Red Hat, Inc.

Michael Tsirkin

Andrea Arcangeli

Uri Lublin

Amnon Ilan

Francisco Javier Martinez Canillas

Alberto Carlos Ruiz Ruiz

Giuseppe Scrivano

A method includes determining to migrate a guest VM from a source host to a destination host and, in response to determining to migrate the guest VM, determining that a page of the guest VM matches a page of a VM image of a plurality of VM images in a VM library associated with the source host. The method further includes forwarding an identifier of the page of the VM image to the destination host, the destination host to retrieve, in view of the identifier, the page of the VM image from a second VM library associated with the destination host to instantiate the guest VM at the destination host.

Library based virtual machine migration

A packet is received by a hypervisor from a first container, the packet to be provided to a second container, the packet including a header including a first network address associated with the second container. A network policy is identified for the packet in view of the first network address. A second network address corresponding to the second container is determined in view of the network policy. A network address translation is performed by the hypervisor to modify the header of the packet to include the second network address corresponding to the second container.

Implementing a service mesh in the hypervisor

Systems, methods, and apparatuses for managing memory usage in virtualized computing environments are provided herein. An example method includes generating a random key, associating the key with a page or range of pages in a memory, and selectively deduplicating pages based upon the key associated with each respective page.

Randomization-based protection for memory deduplication

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

A system includes a physical host, a host operating system, and a virtual machine having a virtual network-interface controller. The virtual network-interface controller comprises an uplink, a virtual function, and a physical function having a physical channel and a virtual channel. The hypervisor is configured to receive data that originates at the virtual function, which is forwarded to the physical function on the physical channel of the physical function. The data is further forwarded from the physical function to the uplink. Additionally, the hypervisor is configured to send data that does not originate at the virtual function. The hypervisor sends the data on the virtual channel of the physical function and the physical function forwards the data to the virtual function.

Reverse virtual ethernet port aggregator bridging for single root I/O virtualization

A method includes receiving a message at a network bridge from a computer system where the network bridge stores a forwarding table. The method also includes determining a type of the message. The method also includes upon a determination that the type of message is a network notification message, determining whether data within the message corresponds to an entry within the forwarding table. The method also includes upon determining that the data within the message corresponds to the entry within the forwarding table, halting a transmission of the message. The method also includes upon determining that the data within the message does not correspond to the entry in the forwarding table, transmitting the message to a device in communication with the network bridge.

Location change notification handling

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.

Growing community of inventors

Westford, MA, United States of America

Michael Tsirkin