Microsoft SharePoint data management solution using IBM Spectrum Scale for object storage and AvePoint DocAve A technical report Udayasuryan Kodoly IBM Systems ISV Enablement July 2015 Copyright IBM Corporation, 2015
Table of contents Abstract... 1 Executive summary... 1 Scope... 2 Intended audience... 2 Prerequisites... 2 Solution components... 3 IBM Spectrum Scale for object storage... 3 AvePoint DocAve Storage Manager... 4 DocAve architecture... 5 Solution architecture... 6 BLOB externalization to the IBM Spectrum Scale for object storage... 7 DocAve installation and configuration... 7 SharePoint document and metadata storage... 7 Configuring IBM Spectrum Scale for object storage... 8 IBM Spectrum Scale for object storage configuration example... 8 Enabling Identity API v2.0... 9 Preparing DocAve Storage Manager for configuring IBM Spectrum Scale for object storage... 10 IBM Spectrum Scale for object storage configuration for BLOB externalization with DocAve Storage Manager... 11 Storage policy... 15 Enabling the BLOB Provider... 17 Running scheduled DocAve Storage Manager jobs with the IBM Spectrum Scale for object storage logical device... 21 Storage report... 23 Summary... 24 Appendix A: Resources... 25 About the author... 25 Trademarks and special notices... 26
Abstract This technical paper illustrates the essential solution, technology integration, and configuration best practices details about building an extremely scalable enterprise-class infrastructure to protect and manage Microsoft SharePoint deployments using IBM Spectrum Scale for object storage and AvePoint DocAve software. Executive summary Microsoft SharePoint is a strategic business platform that allows people to connect seamlessly with each other in terms of centralized content management. Furthermore, as a collaborative tool, SharePoint can be used by anyone, and can be installed and configured quickly. As SharePoint adoption has increased in many enterprises, so has the complexity of many SharePoint deployments. SharePoint is now considered as a platform delivering business-critical services to organization using web portals and extranets, Enterprise Content Management (ECM), workflow, search, and enterprise social networking. With more and more data being stored in SharePoint, enterprises need storage infrastructure to be able to ensure 24x7availability while keeping up with growing storage requirements. Scaling users and storage in addition to changing or upgrading the hardware or software can interrupt business operations, reducing the availability of critical SharePoint data. Managing and protecting SharePoint data can also be time consuming and complex, significantly increasing administration workload. For enterprise IT managers and SharePoint administrators, this development poses of the following challenges: Cost-effectively meeting service level agreements (SLAs) based on increasing business requirements Managing storage and performance for rapidly growing SharePoint server farms Seamlessly scaling SharePoint deployments to manage large data files and more users Protecting SharePoint data efficiently Meeting archive, compliance, and governance requirements To properly address these challenges, enterprises requires a complete infrastructure solution that is proven, on storing and managing large amount of growing SharePoint data more efficiently and cost effectively, while providing extreme availability and optimum performance. The joint solution of IBM Spectrum Scale for object storage and Ave Point DocAve provides powerful combination of manageability, efficiency, data protection, and scalability for SharePoint ECM workloads. As SharePoint 2010 and SharePoint 2013 on-premises become the central repository for enterprise content within organizations, increasing user adoption and integration from data sources can cause unstructured data and binary large object (BLOB) content to consume up to 95 percent of SharePoint SQL Server space. Larger BLOB content can lead to database performance and user experience degradation. The AvePoint DocAve software seamlessly externalizes and store unstructured BLOBs to IBM Spectrum Scale for object storage storage outside of SQL Server, thereby reducing SQL database size. The IBM Spectrum Scale for object storage combines the benefits of IBM Spectrum Scale storage system with the most widely used open source object store today, OpenStack Swift. IBM Spectrum Scale is an agile 1
storage infrastructure that can readily and cost effectively scale to keep pace with the evolving needs of the enterprises. Scope This technical report: Discusses the solution architecture, vital solution configuration, and the related solution configuration workflows with AvePoint DocAve version 6.5 and IBM Spectrum Scale for object storage. This technical report does not: Discuss the installation and basic configuration of Microsoft SharePoint Server. Discuss the installation and basic configuration of AvePoint DocAve version 6.5. Discuss the installation and basic configuration of IBM Spectrum Scale. Replace any already available document that is related to AvePoint DocAve, and IBM Spectrum Scale storage system. Intended audience This technical report is intended for: Users and management seeking information to implement solution for Microsoft SharePoint deployment using AvePoint DocAve and IBM Spectrum Scale for object storage. Prerequisites This technical paper assumes familiarity with the following prerequisites: Basic knowledge of Microsoft SharePoint 2013 Basic knowledge of AvePoint DocAve version 6.5 Basic knowledge of IBM Spectrum Scale for object storage system 2
Solution components This section briefly describes the essential components used in this solution. IBM Spectrum Scale for object storage IBM Spectrum Scale is a proven, scalable, high-performance data and file management solution. IBM Spectrum Scale provides world-class storage management with extreme scalability, flash accelerated performance, and automatic policy-based storage tiering from flash through disk to tape. IBM Spectrum Scale reduces storage costs up to 90% while improving security and management efficiency in cloud, big data, and analytics environments. IBM Spectrum Scale includes a highly differentiated value: Virtually limitless scaling to 9 quintillion files and yottabytes of data High performance - over 400 GBps - and simultaneous access to a common set of shared data Software-defined storage enables you to build your infrastructure your way Easy to scale with relatively inexpensive commodity hardware while maintaining world class storage management capabilities. Use any combination of flash, spinning disk and tape. Use a variety of cluster models that include storage area networks (SANs), Network Shared Disk, and shared nothing clusters. Add more storage capacity without affecting the application to greatly simplify administration. Information lifecycle management (ILM) tools automatically move data based on policies. This can dramatically reduce operational costs as fewer administers can manage larger storage infrastructures Global data access across geographic distances and unreliable wide area network (WAN) connections Proven reliability with use in the most demanding commercial applications Data centers are currently struggling to efficiently and cost-effectively store and manage vast amounts of data. The increasing number of application domains, such as analytics, online transaction processing (OLTP), and high-performance computing (HPC) have created silos of storage within data centers. With each new application, a new storage system can be required, forcing system administrators to become experts in numerous storage management tools. OpenStack Swift is emerging as a dominant object storage solution due to its extreme scalability, extensibility, and resilience. Despite its benefits, however, OpenStack Swift still follows the model of deploying new storage systems for new application domains. IBM Spectrum Scale for object storage, the combination of IBM Spectrum Scale and OpenStack Swift, aims to eliminate silos of storage within data centers, by consolidating files and objects under a single shared storage infrastructure. The global namespace eliminates the physical client-to-server mappings 3
and makes this an ideal platform to perform common storage management tasks, such as automated storage tiering and user transparent data migration. IBM Spectrum Scale for object storage simplifies data management even further by creating a flat namespace and eliminating the hassle of organizing data in a hierarchical namespace. Single Name Space GPFS POSIX NFS CIFS OpenStack Nova Swift Cinder Manila Glance Hadoop GPFS Active File Manager S p e c t r um S c a l e IBM Spectrum Scale Cloud Storage GPFS SSD Fast Disk GNR Tape Policies for Tiering, Data Distribution, Migration to Tape and Cloud Figure 1: IBM Spectrum Scale for object storage architecture AvePoint DocAve Storage Manager As SharePoint 2010 becomes the central repository for enterprise content within organizations, increasing user adoption and integration from data sources can cause unstructured data, called BLOBs to consume up to 95% of SharePoint SQL Server space. If ignored, BLOBs can lead to database performance and user experience degradation. With DocAve Storage Manager, organizations can mitigate the negative consequences of exponential data growth by combining multiple realtime and scheduled business rules to externalize BLOB content based on file size, type, or other document properties, allowing SharePoint administrators to: Reduce SharePoint total cost of ownership by using hierarchical storage management (HSM) systems for BLOB storage. Improve user experience by optimizing SQL Server resources while maintaining seamless user access and interaction to externalized content. Easily comply with information governance policies for content lifecycle management within or across multiple SharePoint farms with highly customizable business rules. Ensure all BLOBs work with SharePoint management functions and most third-party applications by using Microsoft s fully supported external BLOB storage (EBS) or remote BLOB store (RBS) application programming interfaces (APIs). 4
DocAve architecture DocAve architecture is modular and scalable to meet the customer requirements. A DocAve server consists of the following roles: DocAve manager: Manages the communication and operations of the DocAve agents and servers in the farm. DocAve media server: Manages the storage operations for the DocAve platform and coordinates the storing of backup data, audit data, externalized SharePoint content, and all other storage needs required by DocAve. DocAve agents: Manages the content according to the rules defined in the DocAve suite for BLOB externalization, backup, recovery, and archiving the SharePoint content. 5
Solution architecture Upload File Retrieve File DocAve Storage Manager or Connector to RBS Store WFE WFE WFE Agent Agent Agent Load file that has been Stubbed from RBS Store Blob Content to RBS Store Generate Stub / Metadata into SharePoint Content DB Blob Stub To SharePoint Content DB Accessed Blob Stub & Metadata Retrieve Blob Content from RBS Store SQL DocAve Manager SP Content DB1 Containing Metadata Stub DB SP Content DB2 Containing Stubs / Metadata DocAve Application Management Console DocAve Media Service OpenStack Swift Tier Storage (RBS Stores) OpenStack Swift Data Flow Storage Manager, Connect Data Retrieve Storage Manager, Connected Data IBM Spectrum Scale for object storage Powered by OpenStack Swift Figure 2: Solution data flow architecture diagram Figure 2 depicts the solution data flow architecture. The solution might consist of multiple servers installed with SharePoint Server and also known as SharePoint farm. The DocAve agent software is installed on each server in the SharePoint farm. Using DocAve application management console, solution is configured for BLOB externalization to IBM Spectrum Scale for object storage. SQL Server SharePoint content database stores the stub and metadata information. BLOB content is stored and retrieved using RBS APIs by using OpenStack Swift on the IBM Spectrum Scale for object storage storage system. 6
BLOB externalization to the IBM Spectrum Scale for object storage This section describes the installation and configuration process of the AvePoint DocAve products to optimize the SharePoint storage with BLOB externalization to the IBM Spectrum Scale for object storage storage system. You need to complete the following tasks before configuring the BLOB provider. 1. Ensure that Microsoft Active Directory Services are available for authentication. 2. Make sure that SharePoint farm components and SQL server deployments are according to Microsoft recommendations. 3. Install DocAve manager and media service roles. It is not recommended to deploy these services on the SharePoint servers. 4. Install DocAve agents on each server in the SharePoint farm. DocAve installation and configuration For detailed AvePoint DocAve software installation and configuration, refer to the following URL for instructions about installing the DocAve Manager, Control Service, Media Service, and DocAve Agent components. http://www.avepoint.com/assets/pdf/sharepoint_user_guides/docave_6_installation_guide.pdf SharePoint document and metadata storage SharePoint supports documents up to 2 GB in size (http://technet.microsoft.com/enus/library/cc262787.aspx#listlibrary), a software boundary that results from a 32-bit pointer used in SQL Server. SharePoint includes a file size upload limitation that's configurable per web application. The default maximum upload size is 50 megabytes (MB) considerably smaller than the 2 GB hard limit. This lower limit reflects practical concerns including network performance, the performance of transferring large files over Hypertext Transfer Protocol (HTTP), and user expectations for performance of file transfer. Many organizations retain this default upload size or raise the limit. If you choose to raise the maximum upload size, do so slowly and after careful testing. Each document in a SharePoint library has metadata associated with it. Some metadata is userconfigured, such as columns in the library. Other metadata is used internally by SharePoint. The amount of metadata associated with a document will vary based primarily upon user-configured metadata. It is easy to understand that scenarios with larger documents see a higher ratio of BLOB-to-metadata storage, and scenarios with smaller documents and more metadata will see lower BLOB-to-metadata ratios. The 80 percent estimate is based on an average across multiple SharePoint environments. But here is the difficulty: A document is rarely, if ever, stored only once. 7
Configuring IBM Spectrum Scale for object storage Refer IBM Spectrum Scale 4.1.1 documentation before you configure IBM Spectrum Scale for object storage. To deploy object storage on IBM Spectrum Scale, the object storage protocol node must be added to the IBM Spectrum Scale cluster definition. Run the following command to designate a node for object storage on IBM Spectrum Scale./spectrumscale node add NODE_IP [-p export IP] IBM Spectrum Scale for object storage configuration example 1. Adding object storage node with example CES IP of 9.xx.xxx.11./spectrumscale node add prt002st001 -p 9.xx.xx.11 Note: Select an IP that does not overlap with the one used for ssh to the node. 2. Adding additional object storage node with example CES IP of 9.xx.xxx.12./spectrumscale node add prt003st001 -p 9.xx.xx.12 3. Enable the object storage protocol on IBM Spectrum Scale./spectrumscale enable object 4. Configure the object storage on IBM Spectrum Scale./spectrumscale config object -e 9.xx.xx.11 Note: specify the IP to be used for the object storage endpoint. This can be any CES IP or it can be a load balancer virtual IP address or host name or DNS round robin IP address or host name. Note: specify the IP to be used for the object storage endpoint. This can be any CES IP. 5. Specify the device and mount point for the Object_Fileset./spectrumscale config object -f fs1 -m /gpfs/fs1 6. Show the node configuration for object storage about to be applied./spectrumscale node list 7. Validate the configuration for the object storage./spectrumscale deploy --precheck 8. Performs protocol (object storage) deployment on the protocol nodes./spectrumscale deploy On the IBM Spectrum Scale object storage nodes, run the following example swift commands to verify the IBM Spectrum Scale for object storage installation. If the installation is completed successfully, you can list all containers, upload a sample object to a container, and list that container and see the object. source ~/openrc swift list date > object1.txt swift upload test_container object1.txt 8
object1.txt swift list test_container object1.txt Enabling Identity API v2.0 IBM Spectrum Scale for object storage version 4.1.1 by default is configured with OpenStack Identity API v3. In the lab solution testing, the AvePoint DocAve seamlessly worked with OpenStack Identity API v2.0. Following OpenStack commands can enable OpenStack Identity API v2.0. 1. openstack service create --name keystonev2 identity 2. openstack endpoint create keystonev2 public http://9.xx.xx.11:5000/v2.0 3. openstack endpoint create keystonev2 admin http://9.xx.xx.11:35357/v2.0 4. openstack endpoint create keystonev2 internal http://9.xx.xx.11:35357/v2.0 9
Preparing DocAve Storage Manager for configuring IBM Spectrum Scale for object storage Install the test fix for IBM Spectrum Scale for object storage storage for DocAve Storage Manager. To install the test fix, perform the following steps. 1. Download the DocAve_Hotfix_6.5.0.600101_ Serial_Number.zip file by contacting an AvePoint representative for links to this package. 2. Copy this test fix to the system where you log in to DocAve Manager. 3. Log in to DocAve Manager and navigate to the Control Panel. Click Update Manager in the System Settings section, as shown in the Figure 3. Figure 3: DocAve Storage Manager Control Panel 4. In the Update Manager interface, click Manage Updates on the ribbon. 5. In the Manage Updates interface, click Browse and load the DocAve_Hotfix_6.5.0.600101_Serial_Number.zip file into DocAve Manager. 6. Select the DocAve_Hotfix_6.5.0.600101_Serial_Number.zip file and click Install in the Actions group. The Server Selection pop-up window shows all available manager services on the Manager tab and all available farms on the Agent tab. 7. On the Manager tab, select the Install the update for all the managers below check box to update the manager services. On the Agent tab, select all farms that have agents installed on them. 8. Click Install to start the installation. The progress is displayed in the Update Progress column. 9. After all of the manager services and agents are updated, click Finish to finish the installation. 10
10. Navigate to Control Panel > Update Manager > View History to verify the installation. On the View History page, check the Version column of the newly installed update. If the version displays 6.5.0.600101, the test fix was applied successfully. IBM Spectrum Scale for object storage configuration for BLOB externalization with DocAve Storage Manager DocAve Storage Manager stores the uploaded BLOB content to an external device (leaving only a stub of the data in SharePoint). Therefore, it is necessary to first configure one or more physical devices and then set up a logical device. Physical devices allow DocAve to store backup data. In order for DocAve to recognize a physical device for use, it must first be configured. Perform the following steps to create Net Share physical devices: 1. Navigate to DocAve manager interface, click Control Panel > Storage Configuration > Physical Device. Then, click Create on the ribbon and select Physical Device from the dropdown list. 2. Select IBM Spectrum Scale for object storage from the Storage Type drop-down list, as shown in Figure 4. Figure 4: DocAve physical device creation 11
3. Enter the tenant name, user name, password, and authentication endpoint URL information, as shown in the Figure 5. You can obtain all this information from the ~/openrc file from the protocol node of the IBM Spectrum Scale for object storage storage system. Click Validation Test to validate the supplied parameters. Figure 5: DocAve Storage Manager physical device parameters 4. Click Save to create the physical device. Verify that the device is listed under Physical Device, as shown in Figure 6. 12
Figure 6: List of physical devices in DocAve Storage Manager 13
DocAve has the ability to treat multiple storage drives as a single logical unit when saving DocAve data. This is especially helpful for very large DocAve plans as many smaller drives can be combined. A logical drive must be defined before creating a DocAve plan. Perform the following steps to create a Net Share logical device. 1. Navigate to the DocAve Manager interface and then click Control Panel > Storage Configuration > Logical Device. Then, click Create on the ribbon and select Logical Device from the drop-down list. 2. Enter an appropriate logical device name and in the Data Storage Type section, select Standard storage device, and select IBM Spectrum Scale for object storage from the Storage Type drop-down list as shown in the Figure 7. Figure 7: DocAve logical device 14
3. From the Physical Device drop-down list, select the newly created IBM Spectrum Scale for object storage Physical Device and click Add to select the physical device to create the new logical device as shown in Figure 8. Figure 8: Logical device creation 4. Click Save to create the logical device. Verify that the device is listed under logical devices Storage policy Use the Storage Policy option to select which logical device to use when saving backup data, and setting up the retention policy for the data saving in the logical device. Perform the following steps to create a storage policy. 1. In the DocAve Manager interface, click Control Panel > Storage Configuration > Storage Policy. Then, click Create on the ribbon to create a new storage policy 2. Enter the new storage policy name and select the newly created IBM Spectrum Scale for object storage from the Logical device drop-down list, select the appropriate media service from the Media service drop-down list, and click Add as shown in the Figure 9. 15
Figure 9: DocAve storage policy 3. Click Save to create the new storage policy. Verify that the newly created storage policy is listed under storage policy. 16
Enabling the BLOB Provider By enabling the BLOB Provider, you are able to externalize BLOBs from a content database to an IBM Spectrum Scale storage system as the external BLOB storage. The BLOB Provider feature intercepts SharePoint database traffic and redirects all the BLOB traffic to the external BLOB storage; what remains in SharePoint is a stub of the data. The BLOB Provider also creates a stub database and enables the provider on the specified farm or node. Perform the following steps to enable the BLOB provider on the SharePoint content database. 1. Navigate to DocAve manager > Storage Optimization > Real-Time Storage Manager > BLOB Provider to enable BLOB Provider, as shown in the Figure 10. Figure 10: DocAve BLOB provider configuration 17
2. Click Next and select an appropriate site object from the Object list to configure the stub database (as shown in Figure 11). Figure 11: DocAve stub database configuration 3. Click Next to enable RBS for the SharePoint farm and configure the schedule for scanning by clicking Configure (as shown in Figure 12). 18
Figure 12: Enable RBS 19
4. Click Finish to complete the BLOB provider configuration (as shown in Figure 13). Figure 13: Finalize the BLOB configuration 20
Running scheduled DocAve Storage Manager jobs with the IBM Spectrum Scale for object storage logical device DocAve offloads the content based on the rule criteria defined using document attributes such as size, creation date, modified date, and version. Content that meets these rules will be offloaded from the SharePoint storage and stored in the selected IBM Spectrum Scale for object storage logical device. Perform the following steps to create the rules to offload the content from the SharePoint storage. 1. Go to DocAve Manager > Storage Optimization > Scheduled Storage Manager. 2. Select a node on the Scope tab (as shown in the Figure 14). Figure 14: Create DocAve Storage Manager rules 21
3. Click Create on the ribbon to create a scheduled Storage Manager rule. In the Scheduled Rule window, configure the corresponding settings and select the newly created IBM Spectrum Scale for object storage logical device. Click OK to create the DocAve Storage Manager rule (as shown in the Figure 15). Figure 15: DocAve Storage Manager rule 4. Select the newly created rule from the Configure Rules and Settings section by selecting the check box to the left of the rule as shown in the Figure 16. Figure 16: Configure rules and settings 22
5. Click Apply to apply the selected rule. 6. Click Run Now to run the applied rule immediately. Storage report AvePoint DocAve provides a dashboard view of the BLOB and stub information collected from the SQL databases and reports about the optimized capacities for the SharePoint farm. 1. Go to DocAve Manager > Storage Optimization > Scheduled Storage Manager > Storage Report as shown in the Figure 17. Figure 17: Storage report profile creation 23
Summary IBM Spectrum Scale is a proven, enterprise-class file system, and OpenStack Swift is a best-of-breed object-based storage system. IBM Spectrum Scale for object storage combines these technologies to provide a new type of cloud storage that includes efficient data protection and recovery, proven scalability, and performance; snapshot and backup and recovery support; and information lifecycle management. Through these features, IBM Spectrum Scale for object storage can help simplify data management and allow enterprises to realize the full value of their data. DocAve Storage Manager is based on Microsoft EBS and RBS APIs to improve SQL server performance. With DocAve, administrators can use customizable business rules in DocAve SharePoint storage offerings along with a wide variety of supported storage devices to optimize HSM and achieve truly comprehensive SharePoint storage management. The IBM Spectrum Scale for object storage and AvePoint DocAve Storage Manager integrated solution provides a robust and very flexible platform needed for Microsoft SharePoint environments through the outstanding characteristics of the software-defined storage and integration through RBS / EBS API integrations to optimize the SharePoint storage by offloading the larger BLOB content. 24
Appendix A: Resources The following websites provide useful references to supplement the information contained in this paper: IBM Systems on PartnerWorld ibm.com/partnerworld/systems IBM Redbooks ibm.com/redbooks IBM System Storage Interoperation Center (SSIC) ibm.com/systems/support/storage/config/ssic/displayesssearchwithoutjs.wss?start_over= yes IBM Spectrum Scale ibm.com/systems/storage/spectrum/scale IBM Techdocs Library ibm.com/support/techdocs/atsmastr.nsf/web/techdocs AvePoint DocAve documentation http://www.avepoint.com/resources/user-guides About the author Udayasuryan Kodoly (Uday) is a storage technology specialist in the IBM Systems and Technology Group (ISV Enablement) Organization. Uday has years of extensive experience in designing, architecting storage solutions, and developing solution best practices for enterprise data centers and cloud infrastructures, and building and sustaining customer and partner relationships. Presently, Uday is engaged in planning, designing and developing IBM Spectrum Scale, software-defined storage and cloud infrastructure solutions integrating with various ISVs. You can reach Uday at uakodoly@us.ibm.com. 25
Trademarks and special notices Copyright IBM Corporation 2015. References in this document to IBM products or services do not imply that IBM intends to make them available in every country. IBM, the IBM logo, and ibm.com are trademarks or registered trademarks of International Business Machines Corporation in the United States, other countries, or both. If these and other IBM trademarked terms are marked on their first occurrence in this information with a trademark symbol ( or ), these symbols indicate U.S. registered or common law trademarks owned by IBM at the time this information was published. Such trademarks may also be registered or common law trademarks in other countries. A current list of IBM trademarks is available on the Web at "Copyright and trademark information" at www.ibm.com/legal/copytrade.shtml. Microsoft, Windows, Windows NT, and the Windows logo are trademarks of Microsoft Corporation in the United States, other countries, or both. Other company, product, or service names may be trademarks or service marks of others. Information is provided "AS IS" without warranty of any kind. All customer examples described are presented as illustrations of how those customers have used IBM products and the results they may have achieved. Actual environmental costs and performance characteristics may vary by customer. Information concerning non-ibm products was obtained from a supplier of these products, published announcement material, or other publicly available sources and does not constitute an endorsement of such products by IBM. Sources for non-ibm list prices and performance numbers are taken from publicly available information, including vendor announcements and vendor worldwide homepages. IBM has not tested these products and cannot confirm the accuracy of performance, capability, or any other claims related to non-ibm products. Questions on the capability of non-ibm products should be addressed to the supplier of those products. All statements regarding IBM future direction and intent are subject to change or withdrawal without notice, and represent goals and objectives only. Contact your local IBM office or IBM authorized reseller for the full text of the specific Statement of Direction. Some information addresses anticipated future capabilities. Such information is not intended as a definitive statement of a commitment to specific levels of performance, function or delivery schedules with respect to any future products. Such commitments are only made in IBM product announcements. The information is presented here to communicate IBM's current investment and development activities as a good faith effort to help with our customers' future planning. Performance is based on measurements and projections using standard IBM benchmarks in a controlled environment. The actual throughput or performance that any user will experience will vary depending upon considerations such as the amount of multiprogramming in the user's job stream, the I/O configuration, the storage configuration, and the workload processed. Therefore, no assurance can be given that an individual user will achieve throughput or performance improvements equivalent to the ratios stated here. Photographs shown are of engineering prototypes. Changes may be incorporated in production models. 26
Any references in this information to non-ibm websites are provided for convenience only and do not in any manner serve as an endorsement of those websites. The materials at those websites are not part of the materials for this IBM product and use of those websites is at your own risk. 27