International Business Machines Corporation

Jason Robert Almeida

William Bradley Schwartz

Eric Richard Kern

Scott Neil Dunham

William Gabriel Pagan

Adam Lee Soderlund

Edward Klodnicki

Gregg Kent Gibson

Marc V Stracuzza

Willie James Nathan, Jr

Edward Zorek

A method for peer-to-peer management module configuration redundancy and recovery can be provided. The method can include fragmenting configuration data for a specified management module configured to manage systems components in a blade environment. The method also can include identifying peer management modules communicatively connected to the specified management module. The method yet further can include transmitting different ones of the fragmented configuration data to different ones of the peer management modules. In response to a reset condition in the specified management module, the method can provide for the retrieval of the fragmented configuration data from the peer management modules. Thereafter, the method can provide for the re-assembly of the retrieved fragmented configuration data and the application of the re-assembled fragmented configuration data to the specified management module.

Peer-to-peer module configuration redundancy and recovery management

Updating firmware on multiple systems or nodes within a merged networked environment includes providing firmware update code and a firmware update utility to a primary node. The firmware update utility determines the presence of a multi-node partition and detects the partition's configuration. The configuration determination includes determining the location of a remote service processor on each secondary node. The primary node creates an image of the firmware update code and distributes the created image to each of the secondary node service processors over a sideband link. Each of the remote service processors would then restart their respective systems. The node's BIOS detects the presence of the firmware update code on the service processor and forces the node to boot the update code directly. After the firmware update is complete, the firmware update code is deleted. When it subsequent restart occurs, the nodes will boot to the merged state.

Firmware update mechanism in a multi-node data processing system

A method, system, and program product supporting dynamic configuring of a multi-node computer. The system includes a scalability management module directly coupled to each node in the multi-node computer. The scalability management module sets and maintains configuration parameters for the multi-node computer, wherein if one of the nodes is removed from the multi-node computer, a hot-spare node can be dynamically configured to replace the removed node without having to reconfiguring or physically reconnect the remaining nodes

Scalability management module for dynamic node configuration

A method and system for allowing nodes in a multi-node computer to be appropriated by a master node in the multi-node computer. The node to be appropriated is suspended into an ACPI S3 Sleep State, causing current system operations state information to be stored in a backup memory in the appropriated node. The master node then populated a primary memory in the appropriated node with OS and other information required to join a partition that includes the master node. When the master node no longer wishes to use the appropriated node, the backup memory in the appropriated node is mirrored back into the primary memory. When the appropriated node 'wakes up' from the S3 state, it continues executing software commands where it left off, without knowing anything that had happened after going into the S3 state.

Dynamic node partitioning utilizing sleep state

Growing community of inventors

Raleigh, NC, United States of America

Jason Robert Almeida