Red Hat, Inc.

Andrea Arcangeli

Michael Tsirkin

Giuseppe Scrivano

Memory deduplication for encrypted virtual machines can be performed according to some examples. In one example, a virtual machine can select a target memory page stored in an encrypted memory of the virtual machine. The encrypted memory can be inaccessible to a hypervisor configured to manage the virtual machine. The virtual machine can store a copy of the target memory page to a shared memory that is accessible to the hypervisor. The hypervisor can then execute a deduplication process with respect to the copy of the target memory page stored in the shared memory. Subsequent to storing the copy of the target memory page to the shared memory, the virtual machine can remove the target memory page from the encrypted memory. The virtual machine can also prompt the hypervisor to reallocate the memory space of the encrypted memory that was previously used to store the target memory page.

Memory deduplication for encrypted virtual machines

Systems and method for automated efficient memory migration in Non-uniform Memory Access (NUMA) based virtual machines are introduced, comprising exporting one or more informative data objects, from a host machine to at least one virtual machine, wherein the informative data objects include references to pages that have been migrated from a physical source memory node (source node) on the host machine to a new source location on the host machine; inspecting, the informative data objects, by the at least one virtual machine; detecting, by the at least one virtual machine, the pages that have been migrated to the new source location; sending a request, by the at least one virtual machine, to the host machine via the hypervisor, to map the pages to a physical destination memory node (destination node) corresponding to a desired virtual destination memory node (destination vNode); and undertaking at least one efficient data migration operation.

Copyless NUMA balancing hypervisor memory migration

An example system includes a memory, a processor in communication with the memory, and a hypervisor. The hypervisor is configured to store, as dirty memory, data from a virtual machine (VM) at least until the data is written back into a data storage. The hypervisor is also configured to assign a persistence setting for managing write back of the dirty memory of the VM into the data storage. The hypervisor is also configured to periodically trigger writing at least a portion of the dirty memory of the VM into the data storage based on the persistence setting being a first setting. The hypervisor is also configured to disable periodic triggering, by the hypervisor, of the writing of the dirty memory of the VM into the data storage based on the persistence setting being a second setting.

Efficient disk cache management for virtual machines

Systems and methods for enhancing efficient memory swap for virtual machines. An example method may comprise: receiving, by a hypervisor running on a host computer system, a request, from a virtual machine managed by the hypervisor, to write to a virtual disk a content of a memory page identified by a guest physical address (GPA); detecting, by the hypervisor, that the content of the memory page is stored on a storage device; storing, on the virtual disk, an identifier of a location of the content of the memory page on the storage device; and un-mapping the GPA from the storage device.

Efficient memory swap for virtual machines

A system includes a memory, at least one physical processor in communication with the memory, and a plurality of threads executing on the at least one physical processor. A first thread of the plurality of threads is configured to execute a plurality of instructions that includes a restartable sequence. Responsive to a different second thread in communication with the first thread being pre-empted while the first thread is executing the restartable sequence, the first thread is configured to restart the restartable sequence prior to reaching a memory barrier.

Memory barrier elision for multi-threaded workloads

Systems and methods for memory management for virtual machines. An example method may comprise running, by a host computer system, a Level 0 hypervisor managing a Level 1 virtual machine running a Level 1 hypervisor which manages a Level 2 virtual machine. The Level 1 hypervisor may detecting execution of an operation that prevents modification to a set of entries in a Level 2 page table and generate a shadow page table where each shadow page table entry of the plurality of shadow page table entries maps a Level 2 guest virtual address of a Level 2 address space associated with the Level 2 virtual machine to a corresponding Level 1 guest physical address of a Level 1 address space associated with the Level 1 virtual machine. The Level 0 hypervisor may generate a Level 0 page table.

Reverse shadow page tables for nested virtual machines

Systems and methods providing efficient dirty memory page expiration. In one implementation, a processing device may identify a storage device. The processing device may determine a value of an indicator associated with the storage device. The indicator may indicate a level of consistency between a volatile memory device and a non-volatile memory device of the storage device. In view of the value of the indicator, the processing device may modify a synchronization timeout value associated with the volatile memory device.

Efficient dirty page expiration

An example system includes a memory, a processor in communication with the memory, and a supervisor. The supervisor is configured to allocate a memory space in the memory to a workload executing on the processor. The supervisor is configured to store data written by the workload as dirty memory in the memory space at least until the data is written back to a data storage. Based on a type of the workload being a first type, the supervisor is configured to trigger write back of at least a portion of the dirty memory into the data storage in response to the dirty memory exceeding a threshold level. Based on the type of the workload being a second type, the supervisor is configured to delay write back of the dirty memory into the data storage in response to the dirty memory exceeding the threshold level.

Growing community of inventors

New York, NY, United States of America

Andrea Arcangeli