Abstract: Techniques for determining reliability of a workload migration activity are disclosed. In one embodiment, sub-tasks associated with the workload migration activity may be determined. Further, statistical data associated with an execution of the sub-tasks corresponding to different instances of the workload migration activity may be retrieved. Furthermore, a reliability model may be trained through machine learning using the statistical data to determine reliability of the workload migration activity. Then, the reliability of a new workload migration activity may be determined using the trained reliability model.

Abstract: Techniques for determining reliability of a workload migration activity are disclosed. In one embodiment, sub-tasks associated with the workload migration activity may be determined. Further, statistical data associated with an execution of the sub-tasks corresponding to different instances of the workload migration activity may be retrieved. Furthermore, a reliability model may be trained through machine learning using the statistical data to determine reliability of the workload migration activity. Then, the reliability of a new workload migration activity may be determined using the trained reliability model.

Abstract: Techniques for determining reliability of a workload migration activity are disclosed. In one embodiment, sub-tasks associated with the workload migration activity may be determined. Further, statistical data associated with an execution of the sub-tasks corresponding to different instances of the workload migration activity may be retrieved. Furthermore, a reliability model may be trained through machine learning using the statistical data to determine reliability of the workload migration activity. Then, the reliability of a new workload migration activity may be determined using the trained reliability model.

Abstract: A method for transferring memory pages to a first and a second page repository identifies pages in a memory sharing operation for transfer to a first page repository and pages in a memory migration operation for transfer to a second page repository. Pages in the memory migration operation may be prepared for transfer prior to transfer of the pages in the memory sharing operation. Transferring pages in the migration operation may remove the need to transfer pages in the memory sharing operation.

Abstract: A method for improving accuracy of high resolution timers in a live partition migration comprises determining a status of each page of a plurality of pages to be copied from a source partition to a target partition during the live partition migration. One or more pages of the plurality of pages correspond to a respective high resolution timer. The method comprises determining that each of the one or more pages corresponding to a respective high resolution timer has a clean status. A clean status indicates that the corresponding page has been copied to the target partition and has not been modified subsequent to being copied to the target partition. The method also comprises halting operation of the source partition and initiating operation of the target partition in response to determining that each of the one or more pages corresponding to a respective high resolution timer has a clean status.

Abstract: An example method of provisioning a virtual machine in a cloud system includes: receiving a request to provision the virtual machine in the cloud system; provisioning a first virtual machine managed by a hypervisor executing on a host computer in the cloud system, the hypervisor allocating resources to the first virtual machine; provisioning a nested hypervisor in the first virtual machine; and provisioning the virtual machine to execute on the nested hypervisor without re-virtualizing the resources allocated by the hypervisor to the nested hypervisor.

Abstract: Techniques for determining reliability of a workload migration activity are disclosed. In one embodiment, sub-tasks associated with the workload migration activity may be determined. Further, statistical data associated with an execution of the sub-tasks corresponding to different instances of the workload migration activity may be retrieved. Furthermore, a reliability model may be trained through machine learning using the statistical data to determine reliability of the workload migration activity. Then, the reliability of a new workload migration activity may be determined using the trained reliability model.

Abstract: A method for transferring memory pages to a first and a second page repository identifies pages in a memory sharing operation for transfer to a first page repository and pages in a memory migration operation for transfer to a second page repository. Pages in the memory migration operation may be prepared for transfer prior to transfer of the pages in the memory sharing operation. Transferring pages in the migration operation may remove the need to transfer pages in the memory sharing operation.

Abstract: A method for transferring memory pages to a first and a second page repository identifies pages in a memory sharing operation for transfer to a first page repository and pages in a memory migration operation for transfer to a second page repository. Pages in the memory migration operation may be prepared for transfer prior to transfer of the pages in the memory sharing operation. Transferring pages in the migration operation may remove the need to transfer pages in the memory sharing operation.

Abstract: A system and computer program product are provided for optimized timer placement. A request to apply a new timer in a computer system is received and an interrupt time for the new timer is extracted from the new timer. A timer list is accessed for each processor in the system responsive to the received request. A range for placement of the new timer is established with respect to each of the accessed timer lists. A timer expiry delay is calculated between proximal processor interrupts and the extracted interrupt time based on the established range placement. Proximity of the extracted interrupt time within the existing processor interrupts is determined and one of the processors is selected based on the calculation and the determined proximity. The new timer is placed on the selected processor.

Abstract: A method is provided for optimized timer placement. A request to apply a new timer in a computer system is received and an interrupt time for the new timer is extracted from the new timer. A timer list is accessed for each processor in the system responsive to the received request. A range for placement of the new timer is established with respect to each of the accessed timer lists. A timer expiry delay is calculated between proximal processor interrupts and the extracted interrupt time based on the established range placement. Proximity of the extracted interrupt time within the existing processor interrupts is determined and one of the processors is selected based on the calculation and the determined proximity. The new timer is placed on the selected processor.

Abstract: A computer-implemented method, includes, in a pageable operating system environment that does not keep all kernel pages in memory, identifying one or more stack frame pages. The method includes storing the one or more stack frame pages in a logical dump volume, wherein the logical dump volume is accessed upon a system reboot. A corresponding computer system and computer program product are also disclosed.

Abstract: A computer-implemented method includes monitoring page allocations in a file system that includes encrypted files, determining if a page allocation request corresponds to an encrypted file, and balancing encrypted page allocations across a plurality of virtual memory pools in response to determining that the page allocation request corresponds to an encrypted file. In some embodiments, balancing encrypted page allocations across the plurality of virtual memory pools comprises determining a virtual memory pool having a lowest encrypted page count and allocating a page from the virtual memory pool having the lowest encrypted page count. A corresponding computer program product and computer system are also disclosed herein.

Abstract: An example method of provisioning a virtual machine in a cloud system includes: receiving a request to provision the virtual machine in the cloud system; provisioning a first virtual machine managed by a hypervisor executing on a host computer in the cloud system, the hypervisor allocating resources to the first virtual machine; provisioning a nested hypervisor in the first virtual machine; and provisioning the virtual machine to execute on the nested hypervisor without re-virtualizing the resources allocated by the hypervisor to the nested hypervisor.

Abstract: A method is provided for optimized timer placement. A request to apply a new timer in a computer system is received and an interrupt time for the new timer is extracted from the new timer. A timer list is accessed for each processor in the system responsive to the received request. A range for placement of the new timer is established with respect to each of the accessed timer lists. A timer expiry delay is calculated between proximal processor interrupts and the extracted interrupt time based on the established range placement. Proximity of the extracted interrupt time within the existing processor interrupts is determined and one of the processors is selected based on the calculation and the determined proximity. The new timer is placed on the selected processor.

Abstract: A system and computer program product are provided for optimized timer placement. A request to apply a new timer in a computer system is received and an interrupt time for the new timer is extracted from the new timer. A timer list is accessed for each processor in the system responsive to the received request. A range for placement of the new timer is established with respect to each of the accessed timer lists. A timer expiry delay is calculated between proximal processor interrupts and the extracted interrupt time based on the established range placement. Proximity of the extracted interrupt time within the existing processor interrupts is determined and one of the processors is selected based on the calculation and the determined proximity. The new timer is placed on the selected processor.

Abstract: A method for transferring memory pages to a first and a second page repository identifies pages in a memory sharing operation for transfer to a first page repository and pages in a memory migration operation for transfer to a second page repository. Pages in the memory migration operation may be prepared for transfer prior to transfer of the pages in the memory sharing operation. Transferring pages in the migration operation may remove the need to transfer pages in the memory sharing operation.

Abstract: A page type may be identified for each of a plurality of memory pages, the page type corresponding to a particular process that accesses a particular memory page of the plurality of memory pages. The plurality of memory pages may each respectively include duplicate data. The duplicate data may be a same set of data values. Each of the plurality of respective memory pages may be ranked as candidates to deduplicate the set of data values to. The ranking may be based on at least the page type. In response to identifying the first processor and identifying a first memory device, the duplicate data may be deduplicated from the plurality of memory pages to a highest ranked memory page. The deduplication may correspond to coalescing the duplicate data to the highest ranked memory page.

Abstract: A computer-implemented method, includes, in a pageable operating system environment that does not keep all kernel pages in memory, identifying one or more stack frame pages. The method includes storing the one or more stack frame pages in a logical dump volume, wherein the logical dump volume is accessed upon a system reboot. A corresponding computer system and computer program product are also disclosed.

Abstract: A physical address of a page may be identified. A first process that implements copy-on-read techniques for the page may be detected. A determination may be made that the first process is not expected to write to the page. In response to that determination, a different logical address may be established for the first process for the page from the logical address of a second process for the page, but the two logical addresses may be mapped to the same physical page.