International Business Machines Corporation

Matthew Scott Spinler

Brent William Jacobs

Douglas Michael Boecker

Daniel Morgan Crowell

Shaun Allan Wetzstein

Nathan D Miller

Curtis Shannon Eide

Christopher John Engel

Kaveh Naderi

Sheldon Ray Bailey

Wayne Allan Britson

Bradley W Bishop

An approach is provided in which a host system receives a request to power down a selected I/O module located in a PCIe I/O expansion drawer. The host system identifies at least one cable card located in the host system that corresponds to the selected I/O module and transmits at least one set of sideband signals to the PCIe I/O expansion drawer through at least one set of PCIe cable links. The host system, in turn, inhibits the transmission of the at least one set of sideband signals to power down the selected I/O module.

Concurrent maintenance of modular PCIe I/O expansion drawer

A method for maintaining vital product data (VPD) of each field replaceable unit (FRUs) in a computer system, the computer system including a first FRU and a second FRU operatively coupled with the first FRU. The method includes calculating a parity for the VPD of the second FRU, and upon detecting a failure of the second FRU, regenerating the VPD for the failed second FRU using the parity.

Parity-based vital product data backup

A method for maintaining vital product data (VPD) contained in an EEPROM (Electrically Erasable Programmable Read-Only Memory) on a field replaceable unit (FRU) of a computer system that has a cache. The method includes maintaining a copy of the VPD in the cache, retrieving the copy of the VPD from the cache upon receiving a read request of the VPD, and, upon receiving a write request to write data to the VPD, writing the data to the copy of the VPD, determining whether the VPD in the EEPROM is in synchronization with the copy of the VPD in the cache, and, if the VPD and the copy of the VPD are in synchronization, writing the data to the EEPROM.

Recovering failed writes to vital product data devices

A system, method, and computer-usable medium for applying a destructive firmware update in a non-destructive manner. According to a preferred embodiment of the present invention, during operation of a multiprocessor data processing system, a service processor updates firmware in the multiprocessor data processing system from a first firmware setting to a second firmware setting. The service processor iteratively applies the second firmware setting to hardware within the multiprocessor data processing system by de-allocating a first hardware device when the second firmware setting includes at least one destructive operation targeted to the first hardware device, performing the destructive operation on the first hardware device, and re-allocating the first hardware device into the multiprocessor data processing system when the destructive operation is complete.

System and method for applying a destructive firmware update in a non-destructive manner

A method for managing a system's computer resources, includes: detecting an error condition in a computer resource; labeling the computer resource as not usable based on the error condition detected; reconfiguring the remaining computer resources to compensate for the detected error condition based on a failure mode policy; and wherein the failure mode policy manages the computer resources by one of: maximizing the amount of the remaining computer resources (mode 1), and maximizing the speed of the remaining computer resources (mode 2).

Method and system for managing resources during system initialization and startup

A method utilizes targeted boot diagnostics in connection with a boot operation to automate the handling of hardware failures detected during startup or initialization of a computer. In particular, in response to detection of a failure after initiation of and during performance of a boot operation, a targeted diagnostic operation is initiated on at least one hardware device in the computer in response to detecting the failure, such that after the targeted diagnostic operation is initiated, the boot operation may be completed.

Computer boot operation utilizing targeted boot diagnostics

An apparatus, program product and method utilize targeted boot diagnostics in connection with a boot operation to automate the handling of hardware failures detected during startup or initialization of a computer. In particular, in response to detection of a failure after initiation of and during performance of a boot operation, a targeted diagnostic operation is initiated on at least one hardware device in the computer in response to detecting the failure, such that after the targeted diagnostic operation is initiated, the boot operation may be completed.

Growing community of inventors

Rochester, MN, United States of America

Matthew Scott Spinler