Abstract: A mechanism for reducing the power consumption of virtual machine host servers is disclosed. A method for a virtual machine (VM) power reduction agent (PRA) hosted by a VM may include identifying a user activity associated with the VM, determining that the VM is inactive based on the user activity associated with the VM, and notifying a host of the VM that the VM is inactive to facilitate application of a power reduction policy to the VM based on specific power reduction settings associated with the VM.

Abstract: A mechanism for managing power in a virtual machine system is disclosed. A method for a host-based power management system may include monitoring a plurality of VMs in a VM system to detect user activity associated with each of the plurality of VMs, identifying a VM of the plurality of VMs that is inactive based on the user activity associated with the VM, and applying a power reduction policy to the VM.

Abstract: Methods for monitoring operating statuses of hosts are described herein. Operating statuses for one or more hosts are monitored by a management server over a network using a network management protocol. In response to a failure to obtain an operating status of a first host over the network using the network management protocol, the management server instructs a second host to access a predetermined storage location to obtain the operating status of the first host. The predetermined storage location is specifically allocated for the first host from a storage space shared by all the hosts. Thereafter, the management server is configured to determine an operating condition of the first host based on the operating status obtained via the second host.

Abstract: A method and system for handling temporary data of a virtual machine are described. In one embodiment, virtual machines are hosted by a server and accessed by remote clients over a network. The server assigns first storage and second storage to each virtual machine, where the first storage is designated for temporary data of a respective virtual machine and the second storage is designated for persistent data of a respective virtual machine. The server monitors events pertaining to the virtual machine. Upon detecting a predefined event pertaining to one of the virtual machines, the server causes at least a subset of the temporary data to be removed from the first storage of this virtual machine.

Abstract: A method and system for swapping memory of a virtual machine are described. In one embodiment, virtual machines are hosted by a server and accessed by remote clients over a network. The server assigns first storage and second storage to each virtual machine, where the first storage is designated for swap memory of a respective virtual machine and the second storage is designated for persistent data of a respective virtual machine. The server monitors events pertaining to the virtual machines. Upon detecting a predefined event pertaining to one of the virtual machines, the server causes the contents of the first storage to be wiped out.

Abstract: A storage pool is shared by multiple host computers in a cluster that runs virtual machines. In one embodiment, one of the host computers in the cluster is designated to include a storage pool manager. Each host computer in the cluster monitors its storage consumption and notifies the storage pool manager of its storage consumption. Thus, storage space in the storage pool can be dynamically allocated on demand.

Abstract: A method and system for managing images of virtual machines hosted by a server. The server maintains a base virtual machine image in a common data store for sharing by the virtual machines. When the server identifies an image modification for at least one of the virtual machines, the server determines whether the image modification includes data common to images of the other virtual machines. If so, the common data is copied to the base virtual machine image in the common data store, and a pointer to the copied data is added to an image of the virtual machine in an individual data store.

Abstract: Storage expansion for a virtual machine operating system is reduced. In one embodiment, virtual machines are run on a host and accessed by remote clients over a network. When a guest operating system on one of the virtual machines deletes a file, a VM storage manager on the host detects a special write performed by the guest operating system that writes zeros into a logical block of the file. The VM storage manager links the logical block to a designated block, and de-allocates the disk block that is mapped to the logical block. The de-allocation allows the disk block to be reused by the virtual machines.

Abstract: Method and apparatus for playing multimedia content at a remote graphics display client are described herein. According to one embodiment, a stream of data objects is sequentially transmitted to a client over a network. The stream is generated by a desktop application representing a snapshot of a display output of the desktop application. The data objects are to be rendered at the client for graphics remoting purposes. It is detected that a multimedia object is to be rendered by the desktop application. The multimedia object is caused to be rendered remotely at the client without having to render the multimedia object locally and without having to transmit a display result of the rendering to the client over the network. Other methods and apparatuses are also described.

Abstract: The execution of anti-virus programs can be accelerated in a virtual desktop environment. In one embodiment, a server hosts a plurality of virtual machines. Before performing a virus scan on a file, the server computes a signature value of the file, compares the signature value with the stored signature values in a central database, and performs virus scan on the file according to the result of the comparison. If the signature value exists in the central database, the virus scan on the file can be skipped.

Abstract: The load of a server and its client is balanced during connection setup time and dynamically during operation. In one embodiment, a server that hosts virtual machines for a plurality of clients balances its load with its clients. The server receives a request from a requesting client to establish a connection. The request includes capacity information about the requesting client. The server then negotiates with the requesting client about load allocation based on the capacity information. The negotiated load can be dynamically rebalanced after the connection is established.

Abstract: The graphics load of a virtual desktop is estimated to determine the capacity of a virtual desktop system. In one embodiment, the graphics load of a physical desktop is measured by a remoting agent installed on the physical desktop. The graphics load can be used as an estimate of the load that would be created by a deployed virtual desktop. The remoting agent on the physical desktop mimics host operations that are necessary to direct graphics data to a remote site. The remoting agent also measures the graphics load incurred by the host operations to determine a capacity of a virtual desktop system prior to deployment of the virtual desktop system.

Abstract: Virtual machine images are transferred from a source storage location to a target storage location over a network. In one embodiment, a host at the source storage location computes signature values of a plurality of disk blocks that contain a plurality of virtual machine images. Each computed signature value corresponds to one of the disk blocks. A subset of the disk blocks, all of which have different signature values, is then transferred from the source storage location to the target storage location. Only one copy of duplicate disk blocks is transferred.

Abstract: A method for executing a privileged virtual machine (VM) in a secured environment. The method comprises mapping virtual address space of the privileged virtual machine (VM) to start at address zero of a physical memory; configuring memory address space of emulated and real peripheral devices on an interconnect bus; and blocking the privileged VM's operating system from re-configuring the memory address space of the interconnect bus.

Abstract: A method for performing efficient caching through an enumeration process is provided. The objects residing on the storage medium are cached in the order that these objects are kept in the directory of the storage medium. As a result, the directory content is enumerated in the cache. Therefore, the cache does not have to be associated with the server layout. Moreover, it is further possible to support a hierarchy of distributed caches using the disclosed invention.

Abstract: A distributed shared file system (DSFS) comprising a network file system (NFS) capable of receiving at least a request from at least a client, a distributed cache, a metadata storage containing metadata information related to files stored in the NFS, a mapper capable of handling pointers to point to locations of data within the files and the metadata information, an agent capable of handling said request, and a relocator capable of relocating data within the NFS operative with said agent.

Abstract: A method for performing efficient caching of sparse files in a distributed cache by use of an enumeration process is provided. According to the disclosed invention, the storage's objects are cached in the order that these objects are kept in the storage's directory. As a result, the directory content is enumerated in the cache, resulting in the cache not having to be associated with the server layout.

Abstract: A method for performing efficient caching through an enumeration process is provided. The objects residing on the storage medium are cached in the order that these objects are kept in the directory of the storage medium. As a result, the directory content is enumerated in the cache. Therefore, the cache does not have to be associated with the server layout. Moreover, it is further possible to support a hierarchy of distributed caches using the disclosed invention.

Abstract: An apparatus and a method for the implementation of a skip-list based cache is shown. While the traditional cache is basically a fixed length line based or fixed size block based structure, resulting in several performance problems for certain application, the skip-list based cache provides for a variable size line or block that enables a higher level of flexibility in the cache usage.

Abstract: A method for dynamic reconfiguration of a computer network as a result of an instruction for object rebalance. The method comprises selecting an object to be relocated and choosing a relocation server to which the object is to be relocated. A meta data corresponding to the object is updated. The object is transferred to the relocation server; and a view ID table is updated with a new view ID corresponding to the object.