International Business Machines Corporation

Other

Dell Products Inc.

James W Arendt

Ching-Yun Chao

Rodolfo Ausgusto Mancisidor

Hovey Raymond Strong

Jayashree Ramanathan

Rodolfo Augusto Mancisidor

Ravindranath Kasinath Manikundalam

James Michael Phelan

Bulent Abali

Sudhir Vittal Shetty

Linda Ann Riedle

Mohammad Banikazemi

Katherine Barabash

Dan Edward Poff

Gary Valentin

D Scott Guthridge

Irit Loy

Francis Daniel Lawlor

Paul P Giangarra

Ziv Rafalovich

Donald Robert Padgett

Frank Daniel Lawlor

Michael David Kistler

Nancy M Wei

A network infrastructure provisioning system includes a server including a plurality of server ports. At least one switch is coupled to the server and includes a plurality of switch ports. A controller is coupled to the server and the at least one switch. The controller is operable to assign channels to server traffic, enumerate at least some of the plurality of server ports, determine switch ports associated with the enumerated server ports, and assign channels to the switch ports that are associated with the enumerated server ports. The assigning of channels to the switch ports may include assigning a primary storage channel to a first enumerated server port, assigning a primary networking channel to a last enumerated server port, assigning a secondary storage channel to an intermediate enumerated server port, and assigning a secondary networking channel to an intermediate enumerated server port.

Network infrastructure provisioning with automated channel assignment

A method for adding a server to a storage area network, the method comprising identifying a set comprising one or more communication protocols for connecting a second server to a first storage device configured to communicate with a first server using a first protocol, wherein the set of protocols comprises protocols that are supported by both the second server and the first storage device; selecting a second protocol from the set of protocols; and configuring the first storage device, the second server, and associated connection devices, wherein the second server may communicate with the first storage device using the second protocol.

Protocol independent server replacement and replication in a storage area network

A cluster system is treated as a set of resource groups, each resource group including a highly available application and the resources upon which it depends. A resource group may have between 2 and M data processing systems, where M is small relative to the cluster size N of the total cluster. Configuration and status information for the resource group is fully replicated only on those data processing systems which are members of the resource group. A configuration object/database record for the resource group has an associated owner list identifying the data processing systems which are members of the resource group and which may therefore manage the application. A data processing system may belong to more than one resource group, however, and configuration and status information for the data processing system is replicated to each data processing system which could be affected by failure of the subject data processing system&#x2014;that is, any data processing system which belongs to at least one resource group also containing the subject data processing system. The partial replication scheme of the present invention allows resource groups to run in parallel, reduces the cost of data replication and access, is highly scalable and applicable to very large clusters, and provides better performance after a catastrophe such as a network partition.

Highly scalable and highly available cluster system management scheme

Two methods (native and clone) are used for installing software, such as an operating system, on client system(s) booting from shared storage. The native installation method configures an interconnection network to create an exclusive communication zone between the client system and the shared storage system and installs the operating system on the client system using the exclusive communication zone. After the software is installed, the method terminates the exclusive communication zone. The clone installation method utilizes a point-in-time copy feature of the shared storage system to clone an operating system drive instantaneously. After the drive is cloned, it is logically attached to a new client and the operating system is customized for that client.

Method for installing operating system on remote storage: flash deploy and install zone

A cluster system is treated as a set of resource groups, each resource group including an highly available application and the resources upon which it depends. A resource group may have between 2 and M data processing systems, where M is small relative to the cluster size N of the total cluster. Configuration and status information for the resource group is fully replicated only on those data processing systems which are members of the resource group. A configuration object/database record for the resource group has an associated owner list identifying the data processing systems which are members of the resource group and which may therefore manage the application. A data processing system may belong to more than one resource group, however, and configuration and status information for the data processing system is replicated to each data processing system which could be affected by failure of the subject data processing system&#x2014;that is, any data processing system which belongs to at least one resource group also containing the subject data processing system. The partial replication scheme of the present invention allows resource groups to run in parallel, reduces the cost of data replication and access, is highly scalable and applicable to very large clusters, and provides better performance after a catastrophe such as a network partition.

A cluster system is treated as a set of resource groups, each resource group including an highly available application and the resources upon which it depends. A resource group may have between 2 and M data processing systems, where M is small relative to the cluster size N of the total cluster. Configuration and status information for the resource group is fully replicated only on those data processing systems which are members of the resource group. A configuration object/database record for the resource group has an associated owner list identifying the data processing systems which are members of the resource group and which may therefore manage the application. A data processing system may belong to more than one resource group, however, and configuration and status information for the data processing system is replicated to each data processing system which could be affected by failure of the subject data processing system.

A cluster system is treated as a set of resource groups, each resource group including a highly available application and the resources upon which it depends. A resource group may have between 2 and M data processing systems, where M is small relative to the cluster size N of the total cluster. Configuration and status information for the resource group is fully replicated only on those data processing systems which are members of the resource group. In the event of failure of a data processing system within the cluster, only resource groups including the failed data processing system are affected. Each resource group having a quorum of its data processing systems available continues to provide services, allowing many applications within the cluster to continue functioning while the cluster is restored.

Resource group quorum scheme for highly scalable and highly available cluster system management

A method and apparatus that automatically generates and maintains resource groups for a clustered computer network configuration. Resource groups are said to be generated 'automatically' because the system administrator preferably is not directly involved with defining what resources go within a particular group. Rather, the administrator merely identifies a set of resources that must be collocated with a given application in the event of a failure of a computer on which the application is then executing. One or more resource groups are then automatically generated using a set of collocation 'constraints' or rules. A first collocation constraint preferably enforces any user-defined collocations for a given application, and a second constraint collocates disk partition resources residing on the same physical disk. A resource group generated is this manner ensures effective fault-tolerant operation.

Automatic resource group formation and maintenance in a high

Configuration changes are dynamically applied to a cluster multiprocessing system by enqueuing a configuration change event. When the configuration change event is processed, the prior configuration is backed up and each software component applies a relevant portion of a configuration change transaction in an ordered, synchronized manner. Each software component applies its portion of the transaction either by reinitialization or a logged transition operation. If the configuration change transaction fails, the software components roll back the portions, of the configuration change already applied in an ordered, synchronized manner to restore the prior configuration. Multiple events for different configuration changes may be enqueued.

Enqueuing a configuration change in a network cluster and restore a

A user definable set of event rollup relationships are maintained as a configuration element. Transitive closure of event rollup relationships is checked at the time of specification to detect cycles and prevent runtime errors. When an event to be processed is detected, the event is compared to defined rollup relationships and queued events to determined if the detected event may be rolled up into at least one queued event or vice versa. If the detected event may be rolled up into a queued event, the detected event is not queued. When any of the queued event may be rolled up into the detected event, the queued events are deleted if processing has not already begun.

Scheme to perform event rollup

A data processing system stores and maintains a plurality of security levels for dynamically linked libraries. Upon loading of an application, and upon determination of which dynamically linked libraries are required by the application, the data processing system determines the predefined security level assigned to the application and loads dynamically linked libraries previously encoded with the predefined security level.

User level control of degree of client-side processing

Lazy loading of executable library objects reduces operating system overhead and memory commitment requirements by postponing object loading until object references are expected. Initial task loading allocates only the main executable and library objects referenced by that executable. Secondary referenced objects are not allocated. Object references cause page faults for allocated but not loaded pages. Page fault handling causes loading and fixup of executable objects. Page fault handling also determines the next level of object references and allocates memory for the next object level. Shared memory systems allow sharing of executable objects until explicitly referenced. Once referenced, memory fault causes copying and fixup to referencing task memory area.

Growing community of inventors

Round Rock, TX, United States of America

James W Arendt