Abstract: A computer program product and computer-implemented method include operations including identifying a software update payload that is available for distribution and identifying compatibility data for the software update payload, wherein the compatibility data identifies configurations of a computing device that are compatible with the software update payload. The operations further include forming an update package that includes the software update payload and the compatibility data, digitally signing the update package, and providing the signed update package to one or more computing devices over a network.

Abstract: A computer program product includes a non-transitory computer readable medium and program instructions embodied therein. An apparatus includes a non-transitory data storage device storing program instructions and at least one processor configured to process the program instructions. The program instructions are configured to, when processed by the at least one processor, cause the apparatus to perform various operations. The operations may include monitoring a tamper-detection sensor of an edge device, wherein the edge device performs a tamper-prevention operation in response to an output signal from the tamper-detection sensor. The operations may further include detecting entry of an authorized person into a facility where the edge device is located and automatically sending a disabling instruction to the edge device to cause the edge device to temporarily disable the tamper-prevention operation of the edge device in response to detecting entry of the authorized person into the facility.

Abstract: A method for unlocking a firmware setup utility of a computer server without a firmware setup utility user password. The method includes booting the server to a firmware setup utility interface and receiving a user request to unlock the firmware setup utility without the password. The method further includes receiving, via a web interface to a baseboard management controller (BMC) of the server, login credentials for accessing a BMC configuration, wherein the login credentials are authenticated by the BMC. The firmware setup utility causes, in response to the request, the BMC to send a nonce code to a registered destination address stored by the BMC. User input containing the nonce code is received through the web interface to the BMC, and the firmware setup utility is unlocked in response to determining that the nonce code received through the BMC web interface matches the nonce code in the message.

Abstract: Methods of boot process monitoring include receiving, by a service processor, a notice that a boot process for a server has started, monitoring a video buffer of a console of the server, and identifying, based on the monitoring, a potential error in the boot process.

Abstract: A baseboard management controller (BMC) may obtain hardware performance data for hardware devices installed in a server that includes the BMC, provide the hardware performance data to a smart network interface controller (Smart NIC) in the server, and receive from the Smart NIC a hardware failure alert that identifies a hardware device predicted to experience a failure based on the hardware performance data. Optionally, the BMC may access a container stored in firmware of the BMC, wherein the container includes a software application such as an artificial intelligence engine trained for hardware failure prediction. The BMC may copy the container to the Smart NIC for running the software application to analyze the hardware performance data and generate a hardware failure alert. The BMC may receive the alert and output a user notification identifying the hardware device that is subject to the alert.

Abstract: A computer program product, a method and a baseboard management controller for performing the operations of computer program product or method. The operations include identifying a current utilization level of the processor of the baseboard management controller, obtaining hardware performance data for hardware devices installed in a server that includes the baseboard management controller, running an application program that performs hardware failure prediction, and controlling an amount of the hardware performance data that is used by the application program to perform the hardware failure prediction, wherein the amount of the hardware performance data is controlled as a function of the current utilization level of the processor.

Abstract: The present disclosure describes a method for adaptive event forwarding. The method includes receiving a plurality of predefined event subscription rules associated with one or more event subscribers, detecting a system and facility event associated with a system and facility operation of a computing system, determining context of the system and facility operation associated with the detected system and facility event, and determining whether to forward the detected system and facility event to an event subscriber based on the context of the system and facility operation and the plurality of predefined event subscription rules.

Abstract: A method for dynamic compute composition includes determining that a composition condition for a composable system is satisfied, and composing the composable system according to the composition condition to redistribute workloads among two or more composable resources of the composable system.

Abstract: A batch processing method includes receiving a register request from an edge node, determining a queue priority of a batch workload for batch processing of edge-node data in a batch workload line of a Multi-Access Edge Computing (MEC) compute service host, and instructing the MEC compute service host to place the batch workload in the batch workload line according to the determined priority. The register request requests a service of the MEC compute service host for batch processing of the edge-node data stored in a data buffer of the edge node.

Abstract: A replacement node replaces a failed node and a baseboard management controller (BMC) for the replacement node generates a nonce code that is accessible to an authenticated user. An edge management node receives the nonce code from the user and sends a maintenance token to a BMC of a peer node in an edge cluster, wherein the peer nodes BMCs within the cluster are in a BMC federation that included the failed node BMC and have access to a BMC configuration for the failed node. The management node sends the token and the nonce code to the replacement node BMC for authentication of the token. The peer node BMC sends the token received from the management node to the replacement node BMC for authentication of the peer node BMC. The authenticated peer node BMC may then deploy the BMC configuration to the replacement node BMC.

Abstract: A method for replacing at least one hardware assembly of a data processing apparatus includes managing, by a system management software, the data processing apparatus with a service processor and a plurality of hardware assemblies, obtaining, by the system management software, first system configuration data, first system vital product data (SVPD), and first server identity data of the data processing apparatus from the service processor or through the service processor, obtaining, by the system management software, second SVD and second server identity data of the data processing apparatus from the service processor or through the service processor, comparing, by the system management software, the first server identity data with the second server identity data, and configuring, by the system management software, the data processing apparatus based on the first system configuration data and the first SVPD according to a comparison result.

Abstract: A method for reducing a total power consumption of multiple servers includes determining a power consumption characteristic of each of the multiple servers; retrieving, by a manager, the power consumption characteristic of the each of the multiple servers; and performing load balancing on the multiple servers through the manager to reduce the total power consumption of the multiple servers. The load balancing is performed based at least in part on the power consumption characteristic of one or more of the multiple servers.

Abstract: An apparatus, such as a computing node, includes a storage device for storing program instructions and a service processor for processing the program instructions to: send an out-of-band request for access to an operator panel, wherein the out-of-band request is sent over a local network domain operatively coupling a plurality of computing nodes; receive a first out-of-band reply identifying an address and one or more capabilities of an operator panel accessible over the local network domain; and negotiate an active link to the operator panel over the local network domain. Another apparatus is similar but further includes an operator panel operatively coupled to a service processor, the service processor for processing the program instructions to: receive the out-of-band request over the local network domain; send the first out-of-band message; and negotiate an active link between the operator panel and a computing node.

Abstract: Methods, apparatus, and computer program products for configurable secure boots are disclosed. One method includes determining, by a processor of a computing apparatus, whether a geographical location of the computing apparatus corresponds to a predetermined location, performing a boot process for booting up the computing apparatus in response to the geographical location of the computing apparatus corresponding to the predetermined location, and disabling the boot process from booting up the computing apparatus in response to the geographical location of the computing apparatus failing to correspond to the predetermined location. Computing apparatus and computer program products for performing the method are also disclosed.

Abstract: A method for an intelligent multi-path call home includes detecting, at a BMC, an error in a computing device managed by the BMC and sending a call home message to a management server. The computing device is one of a plurality of computing devices each with a BMC in communication with the management server. The management server is programmed to relay the call home message to a call home destination remote from the computing devices and management server. The method includes determining that the management server failed to receive the call home message and/or failed to successfully relay the call home message to the call home destination, and transmitting, from the BMC, the call home message to the call home destination in response to determining that the management server failed to receive the call home message and/or failed to successfully relay the call home message to the call home destination.

Abstract: A computer program product and computer-implemented method include operations including identifying a software update payload that is available for distribution and identifying compatibility data for the software update payload, wherein the compatibility data identifies configurations of a computing device that are compatible with the software update payload. The operations further include forming an update package that includes the software update payload and the compatibility data, digitally signing the update package, and providing the signed update package to one or more computing devices over a network.

Abstract: A computer program product includes a non-transitory computer readable medium and program instructions embodied therein. An apparatus includes a non-transitory data storage device storing program instructions and at least one processor configured to process the program instructions. The program instructions are configured to, when processed by the at least one processor, cause the apparatus to perform various operations. The operations may include monitoring a tamper-detection sensor of an edge device, wherein the edge device performs a tamper-prevention operation in response to an output signal from the tamper-detection sensor. The operations may further include detecting entry of an authorized person into a facility where the edge device is located and automatically sending a disabling instruction to the edge device to cause the edge device to temporarily disable the tamper-prevention operation of the edge device in response to detecting entry of the authorize person into the facility.

Abstract: Transparent memory management for over-subscribed accelerators is disclosed. A request from a remote initiator to execute a workload on a shared accelerator is received at a host system comprising the shared accelerator. A determination is made that there is insufficient physical memory of the accelerator to accommodate the request from the remote initiator. Responsive to determining that there is insufficient physical memory of the accelerator. An allocation of host system memory is requested for the remote initiator from the host system. A mapping between the remote initiator and the allocation of host system memory is then created.

Abstract: A method for an intelligent multicast proxy between containers and an outside network includes receiving, at a proxy, a multicast discovery message from a container of one or more containers running on a host OS of a server. The proxy is running on the host OS and the server is connected to computing devices over a subnet network. The method includes adding a container tag to a user defined field of the multicast discovery message and relaying the multicast discovery message with the container tag to two or more of the computing devices connected to the subnet network. The method includes receiving a response to the multicast discovery message, where the response includes the container tag, and relaying the response to the container based on the container tag.

Abstract: A computer program product and computer-implemented method include various operations. The operations include periodically obtaining a subset of a first failure data capture file from a baseboard management controller, analyzing the subset of the first failure data capture file to identify a performance degradation in one or more services performed by the baseboard management controller, and obtaining a complete copy of the first failure data capture file from the baseboard management controller in response to identifying the performance degradation, wherein the complete copy of the first failure data capture file is obtained from the baseboard management controller prior to the performance degradation reaching a performance level that triggers an automatic reset of the baseboard management controller. The operations may further include sending a notification to a user, wherein the notification identifies that the baseboard management controller has experienced the performance degradation.