Abstract: Transparent network devices intercept unidirectional network traffic and use bidirectional network protocol messages to discover each other and configure an inner connection. A first transparent network device intercepting unidirectional network traffic between a source and destination will send a bidirectional network protocol message addressed to the destination that includes an indicator of its presence. Additional transparent network devices that intercept this network message each add their own indicator to the message. If no response to the bidirectional network message is received, an error message is received, or a response message is received directly from the destination by one of the transparent network devices, this additional transparent network device deduces that it is the closest transparent network device to the destination and sends a response message addressed to the source that includes an indicator of its presence.

Abstract: Virtual storage arrays consolidate branch data storage at data centers connected via wide area networks. Virtual storage arrays appear to storage clients as local data storage; however, virtual storage arrays actually store data at the data center. Virtual storage arrays overcome bandwidth and latency limitations of the wide area network by predicting and prefetching storage blocks, which are then cached at the branch location. Virtual storage arrays leverage an understanding of the semantics and structure of high-level data structures associated with storage blocks to predict which storage blocks are likely to be requested by a storage client. Virtual storage arrays may use proximity-based, heuristic-based, and access time-based prefetching to predict high-level data structure entities that are likely to be accessed by the storage client. Virtual storage arrays then identify and prefetch storage blocks corresponding with the predicted high-level data structure entities.

Abstract: The file creation on remote data storage accessible via a WAN can be optimized by creating temporary files in advance on a remote data storage. The file handles or other file access parameters for these temporary files are cached at a client network location. A file creation request from a client is intercepted at the client network location and one of the cached file handle is returned to the client. This enables the client to immediately write data to the corresponding temporary file, avoiding the delay incurred by communicating the file creation request and its response over a WAN. One or more storage commands are sent to the remote data storage to change the attributes of the temporary file to match those requested by the client, such as the file name, directory, and/or file permissions. File creation requests may be selectively optimized according to rules or criteria specified by users.

Abstract: Systems and techniques are described for load balancing between WAN optimization devices. During operation, a mapping is determined based solely or partially on capacities of a set of remote WAN optimization devices and capacities of a set of local WAN optimization devices, wherein the mapping maps each remote WAN optimization device to a local WAN optimization device. Next, connection requests are directed to WAN optimization devices based on the mapping.

Abstract: Access to compound data over a wide-area network is optimized by analyzing metadata within compound data to identify internal and external data streams to be prefetched. Upon receiving or intercepting a network packet including an access request for a data resource, metadata in this data resource is analyzed to identify associated data streams and their storage locations within and/or outside of the data resource. Data streams may be proactively or reactively prefetched. Proactive prefetching identifies and retrieves data streams or portions thereof likely to be accessed by a client based on attributes associated with the data resource. Reactive prefetching identifies portions of data streams associated with received access requests and retrieves additional portions of these data streams. Prefetched data streams or portions thereof are stored in a data storage on the same local network or near to the local network including the client.

Abstract: In a system where transactions are accelerated with asynchronous writes that require acknowledgements, with pre-acknowledging writes at a source of the writes, a destination-side transaction accelerator includes a queue for queue writes to a destination, at least some of the writes being pre-acknowledged by a source-side transaction accelerator prior to the write completing at the destination, a memory for storing a status of a destination-side queue and possibly other determinants, and logic for signaling to the source-side transaction accelerator with instructions to alter pre-acknowledgement rules to hold off on and pursue pre-acknowledgements based on the destination-side queue status. The rules can take into account adjusting the flow of pre-acknowledged requests or pre-acknowledgements at the sender-side transaction accelerator based at least on the computed logical length.

Abstract: Access to compound data over a wide-area network is optimized by analyzing metadata within compound data to identify internal and external data streams to be prefetched. Upon receiving or intercepting a network packet including an access request for a data resource, metadata in this data resource is analyzed to identify associated data streams and their storage locations within and/or outside of the data resource. Data streams may be proactively or reactively prefetched. Proactive prefetching identifies and retrieves data streams or portions thereof likely to be accessed by a client based on attributes associated with the data resource. Reactive prefetching identifies portions of data streams associated with received access requests and retrieves additional portions of these data streams. Prefetched data streams or portions thereof are stored in a data storage on the same local network or near to the local network including the client.

Abstract: Virtual storage arrays consolidate branch data storage at data centers connected via wide area networks. Virtual storage arrays appear to storage clients as local data storage; however, virtual storage arrays actually store data at the data center. Virtual storage arrays overcome bandwidth and latency limitations of the wide area network by predicting and prefetching storage blocks, which are then cached at the branch location. Virtual storage arrays leverage an understanding of the semantics and structure of high-level data structures associated with storage blocks to predict which storage blocks are likely to be requested by a storage client. Virtual storage arrays may use proximity-based, heuristic-based, and access time-based prefetching to predict high-level data structure entities that are likely to be accessed by the storage client. Virtual storage arrays then identify and prefetch storage blocks corresponding with the predicted high-level data structure entities.

Abstract: In a system where transactions are accelerated with asynchronous writes that require acknowledgements, with pre-acknowledging writes at a source of the writes, a destination-side transaction accelerator includes a queue for queue writes to a destination, at least some of the writes being pre-acknowledged by a source-side transaction accelerator prior to the write completing at the destination, a memory for storing a status of a destination-side queue and possibly other determinants, and logic for signaling to the source-side transaction accelerator with instructions to alter pre-acknowledgement rules to hold off on and pursue pre-acknowledgements based on the destination-side queue status. The rules can take into account adjusting the flow of pre-acknowledged requests or pre-acknowledgements at the sender-side transaction accelerator based at least on the computed logical length.