Abstract: In one embodiment, a network controller receives data indicative of one or more traffic requirements for network traffic. The network controller maps the data indicative of the one or more traffic requirements into a network policy. The network controller causes installation of the network policy onto one or more networking devices. The one or more networking devices are configured to route the network traffic based on the network policy. The network controller receives feedback regarding the installed network policy. The network controller adjusts the network policy based on the received feedback.

Abstract: In one embodiment, a network controller receives data indicative of one or more traffic requirements for network traffic. The network controller maps the data indicative of the one or more traffic requirements into a network policy. The network controller causes installation of the network policy onto one or more networking devices. The one or more networking devices are configured to route the network traffic based on the network policy. The network controller receives feedback regarding the installed network policy. The network controller adjusts the network policy based on the received feedback.

Abstract: In order for intermediary WAAS devices to process and accelerate ICA traffic, they must decrypt the ICA traffic in order to examine it. Disclosed is a mechanism by which the ICA traffic may be re-encrypted for transport over the WAN in a manner that does not require explicit configuration by the administrator of the WAAS devices. For example, VDI traffic may be intercepted and all data redundancy elimination messages may be encrypted and sent to a peer network device.

Abstract: In order for intermediary WAAS devices to process and accelerate ICA traffic, they must decrypt the ICA traffic in order to examine it. Disclosed is a mechanism by which the ICA traffic may be re-encrypted for transport over the WAN in a manner that does not require explicit configuration by the administrator of the WAAS devices. For example, VDI traffic may be intercepted and all data redundancy elimination messages may be encrypted and sent to a peer network device.

Abstract: A system for managing storage accesses for rate guaranteed continuous data streams and non-rate-guaranteed storage requests may include a plurality of rate guaranteed requestors for data streams and one or more non-rate guaranteed requestors. A disk scheduler for the system may have a guaranteed rate queue for queuing storage requests from the rate guaranteed requestors and a non-rate-guaranteed queue for queuing requests from the non-rate-guaranteed requesters. The disk scheduler may include a bandwidth allocator coupled to the guaranteed rate queue and the non-rate-guaranteed queue. The bandwidth allocator may be configured to allocate bandwidth of a storage system between the guaranteed rate queue and the non-rate-guaranteed queue according to a predetermined ratio. The rate guaranteed requestors may be limited so that an aggregate of maximum stream rates guaranteed for each rate guaranteed requestor does not exceed the portion of the bandwidth allocated to the guaranteed rate queue.

Abstract: In order for intermediary WAAS devices to process and accelerate ICA traffic, they must decrypt the ICA traffic in order to examine it. Disclosed is a mechanism by which the ICA traffic may be re-encrypted for transport over the WAN in a manner that does not require explicit configuration by the administrator of the WAAS devices.

Abstract: A system for managing storage accesses for rate guaranteed continuous data streams and non-rate-guaranteed storage requests may include a plurality of rate guaranteed requestors for data streams and one or more non-rate guaranteed requestors. A disk scheduler for the system may have a guaranteed rate queue for queuing storage requests from the rate guaranteed requestors and a non-rate-guaranteed queue for queuing requests from the non-rate-guaranteed requesters. The disk scheduler may include a bandwidth allocator coupled to the guaranteed rate queue and the non-rate-guaranteed queue. The bandwidth allocator may be configured to allocate bandwidth of a storage system between the guaranteed rate queue and the non-rate-guaranteed queue according to a predetermined ratio. The rate guaranteed requestors may be limited so that an aggregate of maximum stream rates guaranteed for each rate guaranteed requestor does not exceed the portion of the bandwidth allocated to the guaranteed rate queue.

Abstract: A system for managing storage accesses for rate guaranteed continuous multimedia data streams and non-rate-guaranteed storage requests may include a plurality of rate guaranteed requestors for multimedia streams and one or more non-rate guaranteed requesters. A disk scheduler may also be included. The disk scheduler may have a guaranteed rate queue for queuing storage requests from the rate guaranteed requestors and a non-rate-guaranteed queue for queuing requests from the non-rate-guaranteed requestors. The disk scheduler may also include a bandwidth allocator coupled to the guaranteed rate queue and the non-rate-guaranteed queue and further coupled to a storage system. The bandwidth allocator may be configured to allocate bandwidth of the storage system between the guaranteed rate queue and the non-rate-guaranteed queue according to a predetermined ratio.

Abstract: A disk scheduling system with bounded request reordering. Disk access requests may be performed during traversals of a disk head across a disk. Each traversal may have a specified direction of motion. A plurality of disk accesses may be performed during a disk head traversal. The overall number of disk access requests for a given disk head traversal may be limited to a maximum number N. By limiting the number of disk requests for each traversal, a bound may effectively be placed on the amount of time it takes to satisfy any single disk request.

Abstract: A disk scheduling system with bounded request reordering. Disk access requests may be performed during traversals of a disk head across a disk. Each traversal may have a specified direction of motion. A plurality of disk accesses may be performed during a disk head traversal. The overall number of disk access requests for a given disk head traversal may be limited to a maximum number N. By limiting the number of disk requests for each traversal, a bound may effectively be placed on the amount of time it takes to satisfy any single disk request.

Abstract: A system for scheduling storage accesses of multiple continuous media streams may include a plurality of media stream clients. Associated with each media stream client is one of a plurality of media stream managers. Each media stream manager maintains a ring of buffers configured to buffer media stream data between its associated media stream client and one or more storage systems. A different deadline queue may be associated with each one of the storage systems. Each deadline queue may be configured to queue buffer requests from the media stream managers. Each buffer request may include a deadline by which the buffer request must be fulfilled by the corresponding storage system. Each media stream manager may be configured so that once one of its buffers is consumed by the associated media stream client, the media stream manager submits a buffer request and deadline for that buffer to the appropriate deadline queue. Buffer requests may be ordered in each deadline queue from earliest to latest deadline.

Abstract: A system and method for tuning a storage system may include characterizing a maximum sustainable throughput for the storage system. The maximum sustainable throughput may be decreased by a primary derate parameter to obtain a primary throughput. Sizes for buffer units may be determined at different stream rates, where during operation the buffer units buffer a data stream between a stream requester and storage. Buffer unit sizes may be determined by generating stream simulators sufficient to consume the primary throughput and then optimizing the buffer sizes to prevent underruns. This may be repeated at different stream rates to determine a table of buffer sizes. The primary throughput may be decreased by a secondary derate parameter to obtain a maximum system bandwidth which sets an upper limit on admission of streams. When buffer sizes are determined, a prefill margin parameter may be set by which request deadlines must be met.

Abstract: A multimedia server system includes a disk array subsystem including a plurality of multimedia files, e.g., movies, a media file system manager for managing the storage of the plurality of multimedia files within the disk array subsystem, and a playlist which includes a list of titles of specific multimedia files to be played at designated times. The multimedia server system advantageously includes synchronization parameters associated with each of titles specified by the playlist. The synchronization parameters are programmed to specify the manner in which particular files should be truncated in order to compensate for admission delays. An admission delay synchronization unit receives the synchronization parameters and truncates the multimedia files as specified by the synchronization parameters. In one implementation, a first synchronization parameter is used to specify that the current file should be truncated at the time for the play of the next file.

Abstract: A system and method for indexing between video streams in an interactive video delivery system. The interactive video delivery system includes at least one media server which stores video streams having different presentation rates. In one embodiment, the system stores a normal play stream and one or more corresponding trick play streams. The trick play video streams are fast forward and/or fast reverse video streams. The system generates index tables or look-up tables between the normal play and trick play video streams which enable indexing between the streams, and uses these look-up tables to switch back and forth between the streams. In creating the index tables, the system first analyzes the normal play stream and creates a normal play time standard based on presentation timestamps from the normal play stream. The system then creates an index table or look-up table for each of the normal play and trick play video streams using the normal play time standard.

Abstract: The present invention is a method that enables single release of applications for multiple architectures and operating systems and to provide ease of use of applications in multiple architecture environments. The present invention provides a single file that contains separate object code each of multiple architectures. A special header on the file identifies each section of object code and includes pointers to its starting location. When the file is to be executed on a particular architecture, the resident operating system identifies that block of object code most suited for that particular architecture and environment. That section of code is then loaded into memory for execution. Each architecture in the file is specified by CPU-type and CPU sub-type. For each CPU type or CPU sub-type, file offset, file size and alignment is also provided. Padded bytes are provided to place each member on its specific alignment.

Abstract: The present invention is a method that enables single release of applications for multiple architectures and operating systems and to provide ease of use of applications in multiple architecture environments. The present invention provides a single file that contains separate object code each of multiple architectures. A special header on the file identifies each section of object code and includes pointers to its starting location. When the file is to be executed on a particular architecture, the resident operating system identifies that block of object code most suited for that particular architecture and environment. That section of code is then loaded into memory for execution. Each architecture in the file is specified by CPU-type and CPU sub-type. For each CPU type or CPU sub-type, file offset, file size and alignment is also provided. Padded bytes are provided to place each member on its specific alignment.