Abstract: A method and system for real-time cloud bursting is provided. The method and system are directed to extending a data center with cloud computing resources by decoupling computing resources and storage devices in a virtualized data center, and booting the decoupled computing resources in a staged process while storage devices are divided and prioritized into components. Data and boot instructions are re-routed and cached as needed through a proxy system.

Abstract: A method and system for real-time cloud bursting is provided. The method and system are directed to extending a data center with cloud computing resources by decoupling computing resources and storage devices in a virtualized data center, and booting the decoupled computing resources in a staged process while storage devices are divided and prioritized into components. Data and boot instructions are re-routed and cached as needed through a proxy system.

Abstract: A method and system for real-time cloud bursting is provided. The method and system are directed to extending a data center with cloud computing resources by decoupling computing resources and storage devices in a virtualized data center, and booting the decoupled computing resources in a staged process while storage devices are divided and prioritized into components. Data and boot instructions are re-routed and cached as needed through a proxy system.

Abstract: A method for enabling access to a data resource, which is held on a file server (25) on a first local area network (LAN) (21a), by a client (28) on a second LAN (21b). A proxy receiver (48) on the second LAN (21b) intercepts a request for the data resource submitted by the client (28) and transmits a message via a wide area network (WAN) (29) to a proxy transmitter (52) on the first LAN (21a), requesting the data resource. The proxy transmitter (52) retrieves a replica of the data resource from the file server (25) and conveys the replica of the data resource over the WAN (29) to the proxy receiver (48), which serves the replica of the data resource from the proxy receiver (48) to the client (28) over the second LAN (21b).

Abstract: A method and system for real-time cloud bursting is provided. The method and system are directed to extending a data center with cloud computing resources by decoupling computing resources and storage devices in a virtualized data center, and booting the decoupled computing resources in a staged process while storage devices are divided and prioritized into components. Data and boot instructions are re-routed and cached as needed through a proxy system.

Abstract: In various embodiments, data processing apparatus, software, or machine-implemented methods can optimize NFSv3 asynchronous write requests or MSRPC calls that traverse a wide area network, for example, by receiving, from a client, a first request directed to a server across a wide area network; determining whether a related second request has been received previously; when a related second request has been received previously, sending, to the client, a first reply to the second request and forwarding the first request to the server, and otherwise forwarding the first request to the server without sending any reply to the client for the first request. Sending local replies from a WAN optimizer induces the client to send continuous requests, improving throughput, but at least one client request remains unreplied to, and one server error reply is always reported to the client, facilitating correct error processing at the client.

Abstract: Techniques are provided for desktop streaming over wide area networks. In one embodiment, a computer comprises logic stored in one or more storage media. The logic is configured to receive a first request for a desktop image comprising a collection of files, and to segment the desktop image into a prefetch set, a streaming set, and a leave-behind set. The prefetch set includes a smallest subset of files, in the collection of files, that is needed for a boot up without requiring retrieval of additional files. The streaming set includes those files, in the collection of files, that are to be sent after the boot up. The leave-behind set includes those files, in the collection of files, that are to be sent when specifically requested. In response to the first request, the logic is configured to send the prefetch set to a computing device.

Abstract: Techniques are provided for desktop streaming over wide area networks. In one embodiment, a computing device comprises logic that is configured to intercept file open requests for files stored in a file system, where at least some of the files in the file system may have not yet been fully downloaded. In response to a request to open a file, the logic is configured to modify a first sharing mode specified therein and to open the file in a read-write sharing mode that allows other processes to open the file. While one or more blocks of the file are being downloaded or written into the file, the logic is configured to check whether a second sharing mode received in a subsequent request to open the file is compatible with the first sharing mode. If the second sharing mode is not compatible with the first sharing mode, the logic is configured to deny the subsequent request even though in the file system the file is opened in the read-write sharing mode.

Abstract: A locking mechanism for a data resource is disclosed, which can operate across LANs and a WAN. The technique temporarily imposes an extended lock on the requested data resource. While the extended lock is in force, all lock and unlock requests issued by the same client for the resource are managed exclusively by the local server. Once the last lock has been released, or after a timeout interval, the extended lock is canceled. Traffic across the WAN is reduced to a minimum of one round trip.

Abstract: In various embodiments, data processing apparatus, software, or machine-implemented methods can optimize NFSv3 asynchronous write requests or MSRPC calls that traverse a wide area network, for example, by receiving, from a client, a first request directed to a server across a wide area network; determining whether a related second request has been received previously; when a related second request has been received previously, sending, to the client, a first reply to the second request and forwarding the first request to the server, and otherwise forwarding the first request to the server without sending any reply to the client for the first request. Sending local replies from a WAN optimizer induces the client to send continuous requests, improving throughput, but at least one client request remains unreplied to, and one server error reply is always reported to the client, facilitating correct error processing at the client.

Abstract: A method for enabling access to a data resource, which is held on a file server (25) on a first local area network (LAN) (21a), by a client (28) on a second LAN (21b). A proxy receiver (48) on the second LAN (21b) intercepts a request for the data resource submitted by the client (28) and transmits a message via a wide area network (WAN) (29) to a proxy transmitter (52) on the first LAN (21a), requesting the data resource. The proxy transmitter (52) retrieves a replica of the data resource from the file server (25) and conveys the replica of the data resource over the WAN (29) to the proxy receiver (48), which serves the replica of the data resource from the proxy receiver (48) to the client (28) over the second LAN (21b).

Abstract: A locking mechanism for a data resource is disclosed, which can operate across LANs and a WAN. The technique temporarily imposes an extended lock on the requested data resource. While the extended lock is in force, all lock and unlock requests issued by the same client for the resource are managed exclusively by the local server. Once the last lock has been released, or after a timeout interval, the extended lock is canceled. Traffic across the WAN is reduced to a minimum of one round trip.

Abstract: A method is disclosed for reducing network traffic. At a sender, a data chunk is identified for transmission to a receiver, which is connected to the sender over a communication link. The sender computes a signature of the data chunk and determines whether the data chunk has been previously transmitted by looking up the signature in a sender index table. The sender index table associates the signatures of previously transmitted data chunks with unique index values. A message is transmitted to the receiver, where if the data chunk has previously been transmitted then the message includes an index value from the sender index table that is associated with the signature of the data chunk. At the receiver, the data chunk is located in a receiver cache that stores the previously transmitted data chunks by looking up the index value included in the message in a receiver index table.

Abstract: A method is disclosed for accessing information based on Distributed File System (DFS) paths and for automatically and transparently modifying the DFS target server set with additional servers that are preferable to a client. A request to resolve a path to a file is sent to a DFS root node. A response is received from the DFS root node. The response includes one or more first DFS referrals. Each of the one or more first DFS referrals identifies a network entity and a directory that is exported by the network entity, where the file is stored in the directory. A second DFS referral is added to the response. The second DFS referral identifies a particular network entity and a particular directory that is exported by the particular network entity. The response is sent to the client.

Abstract: A method for enabling access to a data resource, which is held on a file server (25) on a first local area network (LAN) (21a), by a client (28) on a second LAN (21b). A proxy receiver (48) on the second LAN (21b) intercepts a request for the data resource submitted by the client (28) and transmits a message via a wide area network (WAN) (29) to a proxy transmitter (52) on the first LAN (21a), requesting the data resource. The proxy transmitter (52) retrieves a replica of the data resource from the file server (25) and conveys the replica of the data resource over the WAN (29) to the proxy receiver (48), which serves the replica of the data resource from the proxy receiver (48) to the client (28) over the second LAN (21b).

Abstract: A technique for centralized and differentiated content and application delivery system allows content providers to directly control the delivery of content based on regional and temporal preferences, client identity and content priority. A scalable system is provided in an extensible framework for edge services, employing a combination of a flexible profile definition language and an open edge server architecture in order to add new and unforeseen services on demand. In one or more edge servers content providers are allocated dedicated resources, which are not affected by the demand or the delivery characteristics of other content providers. Each content provider can differentiate different local delivery resources within its global allocation. Since the per-site resources are guaranteed, intra-site differentiation can be guaranteed. Administrative resources are provided to dynamically adjust service policies of the edge servers.

Abstract: A technique for centralized and differentiated content and application delivery system allows content providers to directly control the delivery of content based on regional and temporal preferences, client identity and content priority. A scalable system is provided in an extensible framework for edge services, employing a combination of a flexible profile definition language and an open edge server architecture in order to add new and unforeseen services on demand. In one or more edge servers content providers are allocated dedicated resources, which are not affected by the demand or the delivery characteristics of other content providers. Each content provider can differentiate different local delivery resources within its global allocation. Since the per-site resources are guaranteed, intra-site differentiation can be guaranteed. Administrative resources are provided to dynamically adjust service policies of the edge servers.