Abstract: A mechanism for a manager and host-based integrated power saving policy in virtualization systems is disclosed. A method of the invention includes receiving configuration and power information of a host machine from a management agent on the host machine, performing a macro-level power saving scheduling algorithm that takes into consideration the received configuration and power information of the host machine, and requesting that the host machine alter a number of active running CPU cores as part of the macro-level power saving scheduling algorithm.

Abstract: A mechanism for system-wide target host optimization in load balancing virtualization systems is disclosed. A method of the invention includes detecting a condition triggering a load balancing operation, identifying a plurality of candidate target host machines to receive one or more operating virtual machines (VMs) to be migrated, determining a load per resource on each identified candidate target host machine, and scheduling all operating VMs among all of the identified candidate target host machines in view of an expected load per resource on each candidate target host.

Abstract: A host computer is coupled to data storage and has access to the data storage. The host computer has multiple network interfaces, which are associated with multiple logical networks. The host computer detects a network address of the data storage, and identifies one of the network interfaces that is associated with a best-performing logical network for accessing the data storage. The host computer then receives a routing configuration that routes traffic to the data storage via the identified network interface.

Abstract: A mechanism for live migration of virtual machines (VMs) with memory optimizations is disclosed. A method of embodiments of the invention includes receiving a hash value for each of one or more memory pages of a migrating VM from a source host machine, obtaining a hash value for each of one or more memory pages hosted by a target host machine, and comparing the received hash values with the obtained hash values for matches. The method further comprises for each of the received hash values that do not match any of the obtained hash values, sending a negative acknowledgment to the source host machine for that hash value, and for each of the received hash values that do match any of the obtained hash values, using a memory page associated with the matching hash value at the target host machine for the migrating VM.

Abstract: A mechanism for load balancing in a memory-constrained virtualization system is disclosed. A method of embodiments of the invention includes determining that one or more collected metrics have triggered a load balancing operation of a host controller machine, wherein the one or more collected metrics include memory-related metrics of one or more host machines managed by the host controller machine and of an overall system of the host controller machine. The method further includes selecting a host machine of the one or more host machines to migrate a virtual machine (VM) from as part of the load balancing operation and selecting a VM of a plurality of VMs hosted by the selected host machine to load balance migrate from the selected host machine, wherein the selecting the host machine and the selecting of the VM includes consideration of the memory-related metrics of the host machine and the VM.

Abstract: A mechanism for target host optimization in a load balancing host and virtual machine (VM) selection algorithm is disclosed. A method of embodiments of the invention includes determining that one or more collected metrics have triggered a load balancing operation of a host controller machine, identifying a plurality of source host machines and a plurality of virtual machines (VMs) hosted by the plurality of source host machines as candidates for selection by the load balancing operation for migration, and adjusting a selection score for at least one of a candidate source host machine and a candidate VM based on one or more metrics of the candidate source host and of the candidate VM, wherein the one or more metrics are associated with one or more candidate target host machines to which a candidate VM could be migrated.

Abstract: A mechanism for shared memory history optimization in a host selection algorithm for VM placement is disclosed. A method of embodiments of the invention includes determining candidate hosts to place a target virtual machine (VM), obtaining memory sharing history of the target VM with one or more VMs hosted by each of the candidate hosts, determining an average memory sharing history amount for each of an optimized number of the candidate hosts based on the obtained memory sharing history of the target VM with one or more VMs hosted by each of the optimized number of candidate hosts, and adjusting a score in a general selection algorithm for a candidate host with the highest average memory sharing history amount.

Abstract: Methods for obtaining a snapshot of a shared virtual machine (VM) image are described herein. In response to a request for obtaining a snapshot of a first VM image stored in a storage disk accessed and shared by a plurality of VMs, a virtualization manager selects a VM from the plurality of VMs hosted within one or more hosts. First needs to notify others to prepare for the snapshot by pausing, etc. A process associated with the selected VM is configured to capture a snapshot from the first VM image, generating a second VM image to be stored in storage disk. Thereafter, the virtualization manager notifies the plurality of VMs to utilize the second image after the second VM image has been generated.

Abstract: Techniques for automatic network discovery for host configurations are described herein. A management server may receive a first message from a first host entering a network, where the first message includes a network identifier (ID) identifying a logical network coupled to a network interface card (NIC) of the first host. In response to the first message, the management server may automatically configure the NIC of the first host using one or more network configuration parameters of a second host based on the first message, where the second host has been coupled to the logical network prior to the first host.

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: Techniques for automatically launching a virtual machine associated with a client during startup are described herein. According to one embodiment, a virtual machine (VM) associated with a client is identified by a controller, in response to a message received by the controller from a client over a network indicating that the client is starting up. The VM may be one of a predetermined VM, a member of a group of VMs that are associated with the client, and a VM selected from a pool of VMs. The controller causes the associated VM to be launched automatically over the network as a part of a startup process of the client without user intervention. Other methods and apparatuses are also described.

Abstract: Techniques for improving boot time of a client having a virtualized operating environment are described herein. According to one embodiment, a controller identifies a virtual machine (VM) associated with a client in response to a message received by the controller from a client over a network indicating that the client is starting up. The controller automatically launches the associated VM at a remote node. The associated VM is being started up at the remote node while the client is being started up at the client concurrently, such that a starting time for the client and the associated VM as a whole is reduced. Other methods and apparatuses are also described.

Abstract: Techniques for automatic virtual machine migration in a mixed SBC/CBC environment are described herein. According to one embodiment, a connection is established between a client and a virtual machine (VM) hosted by a remote node in response to a request for accessing the VM. A control server determines whether the client has sufficient processing resources to host the VM. The control server causes the VM to be migrated from the remote node to the client if the client has sufficient processing resources to host the VM. Other methods and apparatuses are also described.

Abstract: Techniques for launching a VM with memory automatically adjusted based on a memory configuration of a client hosting the VM are described herein. According to one embodiment, a control server dynamically determines an amount of memory in view of a memory configuration of a client at the point in time, in response to a request for launching a VM for the client over a network. The amount of memory is allocated to be associated with the VM. Thereafter, the control server launches the VM for the client having the determined amount of memory allocated to the VM, where the VM is to be hosted by the client. Other methods and apparatuses are also described.

Abstract: Techniques for automatically providing a client with access to a virtual machine associated with the client are described herein. According to one embodiment, a message is received by a controller from a client over a network indicating that the client is starting up. In response, the controller causes a connection to be automatically established between the client and a virtual machine (VM) associated with the client once the client has started up. The associated VM may be one of a predetermined VM, a member of a group of VMs that are associated with the client, and a VM selected from a pool of VMs. As a result, a user of the client can instantly access contents provided by the associated VM without having to manually log onto a Web portal in order to select the associated VM to be launched. 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: Apparatus for computer network management, comprising: a knowledge definer, operable for defining a knowledge module comprised of a plurality of knowledge items, hierarchically arranged according to technologies, each of the knowledge items comprising possible values for a configuration activity of one of the technologies. The apparatus further includes a policy definer, associated with the knowledge definer, operable for defining at least one technical policy based on the knowledge module, usable for overriding selected values of the possible values while keeping remaining values of the possible values, the technical policy inheriting from the knowledge module.