International Business Machines Corporation

Kiet Anh Tran

Van Hoa Lee

Tam D Bui

George John Dawkins

David Lee Randall

Jayeshkumar M Patel

Richard Louis Arndt

Adalberto Guillermo Yanes

Chetan Mehta

David R Willoughby

Michael Anthony Perez

Pat Allen Buckland

Amir Simon

Keng-Hiup Ng

A system for managing input/output drawers within a data processing system. A unique identifier is assigned to each of a plurality of drawers, and is used by the operating system to identify the drawers in the system regardless of how these drawers are interconnected. Another unique PCI-bridge identifier is assigned to each of a plurality of PCI Host bridges (PHBs) from all drawers, and is used by the operating system to perform input/output processes to devices associated with the plurality of PHBs such that the ODM object for each of the PHBs remains the same regardless of how the drawer is interconnected in the system. When a new drawer is added to the system, a new unique identifier is assigned to the new drawer ensuring that the unique identifiers previously assigned to the other drawers are not used to identify the new drawer.

Permanent open firmware PCI host bridge (PHB) unit addressing to support dynamic memory mapping and swapping of I/O drawers

A method, system, and apparatus for synchronizing device, node, and drawer addresses between two networks within a data processing system is provided. In one embodiment, a service processor assigns a plurality of SPCN addresses to each of a plurality of devices in the data processing system. System firmware then determines the RIO addresses corresponding to the plurality of devices. If one of the SPCN addresses is not the same as the RIO address for the corresponding device, node, or drawer, then the service processor reassigns a new SPCN address to the corresponding device, node, or drawer such that the new SPCN address is identical to the RIO address for a corresponding device, node, or drawer.

Method of synchronizing multiple networks using permanent addressing scheme

A method, apparatus and program for booting a non-uniform-memory-access (NUMA) machine are provided. The invention comprises configuring a plurality of standalone, symmetrical multiprocessing (SMP) systems to operate within a NUMA system. A master processor is selected within each SMP; the other processors in the SMP are designated as NUMA slave processors. A NUMA master processor is then chosen from the SMP master processors; the other SMP master processors are designated as NUMA slave processors. A unique NUMA ID is assigned to each SMP that will be part of the NUMA system. The SMPs are then booted in NUMA mode in one-pass with memory coherency established right at the beginning of the execution of the system firmware.

Method and apparatus to concurrently boot multiple processors in a non-uniform-memory-access machine

A method, system, and product are described for configuring remote input/output (RIO) hubs within a data processing system. Each one of the RIO hubs is assigned to one of multiple slave processors which are included within the data processing system. Each one of the slave processors which has an assigned RIO hub then configures its assigned RIO hub. Each RIO hub has an associated data structure that is updated with current configuration information by the slave processor assigned to configure that RIO hub. When the slave processor has finished configuring its assigned RIO hub, the slave processor then sets a configuration flag to indicate the completion of the configuration of the RIO hub.

Simultaneous configuration of remote input/output hubs utilizing slave processors in a multi-processor, multi-RIO hub data processing system

A method and apparatus preserve the data structures established in the earliest stage of initial power load, rather than each system firmware component rediscovering the hardware components of the system. Thus, the data structure is available at later stages for other firmware components. In a logical partitioning machine, the open firmware partition manager can utilize the data structure to support the partition's open firmware device tree construction. The partition manager customizes the copies of these data structures residing in the partition's memory. For hardware devices in the system but not belonging to the partition, the device information is cleared and marked invalid. After the data structures are established and updated by the earliest firmware I/O configuration component, the addresses of these structures are provided to the open firmware component. The open firmware copies these data structures to its internally safe working area and uses the copies for its normal operation. When runtime abstraction service firmware component is instantiated, the addresses of the structures of open firmware's copies are provided by the open firmware component to runtime abstraction service. Again, runtime abstraction service makes copies of these structures within its internally safe working space for its operation.

Method and apparatus for preservation of data structures for hardware components discovery and initialization

A method, system and program for architecturally identifying data processor implementations are provided. The invention comprises assigning a plurality of least significant bits in a processor's identification register to a unique value. This value can be assigned to these bits permanently during manufacture and is used to identify the bit specification for a specific processor implementation. The present invention can be generalized to include any processor architecture that comprises a plurality of instruction subsets for different bit specifications.

Identifying architecture and bit specification of processor implementation using bits in identification register

A data processing system and method are disclosed for displaying a graphical depiction of the system configuration of the data processing system. Execution of a boot process of the data processing system is started. Prior to a completion of the boot process, a configuration of the data processing system is determined by the system itself. A graphical depiction of the configuration is then generated. The graphical depiction is then graphically displayed utilizing a display screen which is included in the data processing system. The graphical depiction illustrates each device included in the system as well as how the devices are interconnected. Thereafter, the execution of the boot process is completed. The steps of determining a configuration, generating a graphical depiction, and graphically displaying the graphical depiction are completed prior to completing the booting the data processing system, and thus prior to an operating system being executed by the data processing system.

Data processing system and method for displaying a graphical depiction of system configuration

A method, system, and computer program product for enforcing logical partitioning of input/output slots within a data processing system is provided. In one embodiment, the system includes a hypervisor and at least one DMA address checking component. The hypervisor receives non-direct-memory-access requests for access to input/output slots and prohibits devices within one logical partition from accessing the input/output slots assigned to a different logical partition. The DMA address checking component receives direct-memory-access requests and prohibits requests for addresses not within the same logical partition as the requesting device from being completed. Requests with addresses corresponding to the same logical partition as the requesting device are placed on the primary PCI bus by the DMA address checking component for delivery to the system memory.

Method and apparatus to implement logical partitioning of PCI I/O slots

A method, system, and apparatus for modifying bridges within a data processing system to provide improved performance is provided. In one embodiment, the data processing system determines the number of input/output adapters connected underneath each PCI host bridge. The data processing system also determines the type of each input/output adapter. The size and number of buffers within the PCI host bridge is then modified based on the number of adapters beneath it as well as the type of adapters beneath it to improve data throughput performance as well as prevent thrashing of data. The PCI host bridge is also modified to give load and store operations priority over DMA operations. Each PCI-to-PCI bridge is modified based on the type of adapter connected to it such that the PCI-to-PCI bridge prefetches only an amount of data consistent with the type of adapter such that excess data is not thrashed, thus requiring extensive repetitive use of the system buses to retrieve the same data more than once.

Performance enhancement implementation through buffer management/bridge settings

A method, system, and apparatus of recording information generated by a data processing system prior to completion enablement of programmed input/output services for the data processing system is provided. In one embodiment, a service processor receives an attention interrupt from a host processor. The service processor then stops the operation of all host processors in the data processing system. The service processor then reads the information, such as a system checkpoint, from a buffer within the host processor's system memory and writes the information into a non-volatile random access memory as well as displays the information to a user via a video display. The service processor then restarts the host processors.

Growing community of inventors

Cedar Park, TX, United States of America

Kiet Anh Tran