Abstract: A technique includes selecting paths of an interconnection fabric of a data center based on respective metric values that are associated with the paths. Each path extends from an associated host of the data center to an associated fabric-attached resource of the data center. The technique includes providing, to a fabric manager of the data center, a data structure that includes data representing the paths and the associated respective metric values. The technique includes receiving, by the fabric manger, a resource sharing request. The resource sharing request is associated with given hosts of the data center. The technique includes, responsive to the resource sharing request and based on the data structure, allocating a given fabric-attached resource to be shared by the given hosts.

Abstract: Examples described herein relate to allocating a low latency, healthy fabric-attached memory resource to a host device for downloading media. A resource composer may receive, from a host device, a request to download media from a pool of fabric-attached memory resources. The resource composer may identify, from the pool, a set of memory resources based on resource latency. The resource composer may group, based on a respective error history of a given memory resource, the set into a first group and a second group, where the respective error history of each of the memory resources in the first group includes fewer errors than the second group. The resource composer may select, from the first group, a memory resource to allocate to the host device and may allocate the memory resource to the host device. The media may be accessible to the host device at the allocated memory resource.

Abstract: The technique includes monitoring a secure datacenter, which includes computer platforms. The technique includes, responsive to the monitoring, receiving an alarm that represents a detected event associated with the secure datacenter. The technique includes, responsive to the alarm, determining whether the detected event complies with an approved maintenance task to be performed on a given computer platform. Determining whether the detected event complies with the approved maintenance task includes accessing a record corresponding to the approved maintenance task. The record includes entries corresponding to respective expected events that are associated with the approved maintenance task. Determining whether the detected event complies with the approved maintenance task further includes determining whether the record authorizes the detected event. The technique includes regulating whether the alarm is escalated responsive to the determination of whether the record authorizes the detected event.

Abstract: A system hash for each production system is generated. Each system hash includes a concatenation of a hardware hash and a software hash of each production system in the datacenter. A datacenter hash tree is created based on a combination of the system hashes. A test copy of the software hash of each of the production systems is created in respective test systems in the datacenter. In response to detecting a change in the datacenter hash tree, a modification in a system hash which resulted in the change is identified. The central copy of the software hash is compared with the test copy of the software hash. In response to a mismatch between the central copy and the test copy, occurrence of an unauthorized attack in a software of the production system is detected.

Abstract: A process includes accessing data representing a directed graph model state for a computer system. The directed graph includes a plurality of transitions among the model states, and the directed graph includes, for each transition, a transition identifier that is associated with the transition and a probability that is associated with the transition. The process includes characterizing a history of the computer system to reach a current state of the computer system. The current state corresponds to a given model state and the history corresponds to first transitions. Characterizing the history includes, based on the data, identifying first transition identifiers associated with the first transition, and applying a first arithmetic operator to the first transition identifier to provide a history identifier, which corresponds to the history.

Abstract: Approaches for classifying hardware components of a computing device using a classification system are described. In an example, by the classification system, a hardware configuration information of the computing device installed within a networked environment is obtained. The hardware configuration information may thus be processed based on a system classification model. The system classification model is to classify hardware components of the computing device as one of a plurality of hardware types. Once the hardware components are classified, a category of the computing device is determined. Based on the determined category, a target system software is identified and installed onto the computing device.

Abstract: Approaches for updating an error policy based on boot-time error information and run-time error information, are described. The error policy maps an error type with a prescribed action. In an example, the error policy is updateable based run-time error information corresponding to a computing device. The updated error policy may then be used for addressing boot-time errors of computing devices.

Abstract: Approaches for updating an error policy based on boot-time error information and run-time error information, are described. The error policy maps an error type with a prescribed action. In an example, the error policy is updateable based run-time error information corresponding to a computing device. The updated error policy may then be used for addressing boot-time errors of computing devices.

Abstract: SECURE DATA CENTER UPDATE AND MONITORING A system hash for each production system is generated. Each system hash includes a concatenation of a hardware hash and a software hash of each production system in the datacenter. A datacenter hash tree is created based on a combination of the system hashes. A test copy of the software hash of each of the production systems is created in respective test systems in the datacenter. In response to detecting a change in the datacenter hash tree, a modification in a system hash which resulted in the change is identified. The central copy of the software hash is compared with the test copy of the software hash. In response to a mismatch between the central copy and the test copy, occurrence of an unauthorized attack in a software of the production system is detected.

Abstract: In some examples, a system records, in a data structure stored in a non-volatile storage, information of memory errors in respective segments of a memory. The system determines whether memory errors of a subset of the segments satisfy a criterion, and in response to determining that the memory errors of the subset of the segments satisfy the criterion, the system groups the memory errors of the subset into a partition having a size greater than a size of a segment. The system records, in the data structure, information of memory errors in the partition, and in response to a restart of the system, retrieves the data structure from the non-volatile storage for use in an operation that addresses memory errors in the system.

Abstract: Approaches for classifying hardware components of a computing device using a classification system are described. In an example, by the classification system, a hardware configuration information of the computing device installed within a networked environment is obtained. The hardware configuration information may thus be processed based on a system classification model. The system classification model is to classify hardware components of the computing device as one of a plurality of hardware types. Once the hardware components are classified, a category of the computing device is determined. Based on the determined category, a target system software is identified and installed onto the computing device.

Abstract: In some examples, a method can include detecting, with a cloud controller, a Central Processing Unit (CPU) architecture for a bare metal server; selecting, based on the detected CPU architecture, a specific bootloader, specific Operating System (“OS”) and specific Virtual Machine (“VM”) for the bare metal server; and installing the selected bootloader, OS, and VM on the bare metal server.