International Business Machines Corporation

Ivan Ronald Olguin, Ii

Kevan D Holdaway

Jason James Graves

David Michael Morton

Lourdes Magally Gee

Nhu Thanh Nguyen

Earle Ellsworth

Gregg Steven Lucas

Douglas William Dewey

Brian D Hatfield

William Griswold Sherman

Melissa Jorgette Garcia

Dinesh Chandra Coca

James Blaine Engle

Jason James Gravees

An apparatus for collecting dump data collection receives an on demand data (ODD) dump request, pauses one or more scan loops, transfers dump data to an ODD dump buffer space, unpauses the scan loops, and offloads dump data from the ODD dump buffer space to the storage device. The apparatus may also prioritize dump data for transfer to the ODD dump buffer space, load balance dump data for transfer to the ODD dump buffer space, and schedule offloading of the dump data from the ODD dump buffer space to non-volatile storage.

Failure data collection system apparatus and method

A method is disclosed to update multiple devices disposed in a computing system comprising a plurality of devices. The method receives a request to perform a firmware image update for a plurality of designated target devices, where each of those designated target devices comprises a first firmware image, and where the request comprises a second firmware image. The method uploads the second firmware image to a shared memory device, where each of the designated target devices is in communication with that shared memory device, and broadcasts an update command to each of the plurality of devices. The method determines the device state of each of the designated target devices, and if each of the designated target devices reports either an operational device state or an error device state, then the method reports that the firmware update is complete.

Apparatus and method to update multiple devices disposed in a computing system

A method, apparatus, and system are disclosed for exchanging services in a distributed system. A communication module receives an advertisement of service capabilities for a service provider. The communication module further receives a registration of service requirements for a service consumer. A match module determines if the advertisement service capabilities match the registration service requirements. A configuration module configures the service provider to supply the service requirements of the service consumer if the advertisement service capabilities match the registration service requirements. An establishment module establishes a service relationship between the service provider and the service consumer. The service provider provides the service requirements of the service consumer.

Method, apparatus, and system for exchanging services in a distributed system

A method for implementing a sparing policy for a server by a management module in communication with the server and a plurality of additional servers is provided. The server is designated as a spare server. The spare server is maintained in a powered-off, standby state. A need for the spare server is determined. At least one of a basic input output system (BIOS) and an operating system (OS) for the spare server is selected. A volume operational on the spare server is selected for a sparing operation.

Implementation of sparing policies for servers

A method for implementing a remote basic input/output system (BIOS) on a multi-blade server is provided. A remote BIOS partition is created on a management module of the multi-blade server for each blade of the multi-blade server residing on the management module. BIOS settings for operation on a first blade of the multi-blade server are defined.

Remote BIOS for servers and blades

A system for implementing and controlling a plurality of server-specific policies for a plurality of servers using a management module in communication with the plurality of servers is provided. A policy controller module is operational on the management module. The policy controller module is adapted for defining a first policy of a plurality of policies for each of the plurality of servers, managing a plurality of rules relevant to an execution of the first policy, and coordinating the execution of the first policy with an execution of a second policy of the plurality of policies.

Policy control architecture for blade servers upon inserting into server chassis

A storage device implements a file profiling mechanism to minimize fragmentation. A plurality of files is organized according to a high or low read/write access frequency. A plurality of unchanging file types are placed in a first grouping. A plurality of oscillating file types are placed in a second grouping adjacent to the first grouping. A plurality of the high frequency read/write access files which are growing file types are placed in a third grouping adjacent to the second grouping. A remainder of the growing file types not placed in the third grouping is defragmented. The remainder of the growing file types is then placed in a fourth grouping adjacent to the third grouping.

File profiling to minimize fragmentation

Provided are techniques for restoring firmware. A first programmable hardware device determines that a second programmable hardware device needs a valid firmware image, retrieves a copy of the valid firmware image from an external memory, and sends the valid firmware image to the second programmable hardware device via a private communication link, wherein the private communication link enables private communication between the first programmable hardware device and the second programmable hardware device. The second programmable hardware device restores existing firmware using the valid firmware image.

Automated firmware restoration to a peer programmable hardware device

A method for selecting a basic input output system (BIOS) and an operating system (OS) for a server managed by a controller in communication with a plurality of servers is provided. The server is detected. A map describing a relationship between the server and the plurality of servers is consulted. The map at least partially defines a policy for the server. Vital product data (VPD) of the server is used in conjunction with the map and the policy to select at least one of the BIOS and the OS for the server prior to an application of power to the server.

System using vital product data and map for selecting a BIOS and an OS for a server prior to an application of power

A method of operation of a computer system having a master and slave Inter-IC (I2C) bus network includes detecting and isolating an I2C bus failure, configuring a failed I2C bus as offline, reconfiguring a remaining I2C bus as a multi-mastered bus, and masking the failed I2C bus from operation until the failed I2C bus can be repaired. A first test request is sent to a remote device from a local device. If the remote device receives the first test request, a remote bus mode is switched to a failure position, a local bus mode is switched to a multi-master position, and a second request is sent to the remote device to indicate position changes.

Growing community of inventors

Tucson, AZ, United States of America

Ivan Ronald Olguin, Ii