Abstract: In one embodiment, a system for migrating virtual machines in a virtualization environment includes a plurality of host machines implementing the virtualization environment and a migration controller. Each of the host machines includes a hypervisor, one or more user virtual machines (UVMs) and a virtual machine controller. The system further implements a virtual disk comprising a plurality of storage devices, the virtual disk being accessible by the virtual machine controllers, which conduct I/O transactions with the virtual disk. The migration controller determines a segment size and, for each host machine, determines a number of required segments for the UVMs running on the host machine. The controller computes a number of reserved segments based on a total number of host machines and a largest one of the numbers of required segments. The reserved segments are then assigned among the plurality of host machines.

Abstract: An architecture for implementing a mechanism for displaying GPU resource usage and dynamically allocating GPU resources in a networked virtualization system is provided. The mechanism compares an initial allocation of GPU resources to virtual machines supported by one or more nodes of the networked virtualization system to a current GPU resource usage by the virtual machines. Based at least in part on the comparison and workloads processed by the virtual machines, the mechanism may reallocate GPU resources to one or more of the virtual machines. A virtual machine is reassigned to a different vGPU profile if reassignment is likely to achieve a more efficient allocation of GPU resources to the virtual machine. A user interface indicating GPU resource usage relative to GPU resource allocation may also be generated and displayed.

Abstract: Systems and methods for scheduling storage management tasks over predicted user tasks in a distributed storage system. A method commences upon receiving a set of historical stimulus records that characterize management tasks that are run in the storage system. A corresponding set of historical response records comprising system metrics associated with execution of the system tasks is also received. A learning model is formed from the stimulus records and the response records and formatted to be used as a predictor. A set of forecasted user tasks is input as new stimulus records to the predictor to determine a set of forecasted system metrics that would result from running the forecasted user tasks. Management tasks are selected so as not to impact the forecasted user tasks. Management tasks can be selected based on non-contentions resource usage between historical management task resource usage and predictions of resource usage by the user tasks.

Abstract: Systems for rendering graphs in browsers. A method embodiment for generating and manipulating a high-performance graph in a browser commences by receiving a set of node descriptions of the graph as well as a set of edge descriptions of the graph. In a first display layer, one or more HTML primitives are assigned to the individual ones of the set of nodes. In a second display layer, one or more non-HTML display graphical elements are assigned to the individual ones of the set of edges. The edges and nodes are sorted into a painting order based on size. The first layer and the second layer are combined into an HTML document that comprises at least some of the HTML primitives that correspond to the nodes as well as at least some of the non-HTML display graphical elements that correspond to the edges of the graph. The browser renders the graph.

Abstract: Systems for storage system rollover and rollback. A data mover agent is installed on a source storage system to capture disaster recovery data and send to a target system. Upon receiving a rollover event signal, a virtualized controller creates one or more replica user virtual machines running on the target system that serve to replicate functions of the user virtual machines from the source storage system. The virtualized controller on the target system converts the target disaster recovery data from a first format to a second format to facilitate use of the target disaster recovery data by the replica user virtual machines. Rollback is initiated when the target system receives a rollback event signal. Differences in the data that have occurred between the rollover event and the rollback signal are calculated and sent to the rollback system. The calculated differences are applied to a registered snapshot on the rollback system.

Abstract: A method for configuring components in a data center is disclosed. The method includes receiving, by a management server, a request for an internet protocol (IP) address and media access control (MAC) address from a network-connected component, responsive to receiving the request, issuing, by the management server, an IP address to the network-connected component, associating, by the management server, the issued IP address with the received MAC address, providing, by the management server, a query to the network-connected component for identifying information associated with the network-connected component, receiving, by the management server, the identifying information, and configuring, by the management server, the network-connected component based on the identifying information.

Abstract: In one embodiment, a system for managing a virtualization environment comprises a plurality of host machines, one or more virtual disks comprising a plurality of storage devices, a virtualized file server (VFS) comprising a plurality of file server virtual machines (FSVMs), wherein each of the FSVMs is running on one of the host machines and conducts I/O transactions with the one or more virtual disks, and a virtualized file server backup system configured to back up data stored in a VFS located a cluster of host machines to an object store, and retrieve the backed-up data as needed to restore the data in the VFS. The object store may be located in a public cloud. The object store may include a low-cost storage medium within the cluster. An FSVM of the VFS may provide an object store interface to low-cost storage media.

Abstract: In particular embodiments, a system for managing a virtualization environment includes host machines, each of the host machines including a hypervisor, user virtual machines (UVMs) and a virtual machine controller. The virtualization environment also includes virtual disks comprising a plurality of storage devices, and being accessible by the virtual machine controllers. The virtual machine controllers conduct I/O transactions with the virtual disks. The system stores an entity-relationship graph representing elements in the virtualization environment. Each of the elements is represented by an entity-type node in the entity-relationship graph, and relationships between the elements are represented by edges between the nodes.

Abstract: Examples described herein may provide local key managers on computing nodes of distributed computing systems. The local key managers may protect secrets (e.g. cryptographic keys) in the distributed system such that risk of compromise is reduced or eliminated. In some examples, secure processors, such as trusted platform modules (TPMs), may be incorporated in computing nodes of distributed computing systems described herein. The secure processor may aid in securely protect cryptographic keys in the event of disk or node theft, for example.

Abstract: Systems for bring-up of virtual machines in disaster recovery scenarios where the network configuration differs between the failed system and the recovery system. A method commences upon identifying a disaster recovery plan for restarting a set of virtual machines on a second system (e.g., a recovery system). A disaster event is detected, which event causes initiation of aspects of the disaster recovery plan, including restarting the set of virtual machines that were running on the first system. Other aspects of the disaster recovery plan include determining a set of network configuration directives pertaining to the second system, and providing access to the network configuration directives by any of the restarted virtual machines. During disaster recovery bring-up, at least some of the virtual machines that are restarted on the second system use the network configuration of the recovery system.

Abstract: Techniques for performing compression operations on persistently-stored data blocks during read/write commands. A method embodiment performs in-line data compression operations over data blocks referenced by a caller. The in-line data compression operations are performed during execution of a storage input-output (I/O) command, between the event of receipt of the storage I/O command and the event of returning status of the storage I/O command. The storage I/O operation is associated with at least one data group comprising one or more data blocks that are identified by the caller. Upon receipt of the storage I/O command, one or more compression rules are applied to the data blocks to determine one or more compression parameters, which compression parameters are used to form specific compression operations that are performed over at least a portion of the data group. The status pertaining to the execution of the storage I/O operation is returned to the caller.

Abstract: Disclosed is an approach for implementing disaster recovery for virtual machines. Consistency groups are implemented for virtual machines, where the consistency group link together two or more VMs. The consistency group includes any set of VMs which need to be managed on a consistent basis in the event of a disaster recovery scenario.

Abstract: In one embodiment, a system for managing a virtualization environment includes a set of host machines, each of which includes a hypervisor, virtual machines, and a virtual machine controller, and a first virtualized file server configured to receive a request to access a storage item located at a second virtualized file server, determine that the storage item is designated as being accessible by other virtualized file servers, identify an FSVM of the second virtualized file server at which the storage item is located, and forward the request to the FSVM of the second virtualized file server. The storage item may be designated as being accessible by other virtualized file servers when the storage item is associated with a predetermined tag value indicating that the storage item is shared among virtualized file servers. The predetermined tag value may be stored in a sharding map in association with the storage item.

Abstract: An architecture for implementing a mechanism for displaying GPU resource usage and dynamically allocating GPU resources in a networked virtualization system is provided. The mechanism compares an initial allocation of GPU resources to virtual machines supported by one or more nodes of the networked virtualization system to a current GPU resource usage by the virtual machines. Based at least in part on the comparison and workloads processed by the virtual machines, the mechanism may reallocate GPU resources to one or more of the virtual machines. A virtual machine is reassigned to a different vGPU profile if reassignment is likely to achieve a more efficient allocation of GPU resources to the virtual machine. A user interface indicating GPU resource usage relative to GPU resource allocation may also be generated and displayed.

Abstract: In one embodiment, a system for migrating virtual machines in a virtualization environment includes a plurality of host machines implementing the virtualization environment and a migration controller. Each of the host machines includes a hypervisor, one or more user virtual machines (UVMs) and a virtual machine controller. The system further implements a virtual disk comprising a plurality of storage devices, the virtual disk being accessible by the virtual machine controllers, which conduct I/O transactions with the virtual disk. The migration controller determines a segment size and, for each host machine, determines a number of required segments for the UVMs running on the host machine. The controller computes a number of reserved segments based on a total number of host machines and a largest one of the numbers of required segments. The reserved segments are then assigned among the plurality of host machines.

Abstract: Systems and methods for scheduling storage management tasks over predicted user tasks in a distributed storage system. A method commences upon receiving a set of historical stimulus records that characterize management tasks that are run in the storage system. A corresponding set of historical response records comprising system metrics associated with execution of the system tasks is also received. A learning model is formed from the stimulus records and the response records and formatted to be used as a predictor. A set of forecasted user tasks is input as new stimulus records to the predictor to determine a set of forecasted system metrics that would result from running the forecasted user tasks. Management tasks are selected so as not to impact the forecasted user tasks. Management tasks can be selected based on non-contentions resource usage between historical management task resource usage and predictions of resource usage by the user tasks.

Abstract: Systems for storage system rollover and rollback. A data mover agent is installed on a source storage system to capture disaster recovery data and send to a target system. Upon receiving a rollover event signal, a virtualized controller creates one or more replica user virtual machines running on the target system that serve to replicate functions of the user virtual machines from the source storage system. The virtualized controller on the target system converts the target disaster recovery data from a first format to a second format to facilitate use of the target disaster recovery data by the replica user virtual machines. Rollback is initiated when the target system receives a rollback event signal. Differences in the data that have occurred between the rollover event and the rollback signal are calculated and sent to the rollback system. The calculated differences are applied to a registered snapshot on the rollback system.