Abstract: A clustered system has a subset of nodes coupled to a particular cluster resource. Nodes not coupled to the cluster resource may operate on a cluster resource through a node coupled to that resource. The nodes coupled to the resource form a group, the nodes in the group perform protocols to operate on the cluster resource, nodes not in the group do not participate in the protocols.

Abstract: A clustered system has a subset of nodes coupled to a particular cluster resource. Nodes not coupled to the cluster resource may operate on a cluster resource through a node coupled to that resource. The nodes coupled to the resource form a group, the nodes in the group perform protocols to operate on the cluster resource, nodes not in the group do not participate in the protocols.

Abstract: An independent product upgrade function is associated with each of multiple software products installed in a set of multiple computing devices. Responsive to a triggering event, each upgrade function determines whether the corresponding product can be updated based on rules for the corresponding product. Upgrade may be dependent on other products, but the upgrade function need not know the conditions for upgrading other products. If a product can be updated, update is performed and all other products are notified. Each of the other product upgrade functions then determines whether its corresponding product can be upgraded as a result of the recent upgrade to the first product, and if so, another set of notifications is sent. This cycle continues until all dependent products have been updated. Upgrade functions preferably operate in a peer-to-peer relationship, and upgrade can be initiated in any node.

Abstract: An independent product upgrade function is associated with each of multiple software products installed in a set of multiple computing devices. Responsive to a triggering event, each upgrade function determines whether the corresponding product can be updated based on rules for the corresponding product. Upgrade may be dependent on other products, but the upgrade function need not know the conditions for upgrading other products. If a product can be updated, update is performed and all other products are notified. Each of the other product upgrade functions then determines whether its corresponding product can be upgraded as a result of the recent upgrade to the first product, and if so, another set of notifications is sent. This cycle continues until all dependent products have been updated. Upgrade functions preferably operate in a peer-to-peer relationship, and upgrade can be initiated in any node.

Abstract: Techniques disclosed herein describe performing client-requested disk management operations to storage disk units of a storage area network (SAN). A proxy service receives a request from a client of a SAN provider to perform a disk management operation on one or more storage disk units of the SAN provider. The proxy service evaluates a configuration of storage disk units allocated to the client to determine whether the request is valid. If valid, the proxy service performs the requested action to the specified storage disk units on behalf of the client.

Abstract: Techniques disclosed herein describe performing client-requested disk management operations to storage disk units of a storage area network (SAN). A proxy service receives a request from a client of a SAN provider to perform a disk management operation on one or more storage disk units of the SAN provider. The proxy service evaluates a configuration of storage disk units allocated to the client to determine whether the request is valid. If valid, the proxy service performs the requested action to the specified storage disk units on behalf of the client.

Abstract: A method, and system for implementing enhanced fast full synchronization for remote disk mirroring in a computer system. A source backup copy is made locally available to a target for remote disk mirroring. Sectors are identified that are different between the source and target. A hash function is used over a block to be compared, with an adaptive number of tracking sectors per block, starting with a minimum block size.

Abstract: A method, and system for implementing enhanced fast full synchronization for remote disk mirroring in a computer system. A source backup copy is made locally available to a target for remote disk mirroring. Sectors are identified that are different between the source and target. A hash function is used over a block to be compared, with an adaptive number of tracking sectors per block, starting with a minimum block size.

Abstract: An apparatus, program product and method utilize hidden group membership to facilitate the processing of originator requests to a group in a clustered computer system. With hidden group membership, a requesting originator is temporarily joined to a group in such a manner that the originator is both hidden and provided with limited access rights, e.g., so that some of the messages sent by the members of a group when processing the request are neither sent to nor received by the originator.

Abstract: A computing system group member, signal bearing medium, and method. A configuration of a computing system group member is determined to be able to assume a role of a primary member of the computing system group and, in response thereto, a first status is assigned in the member. All members of the computing system group receive, in order, all messages directed to group members. A second status is assigned in response to determining that the configuration of the member is not able to support performance as a primary member. The member then processes, within the member, all messages that are transmitted to all members of the group when the member is assigned the first status and when the member is assigned the second status. The configuration of the member, while assigned either the first status or the second status, is adjusted based upon contents of the messages.

Abstract: A computing system group member, signal bearing medium, and method. A configuration of a computing system group member is determined to be able to assume a role of a primary member of the computing system group and, in response thereto, a first status is assigned in the member. All members of the computing system group receive, in order, all messages directed to group members. A second status is assigned in response to determining that the configuration of the member is not able to support performance as a primary member. The member then processes, within the member, all messages that are transmitted to all members of the group when the member is assigned the first status and when the member is assigned the second status. The configuration of the member, while assigned either the first status or the second status, is adjusted based upon contents of the messages.

Abstract: An apparatus, program product and method support the dynamic modification of cluster communication parameters such as a fragmentation size parameter through controllably deferring the processing of a requested fragmentation size change in a source node until after receipt an acknowledgment message for at least one unacknowledged message sent by the source node to a plurality of target nodes. By controllably deferring such processing until it is confirmed that any such previously-unacknowledged messages sent by a source node have been received by any target nodes, synchronization between the source node and the target nodes may be obtained, and a fragmentation size change may occur in a coordinated fashion such that future messages from the source node to the target node will be processed by both the source and the target nodes using the modified fragmentation size parameter.

Abstract: A computing node that functions as a member within a computing system group, such as a cluster, that has a status allowing receipt of group messages even though the node is not an active member of the cluster. The node is able to function as a primary member or as a backup member that controls redundant resources to be utilized in case of a failure. The computing node is able to have one of two status values, an “Active” status and an “Ineligible” status. Members that are able to function as a primary member have an “Active” status assigned, and a member that is not configured or otherwise eligible to perform as a primary member is assigned an “Ineligible” status. Members with an Ineligible status receive all group messages and therefore are able to become configured and eligible to become a primary member.

Abstract: A computing system group processing architecture that facilitates asymmetric processing at different computing nodes within a group or cluster of nodes. Nodes within a group are assigned to subgroups. Each node in a subgroup performs similar processing, but nodes in different subgroups are able to perform different processing for the same group level protocol. All nodes monitor processing completion votes that are cast by all nodes, and node in subgroups that finish processing before other subgroups synchronize to the processing of those other subgroups by casting dummy votes during vote rounds of other subgroups that are still processing their subgroup protocol.

Abstract: A method and apparatus for joining a plurality of nodes to a cluster. Each node in the cluster maintains a respective membership list identifying each active member node of the cluster. Membership change messaging is managed relative to multiple concurrent start requests to ensure that a first node is added to the respective membership lists before broadcasting a membership change message (MCM) in response to which, the nodes of the cluster, inclusive of the first node, add the second node to the respective membership lists.

Abstract: An apparatus, program product and method utilize hidden group membership to facilitate the processing of originator requests to a group in a clustered computer system. With hidden group membership, a requesting originator is temporarily joined to a group in such a manner that the originator is both hidden and provided with limited access rights., e.g., so that some of the messages sent by the members of a group when processing the request are neither sent to nor received by the originator.

Abstract: Members of a primary-backup group in a clustered computer system are organized into subgroups to manage primary and backup resources being managed by the group. Group members are placed into subgroups based upon their access to particular resources, such that a primary subgroup may be defined comprised of members having access to a common primary resource, with one or more backup subgroups defined comprised of members having access to a common backup resource. A join protocol is used to determine to which of a plurality of resources managed by the primary-backup group a joining member has access, and to add the joining member to a subgroup for a resource to which the joining member has access.

Abstract: Methods, systems and articles of manufacture for automatically starting a node in a clustered computer system. A starting state value may be assigned to the node and a discovery process initiated to find a sponsor node. If a sponsor node is found, the node is joined with the sponsor node in the clustered computer system. If a sponsor node is not found, the node is started as a one-node cluster in the clustered computer system. An active state value is assigned to the node upon inclusion into the clustered computer system.

Abstract: Failover processing that accommodates failures of backup computing nodes and resources, such as data storage units and printers. Failure of a computing node that controls resources causes another computing node to assume control of the resources controlled by the failed node. Failure of the primary computing node causes another computing node, at either the same or at a different site, to be selected as the new primary node. Failure of a resource at the primary site causes the site with the next highest priority backup resource to become the new primary site. Failure of a backup computing node causes a new backup node at the same site as the failed backup node to replace the failed backup node as host for the site's resources. Backup mirroring data flows are then adjusted to reflect the new functions of the affected nodes.

Abstract: An apparatus and method passively determine when a job in a clustered computing environment is dead. Each node in the cluster has a cluster engine for communicating between each job on the node and jobs on other nodes. A protocol is defined that includes one or more acknowledge (ACK) rounds, and that only performs local processing between ACK rounds. The protocol is executed by jobs that are members of a defined group. Each job in the group has one or more work threads that execute the protocol. In addition, each job has a main thread that communicates between the job and jobs on other nodes (through the cluster engine), routes appropriate messages from the cluster engine to a work thread, and signals to the cluster engine when a fault occurs when the work thread executes the protocol. By assuring that a dead job is reported to other members of the group, liveness information for group members can be monitored without the overhead associated with active liveness checking.