IBM ~ p 5 550 Operating. I System Options

IBM e. Server p. Series POWER 5 transitions on AIX 5 L V 5. 2 and V 5. 3 AIX 5 L V 5. 2 AIX 5 L V 5. 3 POWER 5 Hardware POWER 5 RAS functions I Simultaneous Multi-threading Dynamic LPAR Advanced POWER Virtualization Partition Load Manager - Micro-Partitioning - Shared processor pool - Virtual I/O New on demand capabilities 42 © 2004 IBM Corporation

IBM e. Server p. Series AIX 5 L Software Delivers ƒ Robust, scalable UNIX platform for critical applications ƒ Strong affinity with Linux for flexible solutions that fit your business ƒ Connections needed for e-business and network computing I ƒ Security you can count on ƒ Systems and network management that puts you in control ƒ Open and industry standards-based platform that offers freedom of choice ƒ Service and support to help keep a business running 43 © 2004 IBM Corporation

IBM e. Server p. Series Linux on POWER* ● Enterprise Class Computing with Linux and POWER 5 ● Flexibility with LPAR, DLPAR, and virtualization features ● Reliability with built in self healing capabilities ● Scalability from 2 -way up to 16 -way systems ● Linux distributions available for IBM ~ p 5 are: - SUSE LINUX Enterprise Server 9 for POWER (SLES 9) - Red Hat Enterprise Linux AS 3 for POWER (RHEL AS 3) I ● SUSE LINUX and Red Hat, Inc. also provide support, upgrades and maintenance. Technical support is also available through IBM Support. Line contract. ● Linux on p. Series remains orderable from IBM or directly from Linux distributors ● For more information about Linux running on IBM ~ p 5 or p. Series systems: http: //www. ibm. com/servers/eserver/pseries/linux http: //www. redhat. com/software/rhel/as/ http: //www. suse. com/us/business/products/server/sles/i_pseries. html • Note, many of the features described in this document are operating system dependent and may not be available in Linux. For more information, please check: www. ibm. com/servers/eserver/pseries/linux/whitepapers/linux_pseries. html. 44 © 2004 IBM Corporation

IBM e. Server p. Series IBM ~ p 5 550 Product I Description 45

IBM e. Server p. Series Deskside and Rack Packaging Deskside PACKAGING CHOICE 19" drawer IBM server H C R U 6 server p. Series IBM I 9113 -550 ● Same flexible server available in two packaging options ● Internal structure the same except for operator panel location 46 © 2004 IBM Corporation

IBM e. Server p. Series Internal Structure of p 5 -550 Two 4 -packs Ultra 320 (first standard, second optional) Hot-swappable 10 K rpm disks with 36. 4 GB, 73. 4 GB or 146. 8 GB disks and hot-swappable 15 K rpm disks with 36. 4 GB or 73. 4 GB capacities Maximum internal storage of 1. 17 TB (dual SCSI backplanes) Standard 19 -inch rack 4 U high One half-high bay for VXA tape drive or 4, 8 mm tape H C R U 6 server p. Series I Two slimline bays for DVD-RAM, DVD-ROM IBM Op-panel Front bezel 47 © 2004 IBM Corporation

IBM e. Server p. Series Internal Structure of p 5 -550 Rack Five hot-plug PCI-X slots: Four long 64 -bit 133 MHz 3. 3 v One short 64 -bit 133 MHz 3. 3 v Hot-plug fan Two processor and memory books, each with two 1. 65 GHz processors, and up to 32 GB of DDR 1 memory. Maximum of 4 -way and 64 GB of memory. I Hot-plug fans Optional RAID daughter card fits here Hot-plug power supplies (one redundant – optional) server p. Series Planar board Two 4 -packs (separate backplanes) hot-swappable Ultra 320 SCSI disks 1 st four-pack standard 48 Op-panel RJ-45 connector Three media bays Two slimline, one standard © 2004 IBM Corporation

IBM e. Server p. Series Front View of p 5 -550 Deskside Model (cover open) Op-panel Three media bays Two slimline One half-high I Hot-swappable 10 K rpm disks Two 4 -packs 36. 4 GB, 73. 4 GB or 146. 8 GB disks hot-swappable Maximum internal storage of 1. 17 TB. and optional 15 K rpm disks with 36. 4 GB or 73. 4 GB capacities (dual SCSI backplanes) Ultra 320 SCSI disks 1 st four-pack standard, second optional 49 © 2004 IBM Corporation

IBM e. Server p. Series Rear View of p 5 -550 Rack IBM server H C R U 6 server p. Series IBM Two hot-plug AC power supplies with dual isolated line cords Two serial ports available if the HMC option is not chosen Blower for processors and memory Rack indicator light port I 1 2 3 4 5 S 1 S 2 Five hot-plug PCI-X slots: Four long 64 -bit 133 MHz 3. 3 v Slot #5 is short 64 -bit 133 MHz 3. 3 v Two USB 2. 0 Two 10/1000 ports Mbps Ethernet ports Two RIO-2 ports standard. Two additional RIO-2 ports Two Hardware Management optionally available via the Dual Port I/O Hub Adapter Console ports (HMC) (not PCI-X) that preempts slot number 5 allowing up to four additional I/O drawers (4 -way only) Two SPCN ports 50 © 2004 IBM Corporation

IBM e. Server p. Series Rear View of p 5 -550 Deskside S 1 S 2 Two serial ports* Two hot-plug AC power supplies (One standard and one optional) with dual isolated line cords Two SPCN ports IBM Two HMC ports Two USB 2. 0 ports p. Series 0001/01 ow. T tenreht. E spb. M strop I Blower for processors Two RIO-2 ports Rack Indicator light port 1 server Five PCI-X slots: 64 -bit 133 MHz 3. 3 v Slots 1 -4 are long, slot 5 is short si noitpo CMH eht f. I : eto. N* strop laires owt eht , nesohc. elbaliava eb ton lliw 15 2 3 4 5 © 2004 IBM Corporation

IBM e. Server p. Series p 5 -550 Optional RIO-2 I/O Drawer - 7311 -D 20 Ultra 320 SCSI speed (Up to eight supported*) Front Six-pack of hot-swappable disks; 36. 4, 73. 4 or 146. 8 GB Op panel Six-pack of hot-swappable disks; 36. 4, 73. 4 or 146. 8 GB I Rear Two hot-plug power supplies and fans. The second is optional and redundant 110/220 v AC Seven PCI-X 64 -bit 133 MHz 3. 3 v hot-plug slots not used SPCN Rack indicator light port RIO-2 ports *Note: Slot #5 of the Model 550 preempted if using more than four I/O drawers (4 -way only) 52 © 2004 IBM Corporation

IBM e. Server p. Series p 5 -550 1. 65 GHz Processors Slot # 1 Book #2 Book #1 Mem Ctl Slot Mem Ctl Shared L 2 Distributed switch server p. Series Distributed switch I Connector to backplane Slot Slot Slot #1 Slot #2 #3 #Slot 4 #2 #3 #4 #5 Slot # 6 Slot # 7 #5 Slot # 8 #6 #7 #8 Connector to backplane ● Processor cards protected by sturdy book packaging ● Books each have two POWER 5 64 -bit processors for a 4 -way maximum ● Processors have 1. 9 MB L 2 ECC shared cache and 36 MB L 3 ECC cache ● Separate service processor directs RAS activities on server and is located on planar board ● Eight memory DIMMs are included on each card ● On demand processors for peak workloads 53 © 2004 IBM Corporation

IBM e. Server p. Series p 5 -550 Capacity Upgrade on Demand - Processors Slot # 1 Book #2 Shared L 2 Distributed switch Mem Ctl Book #1 Mem Ctl Slot Distributed switch Shared L 2 Distributed switch server p. Series Connector to backplane I Slot Slot Slot #1 Slot #2 #3 #Slot 4 #5 Slot # 6 Slot # 7 #5 Slot # 8 #6 #7 #8 Connector to backplane ● On demand processors available to order for peak workloads - Minimum of two processors and two activations required - A four processor system may be ordered with two activations, providing a reserve of two processors for use at peak workloads ● Dynamic Processor Sparing - Inactive processors may be activated if a processor is deallocated 54 © 2004 IBM Corporation #2 #3 #4

IBM e. Server p. Series p 5 -550 Memory Quad Positioning ● Main memory ranges from 1 GB to 64 GB ECC DDR 1 SDRAM. ● Memory is configured in two quads on each processor card (4 total), and is pre-balanced by design for optimal performance with each quad split between two synchronous memory interface (SMI) controllers. ● Plan ahead to reach desired maximum memory to avoid discarding memory. I 1 GB quad = 4 X 256 MB DIMMs 2 GB quad = 4 X 512 MB DIMMs 4 GB quad = 4 X 1 GB DIMMs 8 GB quad = 4 X 2 GB DIMMs 16 GB quad = 4 X 4 GB DIMMs Shared L 2 Distributed switch SMI Quad 1 Quad 2 55 © 2004 IBM Corporation Mem Ctl SMI

IBM e. Server p. Series p 5 -550 DDR 1 ECC Chipkill Memory Book #2 (4 -way) Book #2 Slot # 1 Book #1 Mem Ctl Slot Mem Ctl Shared L 2 Distributed switch server Distributed switch p. Series Connector to backplane 56 I Connector to backplane Slot Slot Slot #1 Slot #2 #3 #Slot 4 #2 #3 #4 #5 Slot # 6 Slot # 7 #5 Slot # 8 #6 #7 #8 Book #1 (2 -way) ● Memory options of 1 GB, 2 GB, 4 GB, 8 GB, 16 GB, 32 GB, or 64 GB. Additional granularity is available between binary sizes, e. g. 3 GB, 6 GB, 10 GB, 12 GB, etc. ● Eight memory DIMMs plug into slots on each processor book ● DIMMs are installed in quads (four quads per server) ● Memory should be balanced between the two processor books for best performance ● RAS features include ECC, Chipkill, bit steering to redundant memory bits, and soft error scrubbing ● DIMM sizes are: 256 MB, 512 MB, 1 GB, 2 GB or 4 GB DDR 1 © 2004 IBM Corporation

IBM e. Server p. Series 2 -way p 5 -550 Memory DIMM Positioning Slot # 1 This set of examples is for a 2 -way which can have a memory range of 1 GB to 32 GB using one book Shared L 2 Slot # 3 Slot # 4 Shared L 2 Distributed switch 1 GB Book #1 2 GB Book #1 Slot #5 #6 #7 #8 Book #1 (2 -way) I 4 GB Book #1 8 GB Book #1 DIMM Sizes 4 GB 16 GB Book #1 32 GB Book #1 1 GB 512 MB 256 MB 57 © 2004 IBM Corporation

IBM e. Server p. Series 4 -way p 5 -550 Memory DIMM Positioning Book #2 (4 -way) For a 4 -way, memory should be balanced between both processor books for best performance. Slot # 1 Slot Mem Ctl Slot Mem Ctl Shared L 2 Distributed switch 2 GB Book #1 Shared L 2 Distributed switch Book #2 Distributed switch Slot Connector to backplane I 4 GB Book #1 Connector to backplane Book #1 #2 #3 #4 #5 Slot # 6 Slot # 7 #5 Slot # 8 #6 #7 #8 Book #1 (2 -way) Book #2 32 GB 8 GB Slot #1 Slot #2 #3 #Slot 4 Book #1 Book #2 DIMM Sizes 4 GB 2 GB 16 GB 64 GB Book #1 Book #2 1 GB 512 MB 256 MB 58 © 2004 IBM Corporation

IBM e. Server p. Series Planning Ahead for Proper Memory Management Slot # 1 Slot Slot #1 Slot #2 #3 #Slot 4 Slot Slot #5 Slot #6 #7 #8 Mem Ctl Slot Mem Ctl Shared L 2 Distributed switch Connector to backplane #2 #3 #4 #5 #6 #7 #8 Books #1 and #2 (4 -way) I ● Plan ahead to avoid memory discarding when upgrading: - Determine where maximum desired memory will be, and work backwards to determine proper starting point - If eventually growing to 64 GB, start with a 16 GB quad 2 -way server, since it takes all DIMM positions on a 4 -way to make 64 GB - If starting with a 4 -way server and performance is critical, then place a 16 GB quad in each processor book ● Memory balancing is an important consideration for a 4 -way server - Better performance is achieved by balancing the quads between the two processor books (highly application dependent) 59 © 2004 IBM Corporation

IBM e. Server p. Series p 5 -550 r. Performance Measurements Measured using AIX 5 L V 5. 3 IBM p. Series 1. 65 GHz processors r. Perf 2 -way = 9. 86 r. Perf 4 -way = 19. 66 I server IBM server H C R U 6 server p. Series IBM 60 © 2004 IBM Corporation

IBM e. Server p. Series Hardware Management Console (HMC) Redundant HMC option IBM server H C R U 6 Ethernet server p. Series I Ÿ System control software - Focal point for virtualization management - Cluster control point - Controls multiple non-clustered servers (dependent on server type and mixture) 61 © 2004 IBM Corporation IBM

IBM e. Server p. Series Ten p 5 -550 systems in T 42 Rack Enclosure p 5 -550 installs in T 00, T 42 and other 19 -inch non-IBM racks server HCR server U 6 62 4 U model 550 s IBM 42 U IBM p. Series IBM server HCR server U 6 p. Series server HCR server U 6 p. Series IBM IBM IBM © 2004 IBM Corporation

IBM e. Server p. Series IBM 7316 -TF 3 Flat Panel Display Console Ÿ Rack-mounted flat panel console consisting of: - IBM Flat Panel Color Monitor - Flat Panel Monitor Rack-mounted Kit - Rack Keyboard Tray - IBM Space Saver 2 Keyboard which mounts in Rack Keyboard Tray (Track. Point® mouse is integral to keyboard) I - Fits into a standard 19" rack with only 1 U space - Supported via GXT 135 P graphics adapter - VGA switch supports up to eight systems - Cascade eight switches to support a total of 64 systems 7 foot, 12 foot or 20 foot cable features 63 © 2004 IBM Corporation server HC server R U 6 p. Series IB M

IBM e. Server p. Series Total. Storage Networks and Attachments I Total. Storage® Products

IBM e. Server p. Series IBM Total. Storage and Tivoli Ready to Go Disk Storage IBM Tape Storage LTO, Enterprise, External IBM ESS, FASt. T, NAS p. Series IBM server p 690 I p 655 HCR U 6 IBM server HCR U 6 server IBM p. Series IBM p 5 -570 p 5 -550 p 5 -520 SAN Switch Storage Virtualization IBM, Mc. DATA, CNT, Cisco Tivoli® Storage Software 65 © 2004 IBM Corporation

IBM e. Server p. Series IBM Total. Storage Ready to Go AIX 5 L V 5. 2/V 5. 3 and Linux FASt. T ESS IBM FASt. T 100 FASt. T 200 FASt. T 500 FASt. T 600 Turbo FASt. T 700 FASt. T 900 Data p. Series IBM server p 690 I HCR U 6 IBM server HCR U 6 server IBM p. Series IBM p 5 -550 ESS 750 ESS 800 p 655 p 5 -570 p 5 -520 SAN Integration Server Retention IBM NAS SCSI/SSA H C R U 6 IBM DR 450 66 2104 -SCSI 7133 -SSA Gateway 500 2146 © 2004 IBM Corporation

IBM e. Server p. Series IBM Total. Storage Area Network Ready to Go AIX 5 L V 5. 2/V 5. 3 and Linux CNT (Inrange) IBM FC 9000 - 64 Director FC 9000 - 128 Director FC 9000 - 256 Director IBM p. Series IBM M 12 & M 14 Director F 08 & F 16 SAN Switch F 32 SAN Switch H 08 & H 16 SAN Switch Mc. DATA p 690 I p 655 HCR U 6 IBM server HCR U 6 server IBM p. Series IBM p 5 -550 p 5 -570 p 5 -520 6064 & 6140 Director 2031 & 3232 SAN Switch 4300 & 4500 SAN Switch FC-512 Fibre. Center 67 server Cisco MDS 9506 & 9509 Director MDS 9120 & 9140 SAN Switch MDS 9216 SAN Switch © 2004 IBM Corporation

IBM e. Server p. Series IBM Total. Storage Tape Ready to Go AIX 5 L V 5. 2/V 5. 3 and Linux IBM LTO Enterprise IBM p. Series IBM 3580 Bridge box 3581 Autoloader 3582 Library 3583 Library 3584 Library server p 690 I p 655 HCR U 6 IBM server HCR U 6 server p 5 -550 IBM p. Series IBM p 5 -570 p 5 -520 External Tape DDS, DAT 72, VXA-2 8 mm, DLT, SLR 68 © 2004 IBM Corporation 3592 Drive 3590 drive 3494 Library 3494 VTS

IBM e. Server p. Series IBM Total. Storage and Tivoli Software Ready to Go AIX 5 L V 5. 2/V 5. 3 and Linux IBM Total. Storage SAN Volume Controller Tivoli Storage Manager IBM p. Series IBM server p 690 I p 655 HCR U 6 IBM Total. Storage SAN Volume Controller Blade for Cisco MDS 9000 server HCR U 6 server IBM p. Series IBM p 5 -550 p 5 -520 Total. Storage SAN File System 69 p 5 -570 Tivoli SANergy © 2004 IBM Corporation Tivoli Resource Manager Tivoli SAN Manager

IBM e. Server p. Series Input/Output and Network Requirements I I/O and Network Products

IBM e. Server p. Series IBM Networking and I/O Ready to Go Networking Storage Ethernet, Token-Ring ATM, WAN Fibre Channel, SCSI RAID, SSA IBM p. Series IBM Channels server p 690 I ESCON, Hi. PPi HCR U 6 IBM server HCR U 6 server p 5 -550 IBM p. Series IBM p 655 p 5 -570 Direct Talk p 5 -520 Optical Media DVD ROM, RAM & Tape DASD 10 K and 15 K rpm 71 Async © 2004 IBM Corporation Encryption

IBM e. Server p. Series IBM Networking and I/O Ready to Go AIX 5 L V 5. 2/V 5. 3 and Linux Networking Ethernet 10/100 Ethernet Quad Port 10/100 Gigabit Ethernet (Gig. E) Dual port Gig. E 10 Gig. E* Token-Ring WAN 2 Port 4 Port IBM p. Series IBM server p 690 I HCR U 6 IBM server HCR U 6 server IBM p. Series IBM p 5 -550 p 655 p 5 -570 Async 8 Port 128 Port Direct Talk Optical Media DVD ROM DVD RAM DDS 4 Tape VXA 2 Tape 8 mm Tape DAT 72* Tape DTXA-2 DASD 10 K Ultra 320 SCSI 36, 73 and 146 GB 15 K Ultra 320 SCSI 36 GB and 73 GB Encryption FIPS 4 Coprocessor SSL accelerator *Note: new adapters 72 2 GB FCAL Dual Port Ultra 320 SCSI Dual Port U 320 SCSI RAID SSA p 5 -520 Channels ESCON Hi. PPi Storage adapters © 2004 IBM Corporation

IBM e. Server p. Series I/O Adapter Enhancements 10 Gigabit Ethernet-SR PCI-X Adapter Provides connection on standard shortwave multimode optical cable. -Distances up to 33 m using 62. 5 um multimode fiber -Distances up to 66 m with 50 um I multimode fiber DAT 72 4 mm 36/72 GB tape Provides higher capacity 4 mm tape storage 73 © 2004 IBM Corporation

IBM e. Server p. Series IBM ~ p 5 550 Reliability I Availability and

IBM e. Server p. Series Reliability Availability Serviceability (RAS) Online updating Keep thefirmware system operational! Online parts replacement Utilize system redundancies I Deallocate system resources if necessary Resolve intermittent faults with no intervention Diagnose failures if they happen Fault avoidance - designed to avoid downtime 75 © 2004 IBM Corporation

IBM e. Server p. Series Reliability Availability Serviceability* RAS enhancements available on POWER 5 servers ● Applications remain operational while IBM system firmware is updated for most operations (planned for 4 Q 04) ● ECC has been extended to. I inter-chip connections for the Fabric/processor busses (data, address, control) ● Partial L 2 cache deallocation ● L 3 cache line deletes improved from two to ten for better self-healing capability *Note: some RAS functions may not be available at the same time on Linux SLES 9 and RHEL 3. 3 76 © 2004 IBM Corporation

IBM e. Server p. Series A Self-diagnosing Server ● First Failure Data Capture is key to a self-diagnosing system and is an IBM exclusive! ● Critical parts of system can provide real-time machine status information if faults occur ● Error data is continually being monitored by system I in order to take appropriate actions ● Many errors can be self-corrected or functions varied offline while server remains available ● Server has capability to determine which part or component needs repair and can phone IBM Service to provide precise parts for maintenance at a time acceptable to client 77 © 2004 IBM Corporation

IBM e. Server p. Series Reliability Availability Serviceability 24 x 7 lt Fau ng ki s a M lt Fau nce ida o v A rce u o Res tion a c I llo Dea t ren r u c e Con enanc nt i a M vice r e S ure l i a t. F Firs a Dat ture p a C 78 ivity t c du o r P Self ling a e H © 2004 IBM Corporation N+1 ancy und d e R

IBM e. Server p. Series Capture Error Causes in Real-time lure i a t. F Firs a Dat ture Cap Cornerstone that is basis of p. Series RAS technology ● First Failure Data Capture provides error information in real-time and makes I it possible to determine parts necessary to fix problem ● Trying to recreate intermittent errors at a later time can be extremely time consuming, ineffective, and sometimes impossible 79 © 2004 IBM Corporation

IBM e. Server p. Series First Failure Data Capture Technology l Old Failure Recreate Strategy Error Checkers CPU L 1 Cache L 2/L 3 Cache –Run diagnostic test cases during service call Fault Isolation Register (FIR) –Repair based on test case symptom (unique fingerprint of each –Questionable correlation to original problem error captured) –Development focus on improved test cases –Open service action plan if failure not recreated –Test cases used to try to isolate failures and verify Service correct operation Processor Log Error Memory Nonvolatile RAM Disk Reliably identify each failing component, reducing costly downtime 80 I l. First Failure Data Capture: an IBM Exclusive –Specialized hardware designed to capture failure data at time of failure –Repair based on root-cause analysis –Direct correlation to original client problem –Engineering focus on built-in error detection and capture –Service action plan driven by captured failure information –Test cases used to only to verify correct operation © 2004 IBM Corporation

IBM e. Server p. Series Start Off With Quality-based Design lt Fau nce ida o v A Designing extra quality into system to keep errors from ever happening I ● Mainframe-inspired components and technologies - Designed for reduced power consumption, cooler operating temperatures and increased reliability 81 © 2004 IBM Corporation

IBM e. Server p. Series An Active Server Immune System f. Sel g lin a e H ● Bit-steering to redundant memory in event of failed memory module to keep server operational I ● Single bit error correction via ECC without reaching error thresholds for main, L 2 and L 3 cache memories ● L 3 cache line deletes extended from two to ten for additional self healing ● ECC extended to inter-chip connections on fabric/processor busses ● Soft-error scrubbing to help prevent memory faults 82 © 2004 IBM Corporation

IBM e. Server p. Series ECC Memory Integrity and Availability Memory scrubbing for soft singlebit errors that are corrected in the background while memory is idle, to help prevent multiple-bit errors. Dynamically reassign memory I/O Failing memory bit steered via bit-steering if error threshold to spare memory bit is reached on same bit Chipkill X X . . Spare memory bits I Scatter memory chip bits across four separate ECC words for Chipkill recovery ŸBit-scattering allows normal single bit ECC error processing, thereby keeping system running with a Chipkill failure. ŸBit-steering allows memory lines from spare memory bits to be dynamically reassigned to a memory module with a faulty line to keep system running. ŸIf all spare bits are utilized, and threshold is reached, the Service Processor will be invoked to request deferred maintenance at a time acceptable to client. 83 © 2004 IBM Corporation

IBM e. Server p. Series Built-in Redundancies Designed for Non-stop Operation N+1 ancy nd u d Re Use of redundancy to remain operational with full resources I ● Redundant spare memory bits ● Redundant fans - Fans will speed up to try to compensate for failed fan ● Redundant power supplies (optional) 84 © 2004 IBM Corporation

IBM e. Server p. Series Continued Operation and System Integrity lt Fau ing sk Ma Corrections and retries that don't exceed threshold limits and don't require client or IBM CE intervention I ● CEC bus retry and recovery ● PCI-X bus recovery ● ECC Chipkill soft errors 85 © 2004 IBM Corporation

IBM e. Server p. Series Keep Running With Fewer Resources rce u o Res tion a c llo Dea If threshold reached, resources can be deallocated with system remaining operational, allowing client to plan maintenance at a convenient time I ● Partial L 2 cache deallocation ● PCI-X bus deallocation to the card level ● Removal and replacement of failed PCI-X cards ● Upon reboot, failed components will be deconfigured to avoid repeat of errors 86 © 2004 IBM Corporation

IBM e. Server p. Series PCI Bus and Card Error Recoveries PCI-X Controller X I ● Problem with damaged connection results in PCI-X bus error - That particular slot is varied offline by system - All other slots remain active - System stays operational without the slot active - If PCI card is damaged, replace with new one - If slot is damaged, plan for maintenance at client’s convenience 87 © 2004 IBM Corporation

IBM e. Server p. Series Replacement of Parts While System Runs nt e r r cu e Con enanc nt i a M Online hot-plug of defective electromechanical components keeps system operational ● Disk drives I ● Cooling fans ● Power subsystems ● PCI, PCI-X adapter cards 88 © 2004 IBM Corporation

IBM e. Server p. Series Quicker Service for Client Convenience vice r e S y tivit c u d Pro Increasing service productivity means more client uptime I ● Most firmware updates may be made while the server remains operational (planned for 4 Q 04) ● Internal LED diagnostics identify components that require service ● LEDs on I/O provide status of PCI-X slots and disk drives for power, hot-swap and need for service 89 © 2004 IBM Corporation

IBM e. Server p. Series Health Care of p 5 -550 System Service Processor Drawer performance. H C R U 6 AIX 5 L device drivers provide error information to. I AIX 5 L error log Mo server p. Series IBM rts Input/Output IBM server po nit o Hot Standby Backup In unlikely event of a unresolvable system fault, system can be backed up by another hot-standby system 90 Re Service Focal Point po AIX Error Log Central repository for all system errors Runs asynchronously. Cycles continuously Does not degrade looking for faults rs Re Processors Memory Power Thermal Fans AIX 5 L Service Agent Sends latest error information to CE and/or client when necessary High Availability software: HACMP HAGEO, Geo. RM © 2004 IBM Corporation Service Dispatch Initiates maintenance action with parts required to fix real problem

IBM e. Server p. Series IBM ~ p 5 550 Convenient Starting Points. I

IBM e. Server p. Series IBM ~ Model 550 Value Pak Configurations IBM p. Serie s IBM server H C R U 6 server p. Series IBM Model 550 serv er Model 550 I ŸOffering easy-to-order configurations at considerable savings ŸChoice of Linux, AIX 5 L or no operating system ŸAllows clients to modify these base configurations to match up with specific application requirements 92 © 2004 IBM Corporation

IBM e. Server p. Series Model 550 Value Pak Configurations server IBM H C R U 6 l l p 5 -550 (1. 65 GHz) Two processors, one no-charge activation, 4 GB memory, two 73. 4 GB disks p 5 -550 (1. 65 GHz) Four processors, two no-charge activations, 8 GB memory, two 73. 4 GB disks server p. Series IBM Model 550 I IBM p. Series serve r Model 550 93 © 2004 IBM Corporation