IBM General Parallel File System for Linux on POWER, V3 offers Information Lifecycle Management and enhanced multicluster support
IBM United States Software Announcement 206-100April 25, 2006
 ENUS206-100.PDF (59KB)
|
At a glance
 |
| At a glance |
 |
IBM General Parallel File System (GPFS) for Linux on POWER, V3.1 offers:
- Information Lifecycle Management, to allow more flexible support of different disk classes
- Improved multicluster support and use of multiple networks
- Administration usability and flexibility improvements
-
Support for mixed clusters of IBM
servers sharing file system services running Linux or AIX 5L™
For ordering, contact:
Your IBM representative, an IBM Business Partner, or IBM Americas Call Centers at
800-IBM-CALL
(Reference: RE001).
Back to top
|
|
| Overview |
|
IBM General Parallel File System (GPFS) for Linux™ on POWER™ is ideal for high-performance parallel file transfer and parallel I/O to single or multiple files. The key strengths of GPFS are multicluster support, superior scalability and performance, ability to support extremely large files, failure recovery, and ease of administration.
Version 3.1 enhancements:
-
Information Lifecycle Management support with the introduction of storage pools, policy-based file
management, and filesets. GPFS is designed to help you to achieve data lifecycle management
efficiencies through policy-driven automation and tiered storage management. User-defined policies
provide the ability to better match the cost of your storage resources to the value of your data.
- Storage pools allow you to manage your file system's storage in groups. You may now partition your storage based on such factors as performance, locality, and reliability.
- Filesets provide for partitioning of a file system, allowing administrative operations at a finer granularity than the entire file system.
- New commands and APIs support storage pools, policies, and filesets.
- Elimination of the need for communication between nodes in different remote clusters.
- Enhancements to multicluster file access. You can specify the use of multiple networks for a node in your cluster, thus allowing both the use of internal networks within a cluster and the use of external addresses for remote clusters.
- Enhanced file system mounting and Network Shared Disk functions.
- Improved performance and scalability via option to distribute the token manager.
Back to top
|
|
| Key prerequisites |
|
- IBM System p5™ servers or
-
IBM pSeries® servers or
-
IBM p5 servers or
-
IBM BladeCenter® servers
or
-
IBM OpenPower.
- SUSE Linux Enterprise Server 9 or
- Red Hat Enterprise Linux 4 (AS, ES, or WS).
|
|
| Planned availability date |
|
April 28, 2006
|
|
| Description |
|
IBM General Parallel File System (GPFS) provides file system services to parallel and serial applications. GPFS allows parallel applications simultaneous access to the same files, or different files, from any node that has the GPFS file system mounted, while managing a high level of control over all file system operations. GPFS is particularly appropriate in an environment where the aggregate peak need for data bandwidth exceeds the capability of a distributed file system server.
GPFS allows users shared file access within a single GPFS cluster and across multiple GPFS clusters. A GPFS cluster can consist of Linux nodes, AIX 5L V5.3 nodes, or a combination thereof, and network shared disks (NSDs) created and maintained by the NSD component of GPFS.
GPFS for Linux on POWER V3.1 enhancements:
-
GPFS V3 provides for Information Lifecycle Management with the introduction of storage pools,
policy-based file management, and filesets. GPFS is designed to help you to achieve data lifecycle
management efficiencies through policy-driven automation and tiered storage management.
User-defined policies provide the ability to better match the cost of your storage resources to the
value of your data.
-
Storage pools allow you to manage your file system's storage in groups. You may partition your
storage based on such factors as performance, locality, and reliability. Files are assigned to a
storage pool based on defined policies. Storage policies provide for:
- File placement to a specific storage pool when it is created
- Migration of a file from one storage pool to another
- Deletion of a file based on characteristics of the file
Filesets provide a method for partitioning a file system, and allow administrative operations at a finer granularity than the entire file system. For example, filesets allow you to:
- Define data block and inode quotas at the fileset level
- Apply policy rules to specific filesets
- New commands provide enhanced support of storage pools, policies, and filesets.
- New APIs in support of storage pools and filesets include gpfs_igetstoragepool and gpfs_igetfilesetname.
-
Storage pools allow you to manage your file system's storage in groups. You may partition your
storage based on such factors as performance, locality, and reliability. Files are assigned to a
storage pool based on defined policies. Storage policies provide for:
- This release eliminates the need for communication between nodes in different remote clusters by distributing the token server load over multiple manager nodes in a home cluster and by letting the token server handle revoke requests for tokens rather than delegating this to the client in a remote cluster. This eliminates token traffic required among these different remote clusters.
-
GPFS provides improved multiple-cluster network access and support. You may specify the use of
multiple networks for a node in your cluster, allowing both the use of internal networks within a
cluster and the use of external addresses for remote mounts. The mmchconfig command has been
enhanced so you may specify a list of private IP addresses used to communicate between nodes in a
GPFS cluster.
- Multiple security levels, up to one for each authorized cluster, may be specified by the cluster granting access.
-
The local cluster no longer needs to be shut down prior to changing security keys. GPFS aims to
provide a highly available service while allowing for required periodic changing of keys:
- In order to make connection rate performance acceptable in large clusters, the size of the security keys used for authentication can not be very large. As a result it may be necessary to change security keys in order to prevent a given key from being compromised while it is still in use.
- As a matter of policy, some institutions may require periodic changing of security keys.
Refer to the GPFS FAQ for information on the latest support for GPFS interoperability, at
-
Enhanced file system mounting is supported by three new commands:
- The mmmount and mmunmount commands are provided for cluster-wide file system management, alleviating the administrator from issuing the dsh command.
- The mmlsmount displays the IP addresses and names of the nodes (local and remote) that have a particular file system mounted.
-
Network Shared Disk functions are provided:
- An option to allow or restrict failover from local to remote access is provided on the mmchfs, mmmount, and mmremotefs commands.
- In prior releases of GPFS, the only way to failback to local disk access once the connection had been repaired and access through an NSD server was no longer desired, was to remount the file system. In this release, GPFS discovers if the path has been repaired. If the path has been repaired, GPFS falls back to local disk access.
-
Improved NSD access information is provided by the mmlsnsd command:
- The availability of the disk is displayed.
- The device type of the disk is available when specifying the -X option.
-
The mmpmon performance monitoring tool provides:
- Use of a named socket — the mmpmon command no longer uses ports.
- Ability to include a list of nodes, in the local cluster, to report on instead of just the node from which the command is issued.
- Mount support is provided for clusters utilizing NSD servers.
-
You may specify how long to wait for an NSD server to come online before
allowing the mount to fail. The mmchconfig command has been enhanced,
allowing you to specify wait time when either bringing a cluster online
or bringing an NSD server online when client nodes are already active:
- The cluster formation time is at most nsdServerWaitTimeWindowOnMount seconds from the current time.
- The last failed time is at most nsdServerWaitTimeWindowOnMount seconds from the current time.
- The number of seconds to wait for the server to come up before declaring the mount a failure is as specified by the nsdServerWaitTimeForMount option.
- You may specify different networks for GPFS daemon communication and for GPFS administration command usage within your cluster. The node descriptor for the mmchcluster command now allows you to specify separate node interfaces for these uses, for each node within your cluster. You may choose to use this capability when considering cluster security or performance.
-
An auto-configuration tool is provided for GPFS for Linux installations.
GPFS Linux installations require a set of kernel extensions be built to match a customer's specific hardware, Linux distribution, and kernel. Prior to GPFS V3.1, this was a manual operation (refer to GPFS Concepts, Planning, and Installation Guide and search on the GPFS portability layer). In addition to the manual method, there now exists an autoconfiguration tool to query your system configuration and generate a working configuration file.
-
The use of a single port removes conflicts with existing network
services.
As of November 2004, port number 1191 was officially registered with InterNet Assigned Numbers Authority (IANA) for handling GPFS-specific traffic. With this release, all GPFS-related traffic has been consolidated on port 1191.
- Improved usability and command consistency are provided via the -N flag to indicate which nodes are to participate in execution of the command.
-
Enhanced error messages reporting is provided in the mmfs log.
Messages previously reporting no explanation provide the proper text.
- You may experience performance improvements when issuing either the mmlsnsd -M or the mmlsnsd -m command due to a redesign of the command.
- Quorum semantics are improved when utilizing node quorum with tiebreaker disks. The maximum number of quorum nodes has been increased from two to eight.
- Enhanced quota information is provided in support of filesets.
-
GPFS V3 provides the ability to distribute the token management function
among file system manager nodes in a cluster, reducing possible
bottlenecks.
You may choose to distribute the token server load among the nodes in your cluster that have been designated as file system manager nodes. The mmchconfig command has been enhanced with the distributedTokenServer option, allowing you to turn the distributed token management function on and off.
Refer to Concepts, Planning, and Installation Guide for further information on the roles of the file system manager and General Parallel File System: Advanced Administration for details on distributed token managers.
- Performance and security enhancements have been made to the mmauth command. You may experience performance improvements as GPFS V3 uses a multithreaded receiver for authentication, encryption, and decryption.
Other functional changes in GPFS V3.1:
- The mmpmon command no longer uses ports.
Note: Refer to the GPFS FAQ available from the following Web site for complete information
Accessibility by people with disabilities
A U.S. Section 508 Voluntary Product Accessibility Template (VPAT) containing details on the product's accessibility compliance can be requested via IBM's Web site:
Back to top
|
|
| Product positioning |
|
GPFS can be ideal for high-performance parallel file transfer and parallel I/O to single or multiple files.
The key strengths of GPFS are:
- Information Lifecycle Management
- Shared file system access among GPFS clusters
- Improved system performance
- superior scalability and ability to support extremely large files
- File consistency
- High recoverability and increased data availability
- Enhanced system flexibility
- Simplified storage management
- Simplified administration
- Multiple platform support
GPFS for Linux is also positioned as a complementary offering to GPFS for
AIX 5L.
Back to top
|
|
| Reference information |
|
- Software Announcement 206-095 , dated April 25, 2006 (GPFS for Linux Multiplatform)
- Software Announcement 206-101 , dated April 25, 2006 (GPFS for AIX 5L)
- Withdrawal Announcement 906-059 , dated March 28, 2006 (HPC SW product service end dates)
- Software Announcement 204-298 , dated December 7, 2004 (On/Off Capacity on Demand)
- Withdrawal Announcement 906-089 , dated April 25, 2006 (SW product withdrawals from marketing)
Business Partner information
If you are a Direct Reseller - System Reseller acquiring products from IBM, you may link directly to Business Partner information for this announcement. A PartnerWorld ID and password are required (use IBM ID).
BP Attachment for Announcement Letter 206-100
Trademarks
GPFS for Linux™ on POWER™ V2.3 will remain available via current 5765-G20 billing feature numbers and AIX 5L™ SPO (5692-A5L) supply feature numbers until further notice.
Program warranty service for GPFS V2.2 will end on April 30, 2007, as previously announced.
Program warranty service for GPFS V2.3 will continue until further notice.
For additional GPFS product information, go to
Back to top
|
|
| Offering Information |
|
Product information is available via the Offering Information Web site
Back to top
|
|
| Publications |
|
No publications are shipped with this program; however, the following publications are available from the Web:
IBM General Parallel File System:
- Concepts, Planning and Installation Guide (GA76-0413)
- Administration and Programming Reference (SA23-2221)
- Problem Determination Guide (GA76-0415)
- Data Management API Guide (GA76-0414)
- Advanced Administration Guide (SC23-5182)
These displayable manuals are viewable in PDF format from
The manuals are also available by selecting the "Library" link off of the
IBM Cluster Information Center at
IBM Publications Center
The Publications Center is a worldwide central repository for IBM product
publications and marketing material with a catalog of 70,000 items.
Extensive search facilities are provided. Payment options for orders are
via credit card (in the U.S.) or customer number for 50 countries. A
large number of publications are available online in various file
formats, and they can all be downloaded by all countries free of charge.
Back to top
|
|
| Technical information |
|
Specified operating environment
Hardware requirements
Any of the following IBM servers:
- IBM System p5™ servers
-
IBM pSeries® servers
-
IBM Cluster 1600 (with
supported network interconnect)
-
IBM p5 servers
-
IBM BladeCenter® servers
-
IBM OpenPower™
Any of the following connectivity and storage:
- 100 Mb Ethernet, 1 Gb Ethernet, or Myrinet (IP only)
- IBM TotalStorage® DS4000 disk (DS4100, DS4300, DS4400, DS4500, or DS4800)
- IBM TotalStorage ESS (2105-F20 or 2105-800)
Note: Refer to the GPFS FAQ available from the following Web site for an updated list of formally qualified disk subsystems and servers:
Software requirements
- GPFS service level 3.1.0.1 available at
-
One of the following Linux distributions:
- SUSE Linux Enterprise Server 9
- Red Hat Enterprise Linux 4 (AS, ES, or WS)
- GPFS Portability Layer, which is source code licensed under the Berkeley Software Distribution (BSD) terms and included in the distribution packaged with GPFS for Linux, and which is compiled by the user to produce a set of kernel module binaries for GPFS. For supported kernel levels, consult the Frequently Asked Questions available from
Compatibility: In any cluster or group of clusters that mount the same filesystems, GPFS requires that all nodes be running the same release of code. Nodes running different service or update levels may coexist as long as the different levels do not depend on certain bug fixes for correct execution.
Refer to the online documentation on migration from the "Library" link
off of the IBM Cluster Information Center at
Limitations: For complete and up-to-date information regarding GPFS specifications and capacities, refer to the GPFS for Linux on POWER (5765-G67) Sales Manual, and to the GPFS FAQ available from the following Web site
For additional information, refer to usage restrictions in the Terms and conditions section of this announcement, or to the License Information document that is available on the IBM Software License Agreement Web site at
Planning information
Packaging: This program is distributed as a single package available via CD-ROM media. A product README file and license information are shipped with the product. Publications are available online.
Security, auditability, and control
GPFS uses the security and auditability features of the Linux operating system, OpenSSH, and
OpenSSL. The customer is responsible for evaluation, selection, and implementation of security
features, administrative procedures, and appropriate controls in application systems and
communication facilities.
Back to top
|
|
| Ordering information |
|
Charge metric
Part number
Program name or PID number Charge metric
GPFS for Linux 5765-G67 Per processor --
on POWER V3 5660-GLP small, medium, large
5661-GLP
5662-GLP
5663-GLP
5664-GLP
GPFS V3.1 has one charge unit: number of processors active on either a small, medium, or large server running GPFS for the supported operating environment.
The order quantity is the integer number of processors on which GPFS will be run or installed.
Note: Ordering and billing is per physical processor, regardless of processor sharing ("sub-CPU LPARs").
A new order for GPFS includes one-year IBM Software Maintenance. Upgrades may be acquired via the IBM Software Maintenance agreement up to the current level of use authorized for the qualifying program.
Sub-capacity processor
The required authorized use level for eligible programs is based upon the highest utilization of the partitions where the program or a component of the program executes. The customer agrees to periodically report program use to IBM using an IBM license management tool.
-
The number of authorizations you must acquire is the smaller value of either of the following
methods:
- The total number of activated (available for use) processors in the machine, or
-
The sum of (i) and (ii) as follows (any remaining fraction of a processor must be rounded up to a
full processor in the final aggregation)
(i) When the program is run in partitions with dedicated processors, the sum of the processing units of those partitions, and
(ii) When the program is run in partitions that are members of a shared processing pool, the smaller of:
- The number of processors assigned to the pool, or
- The sum of the virtual processors of each uncapped partition plus the processing units in each capped partition running a program.
New users of GPFS for Linux on POWER, V3.1 should specify type 5765, model G67, and the one-time charge (OTC) feature number in the appropriate server-size column with a quantity equal to the total number of processors active in that server running the supported operating system in which GPFS will be installed. If a processor is active and GPFS will not be running on that processor, an order for GPFS is not required. For CD-ROM media, specify type 5692, model A5L, and feature number 1486.
Note: Throughout the following tables:
- Small means small capacity servers (processor groups C5, D5, and E5)
- Medium means medium capacity servers (processor groups F5 and G5)
- Large means large capacity servers (processor groups H5 and P5)
- OTC means one-time charge
- OOCoD means On/Off Capacity on Demand
5765-G67, General Parallel File System for Linux on POWER, V3.1
Basic license one-time charge
Small Medium Large
OTC OTC OTC
Program feature feature feature
Description number number number number
Per processor 5765-G67 0001 0003 0005
Block of 250 5765-G67 0002 0004 0006
processors(1)
- 1
- The feature for a block of 250 active processors is provided for convenience with large orders. A quantity of one for this feature will order a license for 250 processors.
Media
supply
Program feature
Program name number Media number
GPFS for Linux 5692-A5L CD-ROM 1486
on POWER, V3.1
This software license includes Software Maintenance, previously referred to as Software Subscription and Technical Support.
Extending coverage for a total of three years from date of acquisition may be elected. Order the program number, feature number, and quantity to extend coverage for your software licenses. If maintenance has expired, specify the after-license feature number.
New Software Maintenance products and features for General Parallel File System (GPFS) for Linux on POWER V3 (5765-G67) and GPFS for Linux on POWER V2.3 (5765-G20) effective April 25, 2006.
OTC
Billing
feature
Feature description number
5660-GLP GPFS Software Maintenance 5809
Agreement
5661-GLP GPFS Software Maintenance 5809
Agreement
5662-GLP GPFS Software Maintenance 5809
Agreement
5664-GLP GPFS Software Maintenance 5809
Agreement
5660-GLP Maintenance No-Charge 1-year Registration
Small per processor 0824
Small per block of 250 processors 0825
Medium per processor 0828
Medium per block of 250 processors 0829
Large per processor 0832
Large per block of 250 processors 0833
5660-GLP Maintenance 1-year 24 x 7 support
Small per processor 0826
Small per block of 250 processors 0827
Medium per processor 0830
Medium per block of 250 processors 0831
Large per processor 0834
Large per block of 250 processors 0835
5661-GLP 1-year Software Maintenance After License
Small per processor 0108
Small per block of 250 processors 0109
Medium per processor 0112
Medium per block of 250 processors 0113
Large per processor 0116
Large per block of 250 processors 0117
5661-GLP After License 1-year 24 x 7 support
Small per processor 0110
Small per block of 250 processors 0111
Medium per processor 0114
Medium per block of 250 processors 0115
Large per processor 0118
Large per block of 250 processors 0119
5662-GLP Maintenance 3-year Registration (2-year uplift)
Small per processor 0168
Small per block of 250 processors 0169
Medium per processor 0172
Medium per block of 250 processors 0173
Large per processor 0176
Large per block of 250 processors 0177
5662-GLP Maintenance 3-year 24 x 7 support
Small per processor 0170
Small per block of 250 processors 0171
Medium per processor 0174
Medium per block of 250 processors 0175
Large per processor 0178
Large per block of 250 processors 0179
5664-GLP 3-year Software Maintenance After License
Small per processor 0001
Small per block of 250 processors 0002
Medium per processor 0005
Medium per block of 250 processors 0006
Large per processor 0009
Large per block of 250 processors 0010
5664-GLP After License 3-year 24 x 7 support
Small per processor 0003
Small per block of 250 processors 0004
Medium per processor 0007
Medium per block of 250 processors 0008
Large per processor 0011
Large per block of 250 processors 0012
Withdrawal of SWMA program numbers
For the licensed programs, the SWMA is changing structure and type number from 577x to 566x. GPFS Software Maintenance is now available via the new 566x program numbers announced above. Customers who have current software maintenance will be renewed under the new SWMA product numbers at their normal renewal date.
The following program numbers are withdrawn as of April 25, 2006:
Program
Description number
GPFS for Linux on POWER 5771-GLP
1-Year Software Maintenance
GPFS for Linux on POWER 5773-GLP
3-Year Software Maintenance
Refer to Withdrawal Announcement 906-089 , dated April 25, 2006 (pSeries SW withdrawal).
System Program Order (SPO) (5692-A5L)
A 5692-A5L SPO is mandatory for shipments of program distribution and publications. The individual licensed program orders (for example, 5765-G67) are for registration and billing purposes only. No shipment occurs under these orders.
Machine-readable materials are only available on CD-ROM. To receive shipment of machine-readable materials under SPO (5692-A5L), order the CD-ROM media.
Specify feature code 3410. Billing for the media is generated under the SPO. To prevent additional billing expenses, place only one SPO order per machine.
Select one of the following (5692-A5L) features for the licensed program hardcopy entitled publications.
Program number Program name Number 5692-A5L GPFS for Linux on POWER, V3.1 1486
Under SPO 5692-A5L, feature number 3470 can be used to suppress hardcopy documentation. To order entitled hardcopy documentation only, order feature number 3430.
On/Off Capacity on Demand
IBM offers a daily price option to enable you to dynamically change your available server capacity. On/Off Capacity on Demand (OOCoD) allows you to dynamically increase and decrease server capacity based on changing workload demands. In order to take advantage of OOCoD, you must have activation of the OOCoD hardware offering for pSeries and the applicable base software license on order or on inventory.
This offering allows you to pay a fee to enable and use temporary server capacity of GPFS on a per-day basis using the features below.
Customer must complete and sign contract Z125-6907 — Amendment for iSeries™ and pSeries Software On/Off Capacity on Demand.
For specific terms, refer to Software Announcement 204-298 , dated December 7, 2004.
Small Medium Large
OTC OTC OTC
Program feature feature feature
Description number number number number
Per Processor 5765-G67 0007 0009 0011
Day OOCoD
Temp Use Chrg
Block of 250 5765-G67 0008 0010 0012
processors(1)
- 1
- The feature for a block of 250 active processors is provided for convenience with large orders. A quantity of one for this feature will order a license for 250 processors.
Back to top
|
|
| Terms and conditions |
|
Licensing: IBM International Program License Agreement and License Information document. Proofs of Entitlement (PoE) are required for all authorized use.
This software license includes Software Maintenance, previously referred to as Software Subscription and Technical Support.
The following agreement applies for maintenance and does not require customer signatures: IBM Agreement for Acquisition of Software Maintenance (Z125-6011).
Limited warranty applies: Yes
Warranty: This program includes a warranty for one year from acquisition from IBM or an authorized IBM Business Partner. For one year from acquisition of the program, this warranty provides the customer with access to databases containing program information and FAQs, including any known fixes to defects, which the customer can download or otherwise obtain and install.
Program technical support: Technical support of a program product will be available for a minimum of three years from the general availability date, as long as your Software Maintenance is in effect. This technical support allows you to obtain assistance (via telephone or electronic means) from IBM for product-specific, task-oriented questions regarding the installation and operation of the program product. Software Maintenance also provides you with access to updates, releases, and versions of the program. Customers will be notified, via announcement letter, of discontinuance of support with 12 months' notice. If you require additional technical support from IBM, including an extension of support beyond the discontinuance date, contact your IBM representative or IBM Business Partner. This extension may be available for a fee.
Money-back guarantee: If for any reason you are dissatisfied with the program and you are the original licensee, return it within 30 days from the invoice date, to the party (either IBM or its reseller) from whom you acquired it, for a refund. For clarification, note that for programs acquired under any of IBM's On/Off Capacity on Demand (On/Off CoD) software offerings, this term does not apply since these offerings apply to programs already acquired and in use by the customer.
Copy and use on home/portable computer: No
Volume orders (IVO): Yes. Contact your IBM representative.
Passport Advantage® applies: No
Usage restriction: Yes
For additional information, refer to the License Information document that is available on the IBM Software License Agreement Web site
Software Maintenance applies: Yes
All distributed software licenses include Software Maintenance (Software Subscription and Technical Support) for a period of 12 months from the date of acquisition, providing a streamlined way to acquire IBM software and assure technical support coverage for all licenses. Extending coverage for a total of three years from date of acquisition may be elected.
While your Software Maintenance is in effect, IBM provides you assistance for your routine, short duration installation and usage (how-to) questions, and code-related questions. IBM provides assistance via telephone and, if available, electronic access, only to your information systems (IS) technical support personnel during the normal business hours (published prime shift hours) of your IBM support center. (This assistance is not available to your end users.) IBM provides Severity 1 assistance 24 hours a day, every day of the year. For additional details, consult your IBM Software Support Guide at
Software Maintenance does not include assistance for the design and development of applications, your use of programs in other than their specified operating environment, or failures caused by products for which IBM is not responsible under this agreement.
Acquisition of GPFS V3 via SWMA does not change existing SWMA contract start nor end dates.
IBM Operational Support Services — SoftwareXcel: No
iSeries Software Maintenance applies: No
Variable charges apply: Yes
Educational allowance available
Yes, a 15% education allowance applies to qualified education institution customers.
On/Off Capacity on Demand
To be eligible for On/Off Capacity on Demand pricing, customers must be enabled for temporary capacity on the corresponding hardware, and the required contract — Z125-6907, Amendment for iSeries and pSeries Temporary Capacity On Demand — Software — must be signed prior to use.
|
|
| Prices |
|
The prices provided in this announcement are suggested retail prices for the U.S. only and are provided for your information only. Dealer prices may vary, and prices may also vary by country. Prices are subject to change without notice. For additional information and current prices, contact your local IBM representative.
Program name: 5765-G67 General Parallel File System for Linux on POWER, V3.1
OTC
Billing One-
feature time
Feature description number charge
Base product
Small per processor 0001 $ 650
Small per block of 250 processors 0002 162,500
Medium per processor 0003 857
Medium per block of 250 processors 0004 214,250
Large per processor 0005 1,050
Large per block of 250 processors 0006 262,500
Per processor day OOCoD temp use charge
Small per processor 0007 7
Small per block of 250 processors 0008 1,750
Medium per processor 0009 9
Medium per block of 250 processors 0010 2,250
Large per processor 0011 11
Large per block of 250 processors 0012 2,750
New Software Maintenance Program Identification (PID) and features — GPFS for Linux on POWER, V3.1
OTC
Billing One-
feature time
Feature description number charge
5660-GLP GPFS Software Maintenance Agreement 5809 NC
5661-GLP GPFS Software Maintenance Agreement 5809
5662-GLP GPFS Software Maintenance Agreement 5809
5664-GLP GPFS Software Maintenance Agreement 5809
5660-GLP Maintenance No-Charge 1-year Registration
Small per processor 0824 NC
Small per block of 250 processors 0825
Medium per processor 0828
Medium per block of 250 processors 0829
Large per processor 0832
Large per block of 250 processors 0833
5660-GLP Maintenance 1-year 24 x 7 support
Small per processor 0826 $ 9
Small per block of 250 processors 0827 2,250
Medium per processor 0830 12
Medium per block of 250 processors 0831 3,000
Large per processor 0834 15
Large per block of 250 processors 0835 3,750
5661-GLP 1-year Software Maintenance After License
Small per processor 0108 195
Small per block of 250 processors 0109 48,750
Medium per processor 0112 257
Medium per block of 250 processors 0113 64,250
Large per processor 0116 315
Large per block of 250 processors 0117 78,750
5661-GLP After License 1-year 24 x 7 support
Small per processor 0110 9
Small per block of 250 processors 0111 2,250
Medium per processor 0114 12
Medium per block of 250 processors 0115 3,000
Large per processor 0118 15
Large per block of 250 processors 0119 3,750
5662-GLP Maintenance 3-year Registration (2-year uplift)
Small per processor 0168 221
Small per block of 250 processors 0169 55,250
Medium per processor 0172 291
Medium per block of 250 processors 0173 72,750
Large per processor 0176 357
Large per block of 250 processors 0177 89,250
5662-GLP Maintenance 3-year 24 x 7 support
Small per processor 0170 25
Small per block of 250 processors 0171 6,250
Medium per processor 0174 32
Medium per block of 250 processors 0175 8,000
Large per processor 0178 40
Large per block of 250 processors 0179 10,000
5664-GLP 3-year Software Maintenance After License
Small per processor 0001 415
Small per block of 250 processors 0002 103,750
Medium per processor 0005 547
Medium per block of 250 processors 0006 136,750
Large per processor 0009 671
Large per block of 250 processors 0010 167,750
5664-GLP After License 3-year 24 x 7 support
Small per processor 0003 25
Small per block of 250 processors 0004 6,250
Medium per processor 0007 32
Medium per block of 250 processors 0008 8,000
Large per processor 0011 40
Large per block of 250 processors 0012 10,000
Variable charges
The applicable processor-based one-time charge will be based on the group of the designated machine
on which the program is licensed for use. If the program is designated to a processor in a group
for which no charge is listed, the charge of the next higher group listed applies. For movement to
a machine in a higher group, an upgrade charge equal to the difference in the then-current charges
between the two groups will apply. For movement to a machine in a lower group, there will be no
adjustment or refund of charges paid.
Back to top
|
|
| Order now |
|
To order, contact the Americas Call Centers, your local IBM representative, or your IBM Business Partner.
To identify your local IBM representative or IBM Business Partner, call 800-IBM-4YOU (426-4968).
Phone: 800-IBM-CALL (426-2255)
Fax: 800-2IBM-FAX (242-6329)
Internet: callserv@ca.ibm.com
Mail: IBM Americas Call Centers
Dept. Teleweb Customer Support, 9th floor
105 Moatfield Drive
North York, Ontario
Canada M3B 3R1
Reference: RE001
The Americas Call Centers, our national direct marketing organization, can add your name to the mailing list for catalogs of IBM products.
Note: Shipments will begin after the planned availability date.
Trademarks
Back to top
Printable version