Abstract: Disclosed aspects relate to memory affinity management in a shared pool of configurable computing resources that utilizes non-uniform memory access (NUMA). An access relationship is monitored between a set of hardware memory components and a set of software assets. A set of memory affinity data is stored. The set of memory affinity data indicates the access relationship between the set of software assets and the set of hardware memory components. Using the set of memory affinity data, a NUMA utilization configuration with respect to the set of software assets is determined. Based on the NUMA utilization configuration, a set of accesses pertaining to the set of software assets and the set of hardware memory components is executed.

Abstract: A method, computer program product, and system for selective memory mirroring including identifying, by a computer during an initial program load, predictively deconfigured memory units and memory interfaces, wherein the predictively deconfigured memory units and memory interfaces are marked by the computer for removal from a computer configuration prior to the initial program load, analyzing the predictively deconfigured memory units and memory interfaces to determine a level of granularity for selective memory mirroring and initiating selective memory mirroring at the determined level of granularity using the analyzed predictively deconfigured memory units and memory interfaces.

Abstract: Multiple functional domains are identified for controlling a grouping of servers. A controller assigns, to each functional domain of the multiple functional domains, a separate primary server from among the grouping of servers and a separate backup server from among the grouping of servers, wherein for each functional domain the separate primary server is different from the separate backup server based on a separate affinity selection for each functional domain. Responsive to detecting a failure in a particular primary server of the grouping of servers, the controller automatically switches control of a particular functional domain assigned to the particular primary server from the particular primary server to a particular backup server assigned to the particular functional domain.

Abstract: Data communication between nodes of a symmetric multiprocessing (SMP) computing system can be maintained during the replacement of a faulty cable used to interconnect the nodes. A data bus error caused by the faulty cable is detected, resulting in the activation of an alternative data path between the nodes, and the disabling of a data path through the faulty cable. A system notification indicating the faulty cable is issued, and in response to the nodes being interconnected with a replacement cable, the replacement cable is tested for reliability. After the replacement cable is determined to be reliable, a data path through the replacement cable is activated.

Abstract: Tracking data transfers in an input/output adapter card system to determine whether the adapter cards are well-placed with respect to the components (for example dynamic random access memories) with which the adapter cards respectively are observed to communicate data. Some embodiments use a heuristic value for each adapter card in the system based on inter node transfers and intra node transfers, which are separately weighted and summed over some predetermined time interval in order to obtain the heuristic value.

Abstract: Tracking data transfers in an input/output adapter card system to determine whether the adapter cards are well-placed with respect to the components (for example dynamic random access memories) with which the adapter cards respectively are observed to communicate data. Some embodiments use a heuristic value for each adapter card in the system based on inter node transfers and intra node transfers, which are separately weighted and summed over some predetermined time interval in order to obtain the heuristic value.

Abstract: Disclosed aspects relate to symmetric multiprocessing (SMP) management. A first SMP topology may be identified by a service processor firmware. The first SMP topology may indicate a first set of connection paths for a plurality of processor chips of a multi-node server. A second SMP topology may be identified by the service processor firmware. The second SMP topology may indicate a second set of connection paths for the plurality of processor chips of the multi-node server. The second SMP topology may differ from the first SMP topology. An error event related to the first SMP topology may be detected. A set of traffic may be routed using the second SMP topology. The set of traffic may be routed by the service processor firmware in response to detecting the error event related to the first SMP topology.

Abstract: Disclosed aspects relate to data packet management in a memory-constrained environment. A data packet having a command may be received by a first device. The data packet may be processed by the first device using the command. A first portion of processed data may be loaded in the memory component by the first device. The first portion of processed data may be communicated by the first device to a second device. A second portion of processed data may be loaded in the memory component by the first device. The second portion of processed data may be communicated by the first device to the second device. A trailer may be loaded in the memory component by the first device. The trailer may be communicated by the first device to the second device.

Abstract: Disclosed aspects relate to asset placement management in a shared pool of configurable computing resources having both a plurality of physical servers and a plurality of physical cooling fans. A set of relationships may be identified with respect to the plurality of physical cooling fans. In response to identifying the set of relationships, a placement arrangement may be determined for a set of assets with respect to the plurality of physical servers. The set of assets may be deployed based on the placement arrangement.

Abstract: A computer-implemented method for migrating a buffer used for direct memory access (DMA) may include receiving a request to perform a DMA data transfer between a first partitionable endpoint and a buffer of a first memory in a system having two or more processor chips. Each processor chip may have an associated memory and one or more partitionable endpoints. The buffer from the first memory may be migrated to a second memory based on whether the first memory is local or remote to the first partitionable endpoint, and based on a DMA data transfer activity level. A memory is local to a partitionable endpoint when the memory and the partitionable endpoint are associated with a same processor chip. The DMA data transfer may then be performed.

Abstract: In an approach for selecting a boot-up path in a multi-node server, a processor receives a first set of computing capability data for a first boot-up path of a server and a second set of computing capability data for a second boot-up path of the server. A processor compares the first set of computing capability data to the second set of computing capability data. A processor determines that the first boot-up path has greater computing capabilities than the second boot-up path based on the comparison. Responsive to determining the first boot-up path has greater computing capabilities, a processor boots-up the server using the first boot-up path.

Abstract: Embodiments of the present invention provide systems and methods for resource allocation. The systems and methods for resource allocation include: configuring a plan to utilize computer resources; partitioning computer resources; and applying a set of two or more hypervisors, which use a single service processor, to execute the plan to utilize computer resources. The hypervisors facilitate the partitioning of the computer resources, group partitions of the computer resources, control access to nodes, and change node boundaries.

Abstract: A method, computer program product, and system for selective memory minoring including identifying, by a computer during an initial program load, predictively deconfigured memory units and memory interfaces, wherein the predictively deconfigured memory units and memory interfaces are marked by the computer for removal from a computer configuration prior to the initial program load, analyzing the predictively deconfigured memory units and memory interfaces to determine a level of granularity for selective memory minoring and initiating selective memory minoring at the determined level of granularity using the analyzed predictively deconfigured memory units and memory interfaces.

Abstract: A computer-implemented method for migrating a buffer used for direct memory access (DMA) may include receiving a request to perform a DMA data transfer between a first partitionable endpoint and a buffer of a first memory in a system having two or more processor chips. Each processor chip may have an associated memory and one or more partitionable endpoints. The buffer from the first memory may be migrated to a second memory based on whether the first memory is local or remote to the first partitionable endpoint, and based on a DMA data transfer activity level. A memory is local to a partitionable endpoint when the memory and the partitionable endpoint are associated with a same processor chip. The DMA data transfer may then be performed.

Abstract: In an approach to guided virtual machine migration, one or more computer processors determine a target host computer available for a migration of a virtual machine from a source host computer. The one or more computer processors identify one or more resources of the target host computer with one or more predictive errors. The one or more computer processors determine whether the virtual machine uses one or more of the identified one or more resources with one or more predictive errors. The one or more computer processors rank a migration path for the virtual machine from the source host computer to the target host computer with a designation. The one or more computer processors create a target host map, wherein the target host map indicates at least one migration path for the virtual machine from the source host computer to the target host computer.

Abstract: Multiple functional domains are identified for controlling a grouping of servers. A controller assigns, to each functional domain of the multiple functional domains, a separate primary server from among the grouping of servers and a separate backup server from among the grouping of servers, wherein for each functional domain the separate primary server is different from the separate backup server based on a separate affinity selection for each functional domain. Responsive to detecting a failure in a particular primary server of the grouping of servers, the controller automatically switches control of a particular functional domain assigned to the particular primary server from the particular primary server to a particular backup server assigned to the particular functional domain.

Abstract: To perform a workload, a plurality of virtual machines (VMs) may be assigned to a plurality of blade servers. To assign the VMs, a computing system uses the characteristics of the workloads that will be executed by the virtual machines such as the number of processors or the amount of memory, storage the workload is estimated to use, and the like. Based on these workload characteristics, the computing system determines an optimal solution for deploying the VMs onto the blade servers. In one embodiment, the computing system determines whether two or more of the blade servers should be stitched together. For example, the computing system compares the workload characteristics of one of the virtual machine to the combined available resources of at least two of the blade servers. If the combined available resources satisfy the workload characteristics, the computing system stitches the blade servers together.

Abstract: To perform a workload, a plurality of virtual machines (VMs) may be assigned to a plurality of blade servers. To assign the VMs, a computing system uses the characteristics of the workloads that will be executed by the virtual machines such as the number of processors or the amount of memory, storage the workload is estimated to use, and the like. Based on these workload characteristics, the computing system determines an optimal solution for deploying the VMs onto the blade servers. In one embodiment, the computing system determines whether two or more of the blade servers should be stitched together. For example, the computing system compares the workload characteristics of one of the virtual machine to the combined available resources of at least two of the blade servers. If the combined available resources satisfy the workload characteristics, the computing system stitches the blade servers together.

Abstract: Data communication between nodes of a symmetric multiprocessing (SMP) computing system can be maintained during the replacement of a faulty cable used to interconnect the nodes. A data bus error caused by the faulty cable is detected, resulting in the activation of an alternative data path between the nodes, and the disabling of a data path through the faulty cable. A system notification indicating the faulty cable is issued, and in response to the nodes being interconnected with a replacement cable, the replacement cable is tested for reliability. After the replacement cable is determined to be reliable, a data path through the replacement cable is activated.

Abstract: Embodiments of the present invention provide systems and methods for resource allocation. The systems and methods for resource allocation include: configuring a plan to utilize computer resources; partitioning computer resources; and applying a set of two or more hypervisors, which use a single service processor, to execute the plan to utilize computer resources. The hypervisors facilitate the partitioning of the computer resources, group partitions of the computer resources, control access to nodes, and change node boundaries.