Abstract: Latency reduction for direct memory access operations involving address translation is disclosed. Example methods disclosed herein to perform direct memory access (DMA) operations include initializing a ring of descriptors, the descriptors to index respective buffers for storing received data in a first memory. Such example methods also include causing prefetching of a first address translation associated with a second descriptor in the ring of descriptors to be performed after a first DMA operation is performed to store first received data in a first buffer indexed by a first descriptor in the ring of descriptors and before second received data to be stored in the first memory is received, the first address translation being associated with a second DMA operation for storing the second received data in the first memory.

Abstract: A mechanism for deployment optimization in a multi-tenant Platform-as-a-Service (PaaS) system is disclosed. A method of the disclosure includes receiving, at a source code management (SCM) repository maintained by a node executing on a computing device, updated application code of an application executed on the node, wherein the node is provided by a multi-tenant Platform-as-a-Service (PaaS) system, providing, by the node, the updated application code to one or more cartridge instances that implement framework of the application, determining, by each of the one or more cartridge instances, that a marker file is present in the updated application code, the marker file indicating that hot deployment functionality is to be implemented for the application, and implementing, by each of the one or more cartridge instances using hot deployment functionality that is specific to the cartridge instance, code changes in the updated application code without a restart of the application.

Abstract: Exemplary methods, apparatuses, and systems include determining that at least a portion of a protected site has become unavailable. A first logical storage device within underlying storage of a recovery site is determined to be a stretched storage device stretched across the protected and recovery sites. A failover workflow is initiated in response to the unavailability of the protected site, wherein the failover workflow includes transmitting an instruction to the underlying storage to isolate the first logical storage device from a corresponding logical storage device within the protected site.

Abstract: Systems and methods for virtual machine data replication with shared resources. An example method may include: identifying resources that are shared across a plurality of virtual machines, storing a copy of the resources, receiving, an indication of a portion of virtual storage of a virtual machine to be replicated, determining that the portion of virtual storage is not included in the resources, in response to the determination, updating a replicated copy of the virtual machine in view of the portion of virtual storage, the replicated copy further including the resources that are shared across a plurality of virtual machines, determining an initialization efficiency metric in relation to the replicated copy, and in response to the determination that the initialization efficiency metric exceeds an efficiency threshold, storing a copy of the virtual storage.

Abstract: Structure is disclosed for a non-blocking SAS architecture utilizing virtual connections between SAS devices. One embodiment comprises a SAS expander. The SAS expander comprises a plurality of physical links (PHYs) and a Virtual Connection Manager (VCM) coupled with the plurality of PHYs. The VCM exchanges information over a plurality of concurrently established virtual pathways between a first PHY of the plurality of PHYs and a second PHY of the plurality of PHYs.

Abstract: A system for governing the spawning of a thread from a parent thread by an application in a processor is provided. The system includes a first multiplexor module that selects from one or more registers a policy used to spawn a thread, and makes the policy available for execution. A second multiplexor module selects one or more of the policy values used in a spawn process whose policy was selected by the output of the first multiplexor module, the second multiplexor module outputs a first signal indicative of the selected policy value to accompany the selected policy, which may be given to the child thread as its initial spawn count when the policy so indicates. A third multiplexor module selects either the first signal or a null where the selected policy value of the first signal is used to update the remaining thread credits of the thread's parent.

Abstract: Methods, systems and techniques for synchronizing content, such as a file, between one or more clients and one or more servers are provided. Example embodiments provide a Cross-File Differential Content Synchronization System (CDCSS) to synchronize files between remote systems in a nearly instantaneous manner without necessitating the transfer of the entire contents of a file. These components cooperate to transfer only the differences in data content wherever possible to a recipient system by providing a patch mechanism that instructs the recipient to build the modified or new data content based upon content it already has access to. In addition, in one embodiment the CDCSS synchronization solution provides a client-based index, rather than a server-based index, for tracking patches and files, which reduces the amount of computational and I/O overhead on the server and which does not require a negotiation between a client and a server to provide an update.

Abstract: In a virtual machine system where a first stage VM and a second stage VM generated on the first stage VM are executed, a processor is configured to perform a first determination as to whether to physically instruct to start execution caused by a virtual execution start of the second stage VM and a second determination as to whether a physical end is detected as a result of a virtual end of the second stage VM, and calculate an execution time of the second stage VM based on results of the first determination and the second determination.

Abstract: A hybrid data storage device includes a solid-state memory device, a disc-type memory device and a hybrid data storage device controller in communication with the solid-state memory device and the disc-type memory device. The hybrid data storage device controller is configured to receive Non-Volatile Memory Host Controller Interface (NVMHCI) commands from a host and use logic to make decisions for the optimization and efficient performance of the solid-state memory device and the disc-type memory device.

Abstract: A network storage controller uses a non-volatile solid-state memory (NVSSM) subsystem as a global cache that is shared between a number of network storage servers in a network storage system. Portions of global cache are allocated to each of the network storage servers. Allocation of portions of the global cache is controlled based on a usage pattern of the global cache by each of the network storage servers. The storage operating system determines, for example, a percentage of cache hit and/or a response time for responding to the requests from the clients by a particular network storage server with a particular allocated portion. The percentage of cache hit and response time are projected for various potential sizes of the particular portion. A size of the particular portion that provides a better percentage of cache hit and/or response time is selected, and reallocated to the particular network storage server.

Abstract: Optimizations are provided for frame management operations, including a clear operation and/or a set storage key operation, requested by pageable guests. The operations are performed, absent host intervention, on frames not resident in host memory. The operations may be specified in an instruction issued by the pageable guests.

Abstract: Methods, systems and techniques for synchronizing content, such as a file, between one or more clients and one or more servers are provided. Example embodiments provide a Cross-File Differential Content Synchronization System (CDCSS) to synchronize files between remote systems in a nearly instantaneous manner without necessitating the transfer of the entire contents of a file. These components cooperate to transfer only the differences in data content wherever possible to a recipient system by providing a patch mechanism that instructs the recipient to build the modified or new data content based upon content it already has access to. In addition, in one embodiment the CDCSS synchronization solution provides a client-based index, rather than a server-based index, for tracking patches and files, which reduces the amount of computational and I/O overhead on the server and which does not require a negotiation between a client and a server to provide an update.

Abstract: Managing the guest operating system's eviction of memory pages from a virtual machine. A guest operating system or a hypervisor may cause one or more memory pages within a guest physical frame to become unlikely or ineligible for selection as a candidate for eviction by the guest operating system. Each of the one or more memory pages may also reside, or be intended to reside, in the memory of one or more other virtual machines. In this way, memory pages that are shared across multiple virtual machines may become less likely to be evicted, thereby using memory more efficiently.

Abstract: A network management system deploys a network profile for a virtual machine to a physical switch after a restart of the physical switch when the virtual machine is downstream of the physical switch and the network profile for the virtual machine has been cached but not saved at the physical switch.

Abstract: According to one aspect of the present disclosure a system and technique for refreshing memory topology in virtual machine operating systems is disclosed. The system includes a processor and logic executable by the processor to: responsive to receiving, by an operating system of a virtual machine, a notification of an affinity change relative to workload memory resources, poll a hypervisor for updated memory affinity data; determine, for each logical memory block of the workload memory resources, whether an affinity string for the respective logical memory block has changed; responsive to determining that the affinity string for the respective logical memory block has changed, identify a data structure of the logical memory block maintained by the operating system; and update affinity information in the data structure based on the change to the affinity string of the logical memory block.

Abstract: According to one aspect of the present disclosure, a method and technique for refreshing memory topology in virtual machine operating systems is disclosed. The method includes: responsive to receiving, by an operating system of a virtual machine, a notification of an affinity change relative to workload memory resources, polling a hypervisor for updated memory affinity data; determining, for each logical memory block of the workload memory resources, whether an affinity string for the respective logical memory block has changed; responsive to determining that the affinity string for the respective logical memory block has changed, identifying a data structure of the logical memory block maintained by the operating system; and updating affinity information in the data structure based on the change to the affinity string of the logical memory block.

Abstract: In a method for managing memory pages, responsive to determining that a server is experiencing memory pressure, one or more processors identifying a first memory page in a listing of memory pages in the server. The method further includes determining whether the first memory page corresponds to a logical partition (LPAR) of the server that is scheduled to undergo an operation to migrate data stored on memory pages of the LPAR to another server. The method further includes, responsive to determining that the first memory page does correspond to a LPAR of the server that is scheduled to undergo an operation to migrate data, determining whether to evict the first memory page based on a memory page state associated with the first memory page. The method further includes, responsive to determining to evict the first memory page, evicting data stored in the first memory page to a paging space.

Abstract: A memory management method includes sharing a memory space of a memory component via a network through a host operating system, mounting the shared memory space via the network through a virtual machine, monitoring an memory utilization of a virtual memory of the virtual machine, and allocating a storage block to the virtual machine in a condition that the memory utilization of the virtual memory of the virtual machine is greater than an upper bound. As such, a capacity of the virtual memory of the virtual machine is increased.

Abstract: A “just in time” feedback-driven strategy for provisioning storage in a cloud computing environment is described. An agent miming in a guest virtual machine can monitor the storage needs of the guest virtual machine. When a specified threshold for the guest virtual machine is reached, the host can be notified of the changing storage needs. The host can respond by re-sizing the storage device and notifying the guest virtual machine of the changed storage capacity.

Abstract: A system and method for ballooning with assigned devices includes inflating a memory balloon, determining whether a first memory page is locked based on information associated with the first memory page, when the first memory page is locked unlocking the first memory page and removing first memory addresses associated with the first memory page from management by an input/output memory management unit (IOMMU), and reallocating the first memory page. The first memory page is associated with a first assigned device.

Abstract: Methods, apparatuses, and computer program products for managing virtual machine images in a distributed computing environment are provided. Embodiments includes a management system recording dependencies between the virtual machine images in the image service repository and dependencies between the deployed virtual machines in the compute service and the virtual machine images in the image service repository. Based on the recorded dependencies between the virtual machine images and the dependencies between the deployed virtual machines and the virtual machine images, the management system identifies a virtual machine image that has no deployed virtual machine dependent upon it. Embodiments also include the management system deleting, by the management system, the identified virtual machine image from the image service repository.

Abstract: A method for live conversion and movement of a virtual machine image and state information between hypervisors includes: freezing a current state of a source image; creating a proxy; redirecting any changes made to the source image to a journal of the proxy; reading from the source image; writing to the journal; converting the source image to a target image; and replaying the journal on the target image.

Abstract: Methods, apparatuses, and computer program products for managing virtual machine images in a distributed computing environment are provided. Embodiments includes a management system recording dependencies between the virtual machine images in the image service repository and dependencies between the deployed virtual machines in the compute service and the virtual machine images in the image service repository. Based on the recorded dependencies between the virtual machine images and the dependencies between the deployed virtual machines and the virtual machine images, the management system identifies a virtual machine image that has no deployed virtual machine dependent upon it. Embodiments also include the management system deleting, by the management system, the identified virtual machine image from the image service repository.

Abstract: Generally described, aspects of the present disclosure relate to a live update process of the virtual machine monitor during the operation of the virtual machine instances. An update to a virtual machine monitor can be a difficult process to execute because of the operation of the virtual machine instances. Generally, in order to update the virtual machine monitor, the physical computing device needs to be rebooted, which interrupts operation of the virtual machine instances. The live update process provides for a method of updating the virtual machine monitor without rebooting the physical computing device.

Abstract: Computer system is provided with a first physical computer and a second physical computer. The first physical computer is provided with a control device and a storage device coupled to the control device. The control device of the first physical computer constructs a virtual computer and can execute a predetermined guest program on the virtual computer. A part of a region of the storage device is used as a virtual storage device that is a storage device for the virtual computer. In the case in which the control device executes a live migration which is to migrate the virtual computer of the first physical computer to the second physical computer while executing the guest program in a substantial way, the control device executes a control for reducing a data writing amount in a certain period of time to a virtual storage device that has been allocated to the virtual computer.

Abstract: In a computer system, joint operation of multiple hypervisors is coordinated. A persistent hypervisor and a non-persistent hypervisor are executed. The non-persistent hypervisor is executed in the supervisor mode according to an operating regime controlled by a scheduler engine, and the persistent hypervisor is executed in the hypervisor mode under the control of a handler engine. The handler engine monitors, and responds, to an attempted mode transition of the processor between the hypervisor and supervisor modes, and coordinates the suspension and resumption, as appropriate, of the persistent hypervisor.

Abstract: A storage system comprises a cache for caching data blocks and storage devices for storing blocks. A storage operating system may deduplicate sets of redundant blocks on the storage devices based on a deduplication requirement. Blocks in cache are typically deduplicated based on the deduplication on the storage devices. Sets of redundant blocks that have not met the deduplication requirement for storage devices and have not been deduplicated on the storage devices and cache are targeted for further deduplication processing. Sets of redundant blocks may be further deduplicated based on their popularity (number of accesses) in cache. If a set of redundant blocks in cache is determined to have a combined number of accesses being greater than a predetermined threshold number of accesses, the set of redundant blocks is determined to be “popular.” Popular sets of redundant blocks are selected for deduplication in cache and the storage devices.

Abstract: A system, method and computer program product for implementing a thin hypervisor. The thin hypervisor does not have any association with a VM. The thin hypervisor serves as a wrapper over hardware capabilities of a processor. The processor has privileged low-level capabilities EPT VTX, AMD V and the ARM has virtualization technology. In order to use processor hardware capabilities and receiving root privileges, the system operates in a “super user” mode. The VM operates in a VM environment with kernel privileges in a user mode. A super user space is created in a safe mode. A user space application (or a process) is created. A user space virtualization framework library is used. These entities are separated by a user space and a kernel space. A thin hypervisor is implemented in the user space.

Abstract: The method of the present inventive concept is configured to utilize Operating System data structures related to memory-mapped binaries to reconstruct processes. These structures provide a system configured to facilitate the acquisition of data that traditional memory analysis tools fail to identify, including by providing a system configured to traverse a virtual address descriptor, determine a pointer to a control area, traverse a PPTE array, copy binary data identified in the PPTE array, generate markers to determine whether the binary data is compromised, and utilize the binary data to reconstruct a process.

Abstract: A virtualization computing platform may host a virtual machine. The virtual machine may be hosted by a first set of resources of the virtualization computing platform. A second set of resources for hosting the virtual machine may be identified. The second set of resources may comprise resources of the virtualization computing platform that are distinct from the first set of resources. At least a portion of a plurality of files associated with the virtual machine may be copied from the first set of resources to the second set of resources. A virtual memory swap file may be identified from among the plurality of files associated with the virtual machine. Based on identifying the virtual memory swap file as a virtual memory swap file, the virtual memory swap file may be treated differently from one or more other of the plurality of files associated with the virtual machine.

Abstract: A method and system for managing a virtual computing system including a virtual machine (VM) configured to send an event to a host CPU executing a memory monitoring instruction. The virtual machine is configured to receive from a hypervisor a notification identifying an address range writeable by a virtual central processing unit (VCPU) associated with the virtual machine to send an event to a host central processing unit (CPU). The virtual machine is further configured to receive an instruction to write to the identified address range for sending an event to the host CPU. The VCPU of the virtual machine may then write data identifying an event for execution by the host CPU to the identified address range, without causing an exit to the hypervisor.

Abstract: Optimizations are provided for frame management operations, including a clear operation and/or a set storage key operation, requested by pageable guests. The operations are performed, absent host intervention, on frames not resident in host memory. The operations may be specified in an instruction issued by the pageable guests.

Abstract: Methods and apparatus are disclosed to provision virtual machine resources. An example method includes labeling a copy of memory associated with an established virtual machine with an execution status based on an architecture type associated with the copy, and constraining a fetch operation in response to a page fault to a labeled portion of the copy that matches an architecture type of a received processor instruction.

Abstract: An apparatus, system, and method for virtual memory management. The method includes detecting a memory access to a virtual memory address within a monitored page of data not loaded in main memory of a computing device. The method includes determining a first address for a loaded page of data in the main memory. The first address is defined in a sparse virtual address space exposed by a persistent storage device. The first address is associated in an index with a first deterministic storage location. The method includes storing the loaded page on a persistent storage device at the first deterministic storage location. The method includes moving the monitored page from a second deterministic storage location to the main memory. The second deterministic storage location is associated with a second address in the index.

Abstract: Described techniques increase runtime performance of workloads executing on a hypervisor by executing virtualization-aware code in an otherwise non virtualization-aware guest operating system. In one implementation, the virtualization-aware code allows workloads direct access to physical hardware devices, while allowing the system memory allocated to the workloads to be overcommitted. In one implementation, a DMA filter driver is inserted into an I/O driver stack to ensure that the target virtual memory of a DMA transfer is resident before the transfer begins. The DMA filter driver may utilize a cache to track which pages of memory are resident. The cache may also indicate which pages of memory are in use by one or more transfers, enabling the hypervisor to avoid appropriating pages of memory during a transfer.

Abstract: Embodiments of the invention relate to receiving, by a first processor comprising a processing device, an indication that a migration of a virtual machine from the first processor to a second processor is to occur. The first processor transmits user datagram protocol (UDP) packets intended for the virtual machine to the second processor based on the indication. A signal is transmitted to the virtual machine to enter an offline state, wherein the offline states comprises a transfer of at least one of a central processing unit (CPU) state and a memory state, and wherein the virtual machine is configured to halt a processing of the UDP packets in response to receiving the signal. The virtual machine is reactivated once the migration of the virtual machine from the first processor to the second processor is complete. The virtual machine is instructed to resume the processing of the UDP packets.

Abstract: Embodiments of the invention relate to receiving, by a first processor comprising a processing device, an indication that a migration of a virtual machine from the first processor to a second processor is to occur. The first processor transmits user datagram protocol (UDP) packets intended for the virtual machine to the second processor based on the indication. A signal is transmitted to the virtual machine to enter an offline state, wherein the offline states comprises a transfer of at least one of a central processing unit (CPU) state and a memory state, and wherein the virtual machine is configured to halt a processing of the UDP packets in response to receiving the signal. The virtual machine is reactivated once the migration of the virtual machine from the first processor to the second processor is complete. The virtual machine is instructed to resume the processing of the UDP packets.

Abstract: In certain embodiments, a system comprises a memory and a processor communicatively coupled to the memory. The memory includes executable instructions that upon execution cause the system to generate, at a first time, a first snapshot capturing data stored in storage units of a storage device. The executable instructions upon execution cause the system to receive an indication to delete at least a portion of the data in the storage units and captured by the first snapshot, and to mark, in response to receiving the indication, the one or more storage units that store the at least a first portion of the data as available. The executable instructions upon execution cause the system to generate, at a second time subsequent to the first time, a second snapshot that omits the one or more storage units marked as available.

Abstract: A mechanism for virtual machine resource reduction for live migration optimization is disclosed. A method of the invention includes monitoring a rate of state change of a virtual machine (VM) undergoing a live migration, determining that the rate of state change of the VM exceeds a rate of state transfer of the VM during the live migration process, and adjusting one or more resources of the VM to decrease the rate of state change of the VM to be less than the rate of state transfer of the VM.

Abstract: The translation lookaside buffer (TLB) of a processor is kept in synchronization with a guest page table by use of an indicator referred to as a “T” bit. The T bit of the NPT/EPT entries mapping the guest page table are set when a page walk is performed on the NPT/EPT. When modifications are made to pages mapped by NPT/EPT entries with their T bit set, changes to the TLB are made so that the TLB remains in synchronization with the guest page table. Accordingly, record/replay of virtual machines of virtualized computer systems may be performed reliably with no non-determinism introduced by stale TLBs that fall out of synchronization with the guest page table.

Abstract: There is a need for providing the Xeon CPU with a two-level VM that is independent of VMM types and prevents the throughput from degrading when the OS operates the privilege register. A machine is provided with a processor and memory. The machine includes a first virtual machine manager for managing a virtual machine, a second virtual machine for managing an operating system, first management information, and second management information. The processor is provided with a register and a shadowing function. The machine uses a virtualization method. The first virtual machine manager detects a call from the second virtual machine manager. The first virtual machine manager enables the shadowing function when it is determined that an instruction for enabling the shadowing function caused the call.

Abstract: The present invention relates to a method and a device for adjusting memory of a virtual machine. The method includes: checking memory usages of virtual machines according to a preset memory usage threshold to determine multiple virtual machines whose memory is to be adjusted; determining, according to parameters preselected by the multiple virtual machines whose memory is to be adjusted, priority levels of the virtual machines whose memory is to be adjusted; and adjusting, according to the priority levels of the virtual machines whose memory is to be adjusted, memory of the virtual machines whose memory is to be adjusted. According to embodiments of the present invention, memory of a virtual machine on which a key application or service is deployed is adjusted in time and prevents a process of a priority service from being affected due to delayed memory adjustment.

Abstract: A method and controller device for sharing computing resources in a virtualized environment having a plurality of virtual machines. The method includes assigning a portion of the computing resources to the plurality of virtual machines. The method also includes leasing by a first virtual machine at least a portion of the assigned computing resources of at least one second virtual machine. The first virtual machine leases computing resources from the at least one second virtual machine when the first virtual machine needs additional computing resources and at least a portion of the assigned computing resources of the at least one second virtual machine are not being used by the at least one second virtual machine.

Abstract: A method is provided for placing a virtual machine on a target virtual machine manager out of multiple virtual machine managers. System management software is connected to the virtual machine managers and selects the target virtual machine manager for placing the virtual machine. The method includes: the system management software creating a memory profile for all virtual machines hosted on the multiple virtual machine managers, the system management software evaluating probabilities for samepage mapping of the virtual machine to be placed on the multiple virtual machine managers based on the memory profiles of the virtual machines, the system management software selecting under consideration of the probabilities for samepage mapping a most appropriate virtual machine manager as the target virtual machine manager, and the system management software placing the virtual machine on the target virtual machine manager.

Abstract: According to the present invention, it is possible to construct a backup configuration of a particular application data, without influencing data of another application. A management computer is coupled to a host computer on which an application operates, and to a storage apparatus that includes a plurality of volume groups each having one or more logical volumes. At least one of the logical volumes is allocated to the application. The management computer includes a volume group overlapping use determination part and a backup policy determination part. When the backup of the volume group to which one logical volume belongs is configured, the volume group overlapping use determination part determines whether there is another application that uses the volume group. The backup policy determination part determines whether there is set, for another volume group, backup policy information same as that set for the application.

Abstract: Methods, apparatuses, and computer program products for preserving, from resource management adjustment, portions of an overcommitted resource managed by a hypervisor are provided. Embodiments include identifying, by the hypervisor, a privileged guest from among a plurality of guests of the hypervisor; identifying, by the hypervisor, portions of the overcommitted resource that are allocated to the privileged guest; and preventing, by the hypervisor, resource management adjustment to the identified portions of the overcommitted resource that are allocated to the privileged guest.

Abstract: Processing within a computing environment that supports pageable guests is facilitated. Processing is facilitated in many ways, including, but not limited to, associating guest and host state information with guest blocks of storage; maintaining the state information in control blocks in host memory; enabling the changing of states; and using the state information in management decisions. In one particular example, the guest state includes an indication of usefulness and importance of memory contents to the guest, and the host state reflects the ease of access to memory contents. The host and guest state information is used in managing memory of the host and/or guests.

Abstract: Exemplary methods, apparatuses, and systems include a first host system configuring storage of the first host to serve as a primary cache for a virtual machine running on the first host. A second host system configures storage of the second host to serve as a secondary cache and boots a placeholder virtual machine. The first host transmits, in response to write operations from the virtual machine directed to the primary cache, copies of the write operations to the second host to create mirrored copies on the secondary cache. The first host acknowledges each write operation from the virtual machine when the write operation is committed to both the primary cache and the secondary cache. When the virtual machine is restarted on the second host in response to a failure or migration event, the secondary cache is promoted to serve as a new primary cache for the virtual machine.

Abstract: Methods, apparatuses, and computer program products for preserving, from resource management adjustment, portions of an overcommitted resource managed by a hypervisor are provided. Embodiments include identifying, by the hypervisor, a privileged guest from among a plurality of guests of the hypervisor; identifying, by the hypervisor, portions of the overcommitted resource that are allocated to the privileged guest; and preventing, by the hypervisor, resource management adjustment to the identified portions of the overcommitted resource that are allocated to the privileged guest.

Abstract: A virtual machine system for duplicating a first virtual machine to generate one or more second virtual machines is provided with a management unit that manages each memory area accessible by the first virtual machine so that after generation of the second virtual machines, every virtual machine is permitted to perform a read access to the memory area until any virtual machine performs a write access to the memory area, a determination unit that determines whether each memory area is a specific memory area, a detection unit that detects, after detecting a write access to a specific memory area, that a virtual machine other than the virtual machine performing the write access is attempting access to the specific memory area, and a memory allocation unit that acquires and allocates a new memory area to the virtual machine detected to be attempting access to the specific memory area.